Identifying early gastric cancer under magnifying narrow-band images with deep learning: a multicenter study
Identifying early gastric cancer under magnifying narrow-band images with deep learning: a multicenter study
复制标题
利用深度学习放大窄带图像识别早期胃癌：一项多中心研究
DOI：
10.1016/j.gie.2020.11.014
复制
发表时间：
2021-05-13
影响因子：
7.7
通讯作者：
Tian, Jie
中科院分区：
文献类型：
--
作者：
Hu, Hao;Gong, Lixin;Tian, Jie
背景和目的：放大内窥镜窄带成像（ME-NBI）在诊断早期胃癌（EGC）方面显示出优势。然而，熟练掌握诊断算法需要大量的专业知识和经验。在本研究中，我们旨在开发一种EGM计算机辅助诊断模型（EGCM），以分析和辅助ME-NBI下EGC的诊断。方法：收集来自3个中心的295例患者的1777幅ME-NBI图像。这些病例被随机分为训练队列（n Z 170）、内部测试队列（ITC，n Z 73）和外部测试队列（ETC，n Z 52）。 EGCM 基于 VGG-19 架构（英国牛津大学视觉几何组 [VGG]），具有单个完全连接的 2 分类层，是通过微调开发的，并在所有队列上进行了验证。此外，我们将该模型与 8 位具有不同经验的内窥镜医师进行了比较。主要比较指标包括准确性、受试者工作特征曲线下面积 (AUC)、敏感性、特异性、阳性预测值 (PPV) 和阴性预测值 (NPV)。 结果：EGCM 在 ITC 中获得的 AUC 为 808，在 ETC 中获得的 AUC 为 813。此外，EGCM 实现了与高级内窥镜医师相似的预测性能（准确度：.770 vs.755，P = .355；灵敏度：.792 vs.767，P = .183；特异性：.745 vs.742，P = .931），但优于初级内窥镜医师（准确度：.770 vs.728，P）
Background and Aims: Narrow-band imaging with magnifying endoscopy (ME-NBI) has shown advantages in the diagnosis of early gastric cancer (EGC). However, proficiency in diagnostic algorithms requires substantial expertise and experience. In this study, we aimed to develop a computer-aided diagnostic model for EGM (EGCM) to analyze and assist in the diagnosis of EGC under ME-NBI.Methods: A total of 1777 ME-NBI images from 295 cases were collected from 3 centers. These cases were randomly divided into a training cohort (n Z 170), an internal test cohort (ITC, n Z 73), and an external test cohort (ETC, n Z 52). EGCM based on VGG-19 architecture (Visual Geometry Group [VGG], Oxford University, Oxford, UK) with a single fully connected 2-classification layer was developed through fine-tuning and validated on all cohorts. Furthermore, we compared the model with 8 endoscopists with varying experience. Primary comparison measures included accuracy, area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).Results: EGCM acquired AUCs of.808 in the ITC and.813 in the ETC. Moreover, EGCM achieved similar predictive performance as the senior endoscopists (accuracy:.770 vs.755, P = .355; sensitivity:.792 vs.767, P = .183; specificity:.745 vs.742, P = .931) but better than the junior endoscopists (accuracy:.770 vs.728, P