深度学习在结直肠肿瘤中临床级检测微卫星不稳定
该研究从德国、荷兰、英国和美国的MSIDETECT联盟研究中收集了8836例结直肠肿瘤的H&E染色切片及分子分析结果,训练深度学习检测器识别微卫星不稳定(MSI)或错配修复缺陷(dMMR)。在交叉验证开发队列(N=6406)中,平均AUROC为0.92、AUPRC为0.63,特异性67%、敏感性95%;在外部验证队列(n=771)中,dMMR检测的AUROC为0.95(未预处理)和0.96(颜色归一化后)。作者认为该系统或可用于高通量、低成本的结直肠组织标本评估。
要点
- 深度学习检测器在交叉验证开发队列中识别dMMR或MSI的平均AUROC为0.92,AUPRC为0.63。
- 开发队列中特异性67%、敏感性95%。
- 外部验证队列中dMMR检测AUROC为0.95(未预处理)和0.96(颜色归一化后)。
核心结论
- 作者开发了使用H&E染色切片检测结直肠癌标本dMMR或MSI的深度学习系统,在国际大型验证队列中检测dMMR的AUROC为0.96。
- 作者认为该系统或可用于高通量、低成本的结直肠组织标本评估。
研究设计与样本
- 从德国、荷兰、英国和美国的MSIDETECT联盟研究中收集8836例各分期结直肠肿瘤的H&E染色切片及MSI和dMMR分子分析结果。
- 通过组织微阵列免疫组化分析MLH1、MSH2、MSH6和/或PMS2缺失来鉴定dMMR标本,通过基因分析鉴定MSI标本。
- 训练深度学习检测器从切片中识别MSI样本,通过交叉验证(N=6406例标本)评估性能,并在外部队列(n=771例标本)中验证。
- 预设终点为受试者工作特征曲线下面积(AUROC)和精确率-召回率曲线下面积(AUPRC)。
主要发现
- 在交叉验证开发队列中,深度学习检测器识别dMMR或MSI标本的平均AUROC为0.92(下界0.91,上界0.93),AUPRC为0.63(范围0.59-0.65),特异性67%、敏感性95%。
- 在验证队列中,分类器未进行图像预处理时识别dMMR样本的AUROC为0.95(范围0.92-0.96),颜色归一化后AUROC为0.96(范围0.93-0.98)。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND & AIMS: Microsatellite instability (MSI) and mismatch-repair deficiency (dMMR) in colorectal tumors are used to select treatment for patients. Deep learning can detect MSI and dMMR in tumor samples on routine histology slides faster and less expensively than molecular assays. However, clinical application of this technology requires high performance and multisite validation, which have not yet been performed. METHODS: We collected H&E-stained slides and findings from molecular analyses for MSI and dMMR from 8836 colorectal tumors (of all stages) included in the MSIDETECT consortium study, from Germany, the Netherlands, the United Kingdom, and the United States. Specimens with dMMR were identified by immunohistochemistry analyses of tissue microarrays for loss of MLH1, MSH2, MSH6, and/or PMS2. Specimens with MSI were identified by genetic analyses. We trained a deep-learning detector to identify samples with MSI from these slides; performance was assessed by cross-validation (N = 6406 specimens) and validated in an external cohort (n = 771 specimens). Prespecified endpoints were area under the receiver operating characteristic (AUROC) curve and area under the precision-recall curve (AUPRC). RESULTS: The deep-learning detector identified specimens with dMMR or MSI with a mean AUROC curve of 0.92 (lower bound, 0.91; upper bound, 0.93) and an AUPRC of 0.63 (range, 0.59-0.65), or 67% specificity and 95% sensitivity, in the cross-validation development cohort. In the validation cohort, the classifier identified samples with dMMR with an AUROC of 0.95 (range, 0.92-0.96) without image preprocessing and an AUROC of 0.96 (range, 0.93-0.98) after color normalization. CONCLUSIONS: We developed a deep-learning system that detects colorectal cancer specimens with dMMR or MSI using H&E-stained slides; it detected tissues with dMMR with an AUROC of 0.96 in a large, international validation cohort. This system might be used for high-throughput, low-cost evaluation of colorectal tissue specimens.
引用
- Echle A, Grabsch HI, Quirke P, et al. Clinical-Grade Detection of Microsatellite Instability in Colorectal Tumors by Deep Learning. Gastroenterology. 2020. PMID: 32562722. doi:10.1053/j.gastro.2020.06.021
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。