Department of Biochemistry and Molecular Biology, Biomedicine Discovery Institute, Monash University, Melbourne 3800, Australia.
Faculty of Information Technology, Monash University, Melbourne 3800, Australia.
Bioinformatics. 2022 Sep 2;38(17):4206-4213. doi: 10.1093/bioinformatics/btac456.
The molecular subtyping of gastric cancer (adenocarcinoma) into four main subtypes based on integrated multiomics profiles, as proposed by The Cancer Genome Atlas (TCGA) initiative, represents an effective strategy for patient stratification. However, this approach requires the use of multiple technological platforms, and is quite expensive and time-consuming to perform. A computational approach that uses histopathological image data to infer molecular subtypes could be a practical, cost- and time-efficient complementary tool for prognostic and clinical management purposes.
Here, we propose a deep learning ensemble approach (called DEMoS) capable of predicting the four recognized molecular subtypes of gastric cancer directly from histopathological images. DEMoS achieved tile-level area under the receiver-operating characteristic curve (AUROC) values of 0.785, 0.668, 0.762 and 0.811 for the prediction of these four subtypes of gastric cancer [i.e. (i) Epstein-Barr (EBV)-infected, (ii) microsatellite instability (MSI), (iii) genomically stable (GS) and (iv) chromosomally unstable tumors (CIN)] using an independent test dataset, respectively. At the patient-level, it achieved AUROC values of 0.897, 0.764, 0.890 and 0.898, respectively. Thus, these four subtypes are well-predicted by DEMoS. Benchmarking experiments further suggest that DEMoS is able to achieve an improved classification performance for image-based subtyping and prevent model overfitting. This study highlights the feasibility of using a deep learning ensemble-based method to rapidly and reliably subtype gastric cancer (adenocarcinoma) solely using features from histopathological images.
All whole slide images used in this study was collected from the TCGA database. This study builds upon our previously published HEAL framework, with related documentation and tutorials available at http://heal.erc.monash.edu.au. The source code and related models are freely accessible at https://github.com/Docurdt/DEMoS.git.
Supplementary data are available at Bioinformatics online.
基于整合的多组学图谱，癌症基因组图谱（TCGA）计划将胃癌（腺癌）分为四个主要亚型，这代表了一种对患者进行分层的有效策略。然而，这种方法需要使用多种技术平台，并且执行起来非常昂贵和耗时。一种使用组织病理学图像数据来推断分子亚型的计算方法可能是一种实用、具有成本效益和时间效益的补充工具，可用于预后和临床管理目的。
在这里，我们提出了一种深度学习集成方法（称为 DEMoS），能够直接从组织病理学图像预测胃癌的四个公认的分子亚型。DEMoS 使用独立的测试数据集分别为预测这四种胃癌亚型（即（i）爱泼斯坦-巴尔（EBV）感染、（ii）微卫星不稳定（MSI）、（iii）基因组稳定（GS）和（iv）染色体不稳定肿瘤（CIN））获得了 0.785、0.668、0.762 和 0.811 的tile 级接收者操作特征曲线（AUROC）值。在患者水平，它分别获得了 0.897、0.764、0.890 和 0.898 的 AUROC 值。因此，DEMoS 可以很好地预测这四种亚型。基准测试实验进一步表明，DEMoS 能够提高基于图像的亚型分类性能并防止模型过拟合。这项研究强调了使用基于深度学习集成的方法仅使用组织病理学图像的特征快速可靠地对胃癌（腺癌）进行亚型分类的可行性。
本研究中使用的所有全切片图像均来自 TCGA 数据库。本研究建立在我们之前发表的 HEAL 框架的基础上，相关文档和教程可在 http://heal.erc.monash.edu.au 上获得。源代码和相关模型可在 https://github.com/Docurdt/DEMoS.git 上免费获得。
补充数据可在《生物信息学》在线获取。
