A Genomics-Driven Artificial Intelligence-Based Model Classifies Breast Invasive Lobular Carcinoma and Discovers CDH1 Inactivating Mechanisms.

IF 12.5 1区 医学 Q1 ONCOLOGY
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":" ","pages":"3478-3489"},"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.

基于基因组学的人工智能模型可对乳腺浸润性小叶癌进行分类并发现 CDH1 失活机制
人工智能(AI)系统可以改善癌症诊断,但其开发往往依赖于主观组织学特征作为训练的基本事实。在这里,我们开发了一种应用于组织学全切片图像(WSI)的人工智能模型,该模型以CDH1双等位基因突变(乳腺肿瘤中浸润性小叶癌(ILC)的病理标志)为基本真相。该模型准确预测了 CDH1 双等位基因突变(准确率=0.95),并诊断出了 ILC(准确率=0.96)。在被人工智能模型归类为具有CDH1双等位基因突变但缺乏这些改变的样本中,共有74%的样本显示了CDH1失活的替代机制,包括有害的CDH1融合基因和非编码CDH1基因改变。对内部和外部验证队列的分析表明,ILC诊断的准确率分别为0.95和0.89。人工智能模型的潜在特征与人类可解释的组织病理学特征相关。综上所述,本研究报告了利用遗传学而非组织学基本事实训练的人工智能算法的构建情况,该算法可对 ILC 进行稳健分类,并发现 CDH1 失活机制,为开发应用于 WSI 的诊断人工智能模型提供了正交基本事实利用的基础。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Cancer research
Cancer research 医学-肿瘤学
CiteScore
16.10
自引率
0.90%
发文量
7677
审稿时长
2.5 months
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.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信