A Genomics-Driven Artificial Intelligence – Based Model Classifies Breast Invasive Lobular Carcinoma and Discovers CDH1 Inactivating Mechanisms
Authors:
- Fresia ParejaFPFresia Pareja
- Higinio DopesoHDHiginio Dopeso
- Yi Kan WangYWYi Kan Wang
- Andrea M. GazzoAGAndrea M. Gazzo
- David N. BrownDBDavid N. Brown
- Monami BanerjeeMBMonami Banerjee
- Pier SelenicaPSPier Selenica
- Jan H. BernhardJBJan H. Bernhard
- Fatemeh DerakhshanFDFatemeh Derakhshan
- Edaise M. da SilvaESEdaise M. da Silva
- Lorraine Colon-CartagenaLCLorraine Colon-Cartagena
- Thais BasiliTBThais Basili
- 6 August 2024
- journal article
- research article
- Published by American Association for Cancer Research (AACR) in Cancer Research
- Vol. 84 (20) , 3478-3489
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.Keywords
All Related Versions
Funding Information
- National Cancer Institute (P30CA008748)
- National Cancer Institute (P50 CA247749 01)
- Cycle for Survival
- Breast Cancer Research Foundation
- Susan G. Komen
- Starr Foundation
This publication has 43 references indexed in Scilit:
- Nonlobular Invasive Breast Carcinomas with Biallelic Pathogenic CDH1 Somatic Alterations: A Histologic, Immunophenotypic, and Genomic CharacterizationLaboratory Investigation, 2023
- APOBEC mutagenesis, kataegis, chromothripsis in EGFR-mutant osimertinib-resistant lung adenocarcinomasAnnals of Oncology, 2022
- Current and future diagnostic and treatment strategies for patients with invasive lobular breast cancerAnnals of Oncology, 2022
- Inter‐observer agreement for the histological diagnosis of invasive lobular breast carcinomaThe Journal of Pathology: Clinical Research, 2021
- Differential impact of prognostic parameters in hormone receptor–positive lobular breast cancerCancer, 2020
- Predicting Splicing from Primary Sequence with Deep LearningCell, 2019
- Comprehensive Molecular Portraits of Invasive Lobular Breast CancerCell, 2015
- Genetic Interactions in Cancer Progression and TreatmentCell, 2011
- The biological and clinical characteristics of breast carcinoma with mixed ductal and lobular morphologyBreast Cancer Research and Treatment, 2008
- Epigenetic and genetic alterations of APC and CDH1 genes in lobular breast cancer: Relationships with abnormal E‐cadherin and catenin expression and microsatellite instabilityInternational Journal of Cancer, 2003