Microsatellite instability (MSI) has been approved as a pan-cancer biomarker for immune checkpoint blockade (ICB) therapy. However, current MSI identification methods are not available for all patients. We proposed an ensemble multiple instance deep learning model to predict microsatellite status based on histopathology images, and interpreted the pathomics-based model with multi-omics correlation./nMethods: Two cohorts of patients were collected, including 429 from The Cancer Genome Atlas (TCGA-COAD) and 785 from an Asian colorectal cancer (CRC) cohort (Asian-CRC). We established the pathomics model, named Ensembled Patch Likelihood Aggregation (EPLA), based on two consecutive stages: patch-level prediction and WSI-level prediction. The initial model was developed and validated in TCGA-COAD, and then generalized in Asian-CRC through transfer learning. The pathological signatures extracted from the model were analyzed with genomic and transcriptomic profiles for model interpretation./nResults: The EPLA model achieved an area-under-the-curve (AUC) of 0.8848 (95% CI: 0.8185-0.9512) in the TCGA-COAD test set and an AUC of 0.8504 (95% CI: 0.7591-0.9323) in the external validation set Asian-CRC after transfer learning. Notably, EPLA captured the relationship between pathological phenotype of poor differentiation and MSI (P < 0.001). Furthermore, the five pathological imaging signatures identified from the EPLA model were associated with mutation burden and DNA damage repair related genotype in the genomic profiles, and antitumor immunity activated pathway in the transcriptomic profiles./nConclusions: Our pathomics-based deep learning model can effectively predict MSI from histopathology images and is transferable to a new patient cohort. The interpretability of our model by association with pathological, genomic and transcriptomic phenotypes lays the foundation for prospective clinical trials of the application of this artificial intelligence (AI) platform in ICB therapy.

中文翻译：

---

基于病理学模型的大肠癌微卫星不稳定性预测模型的开发和解释

微卫星不稳定性（MSI）已被批准用作免疫检查点封锁（ICB）治疗的全癌生物标志物。但是，当前的MSI识别方法并不适用于所有患者。我们提出了一个整体的多个实例深度学习模式的基础上病理图像来预测微卫星状态，并解释多组学correlation./n基于pathomics模型方法：收集了两个患者队列，包括来自癌症基因组图谱（TCGA-COAD）的429个患者和来自亚洲结直肠癌（CRC）队列（Asian-CRC）的785个患者。我们基于两个连续的阶段（补丁程序级别的预测和WSI级别的预测）建立了称为完整补丁程序似然聚合（EPLA）的病理模型。最初的模型在TCGA-COAD中开发和验证，然后通过转移学习在Asian-CRC中推广。使用基因组和转录组图谱分析从模型中提取的病理特征，以进行模型解释。EPLA模型在TCGA-COAD测试集中的曲线下面积（AUC）为0.8848（95％CI：0.8185-0.9512），外部的AUC为0.8504（95％CI：0.7591-0.9323）转移学习后，验证设置为Asian-CRC。值得注意的是，EPLA捕获了分化不良的病理表型与MSI之间的关系（P <0.001）。此外，从EPLA模型中鉴定出的五个病理学影像特征与基因组图谱中的突变负担和DNA损伤修复相关基因型以及转录组图谱中的抗肿瘤免疫激活途径相关。/n结论：我们基于病理学的深度学习模型可以根据组织病理学图像有效预测MSI，并可以转移到新的患者队列中。通过与病理，基因组和转录组表型的关联，我们模型的可解释性为该人工智能（AI）平台在ICB治疗中的应用进行前瞻性临床试验奠定了基础。