hypothesis contrastive analysis

• Subject List
• Take a Tour
• For Authors
• Subscriber Services
• Publications
• African American Studies
• African Studies
• American Literature
• Anthropology
• Architecture Planning and Preservation
• Art History
• Atlantic History
• Biblical Studies
• British and Irish Literature
• Childhood Studies
• Chinese Studies
• Cinema and Media Studies
• Communication
• Criminology
• Environmental Science
• Evolutionary Biology
• International Law
• International Relations
• Islamic Studies
• Jewish Studies
• Latin American Studies
• Latino Studies

Linguistics

• Literary and Critical Theory
• Medieval Studies
• Military History
• Political Science
• Public Health
• Renaissance and Reformation
• Social Work
• Urban Studies
• Victorian Literature
• Browse All Subjects

How to Subscribe

• Free Trials

In This Article Expand or collapse the "in this article" section Contrastive Analysis in Linguistics

Introduction, informal beginnings of contrastive linguistics.

• Comparative Stylistics
• Contrastive Linguistics in the United States (1945 to c . 1970)
• Contrastive Linguistics in Europe (1970 to c . 1990)
• Contrastive Pragmatics and Discourse Analysis
• Typological Comparison of Language Pairs
• Corpus-Based Contrastive Analysis
• Corpus-Based Contrastive Interlanguage Research
• Prospects for the Future
• Bibliographies
• Corpora and Digital Resources

Related Articles Expand or collapse the "related articles" section about

About related articles close popup.

Lorem Ipsum Sit Dolor Amet

Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia Curae; Aliquam ligula odio, euismod ut aliquam et, vestibulum nec risus. Nulla viverra, arcu et iaculis consequat, justo diam ornare tellus, semper ultrices tellus nunc eu tellus.

• Acceptability Judgments
• Accessibility Theory in Linguistics
• Acoustic Phonetics
• Acquisition of Possessives
• Anaphora Resolution in Second Language Acquisition
• Articulatory Phonetics
• Auxiliaries
• Bilingual Lexicography
• Bilingualism and Multilingualism
• Classifiers
• Cognitive Grammar
• Compounding
• Cross-Language Speech Perception and Production
• Distinctive Features
• Early Child Phonology
• Educational Linguistics
• English as a Lingua Franca
• Existential
• Languages of the World
• Lexical Semantics
• Linguistic Profiling and Language-Based Discrimination
• Linguistic Relativity
• Mass-Count Distinction
• Nasals and Nasalization
• Politeness in Language
• Reciprocals
• Reduplication
• Reflexives and Reflexivity
• Second Language Listening
• Second Language Writing
• Second-Language Reading
• Sentence Processing in Monolingual and Bilingual Speakers
• Sociolinguistics
• Speech Perception
• Structural Borrowing
• Teaching Pragmatics
• Translation
• Word Classes

Other Subject Areas

Forthcoming articles expand or collapse the "forthcoming articles" section.

• Edward Sapir
• Sentence Comprehension
• Text Comprehension
• Find more forthcoming articles...
• Export Citations
• Share This Facebook LinkedIn Twitter

Contrastive Analysis in Linguistics by Christian Mair LAST REVIEWED: 26 October 2023 LAST MODIFIED: 26 October 2023 DOI: 10.1093/obo/9780199772810-0214

In its core sense, contrastive linguistics can be defined as the theoretically grounded, systematic and synchronic comparison of usually two languages, or at most no more than a small number of languages. In the early stages of the development of the field, comparisons were usually carried out with a view to applying the findings for the benefit of the community, for example in foreign-language teaching or in translation. In recent years, this applied orientation has persisted, but it has been complemented by a growing body of contrastive research with a more theoretical orientation. The languages compared can be genetically related or unrelated, as well as typologically similar or dissimilar. Some comparisons, in particular those with a more theoretical orientation, are symmetrical in the sense that they cover the specifics of one language viewed against another in a balanced way. Applied contrastive comparisons of languages, on the other hand, are often asymmetrical or “directed.” This is typically the case in pedagogically oriented contrastive research, where the focus is on differences in L2, which are seen as potential sources of difficulty in foreign-language learning. Contrastive linguistics emerged as a major subfield of applied linguistics in the 1940s and consolidated quickly throughout the 1950s and 1960s. When it became clear that contrastive linguistics was not going to provide the foundation for a comprehensive theory of foreign-language learning, the field started showing signs of strain. Over time, however, it has avoided disintegration and managed to reposition itself successfully—not as a clearly demarcated subfield, but rather as an approach that has continued to prove its usefulness to a wide range of applied- and theoretical-linguistic domains, such as second-language acquisition (SLA) research, translation studies and translation theory, lexicography, the study of cross-cultural communication, and even cultural studies. Progress in contrastive linguistics has manifested itself on the conceptual level, for example through the constant refinement of notions such as L1 transfer and interference, or through fruitful interdisciplinary dialogue with language typology, but also in contrastivists’ active contribution to the construction of digital research tools such as learner corpora and translation corpora. The following annotated bibliography charts the development of the field on the basis of publications that stand out either because they have become classic points of reference for other work or because they have raised important theoretical and methodological points. Studies of specific phenomena in individual language pairs are mentioned for illustrative purposes. No comprehensive coverage of such largely descriptive work is attempted, however.

The practical usefulness of a contrastive approach to the teaching of foreign languages was obvious to instructors centuries before contrastive linguistics established itself as a distinct subdiscipline within academic linguistics. For example, Lewis 1671 contains the following informal statement of the contrastive hypothesis : “The most facil way of introducing any in a Tongue unknown , is to shew what Grammar it hath beyond, or short of his Mother-Tongue ; following that Maxime, to proceed a noto ad ignotum , making what we know, a step to what we are to learn.” A more or less explicit contrastive approach also informs many publications emanating from the language-teaching reform movements of the late nineteenth and early twentieth centuries, which polemicized against the use of the grammar-and-translation method for the teaching of the modern languages. Works such as Viëtor 1894 , with its three-way comparison of the phonetics of German, French, and English, or Sommer 1921 , with its grammatical comparison of German with the four foreign languages commonly taught in German schools at the time (English, French, Latin, Greek), still contain insights that are of interest beyond their merely historical value. Published more than seventy years after Sommer’s work, Glinz 1994 offers a much-expanded contrastive grammar of the same four languages. Work of the Prague school on linguistic characterology, such as Mathesius 1964 , clearly foreshadows later work on theoretically and typologically informed contrastive linguistics. Works such as Levý 1957 , Levý 1969 , Levý 2011 , and Wandruszka 1969 are representative of a copious literature on translation criticism that contains numerous contrastive-linguistic observations.

Glinz, Hans. 1994. Grammatiken im Vergleich: Deutsch – Französisch – Englisch – Latein, Formen –Bedeutungen – Verstehen . Tübingen, Germany: Niemeyer.

DOI: 10.1515/9783110914801

This monumental contrastive grammar of the four languages presents a summary of the author’s lifelong work on semantically and pragmatically motivated syntax. It contains a wealth of fascinating descriptive insights, but stands somewhat apart from the contemporary mainstream of contrastive linguistics and language typology in its terminology and conceptual structure.

Levý, Jiří. 1957. České theorie překladu . Prague: SNKLHU.

Written in Czech, this massive tome, about a thousand pages in length, presents the sum of the work of this experienced translator and early translation theorist.

Levý, Jiří. 1969. Die literarische Übersetzung . Bonn, Germany: Athenäum.

Selections from Levý’s writings in German translation, with a focus on the translation of literary works. For the present-day reader, the book is worth consulting mainly for its rich illustrative material and experience-based commentary. It is written in a witty and accessible essayistic style.

Levý, Jiří. 2011. The art of translation . Amsterdam: John Benjamins.

DOI: 10.1075/btl.97

Selections from Levý’s writings in English translation.

Lewis, Mark. 1671. Institutio grammaticae puerilis: Or The rudiments of the Latine and Greek tongues; Fitted to childrens capacities as an introduction to larger grammars . London.

Quoted above (from Early English Books Online, original held in the Folger Shakespeare Library, Washington DC) for its early informal formulation of the contrastive hypothesis, this book also contains the controversial assertion that “ Whatever Tongue hath less Grammar than the English, is not intelligible: Whatever hath more, is superfluous ,” which has never been seriously followed up on in later contrastive work.

Mathesius, Vilém. 1964. On linguistic characterology with illustrations from modern English. In A Prague school reader in linguistics . Edited by Josef Vachek, 59–67. Bloomington: Indiana Univ. Press.

A reprint of Mathesius’s original 1928 paper, which introduces the type of theoretically driven comparison of languages that came to be known as “linguistic characterology” in the Prague school tradition.

Sommer, Ferdinand. 1921. Vergleichende Syntax der Schulsprachen (Deutsch, Englisch, Französisch, Griechisch, Lateinisch) mit besonderer Berücksichtigung des Deutschen . Leipzig: Teubner.

Features parallel descriptions of the grammars of German, English, French, (Classical) Greek, and Latin, with numerous contrastive observations.

Viëtor, Wilhelm. 1894. Elemente der Phonetik des Deutschen, Englischen und Französischen: Mit Rücksicht auf die Bedürfnisse der Lehrpraxis . 3d ed. Leipzig: O. R. Reisland.

Viëtor (b. 1850–d. 1918) wrote this book to draw attention to what he saw as the deplorable neglect of pronunciation and the spoken language in the classroom. The contrastive approach is considered to raise awareness of the causes of learner accents and thus improve teaching. The first edition of this work appeared under a slightly different title in 1884; for an adapted English version, see Laura Soames and Wilhelm Viëtor, Introduction to English, French and German Phonetics , 2d ed. (London: Swan Sonnenschein, 1899).

Wandruszka, Mario. 1969. Sprachen, vergleichbar und unvergleichlich . Munich: Piper.

Translation criticism, focusing mainly on lexical and phraseological contrasts, with examples mostly from English, German, and the Romance languages; erudite and essayistic.

back to top

Users without a subscription are not able to see the full content on this page. Please subscribe or login .

Oxford Bibliographies Online is available by subscription and perpetual access to institutions. For more information or to contact an Oxford Sales Representative click here .

• About Linguistics »
• Meet the Editorial Board »
• Acquisition, Second Language, and Bilingualism, Psycholin...
• Adpositions
• African Linguistics
• Afroasiatic Languages
• Algonquian Linguistics
• Altaic Languages
• Ambiguity, Lexical
• Analogy in Language and Linguistics
• Animal Communication
• Applicatives
• Applied Linguistics, Critical
• Arawak Languages
• Argument Structure
• Artificial Languages
• Australian Languages
• Austronesian Linguistics
• Balkans, The Languages of the
• Baudouin de Courtenay, Jan
• Berber Languages and Linguistics
• Biology of Language
• Borrowing, Structural
• Caddoan Languages
• Caucasian Languages
• Celtic Languages
• Celtic Mutations
• Chomsky, Noam
• Chumashan Languages
• Clauses, Relative
• Clinical Linguistics
• Cognitive Linguistics
• Colonial Place Names
• Comparative Reconstruction in Linguistics
• Comparative-Historical Linguistics
• Complementation
• Complexity, Linguistic
• Compositionality
• Computational Linguistics
• Conditionals
• Conjunctions
• Connectionism
• Consonant Epenthesis
• Constructions, Verb-Particle
• Contrastive Analysis in Linguistics
• Conversation Analysis
• Conversation, Maxims of
• Conversational Implicature
• Cooperative Principle
• Coordination
• Creoles, Grammatical Categories in
• Critical Periods
• Cyberpragmatics
• Default Semantics
• Definiteness
• Dementia and Language
• Dene (Athabaskan) Languages
• Dené-Yeniseian Hypothesis, The
• Dependencies
• Dependencies, Long Distance
• Derivational Morphology
• Determiners
• Dialectology
• Dravidian Languages
• Endangered Languages
• English, Early Modern
• English, Old
• Eskimo-Aleut
• Euphemisms and Dysphemisms
• Evidentials
• Exemplar-Based Models in Linguistics
• Existential Wh-Constructions
• Experimental Linguistics
• Fieldwork, Sociolinguistic
• Finite State Languages
• First Language Attrition
• Formulaic Language
• Francoprovençal
• French Grammars
• Gabelentz, Georg von der
• Genealogical Classification
• Generative Syntax
• Genetics and Language
• Grammar, Categorial
• Grammar, Cognitive
• Grammar, Construction
• Grammar, Descriptive
• Grammar, Functional Discourse
• Grammars, Phrase Structure
• Grammaticalization
• Harris, Zellig
• Heritage Languages
• History of Linguistics
• History of the English Language
• Hmong-Mien Languages
• Hokan Languages
• Humor in Language
• Hungarian Vowel Harmony
• Idiom and Phraseology
• Imperatives
• Indefiniteness
• Indo-European Etymology
• Inflected Infinitives
• Information Structure
• Interface Between Phonology and Phonetics
• Interjections
• Iroquoian Languages
• Isolates, Language
• Jakobson, Roman
• Japanese Word Accent
• Jones, Daniel
• Juncture and Boundary
• Khoisan Languages
• Kiowa-Tanoan Languages
• Kra-Dai Languages
• Labov, William
• Language Acquisition
• Language and Law
• Language Contact
• Language Documentation
• Language, Embodiment and
• Language for Specific Purposes/Specialized Communication
• Language, Gender, and Sexuality
• Language Geography
• Language Ideologies and Language Attitudes
• Language in Autism Spectrum Disorders
• Language Nests
• Language Revitalization
• Language Shift
• Language Standardization
• Language, Synesthesia and
• Languages of Africa
• Languages of the Americas, Indigenous
• Learnability
• Lexical Access, Cognitive Mechanisms for
• Lexical-Functional Grammar
• Lexicography
• Lexicography, Bilingual
• Linguistic Accommodation
• Linguistic Anthropology
• Linguistic Areas
• Linguistic Landscapes
• Linguistic Prescriptivism
• Linguistics, Educational
• Listening, Second Language
• Literature and Linguistics
• Machine Translation
• Maintenance, Language
• Mande Languages
• Mathematical Linguistics
• Mayan Languages
• Mental Health Disorders, Language in
• Mental Lexicon, The
• Mesoamerican Languages
• Minority Languages
• Mixed Languages
• Mixe-Zoquean Languages
• Modification
• Mon-Khmer Languages
• Morphological Change
• Morphology, Blending in
• Morphology, Subtractive
• Munda Languages
• Muskogean Languages
• Niger-Congo Languages
• Non-Pama-Nyungan Languages
• Northeast Caucasian Languages
• Oceanic Languages
• Papuan Languages
• Penutian Languages
• Philosophy of Language
• Phonetics, Acoustic
• Phonetics, Articulatory
• Phonological Research, Psycholinguistic Methodology in
• Phonology, Computational
• Phonology, Early Child
• Policy and Planning, Language
• Positive Discourse Analysis
• Possessives, Acquisition of
• Pragmatics, Acquisition of
• Pragmatics, Cognitive
• Pragmatics, Computational
• Pragmatics, Cross-Cultural
• Pragmatics, Developmental
• Pragmatics, Experimental
• Pragmatics, Game Theory in
• Pragmatics, Historical
• Pragmatics, Institutional
• Pragmatics, Second Language
• Pragmatics, Teaching
• Prague Linguistic Circle, The
• Presupposition
• Psycholinguistics
• Quechuan and Aymaran Languages
• Reading, Second-Language
• Register and Register Variation
• Relevance Theory
• Representation and Processing of Multi-Word Expressions in...
• Salish Languages
• Sapir, Edward
• Saussure, Ferdinand de
• Second Language Acquisition, Anaphora Resolution in
• Semantic Maps
• Semantic Roles
• Semantic-Pragmatic Change
• Semantics, Cognitive
• Sign Language Linguistics
• Sociolinguistics, Variationist
• Sociopragmatics
• Sound Change
• South American Indian Languages
• Specific Language Impairment
• Speech, Deceptive
• Speech Production
• Speech Synthesis
• Switch-Reference
• Syntactic Change
• Syntactic Knowledge, Children’s Acquisition of
• Tense, Aspect, and Mood
• Text Mining
• Tone Sandhi
• Transcription
• Transitivity and Voice
• Translanguaging
• Trubetzkoy, Nikolai
• Tucanoan Languages
• Tupian Languages
• Usage-Based Linguistics
• Uto-Aztecan Languages
• Valency Theory
• Verbs, Serial
• Vocabulary, Second Language
• Voice and Voice Quality
• Vowel Harmony
• Whitney, William Dwight
• Word Formation in Japanese
• Word Recognition, Spoken
• Word Recognition, Visual
• Word Stress
• Writing, Second Language
• Writing Systems
• Zapotecan Languages
• Privacy Policy
• Cookie Policy
• Legal Notice
• Accessibility

Powered by:

• [185.66.15.189]
• 185.66.15.189

Academia.edu no longer supports Internet Explorer.

To browse Academia.edu and the wider internet faster and more securely, please take a few seconds to  upgrade your browser .

Enter the email address you signed up with and we'll email you a reset link.

• We're Hiring!
• Help Center

Contrastive Analysis Hypothesis and Second Language Learning

Journal of ELT Research

This article aims to provide an overview of some of the issues related to contrastive analysis hypothesis in second language learning. Contrastive hypothesis is one of the branches of applied linguistics which concerns with the study of two systems of languages between first language and target language. Contrastive hypothesis has fairly played an important role in language studies. Thus, in recent years, contrastive analysis has been used in language teaching contexts, syllabus design, and language classrooms by language teachers over the world. Many research works have been done by many language researchers in different aspects of contrastive hypothesis and also error analysis in the world. Language teachers always see contrastive analysis as a pedagogical imperative in target language and they use it as a functional approach in language classroom. However, contrastive hypothesis follows the errors of language learners in second language education.

Related Papers

Sinan Bayraktaroglu

Italica. Vol. 70, No. 2. Pp. 228-229.

Frank Nuessel

This review of Danesi and Di Pietro's volume on Contrastive Analysis is the definitive statement on this topic. This volume features an innovation, which the authors label the "stage hypothesis", which is designed to illustrate that CA is not a comprehensive theory of second-language acquisition, but rather a mechanism for the earliest stages of second-language instruction.

International Journal of Education (IJE)

Nathalie DJIGUIMKOUDRE

Contrastive analysis (CA) was primarily used in the 1950’s as an effective means to address second or foreign language teaching and learning. In this context, it was used to compare pairs of languages, identify similarities and differences in order to predict learning difficulties, with the ultimate goal of addressing them (Fries, 1943; Lado, 1957). Yet, in the 1980’s and 1990’s the relevance of CA has been disputed. Many studies have pointed out the limit of CA with respect to its weak and strong versions (Oller and Ziahosseiny, 1970), (Wardhaugh, 1970) (Brown, 1989), (Hughes, 1980), (Yang, 1992), and (Whitman and Jackson, 1972). To answer the limits of CA with regards to its weak, strong, and moderate versions, many language teachers used CA with a new approach. Kupferberg and Olshtain (1996), James (1996), and Ruzhekova-Rogozherova (2007). Here, salient contrastive linguistic input (CLI) is presented to learners for an effective noticing. Yet, mere exposition of contrastive lingu...

International Letters of Social and Humanistic Sciences

Masoud Mahmoodzadeh

The current paper reflects on the evolving course and place of contrastive aspects of second language research. It attempts to give a concise overview of the related cross-linguistic perspectives over the last decades and elucidates their ascribed nuts and bolts in order to shed further light on the role and significance of cross-linguistic studies in second language research from the past up until now. To this end, the author expressly elaborates on different versions of Contrastive Analysis (CA) to come up with a clear picture of…

Dennis Kojo Appiah

Theory and Practice in Language Studies

Văn Quyến Lê

Lazarus Gawazah

This study problematizes contrastive linguistics by highlighting the connection between interlanguage and error analysis. A qualitative method for data collection and analysis was used. The study applied the theories of Contrastive Analysis (CA) to compare and contrast linguistic and socio-cultural data between the Shona and the English languages. It was revealed that although there are similarities in the Subject Verb Agreement (SVO) between the two languages, there are also differences in that the Shona language is implicit in addressing the gender of the subject whereas the English language is explicit in identifying the gender of the subject by the use of explicit pronouns. The study concludes that the difficulties in language learning emanate from the differences between the new language (L2) and learners first language (L1) interference. In addition to that, the two languages under this study have differences in typological features. The study recommends the prescription of contrastive analysis theories in the teaching and learning of language.

IJELS AIAC , Dr. Bandar Al-Sobhi

The major aim of the current paper is to review and discuss three prevailing approaches to the study of Second Language Acquisition (SLA) since the middle of the twentieth century: Contrastive Analysis (CA, henceforth), Error Analysis (EA) and Interlanguage (IL). It begins with a general overview of how the CA approach was formulated and developed and discusses the three versions of CA which were displaced later by other approaches, such as EA and IL. The paper also provides an in-depth theoretical discussion of the notion of EA in terms of its definitions, goals, significance, development, causes and procedures. The discussion about the SLA approaches concludes with a review of IL which claims that language learners produce a separate linguistic system with its own salient features, which differs from their L1 and target language. Additionally, a bulk of previous studies conducted on EA in different contexts are reviewed throughout the paper.

Contrastive linguistics and language teacher. Oxford: …

S. N. Sridhar

Loading Preview

Sorry, preview is currently unavailable. You can download the paper by clicking the button above.

RELATED PAPERS

Readings on English as a Second language for Teachers and Teacher Trainers

Fatma Seçkin

univagro-iasi.ro

Roxana Mihalache

Ruth A . Berman

Endang Fauziati

Parviz Maftoon

Philip Joshua Aristoteles

Ngoc Lan Luu

Amjed Al-Rickaby

Acer Aspire

Ebru Yener Gökşenli

eprahim sagala

moses kambou

Journal of Humanities and Cultural Studies R&D

Marc D. Sakellarios , Gregory D Price

Sabiha Sultana

Dictionaries of Linguistics and Communication Science: Linguistic theory and methodology

Volker Gast

Stephen Ryan

Lahivordlusi Lahivertailuja

Annekatrin Kaivapalu

Dr. Abdullah M . M . A . Shaghi

Proceedings of the 1st Yogyakarta International Conference on Educational Management/Administration and Pedagogy (YICEMAP 2017)

Roni Sulistiyono

Amin Elkhadri

English Language Teaching

Milton Alcides Pajaro Manjarres

Contrastive Analysis

Overt Writes

RELATED TOPICS

•   We're Hiring!
•   Help Center
• Find new research papers in:
• Health Sciences
• Earth Sciences
• Cognitive Science
• Mathematics
• Computer Science
• Academia ©2024

• DOI: 10.22236/jer_vol4issue1pp35-43
• Corpus ID: 164683481

Contrastive Analysis Hypothesis and Second Language Learning

• Ali Akbar Khansir , Farhad Pakdel
• Published in Journal of ELT Research 27 February 2019
• Linguistics, Education

21 Citations

Error analysis and english syllabus, cognitive awareness of the efl learner of contrastive linguistics between english and arabic: a case study, integrating linguistics theories in developing foreign language teaching materials (german grammar textbook for indonesian learners), a contrastive analysis between english and indonesian copulative verbs, a preliminary study in developing a contrastive and error analyses-based german grammar textbook, verb conjugation in different languages: a preliminary study in developing german grammar book based contrastive analysis, the effect of using discussion method in promoting english language knowledge among english foreign language learners, a contrastive analysis of english and bisayan languages: cases of pronouns in focus, improving chinese reading and writing skills: second language acquisition theory perspective, contrastive analysis of english and indonesian adverbs, 37 references, linguistics in language teaching, place of linguistics in english language teaching, exploring language pedagogy through second language acquisition research, applied linguistics and english language teaching, error analysis and second language acquisition.

• Highly Influential

Theory and Practice in Language Studies

Instructed second language acquisition, language learning and teaching, a comparative linguistic study of errors, the study of second language acquisition.: rod ellis, related papers.

Showing 1 through 3 of 0 Related Papers

• Architecture and Design
• Asian and Pacific Studies
• Business and Economics
• Classical and Ancient Near Eastern Studies
• Computer Sciences
• Cultural Studies
• Engineering
• General Interest
• Geosciences
• Industrial Chemistry
• Islamic and Middle Eastern Studies
• Jewish Studies
• Library and Information Science, Book Studies
• Life Sciences
• Linguistics and Semiotics
• Literary Studies
• Materials Sciences
• Mathematics
• Social Sciences
• Sports and Recreation
• Theology and Religion
• Publish your article
• The role of authors
• Promoting your article
• Abstracting & indexing
• Publishing Ethics
• Why publish with De Gruyter
• How to publish with De Gruyter
• Our book series
• Our subject areas
• Your digital product at De Gruyter
• Contribute to our reference works
• Product information
• Tools & resources
• Product Information
• Promotional Materials
• Orders and Inquiries
• FAQ for Library Suppliers and Book Sellers
• Repository Policy
• Free access policy
• Open Access agreements
• Database portals
• For Authors
• Customer service
• People + Culture
• Journal Management
• How to join us
• Working at De Gruyter
• Mission & Vision
• De Gruyter Foundation
• De Gruyter Ebound
• Our Responsibility
• Partner publishers

Your purchase has been completed. Your documents are now available to view.

1. Was there Really Ever a Contrastive Analysis Hypothesis?

From the book crosslinguistic influence in second language acquisition.

• Terence Odlin
• X / Twitter

Supplementary Materials

Please login or register with De Gruyter to order this product.

Chapters in this book (16)

Information

• Author Services

Initiatives

You are accessing a machine-readable page. In order to be human-readable, please install an RSS reader.

All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess .

Feature papers represent the most advanced research with significant potential for high impact in the field. A Feature Paper should be a substantial original Article that involves several techniques or approaches, provides an outlook for future research directions and describes possible research applications.

Feature papers are submitted upon individual invitation or recommendation by the scientific editors and must receive positive feedback from the reviewers.

Editor’s Choice articles are based on recommendations by the scientific editors of MDPI journals from around the world. Editors select a small number of articles recently published in the journal that they believe will be particularly interesting to readers, or important in the respective research area. The aim is to provide a snapshot of some of the most exciting work published in the various research areas of the journal.

Original Submission Date Received: .

• Active Journals
• Find a Journal
• Proceedings Series
• For Authors
• For Reviewers
• For Editors
• For Librarians
• For Publishers
• For Societies
• For Conference Organizers
• Open Access Policy
• Institutional Open Access Program
• Special Issues Guidelines
• Editorial Process
• Research and Publication Ethics
• Article Processing Charges
• Testimonials
• Preprints.org
• SciProfiles
• Encyclopedia

Article Menu

• Subscribe SciFeed
• Recommended Articles
• Google Scholar
• on Google Scholar
• Table of Contents

Find support for a specific problem in the support section of our website.

Please let us know what you think of our products and services.

Visit our dedicated information section to learn more about MDPI.

JSmol Viewer

Generating complex explanations for artificial intelligence models: an application to clinical data on severe mental illness.

1. Introduction

2. data and methods, 2.1. overview of methods.

• We took de-identified data from an electronic patient record system for mental health.
• We established a collection of features that are not dependent on time, such as age, diagnosis categories, medication categories, and bio-social elements that are essential in severe mental illness (SMI). These features included data on mental health, personal history (e.g., previous suicide attempts and substance abuse), and social predisposing factors (e.g., lack of family support).
• We used these features to predict death during the time of observation.
• We then fit machine learning models and classical statistical models.
• We generated class-contrastive heatmaps to illustrate the explanations of statistical models and machine learning predictions, as well as accompanying statements to facilitate human understanding.
• Machine learning scientists can use these class-contrastive heatmaps to create complex explanations.

2.2. Mental Health Clinical Record Database

2.3. data input to statistical algorithms.

• High-level medication categories were created based on domain-specific knowledge from a clinician. These medication categories were as follows: second-generation antipsychotics (SGA: clozapine, olanzapine, risperidone, quetiapine, aripiprazole, asenapine, amisulpride, iloperidone, lurasidone, paliperidone, sertindole, sulpiride, ziprasidone, zotepine), first-generation antipsychotics (FGA: haloperidol, benperidol, chlorpromazine, flupentixol, fluphenazine, levomepromazine, pericyazine, perphenazine, pimozide, pipotiazine, prochlorperazine, promazine, trifluoperazine, zuclopenthixol), antidepressants (agomelatine, amitriptyline, bupropion, clomipramine, dosulepin, doxepin, duloxetine, imipramine, isocarboxazid, lofepramine, maprotiline, mianserin, mirtazapine, moclobemide, nefazodone, nortriptyline, phenelzine, reboxetine, tranylcypromine, trazodone, trimipramine, tryptophan, sertraline, citalopram, escitalopram, fluoxetine, fluvoxamine, paroxetine, vortioxetine and venlafaxine), diuretics (furosemide), thyroid medication (drug mention of levothyroxine), antimanic drugs (lithium), and medications for dementia (memantine and donepezil).
• Relevant co-morbidities we included were diabetes (inferred from ICD-10 codes E10, E11, E12, E13, and E14, and any mentions of the drugs metformin and insulin), cardiovascular diseases (inferred from ICD-10 diagnoses codes I10, I11, I26, I82, G45, and drug mentions of atorvastatin, simvastatin, and aspirin), respiratory illnesses (J44 and J45) and anti-hypertensives (mentions of drugs bisoprolol and amlodipine).
• We included all patients with a coded diagnosis of schizophrenia (F20). For these patients with schizophrenia, we also included any additional coded diagnosis from the following broad diagnostic categories: dementia in Alzheimer’s disease (ICD-10 code starting F00), delirium (F05), mild cognitive disorder (F06.7), depressive disorders (F32, F33), and personality disorders (F60).
• We also included relevant social factors: lack of family support (ICD-10 chapter code Z63) and personal risk factors (Z91: a code encompassing allergies other than to drugs and biological substances, medication noncompliance, a history of psychological trauma, and unspecified personal risk factors); alcohol and substance abuse (this was inferred from ICD-10 coded diagnoses of Z86, F10, F12, F17, F19, and references to thiamine, which is prescribed for alcohol abuse). Other features included were self-harm (ICD-10 codes T39, T50, X60, X61, X62, X63, X64, X78, and Z91.5), non-compliance and personal risk factors (Z91.1), referral to a crisis team at CPFT (recorded in the electronic healthcare record system), and any prior suicide attempts (in the last 6 months or any time in the past) coded in structured risk assessments.

2.4. Data Pre-Processing

2.5. machine learning and statistical techniques.

• Logistic regression model with all original input features.
• All the original input features used as input for the autoencoder. The reduced dimensions from an autoencoder were then used as input to a random forest model ( Figure 2 ).

Class-Contrastive Reasoning

2.6. machine learning methods, 2.7. software, 3.1. class-contrastive reasoning and modifying the training data to generate explanations.

• we used case-based reasoning to determine which patients are similar and have these characteristics.
• we then removed these data from the training set.
• we retrained the statistical model on this modified data.

3.2. Class-Contrastive Reasoning Applied to Machine Learning Models

3.3. generating complex explanations, 3.4. counter-intuitive narratives, 3.5. additional analysis with simpler models, 4. discussion, 4.1. overview, 4.2. implications of findings, 4.3. relevant work, 4.4. limitations and future work, 4.5. concluding remarks, institutional review board statement, informed consent statement, data availability statement, acknowledgments, conflicts of interest.

• Sokol, K.; Flach, P. Conversational Explanations of Machine Learning Predictions through Class-contrastive Counterfactual Statements. Int. Jt. Conf. Artif. Intell. Organ. 2018 , 7 , 5785–5786. [ Google Scholar ] [ CrossRef ]
• Banerjee, S.; Lio, P.; Jones, P.B.; Cardinal, R.N. A class-contrastive human-interpretable machine learning approach to predict mortality in severe mental illness. NPJ Schizophr. 2021 , 7 , 60. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Olfson, M.; Gerhard, T.; Huang, C.; Crystal, S.; Stroup, T.S. Premature mortality among adults with schizophrenia in the United States. JAMA Psychiatry 2015 , 72 , 1172–1181. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Cardinal, R.N. Clinical records anonymisation and text extraction (CRATE): An open-source software system. BMC Med. Inform. Decis. Mak. 2017 , 17 , 50. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Cunningham, H.; Tablan, V.; Roberts, A.; Bontcheva, K. Getting More Out of Biomedical Documents with GATE’s Full Lifecycle Open Source Text Analytics. PLoS Comput. Biol. 2013 , 9 , e1002854. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Sultana, J.; Chang, C.K.; Hayes, R.D.; Broadbent, M.; Stewart, R.; Corbett, A.; Ballard, C. Associations between risk of mortality and atypical antipsychotic use in vascular dementia: A clinical cohort study. Int. J. Geriatr. Psychiatry 2014 , 29 , 1249–1254. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• WHO. The ICD-10 Classification of Mental and Behavioural Disorders: Clinical Descriptions and Diagnostic Guidelines ; World Health Organization: Geneva, Switzerland, 1992. [ Google Scholar ]
• Winter, B. Linear models and linear mixed effects models in R with linguistic applications. arXiv 2013 , arXiv:1308.5499. [ Google Scholar ]
• Bates, D.; Mächler, M.; Bolker, B.; Walker, S. Fitting Linear Mixed-Effects Models Using lme4. J. Stat. Softw. 2015 , 67 , 1–48. [ Google Scholar ] [ CrossRef ]
• Gareth, J.; Daniela, W.; Trevor, H.; Robert, T. Introduction to Statistical Learning with Applications in R ; Springer: Berlin/Heidelberg, Germany, 2017. [ Google Scholar ]
• Beaulieu-Jones, B.K.; Greene, C.S. Semi-supervised learning of the electronic health record for phenotype stratification. J. Biomed. Inform. 2016 , 64 , 168–178. [ Google Scholar ] [ CrossRef ]
• Chollet, F. Keras, Version 2.3.0. 2015. Available online: https://github.com/keras-team/keras (accessed on 1 June 2019).
• Abadi, M.; Barham, P.; Chen, J.; Chen, Z.; Davis, A.; Dean, J.; Devin, M.; Ghemawat, S.; Irving, G.; Isard, M.; et al. TensorFlow: A system for large-scale machine learning. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), Savannah, GA, USA, 2–4 November 2016; pp. 265–283. [ Google Scholar ]
• Glorot, X.; Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS’10), Sardinia, Italy, 13–15 May 2010; Volume 9, pp. 249–256. [ Google Scholar ]
• Zeiler, M.D. ADADELTA: An Adaptive Learning Rate Method. arXiv 2012 , arXiv:1212.5701. [ Google Scholar ]
• R Core Team. R: A Language and Environment for Statistical Computing ; R Foundation for Statistical Computing: Vienna, Austria, 2018. [ Google Scholar ]
• Kuznetsova, A.; Brockhoff, P.B.; Christensen, R.H.B. lmerTest Package: Tests in Linear Mixed Effects Models. J. Stat. Softw. 2017 , 82 , 1–26. [ Google Scholar ] [ CrossRef ]
• Kolde, R. Pheatmap: Pretty Heatmaps, Version 1.0.12. 2018. Available online: https://cran.r-project.org/web/packages/pheatmap/ (accessed on 1 June 2019).
• Yang, Y.; Banerjee, S. Generating complex explanations from machine learning models using class-contrastive reasoning. medRxiv 2023 . Available online: https://www.medrxiv.org/content/10.1101/2023.10.06.23296591v1 (accessed on 3 April 2024).
• Geirhos, R.; Jacobsen, J.H.; Michaelis, C.; Zemel, R.; Brendel, W.; Bethge, M.; Wichmann, F.A. Shortcut Learning in Deep Neural Networks. Nat. Mach. Intell. 2020 , 2 , 665–673. [ Google Scholar ] [ CrossRef ]
• Koton, P. Using Experience in Learning and Problem Solving. Ph.D. Thesis, Massachusetts Institute of Technology, Cambridge, MA, USA, 1988. [ Google Scholar ]
• Langley, P.; Jones, R. A computational model of scientific insight. In The Nature of Creativity: Contemporary Psychological Perspectives ; Sternberg, R.J., Ed.; Cambridge University Press: Cambridge, UK, 1997; pp. 177–201. [ Google Scholar ]
• Olah, C.; Cammarata, N.; Schubert, L.; Goh, G.; Petrov, M.; Carter, S. Zoom In: An Introduction to Circuits. Distill 2020 , 5 , e00024.001. [ Google Scholar ] [ CrossRef ]
• Winston, P.H. The next 50 years: A personal view. Biol. Inspired Cogn. Archit. 2012 , 1 , 92–99. [ Google Scholar ] [ CrossRef ]
• Winston, P.H. The strong story hypothesis and the directed perception hypothesis. Assoc. Adv. Artif. Intell. 2011 , FS-11-01 , 345–352. [ Google Scholar ]
• Davis, E.; Marcus, G. Commonsense reasoning and commonsense knowledge in artificial intelligence. Commun. ACM 2015 , 58 , 92–103. [ Google Scholar ] [ CrossRef ]
• Marcus, G. The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence. arXiv 2020 , arXiv:2002.06177. [ Google Scholar ]
• Banerjee, S. A Framework for Designing Compassionate and Ethical Artificial Intelligence and Artificial Consciousness. Interdiscip. Descr. Complex Syst. 2020 , 18 , 85–95. [ Google Scholar ] [ CrossRef ]
• Banerjee, S.; Alsop, P.; Jones, L.; Cardinal, R.N. Patient and public involvement to build trust in artificial intelligence: A framework, tools, and case studies. Patterns 2022 , 3 , 100506. [ Google Scholar ] [ CrossRef ]
• Dillon, S.; Craig, C. Storylistening: Narrative Evidence and Public Reasoning ; Routledge: Oxfordshire, UK, 2021. [ Google Scholar ]
• Lenzen, V.F.; Craik, K.J.W. The Nature of Explanation. Philos. Rev. 1944 , 53 , 503. [ Google Scholar ] [ CrossRef ]
• Winston, P.H. The right way. Adv. Cogn. Syst. 2012 , 1 , 23–36. [ Google Scholar ]
• Winston, P. Genesis Project. Available online: https://robohub.org/professor-patrick-winston-former-director-of-mits-artificial-intelligence-laboratory-dies-at-76/ (accessed on 1 June 2019).
• Elhanashi, A.; Saponara, S.; Dini, P.; Zheng, Q.; Morita, D.; Raytchev, B. An integrated and real-time social distancing, mask detection, and facial temperature video measurement system for pandemic monitoring. J. Real-Time Image Process. 2023 , 20 , 1–14. [ Google Scholar ] [ CrossRef ]
• Shoham, Y. Viewpoint: Why knowledge representation matters. Commun. ACM 2016 , 59 , 47–49. [ Google Scholar ] [ CrossRef ]
• Software Vendors Are Pushing Explainable A.I., But Those Explanations May Be Meaningless | Fortune. Available online: https://fortune-com.cdn.ampproject.org/c/s/fortune.com/2022/03/22/ai-explainable-radiology-medicine-crisis-eye-on-ai/amp/ (accessed on 6 June 2024).
• Krishna, S.; Han, T.; Gu, A.; Pombra, J.; Jabbari, S.; Wu, S.; Lakkaraju, H. The Disagreement Problem in Explainable Machine Learning: A Practitioner’s Perspective. arXiv 2022 , arXiv:2202.01602. [ Google Scholar ]
• Ghassemi, M.; Oakden-Rayner, L.; Beam, A.L. The false hope of current approaches to explainable artificial intelligence in health care. Lancet 2021 , 3 , E745–E750. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Gilmer, J.; Metz, L.; Faghri, F.; Schoenholz, S.S.; Raghu, M.; Wattenberg, M.; Goodfellow, I. Adversarial Spheres. arXiv 2018 , arXiv:1801.02774. [ Google Scholar ]
• Kůrková, V. Some insights from high-dimensional spheres: Comment on “The unreasonable effectiveness of small neural ensembles in high-dimensional brain” by Alexander N. Gorban et al. Phys. Life Rev. 2019 , 29 , 98–100. [ Google Scholar ] [ CrossRef ]

Click here to enlarge figure

Share and Cite

Banerjee, S. Generating Complex Explanations for Artificial Intelligence Models: An Application to Clinical Data on Severe Mental Illness. Life 2024 , 14 , 807. https://doi.org/10.3390/life14070807

Banerjee S. Generating Complex Explanations for Artificial Intelligence Models: An Application to Clinical Data on Severe Mental Illness. Life . 2024; 14(7):807. https://doi.org/10.3390/life14070807

Banerjee, Soumya. 2024. "Generating Complex Explanations for Artificial Intelligence Models: An Application to Clinical Data on Severe Mental Illness" Life 14, no. 7: 807. https://doi.org/10.3390/life14070807

Article Metrics

Further information, mdpi initiatives, follow mdpi.

Subscribe to receive issue release notifications and newsletters from MDPI journals

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Open access
• Published: 26 June 2024

AI-based histopathology image analysis reveals a distinct subset of endometrial cancers

• Amirali Darbandsari 1   na1 ,
• Hossein Farahani   ORCID: orcid.org/0000-0002-9503-1875 2 , 3   na1 ,
• Maryam Asadi 2   na1 ,
• Matthew Wiens 2 ,
• Dawn Cochrane 4 ,
• Ali Khajegili Mirabadi   ORCID: orcid.org/0000-0002-0489-6583 2 ,
• Amy Jamieson 5 ,
• David Farnell 3 , 6 ,
• Pouya Ahmadvand 2 ,
• Maxwell Douglas 4 ,
• Samuel Leung 4 ,
• Purang Abolmaesumi 1 ,
• Steven J. M. Jones   ORCID: orcid.org/0000-0003-3394-2208 7 ,
• Aline Talhouk 5 ,
• Stefan Kommoss 8 ,
• C. Blake Gilks 3 , 6 ,
• David G. Huntsman 3 , 4   na2 ,
• Naveena Singh 3 , 6   na2   na3 ,
• Jessica N. McAlpine   ORCID: orcid.org/0000-0001-6003-485X 5   na2 &
• Ali Bashashati   ORCID: orcid.org/0000-0002-4212-7224 2 , 3   na2  

Nature Communications volume  15 , Article number:  4973 ( 2024 ) Cite this article

Metrics details

• Cancer genomics
• Cancer imaging
• Endometrial cancer
• Machine learning
• Prognostic markers

Endometrial cancer (EC) has four molecular subtypes with strong prognostic value and therapeutic implications. The most common subtype (NSMP; No Specific Molecular Profile) is assigned after exclusion of the defining features of the other three molecular subtypes and includes patients with heterogeneous clinical outcomes. In this study, we employ artificial intelligence (AI)-powered histopathology image analysis to differentiate between p53abn and NSMP EC subtypes and consequently identify a sub-group of NSMP EC patients that has markedly inferior progression-free and disease-specific survival (termed ‘p53abn-like NSMP’), in a discovery cohort of 368 patients and two independent validation cohorts of 290 and 614 from other centers. Shallow whole genome sequencing reveals a higher burden of copy number abnormalities in the ‘p53abn-like NSMP’ group compared to NSMP, suggesting that this group is biologically distinct compared to other NSMP ECs. Our work demonstrates the power of AI to detect prognostically different and otherwise unrecognizable subsets of EC where conventional and standard molecular or pathologic criteria fall short, refining image-based tumor classification. This study’s findings are applicable exclusively to females.

Introduction

The clinicopathological parameters used for decades to classify endometrial cancers (EC) and guide management have been sub-optimally reproducible, particularly in high-grade tumors 1 , 2 . Specifically, inconsistency in grade and histotype assignment has yielded an inaccurate assessment of the risk of disease recurrence and death. As a result, many women affected by EC may be over-treated or are not directed to treatment that might have reduced their risk of recurrence. In 2013, the Cancer Genome Atlas (TCGA) project demonstrated that endometrial cancers could be stratified into four distinct prognostic groups using a combination of whole genome and exome sequencing, microsatellite instability (MSI) assays, and copy number analysis 3 . These subtypes were labeled according to dominant genomic abnormalities and included ‘ultra-mutated’ ECs harboring POLE mutations, ‘hypermutated’ identified to have microsatellite instability, copy-number low, and copy-number high endometrial cancers.

Inspired by this initial discovery, our team and a group from the Netherlands independently and concurrently developed a pragmatic, clinically applicable molecular classification system that classifies ECs into: (i) POLE mutant ( POLE mut) with pathogenic mutations in the exonuclease domain of POLE (DNA polymerase epsilon, involved in DNA proofreading repair), (ii) mismatch repair deficient (MMRd) diagnosed based on the absence of key mismatch repair proteins on immunohistochemistry (IHC), (iii) p53 abnormal (p53abn) as assessed by IHC, and (iv) NSMP (No Specific Molecular Profile), lacking any of the defining features of the other three subtypes 4 , 5 . Categorization of ECs into these subtypes recapitulates the survival curves/prognostic value of the four TCGA molecular subgroups and enhances histopathological evaluation, offering an objective and reproducible classification system with strong prognostic value and therapeutic implications. In 2020, the World Health Organization (WHO) recommended integrating these key molecular features into standard pathological reporting of ECs when available 6 .

POLE mut endometrial cancers have highly favorable outcomes with almost no deaths due to disease. While the three other molecular subtypes are associated with more variable outcomes (MMRd and NSMP are considered ‘intermediate risk’ and p53abn ECs have the worst prognosis), within each subtype there are clinical and prognostic outliers 7 , 8 , 9 , 10 . This is particularly true within the largest subtype, NSMP (representing ~ 50% of ECs). The majority of NSMP tumors are early-stage, low-grade, estrogen-driven tumors likely cured by surgery alone. However, a subset of patients with NSMP EC experience a very aggressive disease course, comparable to what is observed in patients with p53abn ECs. At present, limited tools exist to identify these aggressive outliers and current clinical guidelines do not stratify or direct treatment within NSMP EC beyond using pathologic features 11 , 12 . Thus, for half of diagnosed endometrial cancers, i.e., NSMP EC, the assumption of indolence is inappropriate and clinicians need tools for accurate risk stratification of individual patients when making treatment decisions.

With the rise of artificial intelligence (AI) in the past decade, deep learning methods (e.g., deep convolutional neural networks and their extensions) have shown impressive results in processing text and image data 13 . The paradigm-shifting ability of these models to learn predictive features from raw data presents exciting opportunities with medical images, including digitized histopathology slides 14 , 15 , 16 , 17 . In recent years, these models have been deployed to reproduce or improve pathology diagnosis in various disease conditions (e.g., 18 , 19 , 20 ), explore the potential link between histopathologic features and molecular markers in different cancers including EC 17 , 21 , 22 , 23 , 24 , and directly link histopathology to clinical outcomes 25 , 26 , 27 , 28 . More specifically, three recent studies have reported promising results in the application of deep learning-based models to identify the four molecular subtypes of EC from histopathology images 22 , 23 , 29 .

In this work, building on a recent study reporting morphological heterogeneity in NSMP ECs and nuclear features typical of p53abn ECs in some tumors of this subtype 30 , we built a deep learning-based image classifier to differentiate between the NSMP and p53abn ECs. We then hypothesized that within the NSMP molecular subtype of endometrial cancer, there is a subset of patients with aggressive disease whose tumors have histological features similar to p53abn EC and that these tumors can be identified by deep learning models applied to hematoxylin & eosin (H&E)-stained slides. Our results show that these cases (referred to as p53abn-like NSMP ) have inferior outcomes compared to the other NSMP ECs, similar to that of p53abn EC, in three independent cohorts. Furthermore, shallow whole genome sequencing studies suggested that the genomic architecture of the p53abn-like NSMP differs from other NSMP ECs, showing increased copy number abnormalities, a characteristic of p53abn EC.

Patient cohort selection and description

2318 H&E-stained hysterectomy tissue sections from 1272 patients with histologically confirmed endometrial carcinoma of NSMP or p53abn subtypes were included in this study 3 , 4 , 5 . Our discovery cohort included 155 whole-section slides (WSI) from 146 patients from TCGA 3 and 431 WSIs (222 patients) from Tubingen University 5 . Two separate validation Canadian cohorts were included in this study: (1) the British Columbia (BC) cohort, a tissue microarray (TMA) dataset corresponding to 290 patients from our own center 4 , and (2) Cross Canada (CC) cohort, 640 WSIs (614 patients) collected from 26 hospitals across Canada 31 . Tables  1 – 3 show the clinicopathological features of the discovery and validation cohorts. Overview of the cohorts, outcome information, treatment information, and distribution of samples in the CC cohort across different centers can be found in Supplementary Tables  1 – 4 .

Histopathology-based machine learning classifier to differentiate NSMP and p53abn ECs

Fig.  1 depicts our AI-based histopathology image analysis pipeline. A subset of 27 whole-section H&E slides from the TCGA cohort were annotated by a board-certified pathologist (DF) using a custom in-house histopathology slide viewer ( cPathPortal ) to identify areas containing tumor and non-tumor cells (myometrium, endometrial stroma, and benign endometrial epithelium). A deep convolutional neural network (CNN)-based classifier was then trained to acquire pseudo-tumor and benign annotations for the remaining slides in the discovery cohort. The identified tumor regions were then divided into 512 × 512 pixel patches at 20x objective magnification. The number of extracted patches from each subtype and performance measure for the tumor stroma classifier can be found in Supplementary Tables  1 and 5 , respectively. To address variability in slide staining due to differences in staining protocols across different centers, and inter-patient variability, we utilized the Vahadane color normalization technique 32 . We then trained a VarMIL model 33 based on multiple instance learning (MIL) to differentiate H&E image patches associated with p53abn and NSMP ECs.

First, the quality control framework, HistoQC 81 , generates a mask that comprises tissue regions exclusively and removes artifacts. Then, an AI model to identify tumor regions within histopathology slides is trained. Next, images are tessellated into small patches and normalized to remove color variations. The normalized patches are fed to a deep-learning model to derive patch-level representations. Finally, a model based on multiple instance learning (VarMIL) was utilized to predict the patient subtype.

In a “group 10-fold” cross-validation strategy, the patients in our discovery cohort were divided into 10 groups, and in various combinations, 60% were used for training, 20% for validation, and 20% for testing; resulting in 10 different binary p53abn vs. NSMP classifiers. These 10 classifiers were then used to label the cases as p53abn or NSMP and their consensus was used to come up with a label for a given case. For patients with multiple slides, to prevent data leakage between training, validation, and test sets, we assigned slides from each patient to only one of these sets.

Fig.  2A and Supplementary Table  6 show the receiver operating characteristics (ROC) and precision/recall curves as well as performance metrics of the resulting classifiers for the discovery and BC validation cohorts, respectively. These results suggest that our p53abn vs. NSMP classifier achieves 89.4% and 79.8% mean balanced accuracy (across the 10 classifiers) and area under the curve (AUC) of 0.95 and 0.88 in both the discovery and BC validation sets, respectively (for details see Supplementary Tables  7 and 8 and Supplementary Fig.  1 ).

A AUROC and precision-recall plots of average of 10 splits for p53abn vs. NSMP classifier for discovery and validation sets, ( B ) KM curves associated with PFS and DSS (where available) for the discovery set, using a two-sided log-rank statistical test, ( C ) KM curves associated with PFS and DSS (where available) in the BC validation set, using a two-sided log-rank statistical test (Source data are provided as a Source Data file).

Identification of a subset of NSMP ECs with inferior survival

Our proposed ML-based models classified 17.65% and 20% of NSMPs as p53abn for the discovery and validation cohorts, respectively (Supplementary Table  6 ). These cases (referred to as p53abn-like NSMP group) presumably show p53abn histological features in the assessment of H&E images even though immunohistochemistry did not show mutant-pattern p53 expression and these were therefore classified as NSMP by the molecular classifier. We hypothesized that such cases may in fact exhibit similar clinical behavior as p53abn ECs.

Fig.  2B, C show the progression free survival (PFS) and disease-specific survival (DSS) of the discovery and BC validation sets. Compared to the rest of the NSMP cases, p53abn-like NSMP s had markedly inferior PFS (10-year PFS 55.7% vs. 89.6% ( p  = 2.7e-7)) and DSS (10-year DSS 62.6% vs. 93.7% ( p  = 1.8e-7)) in our discovery cohort. These findings were confirmed in the BC cohort, with 20% of the 195 patients categorized as p53abn-like tumors, showing 10-year PFS of 65.4% vs. 91.2% ( p  = 1.1e-4) and DSS of 58.3% vs. 84.3% ( p  = 5.3e-5). In addition, a comparison of the PFS and DSS between p53abn-like NSMP and p53abn ECs revealed a trend, though not statistically significant, in which p53abn-like NSMP s had better outcomes compared to p53abn ECs in both the discovery and BC validation cohorts (Supplementary Fig.  2A, B ).

Of note, our model also identified a subset of p53abn ECs (representing 20%; referred to as NSMP-like p53abn ) with a resemblance to NSMP as assessed by H&E staining. While we observed marginally superior disease-specific survival in the identified cases compared to the rest of the p53abn group both in the discovery and BC validation cohorts, progression free survival was not significantly different between the groups (Supplementary Fig.  3A, B ).

Robustness of p53abn-like NSMP subtype

Our proposed deep learning-based model was built to differentiate between NSMP and p53abn EC subtypes. Given that these subtypes are determined based on molecular assays, their accurate identification from routine H&E-stained slides would have removed the need to perform molecular testing that might only be available in specialized centers. However, our observation of imperfect results and characterization of discordant cases as p53abn-like NSMP required further investigation to rule out the possibility of a superior deep learning model that could result in a better performance in differentiating p53abn and NSPMP molecular subtypes. Therefore, we implemented seven other deep learning-based image analysis strategies including more recent state-of-the-art models to test the stability of the identified classes (see Methods section for further details). Our results showed that these models also achieve balanced accuracies ranging from 83.5–95% and 77.3–80.2% and AUCs ranging from 0.88–0.98 and 0.8–0.88 in both the discovery and validation sets, respectively (Supplementary Fig.  4 and Supplementary Tables  9 , 10 ). Furthermore, Kaplan-Meier survival analysis of the so-called p53abn-like NSMP group identified by these models also corroborated with our initial findings in which this subgroup had statistically significant inferior survival compared to the rest of the patients (Supplementary Fig.  5 ). These results suggest that the choice of the algorithm did not substantially affect the findings and outcome of our study. To further investigate the robustness of our results, we utilized an unsupervised approach in which we extracted histopathological features from the slides in our validation cohort utilizing KimiaNet 34 feature representation. Our results suggested that p53abn-like NSMP and the rest of the NSMP cases constitute two separate clusters with no overlap (Fig.  3A ) suggesting that our findings could also be achieved with unsupervised approaches. It is noteworthy to mention that we utilized the original KimiaNet weights for feature extraction without any finetuning the model on our datasets. To assess the sensitivity of the unsupervised approach to the choice of dimensionality reduction technique, we experimented with DenseNet121 35 , Swin 36 , and ResNet50. The analysis revealed that identified clusters remain consistent (i.e., two clusters) across these techniques (Supplementary Fig.  6 ).

A Histopathological features from the slides in the validation cohort utilizing KimiaNet feature representation from the slides in the validation cohort demonstrate that p53abn-like NSMP and the rest of the NSMP cases constitute two separate clusters, ( B ) Clinicopathological features and point mutation data for the BC validation cohort, ( C ) KM curves associated with PFS and DSS for the BC validation cohort after removing TP53 mutant cases, using a two-sided log-rank statistical test (Source data are provided as a Source Data file).

Comparison of NSMP and p53abn-like NSMP

We compared various clinical, pathological, and molecular variables to investigate further the differences between NSMP and p53abn-like NSMP cases (Supplementary Tables  11 – 13 ). Our analysis showed an enrichment of p53abn-like NSMP cases with higher grade and higher stage tumors ( p  = 1.4e-25; p  = 2.4e-4, respectively). In a multivariate Cox regression analysis, the association between p53abn-like NSMP and progression free survival remained significant in the presence of grade, stage, and histology ( p  = 0.01 and Hazard Ratio = 2.5; Supplementary Table  14 ). Furthermore, Fig.  3B shows enrichment for estrogen receptor (ER) and progesterone receptor (PR) positive cases in the p53abn-like NSMP s (compared to NSMP cases that were classified as NSMP by AI) in the subset of the cohort that the status of these markers were available ( p  = 5.2e-3 and p  = 2.3e-4, respectively).

Independent pathology review of selected NSMP cases

Two expert gynepathologists (NS, CBG) independently reviewed whole section slides of a subset of NSMP cases including the p53abn-like NSMP subtype. They specifically assessed whether tumors showed nuclear features that have been previously described as being associated with TP53 mutation/mutant pattern p53 expression in endometrial carcinoma 30 . The p53abn-like NSMP cases were enriched with tumors showing increased nuclear atypia, as assessed by altered chromatin pattern, nucleolar features, pleomorphism, atypical mitoses, or giant tumor cells ( p  = 0.00005 for both reviewers).

Genomic characterization of p53abn-like NSMP cases

We next sought to investigate the molecular profiles of p53abn-like NSMP cases in our BC validation set for which we had access to tissue material. Targeted sequencing of exonic regions in a number of genes (more details in the Targeted point mutation profiling section of the Methods) revealed enrichment of p53abn-like NSMP cases with TP53 mutations (Fisher’s exact test p-values = 3.14e-4; Fig.  3B ). More specifically, we identified eight (out of 39) p53abn-like NSMP tumors that had normal p53 IHC results (hence classified as NSMP by ProMisE classifier) but in fact harbored TP53 mutations by sequencing. These cases are examples of the well-known phenomenon of normal p53 protein levels despite there being a pathogenic mutation, which occurs in <5% of cases. However, even after removing these eight TP53 mutant cases, the worse prognosis of p53abn-like NSMP tumors persisted (Fig.  3C ). Our ML model, therefore, identifies tumors with false negative immunostaining for p53, i.e., they lack mutant pattern protein expression despite having a TP53 mutation, but also identifies a subset of NSMP cases with features of p53abn morphology by H&E but neither mutation pattern immunostaining nor a mutation in sequencing TP53, and these have inferior survival compared to the rest of the NSMP cases.

We next selected representative samples of NSMP, p53abn, and p53abn-like NSMP cases in our validation cohort and performed shallow whole genome sequencing (sWGS). Overall, copy number profile analysis of these cases revealed that p53abn-like NSMP cases harbor a higher fraction of altered genome compared to NSMP cases but still lower than what we observe in p53abn cases (Fig.  4A ; p  = 0.035). These findings were further validated in the TCGA cohort (Fig.  4B ; p  = 5.46e-5).

Boxplots of copy number burden (i.e., fraction genome altered) in NSMP, p53abn-like NSMP , and p53abn cases in the ( A ) BC validation cohort (6 NSMP, 7 p53abn-like NSMP , 5 p53abn) and ( B ) TCGA (69 NSMP, 21 p53abn-like NSMP , 56 p53abn) cohorts. In box plots in A and B, the central line represents the median, while the bottom and top edges of the box correspond to the 25th and 75th percentiles, respectively. The whiskers extend to the most extreme data points that are not identified as outliers. Any data points beyond the lower and upper whiskers are considered outliers. C Gene expression profiles associated with the p53abn-like NSMP ( n  = 21), NSMP ( n  = 69), and p53abn ( n  = 56) tumors in the TCGA cohort. D KM curves associated with PFS and DSS (where available) in the CC validation set (Source data are provided as a Source Data file).

We next investigated the gene expression profiles associated with the p53abn-like NSMP , NSMP, and p53abn tumors within the TCGA cohort. While majority of the p53abn and NSMP groups were clustered separately, unsupervised analysis of the gene expression profiles did not reveal any differences between p53abn-like NSMP group and other subtypes, i.e., they did not have a unique gene expression profile but instead clustered with one of the known molecular subtypes (Fig.  4C ). We then performed pairwise differential expression analysis and pathway analysis, separately comparing p53abn-like NSMP and p53abn groups against NSMP cases. These results suggested the upregulation of PI3k-Akt, Wnt, and Cadherin signaling pathways both in p53abn-like NSMP and p53abn groups (compared to NSMP). Interestingly, while these pathways were up-regulated in both groups, we found little to no overlap between the specific down- and up-regulated genes in the p53abn-like NSMP and p53abn groups (compared to NSMP) suggesting that the molecular mechanisms associated with p53abn and p53abn-like tumors might be different even though p53abn and p53abn-like NSMP groups had similar histopathological profiles as assessed based on H&E slides.

Validation of p53abn-like NSMP subtype in a multi-center dataset

Variability in tissue processing and data collection across different centers and hospitals is known to introduce inconsistencies in the appearance of histopathology slides. While expert human pathologists can adapt to visual color variability between stained slides, AI-based diagnostic models trained on digitized pathology slides from one center may face challenges in generalizing to data collected from other centers 37 . We next evaluated the generalizability of our proposed AI-based p53abn vs. NSMP classifier on a dataset collected from 26 hospitals across Canada (CC cohort). Our proposed models achieved a balanced accuracy and AUC of 66.3–88.5% and 0.88–0.95, respectively (Supplementary Tables  6 , 7 and Supplementary Fig.  4 ) and classified 6.25% of NSMP cases as p53abn-like NSMPs . Similar to the discovery and BC validation cohorts, the p53abn-like NSMP subtype in the CC cohort had inferior PFS and DSS (Fig.  4D , 5-year PFS 62.52% vs. 88.92% ( p  = 5.41e-6)) and DSS (5-year DSS 66.60% vs. 99.39% ( p  = 8.20e-13)), suggesting that the proposed AI-based classifier is generalizable to datasets collected from other centers.

AI-enhanced NSMP stratification. The refined classification scheme that leverages AI screening as a supplementary stratification mechanism within the NSMP molecular subtype.

Impact of p53abn-like NSMP on risk group assignment

We next sought to determine whether the finding of p53abn-like status by AI, in an NSMP endometrial carcinoma, would potentially change the risk group category i.e., if the tumor was classified as if it were p53abn molecular subtype rather than NSMP, would that impact on the final risk group assignment. The ESGO/ESTRO/ECP 2021 38 risk group classification is based on molecular subtype, stage, histotype, grade, lymphovascular invasion, and the presence of residual disease; this risk group (Low, Intermediate, High-intermediate, High, Advanced metastatic) guides adjuvant treatment. In 19 of 39 p53abn-like NSMP cases, the risk group would change (2 from Low to High, 7 from Intermediate to High, and 10 from High-intermediate to High). The remaining 20 cases (2 Intermediate risk and 18 High risk) would not have changed the risk group. Thus p53abn-like NSMP classification is potentially highly impactful on patient management, independent of other clinical and pathological parameters such as stage, histotype, grade, and lymphovascular invasion.

Although many patients with endometrial carcinoma may be cured by surgery alone, about 1 in 5 patients have more aggressive disease and/or have the disease spread beyond the uterus at the time of diagnosis. Identifying these at-risk individuals remains a challenge, with current tools lacking precision. Molecular classification offers an objective and reproducible classification system that has strong prognostic value; improving the ability to discriminate outcomes compared to conventional pathology-based risk stratification criteria. However, it has become apparent that within molecular subtypes and most profoundly within NSMP ECs, there are clinical outcome outliers. The current study addresses this diversity by employing AI-powered histopathology image analysis, in an attempt to identify clinical outcome outliers within the most common molecular subtype of endometrial cancer (Fig.  5 ). Our results have several clinical and biological implications.

To be clear, for some molecular subtypes, such as POLE mut endometrial cancers with almost uniformly favorable outcomes, no further stratification, at least within Stage I-II disease (encompassing > 90% of POLE mut ECs), is needed. Multiple studies, as well as meta-analyses 39 , have shown that in patients with POLE mut endometrial cancers, additional pathological or molecular features are not associated with outcomes, i.e., are not prognostic, as POLE is the overriding feature that determines survival. However, for NSMP endometrial cancers, additional stratification tools are greatly needed. Designation of NSMP is the last step in molecular classification, only defined by what molecular features it does not have; that is without pathogenic POLE mutations, without mismatch repair deficiency or p53 abnormalities as assessed by IHC. This leaves a large group of pathologically and molecularly diverse tumors with markedly varied clinical outcomes.

Our AI-based histomorphological image analysis model identified a subset of NSMP endometrial cancers with inferior survival. This subset of patients encompassed approximately 20% of NSMP tumors which are the most common molecular subtype, representing half of endometrial cancers diagnosed in the general population, and thus account for 10% of all ECs. Our results suggest that clinicopathological, IHC, gene expression profiles, or NGS molecular markers (except for copy number burden to some extent) may not be able to identify these p53abn-like outliers. The AI classifier was able to identify those tumors with TP53 mutations (but normal p53 immunostaining), a result we view as encouraging, in that these are “false negative” cases using the IHC classification and more appropriately assigned as p53abn, but even when these were removed from consideration AI imaging discerned other patients with NSMP EC where no molecular or pathological features would have identified them as having inferior outcomes. Of note, our results corroborated with a recent report that identified a similar subset of NSMP cases with higher nuclear atypia in 3% of NSMP cases ( n  = 4 out of 120) with poor outcomes, although this difference was not statistically significant likely due to small sample size and differences in the image analysis models ( p  = 0.13) 23 . Taken together, AI applied to histomorphological images of routinely generated H&E slides appears to enable a more encompassing and easily implementable stratification of NSMP tumors and provides greater value than any single or combined pathological/molecular profile could achieve.

Molecular characterization of the identified subtype using sWGS suggests that these cases harbor an unstable genome with a higher fraction of altered genome, similar to the p53abn group but with a lesser degree of instability. These results suggest that the identified subgroup based on histopathology images is biologically distinct. Furthermore, our gene expression analysis revealed the upregulation of PI3k-Akt, Wnt, and Cadherin signaling pathways both in p53abn-like NSMP and p53abn groups (compared to NSMP). All these results suggest genomic and transcriptomic similarities between the p53abn-like NSMP and p53abn cases and potential defects in the DNA damage repair process as a possible biological mechanism. However, in spite of the fact that similar gene expression pathways were implicated in both groups and H&E images of both groups as assessed by AI had resemblances, expression data analysis revealed minimal overlap between the differentially expressed genes in both p53abn and p53abn-like NSMP ECs compared to other NSMP cases. This observation suggests that they may have different etiologies and warrants further biological interrogation of these groups in future studies.

Certainly, others have attempted to refine stratification within early-stage endometrial cancers, including within the molecularly defined NSMP subset. PORTEC4a used a combination of pathologic and molecular features (MMRd, L1CAM overexpression , POLE , CTNNB1 status) to identify low, intermediate, and high-risk individuals assigned to favorable, intermediate, and unfavorable risk groups which then determined observations vs. treatment 40 . TAPER/EN.10 also stratifies early-stage NSMP tumors by pathological (e.g., histotype, grade, LVI status) and molecular features ( TP53 , ER status) to identify those individuals appropriate for de-escalated therapy 41 . In a retrospective series, key parameters of ER and grade have been suggested to discern outcomes within NSMP. ER status was also demonstrated to stratify outcomes in patients with NSMP ECs enrolled in clinical trials 42 . However, even in-depth profiling of apparent low-risk ECs has failed to find pathogenic features that would discern individuals who develop recurrence from other apparent indolent tumors 43 . Stasenko et al. 43 . assessed a series of 486 cases of ‘ultra-low risk’ endometrial cancers defined as stage 1 A with no myoinvasion, no LVI, grade 1 of which 2.9% developed recurrence with no identifiable associated clinical, pathological, or molecular features 43 . Current treatment guidelines, even where molecular features are incorporated, offer little in terms of directing management within NSMP endometrial cancers beyond consideration of pathological features, leaving clinicians to struggle with optimal management 12 . A more comprehensive stratification tool within NSMP endometrial cancers would be of tremendous value, and AI discernment from histopathological images as a tool that can be readily applied to H&E slides that are routinely generated as part of the practice is appealing.

Our proposed AI model also identified a subset of p53abn ECs with marginally superior DSS and resemblance to NSMP ( NSMP-like p53abn ) as assessed by H&E staining. Further investigation of the identified groups and deep molecular and omics characterization of this subset of p53abn ECs may in fact aid us in refining this subtype and identifying a subset of p53abn cases with statistically superior outcomes.

This study utilizes AI for refining endometrial cancer molecular subtypes. In general, such studies to generate new knowledge using AI in histopathology are extremely sparse as a majority of the effort has focused on recapitulating the existing body of knowledge (e.g., to diagnose cancer, to identify histological subtypes, to identify known molecular subtypes). This study moves beyond the mainstream AI applications within the current context of standard histopathology and molecular classification. This enables us to direct efforts to understand the biological mechanisms of this subset. This could present an exciting opportunity to utilize the power of AI to inform clinical trials and deep biological interrogation by adding more precision in patient stratification and selection.

AI histopathologic imaging-based application within NSMP enables discernment of outcomes within the largest endometrial cancer molecular subtype. It can be easily added to clinical algorithms after performing hysterectomy, identifying some patients ( p53abn-like NSMP ) as candidates for treatment analogous to what is given in p53abn tumors. Furthermore, the proposed AI model can be easier to implement in practice (for example, in a cloud-based environment where scanned routine H&E images could be uploaded to a platform for AI assessment), leading to a greater impact on patient management. Furthermore, we envision that an AI algorithm, after appropriate validation, could be utilized on diagnostic biopsy specimens, along with molecular subtype markers (p53, MMR, POLE). This would allow diagnosis of molecular subtype and further classify NSMP into lower risk and higher risk (p53abn-like), with the former patients being candidates for de-escalation of treatment (e.g., simple hysterectomy in the community) and the latter group potentially directed to cancer centers for lymph node assessment, omental sampling and directed biopsies given a higher likelihood of upstaging. It is possible that with further refinement and validation of the algorithm, which can be run in minutes on the diagnostic slide image, that it could take the place of molecular subtype markers, saving time and money.

Ethics statement

The Declaration of Helsinki and the International Ethical Guidelines for Biomedical Research Involving Human Subjects were strictly adhered to throughout this study. All protocols for this study, including the waiver of consent, have been approved by the University of British Columbia/BC Cancer Research Ethics Board. Participants did not receive compensation.

Histopathology slide digitization

Histopathology slide images associated with the TCGA cohort were acquired from the TCGA GDC portal ( https://portal.gdc.cancer.gov ). Histopathology slides associated with the Canadian cohorts as well as the Tübingen University Women’s Hospital were scanned using an Aperio AT2 scanner.

AI tumor-normal classifier and automatic annotation

The downstream tumor subtype classifier relies on the tumor areas of the tissues. Given that the manual annotation of all slides by pathologists is tedious and time-consuming, we first trained a deep learning model to identify the tumor areas of the slides automatically (Supplementary Fig.  7 ) . To train the model, we utilized 27 slides that were annotated by a board-certified pathologist. First, we split the slides into training (51.8%), validation (22.2%), and testing (26%) sets. To identify the tumor regions of WSIs, we divided them into smaller tiles referred to as patches and extracted 5091 (2167 tumor, 2924 stroma) non-overlapping patches. A maximum of 200 patches with a size of 512 × 512 pixels at 20x objective magnification were extracted from the annotated regions of each slide. As the baseline architecture for our classifier, we exploited ResNet18 44 , a simple and effective residual network, with the pre-trained ImageNet 45 weights. We trained the model with the learning rate and weight decay of 1e-4 for five epochs using the Adam optimizer 46 . As the amount of tumor and stroma patches were not equal, we used a balanced sampler with a batch size of 150 which meant that in each batch, the model was trained using 75 tumor patches and 75 stroma patches. The resulting classifier achieved 99.76% balanced accuracy on the testing set, indicating the outstanding performance of this tumor/non-tumor model (Supplementary Table  5 ). The trained model was then applied to detect tumor regions on the rest of the WSIs. To that end, we extracted patches with identical size and magnification to the training phase. To achieve smoother boundaries for the predicted tumor areas we enforced a 60% overlap between neighboring patches. In addition, to reduce false positives we used a minimum threshold probability of 90% for tumor patches. Finally, for consistency, we applied the trained model on the discovery set, including the cases that were manually annotated by a pathologist.

Deep learning models for tumor subtype classification

Due to the lack of pixel-wise annotations, we employed variability-aware multiple instance learning (VarMIL) 33 that utilizes the multiple instance learning technique in which an image is modeled as an instance containing a bag of unlabeled patches or tiles. The algorithm in Box  1 elaborates on the prediction mechanism of \({{{{{{\mathcal{F}}}}}}}_{{{{{{\mathcal{F}}}}}}{{{{{\mathcal{C}}}}}}}\) in detail. \({{{{{{\rm{z}}}}}}}_{{{{{{\rm{j}}}}}}}\in {{\mathbb{R}}}^{{{{{{\rm{d}}}}}}}\) consists of three sections: a feature extractor network ( \({{{{{\rm{d}}}}}}\) ), attention layers, and classification layers ( \({{{{{{\rm{a}}}}}}}_{{{{{{\rm{j}}}}}}} \, {\mathbb{\in }} \, {\mathbb{R}}\) ). First, the feature extractor network computes feature embeddings ( \({{{{{\rm{z}}}}}}\in {{\mathbb{R}}}^{{\mathbb{2}}{{{{{\rm{d}}}}}}}\) ) for the extracted patches of an instance (i.e., image), where \({{{{{{\rm{z}}}}}}}_{{{{{{\rm{\sigma }}}}}}}\in {{\mathbb{R}}}^{{{{{{\rm{d}}}}}}}\) is the dimension of the embeddings. Second, given that patches of a given image are not necessarily equally important in subtype prediction, an attention mechanism calculates the contribution of each patch ( \(\bar{{{{{{\rm{z}}}}}}}\in {{\mathbb{R}}}^{{{{{{\rm{d}}}}}}}\) ) based on its embedding. Subsequently, VarMIL computes the image’s representation ( \({{{{{\rm{z}}}}}}\in {{\mathbb{R}}}^{{\mathbb{2}}{{{{{\rm{d}}}}}}}\) )) into account alongside their weighted average ( \({{{{{{\rm{z}}}}}}}_{{{{{{\rm{\sigma }}}}}}}\in {{\mathbb{R}}}^{{{{{{\rm{d}}}}}}}\) )). Finally, the model feeds the derived representation as the input of the classification section to predict the subtype. To avoid over-fitting, we employed a variety of augmentation methods including horizontal and vertical flipping, color jitter, size jitter, random rotation, and Cutout 47 . Furthermore, we utilized early stopping 48 as an additional form of regularization in training, and if the validation loss did not decrease after five epochs, we decreased the learning rate. Furthermore, we stopped the training if the validation loss did not decrease after 10 consecutive epochs. We devised a two-step training procedure for the proposed network, in which the feature extractor network was trained independently from the attention and classification layers. First, we trained the feature extractor, ResNet34 44 ( \({{{{{\rm{d}}}}}}=512\) ). For the attention and classification layers, we selected a multilayer perceptron (MLP) with a single hidden layer with 128 nodes (q = 128). We trained these layers with the same number of epochs and weight decay as before but with a learning rate of 1e-5. Models were trained using a single dgxV100 GPU with 32GB RAM. The programming language was PyTorch 49 (version 1.8.0), and we selected the hyperparameters experimentally.

We further assessed the robustness of our findings with five other models formulated on distinct concepts: (1) Vanilla 37 , 50 , (2) Histogram-Based 51 , (3) Iterative Draw and Rank Sampling (IDaRS) 52 , (4) Attention-based 53 , 54 , and (5) Vector of Locally Aggregated Descriptor (VLAD) 55 , 56 , CLAM-MB, CLAM-SB, and TransMIL.

(1) Vanilla is a simple and frequently used concept in digital pathology 37 , 57 . In this setting, we train a DL model on the extracted patches from a histopathology slide in a fully supervised manner. Here, each patch’s label corresponds to the subtype of its corresponding histopathology slide. The process involves passing patches through convolutional layers and feeding the generated feature maps into fully connected layers. The model is trained using the cross-entropy loss function 58 , similar to standard classification tasks.

(2) IDaRS shares similar assumptions with Vanilla, involving training a model on image patches in a fully supervised manner and assigning the image’s label to its patches 52 . However, unlike Vanilla, where all extracted patches are used in training, IDaRS employs a selection procedure. Only informative patches that contribute to the image’s subtype are included during training. The selection algorithm utilizes the Monte-Carlo 59 sampling approach.

(3) The Histogram-Based concept 51 addresses the task of identifying a slide’s subtype, similar to IDaRS and Vanilla, by transforming a weakly supervised problem into a fully supervised one. A key distinction of this concept is the integration of a histogram and a classification module, instead of relying on majority voting. This modification improves the model’s interpretability without significantly increasing the parameter count.

(4) DeepMIL 60 combines the concepts of MIL and attention. It leverages MIL techniques, treating an image as a collection(bag) of unlabeled patches, while the attention-based approach maintains the nature of the weakly supervised task, in contrast to the previously mentioned concepts. This perspective removes the need to assign labels to individual patches within an image. Moreover, it recognizes that patches within an image have varying degrees of importance to its subtype, and their contributions are calculated using an attention mechanism.

(5) VLAD 55 , a family of algorithms, considers histopathology images as Bag of Words (BoWs), where extracted patches serve as the words. Due to its favorable performance in large-scale databases, surpassing other BoWs methods, we adopt VLAD as a technique to construct slide representation 55 .

(6) CLAM 61 adopts an attention-based pooling function to aggregate patch-level features to form slide-level representations for classification. By ranking all patches within a slide, the model assigns attention scores to each patch, revealing their unique contributions and significance to the overall slide-level representation for a specific class. In addition, CLAM utilizes instance-level clustering over identified representative regions to constrain and refine the feature space. Distinguishingly, CLAM-SB utilizes a single attention branch for aggregating patch information, while CLAM-MB employs multiple attention branches, corresponding to the number of classes used for classification.

(7) TransMIL 62 represents a transformer-based methodology devised for the classification of whole slide histopathology images. This framework incorporates both morphological and spatial information through a comprehensive consideration of contextual details surrounding a singular area and the inter-correlation between distinct areas. Furthermore, the approach employs a Pyramid Position Encoding Generator (PPEG) module for transforming local features and encoding positional information.

Box 1 Subtype prediction algorithm

Input: \({{{{{{\rm{P}}}}}}}_{{{{{{\rm{i}}}}}}}=\left\{{{{{{{\rm{p}}}}}}}_{{{{{{\rm{i}}}}}}1},..,{{{{{{\rm{p}}}}}}}_{{{{{{\rm{i}}}}}}{{{{{{\rm{k}}}}}}}_{{{{{{\rm{i}}}}}}}}\right\}\) : a set of extracted patches from the \({{{{{{\rm{i}}}}}}}^{{{{{{\rm{th}}}}}}}\) image, i.e., \({{{{{{\rm{I}}}}}}}_{{{{{{\rm{i}}}}}}}\)

1: for j ← 1 to k i do

2: \({{z}}_{{j}}\leftarrow {{{\mathcal{F}}}}_{Conv2D}({{p}}_{{{{{i}}}}{{{{j}}}}})\)

4: Let \({{{{{\rm{W}}}}}}\in {{\mathbb{R}}}^{{{{{{\rm{q}}}}}}}\) and \({{{{{\rm{V}}}}}}\in {{\mathbb{R}}}^{{{{{{\rm{q}}}}}}\times {{{{{\rm{d}}}}}}}\) be the attention parameters

5: for j ← 1 to \({{{{{{\rm{k}}}}}}}_{{{{{{\rm{i}}}}}}}\) do

6: \({{{{{{\rm{a}}}}}}}_{{{{{{\rm{j}}}}}}}\leftarrow \exp ({{{{{{\rm{W}}}}}}}^{{{\top }}}\tanh ({{{{{\rm{V}}}}}}{{{{{{\rm{z}}}}}}}_{{{{{{\rm{j}}}}}}}))\) / \({\sum }_{{{{{{\rm{t}}}}}}=1}^{{{{{{{\rm{K}}}}}}}_{{{{{{\rm{i}}}}}}}}\exp \left({{{{{{\rm{W}}}}}}}^{{{\top }}}\tanh \left({{{{{\rm{V}}}}}}{{{{{{\rm{z}}}}}}}_{{{{{{\rm{t}}}}}}}\right)\right)\)

8: \(\bar{{{{{{\rm{z}}}}}}}\leftarrow {\sum }_{{{{{{\rm{j}}}}}}=1}^{{{{{{{\rm{k}}}}}}}_{{{{{{\rm{i}}}}}}}}{{{{{{\rm{a}}}}}}}_{{{{{{\rm{j}}}}}}}{{{{{{\rm{z}}}}}}}_{{{{{{\rm{j}}}}}}}\)

9: \({{{{{{\rm{z}}}}}}}_{{{{{{\rm{\sigma }}}}}}}\leftarrow \frac{{{{{{{\rm{k}}}}}}}_{{{{{{\rm{i}}}}}}}}{{{{{{{\rm{k}}}}}}}_{{{{{{\rm{i}}}}}}}-1}{\sum }_{{{{{{\rm{j}}}}}}=1}^{{{{{{{\rm{k}}}}}}}_{{{{{{\rm{i}}}}}}}}{{{{{{\rm{a}}}}}}}_{{{{{{\rm{j}}}}}}}{\left({{{{{{\rm{z}}}}}}}_{{{{{{\rm{j}}}}}}}-\bar{{{{{{\rm{z}}}}}}}\right)}^{2}\)

10: \({{{{{\rm{z}}}}}}\leftarrow \bar{{{{{{\rm{z}}}}}}}\oplus {{{{{{\rm{z}}}}}}}_{{{{{{\rm{\sigma }}}}}}}\)

11: \({{{{{{\rm{Y}}}}}}}_{{{{{{\rm{i}}}}}}}\leftarrow {{{{{{\mathcal{F}}}}}}}_{{{{{{\mathcal{F}}}}}}{{{{{\mathcal{C}}}}}}}\left({{{{{\rm{z}}}}}}\right)\)

Output: \({{{{{{\rm{Y}}}}}}}_{{{{{{\rm{i}}}}}}}\) : the predicted subtype of \({{{{{{\rm{I}}}}}}}_{{{{{{\rm{i}}}}}}}\)

Identification of p53abn-like NSMP s

The initial hypothesis was that NSMP cases with a poor prognosis resemble p53abn morphologically. Assuming the hypothesis is correct, subtype classifiers should label cases in this group as p53abn. Using the same rationale, we partitioned the NSMP subtype into two subgroups: p53abn-like NSMP and the remaining NSMP cases. To this end, we devised a voting system based on the classifiers’ consensus. If the fraction of classifiers predicting an NSMP case as p53abn exceeded a specified confidence threshold, the image was labeled as p53abn-like NSMP ; otherwise, the image was labeled as NSMP. In this work, we labeled a sample as p53abn-like NSMP when an NSMP sample, based on ProMisE, was classified as p53abn in more than seven out of the 10 cross-validation classifiers.

Unsupervised clustering of NSMP patch representations

To investigate the robustness of our results in identifying p53abn-like NSMPs and visualize the distribution of the patch representations, we employed a two-step approach. In the first step, we applied KimiaNet 34 to the patches that were extracted from the histopathology slides associated with the NSMP EC cases. KimiaNet is a deep model trained on a large set of histopathology data, to encode each patch with dimensions of 512 × 512 pixels into a compact 1024 × 1 vector. By leveraging the embeddings from KimiaNet’s last pooling layer, we condensed the essential features of each patch into a representative vector. In the second step, we applied Uniform Manifold Approximation and Projection (UMAP) 63 , a dimensionality reduction technique, to project the encoded vectors of all the patches within the NSMP and p53abn-like NSMP onto a two-dimensional space. UMAP excels at preserving both local and global structures of high-dimensional data, enabling us to visualize the relationships and patterns within the encoded patches in a more interpretable manner.

Targeted point mutation profiling

Targeted mutation profiling was performed as part of our team’s previous efforts 4 , 5 , 64 , 65 . Briefly, the exon capture libraries were sequenced using the Illumina Genome Analyzer (GAIIx), MiSeq, or Sanger sequencing. The reads were aligned to the human genome using the BWA aligner version v0.5.9. and SNVs were called by a combination of binomial exact test and MutationSeq as previously described 66 , 67 . To remove the germline mutations, the predicted SNVs were filtered through dbSNP, 1000 Genome ( http://www.1000genomes.org/ ), and the control normals. All SNVs were profiled by MutationAssessor 68 for the functional impact of the missense mutations. snpEff ( http://snpeff.sourceforge.net/ ) was used to find splice site mutations. All silent mutations were removed. The indels were filtered by the control normals and then profiled by Oncotator ( http://www.broadinstitute.org/oncotator/ ).

Survival analysis

We assessed the significance of subgroups using the Kaplan-Meier (KM) estimator on two survival endpoints: Disease Specific Survival (DSS) and Progression Free Survival (PFS). Survival outcomes were not accessible for four (1.47%; three NSMP and one p53abn-like NSMP ) and two (1.03%; one NSMP and one p53abn-like NSMP ) patients in the discovery and validation sets, respectively. In some individuals, clinical data were partially available (for example, survival data of a patient only contained DSS while PFS was unknown), explaining why the number of cases varies among KM curves for the same set. In addition, given that the TCGA survival data lacked DSS, the German cohort served as the discovery set for the DSS KM curves.

Shallow whole genome sequencing (cohort and experiments)

DNA was extracted (GeneRead FFPE DNA kit from Qiagen) from FFPE core tumor samples and was sheared to 200 bp using a Covaris S220. Libraries were constructed using the ThruPlex DNA-seq kit (Takara) with seven cycles of amplification (library prep strategy from Brenton Lab similar to the one published in 2018) 69 . Library quality was assessed using the Agilent High Sensitivity DNA kit (Agilent Technologies), and pooled libraries were run on the Illumina NovaSeq at the Michael Smith Genome Sciences Center targeting 600 M reads per pooled batch. The sWGS data was run through basic processing which includes trimming with Trimmomatic 70 , alignment with bwa-mem2 71 , duplicate removal with Picard 72 , and sorting with samtools 73 . Sequencing coverage and quality were evaluated using fastQC 74 and samtools. If acceptable, the data was passed along to the next step of determining genomic copy numbers (QDNAseq 75  + rascal 76 ) and signature calls. The signature calling step uses techniques including mixture modeling and non-negative matrix factorization and is composed mostly of software from the CN-Signatures 69 package with a few in-house modifications and additions. Interim data munging and ETL (extract, transform, load) are done primarily in bash and R (tidyverse), while visualization and plotting is performed mostly just in R using ggplot2 and pheatmap.

Gene expression analysis

For expression profiling, we used RNA-seq profiles obtained from the TCGA-UCEC cohort 3 . Specifically, we used the GDC data portal 77 to download primary tumors sequenced on the Illumina Genome Analyzer platform with patient IDs matching those used in our study. Raw, un-normalized counts were used. DeSeq2 78 was used to process the raw count matrix and perform differential expression analysis (DEA) and hierarchical clustering. Samples were categorized as NSMP, p53abn-like NSMP , and p53abn. Genes with a total count of five or less were removed. Counts were normalized using DeSeq2’s variance-stabilizing transform tool. The 500 most variable genes based on DEA were kept for hierarchical clustering. Per-gene Z-scaling was applied to normalize the clustering features. Finally, the complete-linkage method was used for both gene-clustering and sample-clustering. Subsequent pathway analysis on the list of differentially expressed genes was performed using the Reactome 79 FI plugin in Cytoscape 80 .

Statistical assessment

A two-sided log-rank test was utilized to assess the significance of the difference between KM curves for the identified patient groups. In addition, the significance of groups for the enrichment of specific genomic or molecular features was assessed using the Fisher’s exact test and the Mann-Whitney U rank test for discrete and continuous data, respectively. Throughout all experiments, p  < 0.05 was regarded as the significance level.

Reporting summary

Further information on research design is available in the  Nature Portfolio Reporting Summary linked to this article.

Data availability

All histopathology slide images in this study can be obtained by direct email to the corresponding author. All data access is subject to institutional permission and compliance with ethics from the corresponding institutions. Data can only be shared for non-commercial academic purposes and will require a data user agreement. The whole-genome sequencing data for this study have been deposited in the European Nucleotide Archive (ENA) at EMBL-EBI under accession number PRJEB60600 . Endometrial (uterine) carcinoma samples from The Cancer Genome Atlas (TCGA), used in this study, can be freely downloaded from [ https://portal.gdc.cancer.gov/analysis_page?app=Projects ]. The exome-wide and targeted point mutation data discussed in this manuscript were previously published in earlier studies 4 , 5 , 64 , 65 . The aggregated mutation calls including the genomic coordinates of the mutations and reference and tumor alleles were extracted directly from those studies 4 , 5 , 64 , 65 and can be found in the Source Data of Fig.  3B .  Source data are provided with this paper.

Code availability

The code used in this manuscript is available on https://github.com/AIMLab-UBC/EC-p53abnlike-AIclassifier

Gilks, C. B., Oliva, E. & Soslow, R. A. Poor interobserver reproducibility in the diagnosis of high-grade endometrial carcinoma. Am. J. Surg. Pathol. 37 , 874–881 (2013).

Article   PubMed   Google Scholar  

Hoang, L. N. et al. Histotype-genotype correlation in 36 high-grade endometrial carcinomas. Am. J. Surg. Pathol. 37 , 1421–1432 (2013).

Levine, D. A. et al. Integrated genomic characterization of endometrial carcinoma. Nature 497 , 67–73 (2013).

Article   ADS   PubMed   PubMed Central   Google Scholar  

Talhouk, A. et al. Confirmation of ProMisE: A simple, genomics-based clinical classifier for endometrial cancer. Cancer 123 , 802–813 (2017).

Article   CAS   PubMed   Google Scholar  

Kommoss, S. et al. Final validation of the ProMisE molecular classifier for endometrial carcinoma in a large population-based case series. Ann. Oncol. 29 , 1180–1188 (2018).

Editorial Board WC of T. WHO Classification of Tumours Female Genital Tumours, vol. 6, 5th edn. International Agency for Research on Cancer, 2020.

Kasius, J. C. et al. Risk stratification of endometrial cancer patients: FIGO stage, biomarkers and molecular classification. Cancers 13 , 5848 (2021).

Article   CAS   PubMed   PubMed Central   Google Scholar  

Thompson, E. et al. Further stratification of no specific molecular profile (NSMP/P53WT) endometrial carcinomas to refine prognosis and identify therapeutic opportunities. Int. J. Gynecol. Cancer 31 , A17–A17 (2021).

Google Scholar  

De Leo, A. et al. ARID1A and CTNNB1 /β-Catenin molecular status affects the clinicopathologic features and prognosis of endometrial carcinoma: implications for an improved surrogate molecular classification. Cancers 13 , 950 (2021).

Article   PubMed   PubMed Central   Google Scholar  

Kolehmainen, A. et al. Clinical factors as prognostic variables among molecular subgroups of endometrial cancer. PLoS ONE 15 , e0242733 (2020).

Prakasan, A. M. et al. The pattern of recurrence in carcinoma endometrium. Indian J. Gynecol. Oncol. 20 , 1–7 (2022).

National Comprehensive Cancer Network (NCCN). Uterine Neoplasms NCCN Guidelines Version 4.2021. https://www.nccn.org/guidelines/guidelines-detail?category=1&id=1473 (2021).

LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521 , 436–444 (2015).

Article   ADS   CAS   PubMed   Google Scholar  

Bera, K., Schalper, K. A., Rimm, D. L., Velcheti, V. & Madabhushi, A. Artificial intelligence in digital pathology — new tools for diagnosis and precision oncology. Nat. Rev. Clin. Oncol. 16 , 703–715 (2019).

Srinidhi, C. L., Ciga, O. & Martel, A. L. Deep neural network models for computational histopathology: A survey. Med. Image Anal. 67 , 101813 (2021).

Shmatko, A., Ghaffari Laleh, N., Gerstung, M. & Kather, J. N. Artificial intelligence in histopathology: enhancing cancer research and clinical oncology. Nat. Cancer 3 , 1026–1038 (2022).

Kather, J. N. et al. Pan-cancer image-based detection of clinically actionable genetic alterations. Nat. Cancer 1 , 789–799 (2020).

Ehteshami Bejnordi, B. et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 318 , 2199–2210 (2017).

Article   Google Scholar  

Bulten, W. et al. Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge. Nat. Med. 28 , 154–163 (2022).

Campanella, G. et al. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nat. Med. 25 , 1301–1309 (2019).

Fu, Y. et al. Pan-cancer computational histopathology reveals mutations, tumor composition and prognosis. Nat. Cancer 1 , 800–810 (2020).

Hong, R., Liu, W., DeLair, D., Razavian, N. & Fenyö, D. Predicting endometrial cancer subtypes and molecular features from histopathology images using multi-resolution deep learning models. Cell Rep. Med. 2 , 100400 (2021).

Fremond, S. et al. Interpretable deep learning model to predict the molecular classification of endometrial cancer from haematoxylin and eosin-stained whole-slide images: a combined analysis of the PORTEC randomised trials and clinical cohorts. Lancet Digit. Health 5 , e71–e82 (2023).

Wang, T. et al. Microsatellite Instability Prediction of Uterine Corpus Endometrial Carcinoma Based on H&E Histology Whole-Slide Imaging. In 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI): 1289–1292 (2020).

Wetstein, S. C. et al. Deep learning-based breast cancer grading and survival analysis on whole-slide histopathology images. Sci. Rep. 12 , 15102 (2022).

Article   ADS   CAS   PubMed   PubMed Central   Google Scholar  

Lee, Y. et al. Derivation of prognostic contextual histopathological features from whole-slide images of tumours via graph deep learning. Nat. Biomed. Eng. 1–15 (2022).

Zadeh Shirazi, A. et al. A deep convolutional neural network for segmentation of whole-slide pathology images identifies novel tumour cell-perivascular niche interactions that are associated with poor survival in glioblastoma. Br. J. Cancer 125 , 337–350 (2021).

Jiang, S., Zanazzi, G. J. & Hassanpour, S. Predicting prognosis and IDH mutation status for patients with lower-grade gliomas using whole slide images. Sci. Rep. 11 , 16849 (2021).

Dou, Y. et al. Proteogenomic insights suggest druggable pathways in endometrial carcinoma. Cancer Cell 41 , 1586–1605 (2023).

Kang, E. Y. et al. Selection of endometrial carcinomas for p53 immunohistochemistry based on nuclear features. J. Pathol. Clin. Res. 8 , 19–32 (2022).

Thompson, E. F. et al. Variability in endometrial carcinoma pathology practice: opportunities for improvement with molecular classification. Modern Pathol. 35 , 1974–1982 (2022).

Article   CAS   Google Scholar  

Vahadane, A. et al. Structure-preserving color normalization and sparse stain separation for histological images. IEEE Trans. Med. Imaging 35 , 1962–1971 (2016).

Schirris, Y., Gavves, E., Nederlof, I., Horlings, H. M. & Teuwen, J. DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancer. Med. Image Anal. 79 , 102464 (2022).

Riasatian, A. et al. Fine-tuning and training of densenet for histopathology image representation using TCGA diagnostic slides. Med. Image Anal. 70 , 102032 (2021).

Huang, G., Liu, Z., Van Der Maaten, L. & Weinberger, K. Q. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 4700–4708 (2017).

Liu, Z. et al. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF International Conference on Computer Vision 10012–10022 (2021).

Boschman, J. et al. The utility of color normalization for AI-based diagnosis of hematoxylin and eosin-stained pathology images. J. Pathol. 256 , 15–24 (2022).

Concin, N. et al. ESGO/ESTRO/ESP guidelines for the management of patients with endometrial carcinoma. Int. J. Gynecol. Cancer. 31 , 12–39 (2021).

McAlpine, J. N. et al. Evaluation of treatment effects in patients with endometrial cancer and POLE mutations: An individual patient data meta-analysis. Cancer 127 , 2409–2422 (2021).

Wortman, B. et al. Molecular-integrated risk profile to determine adjuvant radiotherapy in endometrial cancer: evaluation of the pilot phase of the PORTEC-4a trial. Gynecol. Oncol. 151 , 69–75 (2018).

ClinicalTrials.gov identifier (NCT number): NCT04705649. Tailored Adjuvant Therapy in POLE-mutated and p53-wildtype Early Stage Endometrial Cancer (TAPER). https://clinicaltrials.gov/ct2/show/NCT04705649 (accessed Feb 2, 2022) (2021).

Vermij, L., Smit, V., Nout, R. & Bosse, T. Incorporation of molecular characteristics into endometrial cancer management. Histopathology 76 , 52–63 (2020).

Stasenko, M. et al. Clinical patterns and genomic profiling of recurrent ‘ultra-low risk’ endometrial cancer. Int. J. Gynecol. Cancer 30 , 717–723 (2020).

He, K., Zhang, X., Ren, S. & Sun, J. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 770–778 (2016).

Deng, J. et al. ImageNet: A large-scale hierarchical image database. IEEE Conf. Comput. Vision and Pattern Recognit. 2009 , 248–255 (2009).

P. Kingma & J. Ba. Adam: A method for stochastic optimization. In Proceedings of International Conference on Learning Representations (ICLR) http://arxiv.org/abs/1412.6980 (2015).

DeVries, T. & Taylor, G. W. Improved Regularization of Convolutional Neural Networks with Cutout. Preprint at http://arxiv.org/abs/1708.04552 (2022).

Caruana, R., Lawrence, S. & Giles, L. Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping. In Proceedings of the 13th International Conference on Neural Information Processing Systems . 381–387 (Cambridge, MA, USA: MIT Press 2000).

Paszke, A. et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems. (2019).

Echle, A. et al. Deep learning in cancer pathology: a new generation of clinical biomarkers. Br. J. Cancer 124 , 686–696 (2021).

Sali, R. et al. Deep learning for whole-slide tissue histopathology classification: A comparative study in the identification of dysplastic and non-dysplastic barrett’s esophagus. J. Pers. Med. 10 , 141 (2020).

Bilal, M. et al. Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study. Lancet Digit. Health 3 , e763–e772 (2021).

Ilse, M., Tomczak, J. & Welling, M. Attention-based Deep Multiple Instance Learning. In: Proceedings of the 35th International Conference on Machine Learning. PMLR: 2127–2136, (2018).

Schirris, Y., Gavves, E., Nederlof, I., Horlings, H. M., & Teuwen, J. DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancer. Med. Image Anal. 79 , 102464 (2022).

Jégou, H., Douze, M., Schmid C. & Pérez P. Aggregating local descriptors into a compact image representation. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition 3304–3311 (2010).

Arandjelovic, R. & Zisserman, A. All About VLAD. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition 1578–1585 (2013).

Kather, J. N. et al. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat. Med. 25 , 1054–1056 (2019).

Cox, D. R. The regression analysis of binary sequences. J. R. Stat. Soc. Ser. B Stat. Method. 20 , 215–242 (1958).

Article   MathSciNet   Google Scholar  

Metropolis, N. & Ulam, S. The monte carlo method. J. Am. Stat. Assoc. 44 , 335–341 (1949).

Dietterich, T. G., Lathrop, R. H. & Lozano-Pérez, T. Solving the multiple instance problem with axis-parallel rectangles. Artif. Intell. 89 , 31–71 (1997).

Lu, M. Y. et al. Data-efficient and weakly supervised computational pathology on whole-slide images. Nat. Biomed. Eng. 5 , 555–570 (2021).

Shao, Z. et al. TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification. In Advances in Neural Information Processing Systems (2021).

McInnes, L., Healy, J. & Melville, J. Umap: Uniform manifold approximation and projection for dimension reduction. J. Open Source Softw. 3 , 861 https://doi.org/10.48550/arXiv.1802.03426 (2018).

McConechy, M. K. et al. Use of mutation profiles to refine the classification of endometrial carcinomas. J. Pathol. 228 , 20–30 (2012).

Talhouk, A. et al. A clinically applicable molecular-based classification for endometrial cancers. Br. J. Cancer 113 , 299–310 (2015).

Shah, S. P. et al. Mutational evolution in a lobular breast tumour profiled at single nucleotide resolution. Nature 461 , 809–813 (2009).

Ding, J. et al. Feature-based classifiers for somatic mutation detection in tumour–normal paired sequencing data. Bioinformatics 28 , 167–175 (2012).

Reva, B., Antipin, Y. & Sander, C. Predicting the functional impact of protein mutations: application to cancer genomics. Nucleic Acids Res. 39 , e118 (2011).

Macintyre, G. et al. Copy number signatures and mutational processes in ovarian carcinoma. Nat. Genet. 50 , 1262–1270 (2018).

Bolger, A. M., Lohse, M. & Usadel, B. Trimmomatic: a flexible trimmer for Illumina sequence data. Bioinformatics 30 , 2114–2120 (2014).

Vasimuddin, Md, Misra, S., Li, H. & Aluru, S. Efficient Architecture-Aware Acceleration of BWA-MEM for Multicore Systems. In: 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS): 314–324 (2019).

Picard toolkit. Broad Institute, GitHub Repository https://broadinstitute.github.io/picard/ (2019).

Danecek, P. et al. Twelve years of SAMtools and BCFtools. GigaScience 10 , giab008 (2021).

Andrews, S. FastQC: a quality control tool for high throughput sequence data. Babraham Bioinformatics, Babraham Institute , Cambridge, United Kingdom https://www.bioinformatics.babraham.ac.uk/projects/fastqc/ (2023).

Scheinin, I. et al. DNA copy number analysis of fresh and formalin-fixed specimens by shallow whole-genome sequencing with identification and exclusion of problematic regions in the genome assembly. Genome Res. 24 , 2022–2032 (2014).

Sauer, C. M. et al. Absolute copy number fitting from shallow whole genome sequencing data. Preprint at https://doi.org/10.1101/2021.07.19.452658 (2021).

Grossman, R. L. et al. Toward a shared vision for cancer genomic data. N. Engl. J. Med. 375 , 1109–1112 (2016).

Love, M. I., Huber, W. & Anders, S. Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2. Genome Biol. 15 , 550 (2014).

Wu, G., Feng, X. & Stein, L. A human functional protein interaction network and its application to cancer data analysis. Genome Biol. 11 , R53 (2010).

Shannon, P. et al. Cytoscape: a software environment for integrated models of biomolecular interaction networks. Genome Res. 13 , 2498–2504 (2003).

Janowczyk, A., Zuo, R., Gilmore, H., Feldman, M. & Madabhushi, A. HistoQC: An Open-Source Quality Control Tool for Digital Pathology Slides. JCO Clin. Cancer Inform. 3 , 1–7. 2019.

Download references

Acknowledgements

This work was supported by Terry Fox Research Institute (J.M., A.B., D.G.H., grant number: 1116), Canadian Institute of Health Research (A.B., grant number: 201903PJT-418734), Natural Sciences and Engineering Research Council of Canada (A.B., grant number: RGPIN-2019-04896), Michael Smith Foundation for Health Research (A.B., grant number: SCH-2021-1546), Canada Research Chair (J.M., S.J.M.J., D.G.H), Canada Foundation for Innovation/BC Knowledge Development Funds (A.B., grant number: 41144), OVCARE Carraresi and VGH UBC Hospital Foundation (A.B.). The funders had no involvement in study conception, data collection, data analysis, data interpretation, writing of the report, or publication decisions.

Author information

These authors contributed equally: Amirali Darbandsari, Hossein Farahani, Maryam Asadi.

These authors jointly supervised this work: David G. Huntsman, Naveena Singh, Jessica N. McAlpine, Ali Bashashati.

Deceased: Naveena Singh.

Authors and Affiliations

Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC, Canada

Amirali Darbandsari & Purang Abolmaesumi

School of Biomedical Engineering, University of British Columbia, Vancouver, BC, Canada

Hossein Farahani, Maryam Asadi, Matthew Wiens, Ali Khajegili Mirabadi, Pouya Ahmadvand & Ali Bashashati

Department of Pathology and Laboratory Medicine, University of British Columbia, Vancouver, BC, Canada

Hossein Farahani, David Farnell, C. Blake Gilks, David G. Huntsman, Naveena Singh & Ali Bashashati

Department of Molecular Oncology, British Columbia Cancer Research Institute, Vancouver, BC, Canada

Dawn Cochrane, Maxwell Douglas, Samuel Leung & David G. Huntsman

Department of Obstetrics and Gynaecology, University of British Columbia, Vancouver, BC, Canada

Amy Jamieson, Aline Talhouk & Jessica N. McAlpine

Vancouver General Hospital, Vancouver, BC, Canada

David Farnell, C. Blake Gilks & Naveena Singh

Michael Smith Genome Sciences Center, British Columbia Cancer Research Center, Vancouver, BC, Canada

Steven J. M. Jones

Department of Women’s Health, Tübingen University Hospital, Tübingen, Germany

Stefan Kommoss

You can also search for this author in PubMed   Google Scholar

Contributions

A.D. and H.F. were the research project leaders and led and designed all data analysis. M.A. performed the data analysis in the revision of the manuscript. A.D. implemented all the deep learning pipelines. M.W. and A.B. performed the gene expression analysis. M.A. and A.K. performed image analysis. D.C. and A.J. contributed to the clinical review and case selection for molecular profiling. D.F. performed the histopathology slide annotations. P.Ah. contributed to software infrastructure for slide annotation. M.D. and H.F. performed bioinformatics analysis. P.Ab and S.J.M.J. provided advice on machine learning analysis and provided computational resources. A.T. and S.L. contributed to clinical informatics and biobanking. C.B.G. and N.S. reviewed all specimens for histological and molecular pathology and contributed to manuscript writing. S.K. were responsible for the specimen and clinical data from Tübingen University. J.N.M. and C.B.G. contributed to cohort construction, tumor banking, and the initial draft of the manuscript. A.D., H.F., and A.B. wrote the first draft of the manuscript. D.G.H., N.S., and J.N.M. provided oversight, edited the manuscript, and supervised the study. A.B. conceived and oversaw the project and is the senior corresponding author. All authors have reviewed and approved the manuscript content.

Corresponding author

Correspondence to Ali Bashashati .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Peer review

Peer review information.

Nature Communications thanks Xiaojun Chen and Nianyin Zeng for their contribution to the peer review of this work. A peer review file is available.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary information, peer review file, reporting summary, source data, source data, rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Darbandsari, A., Farahani, H., Asadi, M. et al. AI-based histopathology image analysis reveals a distinct subset of endometrial cancers. Nat Commun 15 , 4973 (2024). https://doi.org/10.1038/s41467-024-49017-2

Download citation

Received : 11 July 2023

Accepted : 21 May 2024

Published : 26 June 2024

DOI : https://doi.org/10.1038/s41467-024-49017-2

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

By submitting a comment you agree to abide by our Terms and Community Guidelines . If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Sign up for the Nature Briefing: Cancer newsletter — what matters in cancer research, free to your inbox weekly.