School of Software, Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province, Dalian University of Technology, Dalian, Liaoning, China.
Dalian Municipal Central Hospital, Dalian, Liaoning, China.
Comput Math Methods Med. 2022 Sep 26;2022:6899448. doi: 10.1155/2022/6899448. eCollection 2022.
Accurate pathological diagnosis of gastric endoscopic biopsy could greatly improve the opportunity of early diagnosis and treatment of gastric cancer. The Japanese "Group classification" of gastric biopsy corresponds well with the endoscopic diagnostic system and can guide clinical treatment. However, severe shortage of pathologists and their heavy workload limit the diagnostic accuracy. This study presents the first attempt to investigate the applicability and effectiveness of AI-aided system for automated Japanese "Group classification" of gastric endoscopic biopsy.
In total, 260 whole-slide images of gastric endoscopic biopsy were collected from Dalian Municipal Central Hospital from January 2015 to January 2021. These images were annotated by experienced pathologists according to the Japanese "Group classification." Five popular convolutional neural networks, i.e., VGG16, VGG19, ResNet50, Xception, and InceptionV3 were trained and tested. The performance of the models was compared in terms of widely used metrics, namely, AUC (area under the receiver operating characteristic curve, i.e., ROC curve), accuracy, recall, precision, and F1 score.
Results showed that ResNet50 achieved the best performance with accuracy 93.16% and AUC 0.994.
Our results demonstrated the applicability and effectiveness of DL-based system for automated Japanese "Group classification" of gastric endoscopic biopsy.
准确的胃部内镜活检病理诊断可以大大提高胃癌的早期诊断和治疗机会。日本的胃部内镜活检“组织学分类”与内镜诊断系统相吻合，能够指导临床治疗。然而，病理医生的严重短缺和工作量大限制了诊断的准确性。本研究首次尝试探索人工智能辅助系统在自动化日本胃部内镜活检“组织学分类”中的适用性和有效性。
本研究共收集了 2015 年 1 月至 2021 年 1 月大连市中心医院的 260 张胃部内镜活检全切片图像。这些图像由经验丰富的病理医生根据日本“组织学分类”进行标注。我们训练和测试了 5 种流行的卷积神经网络，即 VGG16、VGG19、ResNet50、Xception 和 InceptionV3。我们使用广泛使用的度量标准，如 AUC（接受者操作特征曲线下的面积，即 ROC 曲线）、准确性、召回率、精度和 F1 分数来比较模型的性能。
结果表明，ResNet50 的性能最佳，准确率为 93.16%，AUC 为 0.994。
我们的研究结果表明，基于深度学习的系统在自动化日本胃部内镜活检“组织学分类”中具有适用性和有效性。
