Fresia Pareja, Higinio Dopeso, Yi Kan Wang, Andrea M Gazzo, David N Brown, Monami Banerjee, Pier Selenica, Jan H Bernhard, Fatemeh Derakhshan, Edaise M da Silva, Lorraine Colon-Cartagena, Thais Basili, Antonio Marra, Jillian Sue, Qiqi Ye, Arnaud Da Cruz Paula, Selma Yeni Yildirim, Xin Pei, Anton Safonov, Hunter Green, Kaitlyn Y Gill, Yingjie Zhu, Matthew C H Lee, Ran A Godrich, Adam Casson, Britta Weigelt, Nadeem Riaz, Hannah Y Wen, Edi Brogi, Diana L Mandelker, Matthew G Hanna, Jeremy D Kunz, Brandon Rothrock, Sarat Chandarlapaty, Christopher Kanan, Joe Oakley, David S Klimstra, Thomas J Fuchs, Jorge S Reis-Filho
{"title":"A Genomics-Driven Artificial Intelligence-Based Model Classifies Breast Invasive Lobular Carcinoma and Discovers CDH1 Inactivating Mechanisms.","authors":"Fresia Pareja, Higinio Dopeso, Yi Kan Wang, Andrea M Gazzo, David N Brown, Monami Banerjee, Pier Selenica, Jan H Bernhard, Fatemeh Derakhshan, Edaise M da Silva, Lorraine Colon-Cartagena, Thais Basili, Antonio Marra, Jillian Sue, Qiqi Ye, Arnaud Da Cruz Paula, Selma Yeni Yildirim, Xin Pei, Anton Safonov, Hunter Green, Kaitlyn Y Gill, Yingjie Zhu, Matthew C H Lee, Ran A Godrich, Adam Casson, Britta Weigelt, Nadeem Riaz, Hannah Y Wen, Edi Brogi, Diana L Mandelker, Matthew G Hanna, Jeremy D Kunz, Brandon Rothrock, Sarat Chandarlapaty, Christopher Kanan, Joe Oakley, David S Klimstra, Thomas J Fuchs, Jorge S Reis-Filho","doi":"10.1158/0008-5472.CAN-24-1322","DOIUrl":null,"url":null,"abstract":"<p><p>Artificial intelligence (AI) systems can improve cancer diagnosis, yet their development often relies on subjective histologic features as ground truth for training. Herein, we developed an AI model applied to histologic whole-slide images using CDH1 biallelic mutations, pathognomonic for invasive lobular carcinoma (ILC) in breast neoplasms, as ground truth. The model accurately predicted CDH1 biallelic mutations (accuracy = 0.95) and diagnosed ILC (accuracy = 0.96). A total of 74% of samples classified by the AI model as having CDH1 biallelic mutations but lacking these alterations displayed alternative CDH1 inactivating mechanisms, including a deleterious CDH1 fusion gene and noncoding CDH1 genetic alterations. Analysis of internal and external validation cohorts demonstrated 0.95 and 0.89 accuracy for ILC diagnosis, respectively. The latent features of the AI model correlated with human-explainable histopathologic features. Taken together, this study reports the construction of an AI algorithm trained using a genetic rather than histologic ground truth that can robustly classify ILCs and uncover CDH1 inactivating mechanisms, providing the basis for orthogonal ground truth utilization for development of diagnostic AI models applied to whole-slide image. Significance: Genetic alterations linked to strong genotypic-phenotypic correlations can be utilized to develop AI systems applied to pathology that facilitate cancer diagnosis and biologic discoveries.</p>","PeriodicalId":9441,"journal":{"name":"Cancer research","volume":null,"pages":null},"PeriodicalIF":12.5000,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11479818/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cancer research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1158/0008-5472.CAN-24-1322","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Artificial intelligence (AI) systems can improve cancer diagnosis, yet their development often relies on subjective histologic features as ground truth for training. Herein, we developed an AI model applied to histologic whole-slide images using CDH1 biallelic mutations, pathognomonic for invasive lobular carcinoma (ILC) in breast neoplasms, as ground truth. The model accurately predicted CDH1 biallelic mutations (accuracy = 0.95) and diagnosed ILC (accuracy = 0.96). A total of 74% of samples classified by the AI model as having CDH1 biallelic mutations but lacking these alterations displayed alternative CDH1 inactivating mechanisms, including a deleterious CDH1 fusion gene and noncoding CDH1 genetic alterations. Analysis of internal and external validation cohorts demonstrated 0.95 and 0.89 accuracy for ILC diagnosis, respectively. The latent features of the AI model correlated with human-explainable histopathologic features. Taken together, this study reports the construction of an AI algorithm trained using a genetic rather than histologic ground truth that can robustly classify ILCs and uncover CDH1 inactivating mechanisms, providing the basis for orthogonal ground truth utilization for development of diagnostic AI models applied to whole-slide image. Significance: Genetic alterations linked to strong genotypic-phenotypic correlations can be utilized to develop AI systems applied to pathology that facilitate cancer diagnosis and biologic discoveries.
期刊介绍:
Cancer Research, published by the American Association for Cancer Research (AACR), is a journal that focuses on impactful original studies, reviews, and opinion pieces relevant to the broad cancer research community. Manuscripts that present conceptual or technological advances leading to insights into cancer biology are particularly sought after. The journal also places emphasis on convergence science, which involves bridging multiple distinct areas of cancer research.
With primary subsections including Cancer Biology, Cancer Immunology, Cancer Metabolism and Molecular Mechanisms, Translational Cancer Biology, Cancer Landscapes, and Convergence Science, Cancer Research has a comprehensive scope. It is published twice a month and has one volume per year, with a print ISSN of 0008-5472 and an online ISSN of 1538-7445.
Cancer Research is abstracted and/or indexed in various databases and platforms, including BIOSIS Previews (R) Database, MEDLINE, Current Contents/Life Sciences, Current Contents/Clinical Medicine, Science Citation Index, Scopus, and Web of Science.