School of Mechanical Engineering, Hubei University of Arts and Science, Xiangyang, 441053, China; Department of Electromechanical Engineering, University of Macau, Taipa, 999078, Macau, China.
Department of Electromechanical Engineering, University of Macau, Taipa, 999078, Macau, China.
Comput Biol Med. 2020 Nov;126:104026. doi: 10.1016/j.compbiomed.2020.104026. Epub 2020 Oct 12.
Gastric intestinal metaplasia (GIM) is a precancerous lesion of gastric cancer. Currently, diagnosis of GIM is based on the experience of a physician, which is liable to interobserver variability. Thus, an intelligent diagnostic (ID) system, based on narrow-band and magnifying narrow-band images, was constructed to provide objective assistance in the diagnosis of GIM.
We retrospectively collected 1880 endoscopic images (1048 GIM and 832 non-GIM) via biopsy from 336 patients confirmed histologically as GIM or non-GIM, from the Kiang Wu Hospital, Macau. We developed an ID system with these images using a modified convolutional neural network algorithm. A separate test dataset containing 477 pathologically confirmed images (242 GIM and 235 non-GIM) from 80 patients was used to test the performance of the ID system. Experienced endoscopists also examined the same test dataset, for comparison with the ID system. One of the challenges faced in this study was that it was difficult to obtain a large number of training images. Thus, data augmentation and transfer learning were applied together.
The area under the receiver operating characteristic curve was 0.928 for the pre-patient analysis of the ID system, while the sensitivities, specificities, and accuracies of the ID system against those of the human experts were (91.9% vs. 86.5%, p-value = 1.000) (86.0% vs. 81.4%, p-value = 0.754), and (88.8% vs. 83.8%, p-value = 0.424), respectively. Even though the three indices of the ID system were slightly higher than those of the human experts, there were no significant differences.
In this pilot study, a novel ID system was developed to diagnose GIM. This system exhibits promising diagnostic performance. It is believed that the proposed system has the potential for clinical application in the future.
胃肠上皮化生（GIM）是胃癌的癌前病变。目前，GIM 的诊断基于医生的经验，容易受到观察者间变异性的影响。因此，构建了一种基于窄带和放大窄带图像的智能诊断（ID）系统，为 GIM 的诊断提供客观辅助。
我们通过活检从澳门镜湖医院的 336 名经组织学证实为 GIM 或非 GIM 的患者中回顾性收集了 1880 张内镜图像（1048 张 GIM 和 832 张非 GIM）。我们使用改良的卷积神经网络算法开发了一个 ID 系统，该系统使用这些图像。一个单独的包含 80 名患者的 477 张经病理证实的图像（242 张 GIM 和 235 张非 GIM）的测试数据集用于测试 ID 系统的性能。经验丰富的内镜医生也检查了相同的测试数据集，以便与 ID 系统进行比较。本研究面临的挑战之一是很难获得大量的训练图像。因此，应用了数据增强和迁移学习。
ID 系统的患者前分析的受试者工作特征曲线下面积为 0.928，而 ID 系统对人类专家的敏感性、特异性和准确性分别为（91.9%对 86.5%，p 值=1.000）、（86.0%对 81.4%，p 值=0.754）和（88.8%对 83.8%，p 值=0.424）。尽管 ID 系统的三个指标略高于人类专家，但无显著差异。
在这项初步研究中，开发了一种新的 ID 系统来诊断 GIM。该系统表现出有希望的诊断性能。相信该系统将来有临床应用的潜力。
