Shi Yanting, Wei Ning, Wang Kunhong, Wu Jingjing, Tao Tao, Li Na, Lv Bing
Department of Gastroenterology, Zibo Central Hospital, Zibo, Shandong, China.
Department of Internal Medicine, Zhangdian Maternal and Child Health Care Hospital, Zibo, Shandong, China.
Front Oncol. 2023 Mar 6;13:1122247. doi: 10.3389/fonc.2023.1122247. eCollection 2023.
Chronic atrophic gastritis (CAG) is a precancerous condition. It is not easy to detect CAG in endoscopy. Improving the detection rate of CAG under endoscopy is essential to reduce or interrupt the occurrence of gastric cancer. This study aimed to construct a deep learning (DL) model for CAG recognition based on endoscopic images to improve the CAG detection rate during endoscopy.
We collected 10,961 endoscopic images and 118 video clips from 4,050 patients. For model training and testing, we divided them into two groups based on the pathological results: CAG and chronic non-atrophic gastritis (CNAG). We compared the performance of four state-of-the-art (SOTA) DL networks for CAG recognition and selected one of them for further improvement. The improved network was called GAM-EfficientNet. Finally, we compared GAM-EfficientNet with three endoscopists and analyzed the decision basis of the network in the form of heatmaps.
After fine-tuning and transfer learning, the sensitivity, specificity, and accuracy of GAM-EfficientNet reached 93%, 94%, and 93.5% in the external test set and 96.23%, 89.23%, and 92.37% in the video test set, respectively, which were higher than those of the three endoscopists.
The CAG recognition model based on deep learning has high sensitivity and accuracy, and its performance is higher than that of endoscopists.
慢性萎缩性胃炎（CAG）是一种癌前状态。在内镜检查中检测CAG并不容易。提高内镜下CAG的检出率对于降低或阻断胃癌的发生至关重要。本研究旨在构建一种基于内镜图像的深度学习（DL）模型用于CAG识别，以提高内镜检查时CAG的检出率。
我们从4050例患者中收集了10961张内镜图像和118个视频片段。为了进行模型训练和测试，我们根据病理结果将它们分为两组：CAG和慢性非萎缩性胃炎（CNAG）。我们比较了四种最先进的（SOTA）DL网络对CAG识别的性能，并选择其中一种进行进一步改进。改进后的网络称为GAM-EfficientNet。最后，我们将GAM-EfficientNet与三位内镜医师进行比较，并以热图的形式分析了该网络的决策依据。
经过微调与迁移学习后，GAM-EfficientNet在外部测试集中的灵敏度、特异度和准确率分别达到93%、94%和93.5%，在视频测试集中分别达到96.23%、89.23%和92.37%，均高于三位内镜医师的表现。
基于深度学习的CAG识别模型具有较高的灵敏度和准确率，其性能高于内镜医师。
