Colorectal cancer (CRC) is the third most common and second most lethal cancer globally. It is highly heterogeneous with different clinical-pathological characteristics, prognostic status, and therapy responses. Thus, the precise diagnosis of CRC subtypes is of great significance for improving the prognosis and survival of CRC patients. Nowadays, the most commonly used molecular-level CRC classification system is the Consensus Molecular Subtypes (CMSs). In this study, we applied a weakly supervised deep learning method, named attention-based multi-instance learning (MIL), on formalin-fixed paraffin-embedded (FFPE) whole-slide images (WSIs) to distinguish CMS1 subtype from CMS2, CMS3, and CMS4 subtypes, as well as distinguish CMS4 from CMS1, CMS2, and CMS3 subtypes. The advantage of MIL is training a bag of the tiled instance with bag-level labels only. Our experiment was performed on 1218 WSIs obtained from The Cancer Genome Atlas (TCGA). We constructed three convolutional neural network-based structures for model training and evaluated the ability of the max-pooling operator and mean-pooling operator on aggregating bag-level scores. The results showed that the 3-layer model achieved the best performance in both comparison groups. When compared CMS1 with CMS234, max-pooling reached the ACC of 83.86 % and the mean-pooling operator reached the AUC of 0.731. While comparing CMS4 with CMS123, mean-pooling reached the ACC of 74.26 % and max-pooling reached the AUC of 0.609. Our results implied that WSIs could be utilized to classify CMSs, and manual pixel-level annotation is not a necessity for computational pathology imaging analysis.

结直肠癌 (CRC) 是全球第三大常见癌症和第二大致命癌症。它具有高度异质性，具有不同的临床病理特征、预后状态和治疗反应。因此，CRC亚型的精确诊断对于改善CRC患者的预后和生存具有重要意义。如今，最常用的分子水平 CRC 分类系统是共识分子亚型 (CMS)。在本研究中，我们在福尔马林固定石蜡包埋 (FFPE) 全玻片图像 (WSI) 上应用了一种弱监督深度学习方法，称为基于注意的多实例学习 (MIL)，以区分 CMS1 亚型与 CMS2、CMS3 、 和 CMS4 亚型，并将 CMS4 与 CMS1、CMS2 和 CMS3 亚型区分开来。MIL 的优点是仅使用包级标签训练平铺实例的包。我们的实验是在从癌症基因组图谱 (TCGA) 获得的 1218 个 WSI 上进行的。我们构建了三种基于卷积神经网络的结构用于模型训练，并评估了最大池算子和均值池算子聚合袋级分数的能力。结果表明，3 层模型在两个比较组中均取得了最佳性能。比较 CMS1 和 CMS234 时，最大池化的 ACC 达到 83.86%，平均池化算子的 AUC 达到 0.731。将 CMS4 与 CMS123 进行比较时，平均池化的 ACC 达到 74.26%，最大池化的 AUC 达到 0.609。我们的结果表明 WSI 可用于对 CMS 进行分类，并且手动像素级注释并不是计算病理学成像分析的必要条件。