Clinical actionability of triaging DNA mismatch repair deficient colorectal cancer from biopsy samples using deep learning

作者：Jiang Wu, Wei-Jian Mei, Shuoyu Xu, Yihong Ling, Weirong Li, Jin-Bo Kuang, Hao‐Sen Li, Hui Hui, Jibin Li, Muyan Cai, Zhizhong Pan, Huizhong Zhang, Li Li, Peirong Ding · 发表于：EBioMedicine · 年份：2022 · DOI：10.1016/j.ebiom.2022.104120 · 被引用次数：44 · 研究领域：AI in cancer detection、Radiomics and Machine Learning in Medical Imaging、Genetic factors in colorectal cancer

BACKGROUND: We aimed to develop a deep learning (DL) model to predict DNA mismatch repair (MMR) status in colorectal cancers (CRC) based on hematoxylin and eosin-stained whole-slide images (WSIs) and assess its clinical applicability. METHODS: The DL model was developed and validated through three-fold cross validation using 441 WSIs from the Cancer Genome Atlas (TCGA) and externally validated using 78 WSIs from the Pathology AI Platform (PAIP), and 355 WSIs from surgical specimens and 341 WSIs from biopsy specimens of the Sun Yet-sun University Cancer Center (SYSUCC). Domain adaption and multiple instance learning (MIL) techniques were adopted for model development. The performance of the models was evaluated using the area under the receiver operating characteristic curve (AUROC). A dual-threshold strategy was also built from the surgical cohorts and validated in the biopsy cohort. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1-score, and the percentage of patients avoiding IHC testing were evaluated. FINDINGS: The MIL model achieved an AUROC of 0·8888±0·0357 in the TCGA-validation cohort, 0·8806±0·0232 in the PAIP cohort, 0·8457±0·0233 in the SYSUCC-surgical cohort, and 0·7679±0·0342 in the SYSUCC-biopsy cohort. A dual-threshold triage strategy was used to rule-in and rule-out dMMR patients with remaining uncertain patients recommended for further IHC testing, which kept sensitivity higher than 90% and specificity higher than...