Department of Pathology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.
Department of Pathology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, China.
Cell Rep Med. 2023 Feb 21;4(2):100914. doi: 10.1016/j.xcrm.2022.100914. Epub 2023 Jan 30.
This study develops a method combining a convolutional neural network model, INSIGHT, with a self-attention model, WiseMSI, to predict microsatellite instability (MSI) based on the tiles in colorectal cancer patients from a multicenter Chinese cohort. After INSIGHT differentiates tumor tiles from normal tissue tiles in a whole slide image, features of tumor tiles are extracted with a ResNet model pre-trained on ImageNet. Attention-based pooling is adopted to aggregate tile-level features into slide-level representation. INSIGHT has an area under the curve (AUC) of 0.985 for tumor patch classification. The Spearman correlation coefficient of tumor cell fraction given by expert pathologist and INSIGHT is 0.7909. WiseMSI achieves a specificity of 94.7% (95% confidence interval [CI] 93.7%-95.7%), a sensitivity of 84.7% (95% CI 82.6%-86.9%), and an AUC of 0.954 (95% CI 0.948-0.960). Comparative analysis shows that this method has better performance than the other five classic deep learning methods.
本研究开发了一种将卷积神经网络模型 INSIGHT 与自注意力模型 WiseMSI 相结合的方法，用于基于来自中国多中心队列的结直肠癌患者的幻灯片中的斑块来预测微卫星不稳定性 (MSI)。在 INSIGHT 将全幻灯片图像中的肿瘤斑块与正常组织斑块区分开后，使用在 ImageNet 上预训练的 ResNet 模型提取肿瘤斑块的特征。采用基于注意力的池化方法将斑块级特征聚合为幻灯片级表示。INSIGHT 对肿瘤斑块分类的曲线下面积 (AUC) 为 0.985。专家病理学家和 INSIGHT 给出的肿瘤细胞分数的斯皮尔曼相关系数为 0.7909。WiseMSI 的特异性为 94.7%（95%置信区间 [93.7%-95.7%]），敏感性为 84.7%（95%置信区间 [82.6%-86.9%]），AUC 为 0.954（95%置信区间 [94.8%-96.0%]）。对比分析表明，该方法的性能优于其他五种经典深度学习方法。
