Department of Gastroenterology, Peking University People's Hospital, Beijing, China.
Internet Medical Department of Love Life Insurance Company, Beijing, China.
Dig Endosc. 2021 Jul;33(5):788-796. doi: 10.1111/den.13844. Epub 2020 Oct 27.
A deep convolutional neural network (CNN) was used to achieve fast and accurate artificial intelligence (AI)-assisted diagnosis of early gastric cancer (GC) and other gastric lesions based on endoscopic images.
A CNN-based diagnostic system based on a ResNet34 residual network structure and a DeepLabv3 structure was constructed and trained using 21,217 gastroendoscopic images of five gastric conditions, peptic ulcer (PU), early gastric cancer (EGC) and high-grade intraepithelial neoplasia (HGIN), advanced gastric cancer (AGC), gastric submucosal tumors (SMTs), and normal gastric mucosa without lesions. The trained CNN was evaluated using a test dataset of 1091 images. The accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the CNN were calculated. The CNN diagnosis was compared with those of 10 endoscopists with over 8 years of experience in endoscopic diagnosis.
The diagnostic specificity and PPV of the CNN were higher than that of the endoscopists for the EGC and HGIN images (specificity: 91.2% vs. 86.7%, by 4.5%, 95% CI 2.8-7.2%; PPV: 55.4% vs. 41.7%, by 13.7%, 95% CI 11.2-16.8%) and the diagnostic accuracy of the CNN was close to those of the endoscopists for the lesion-free, EGC and HGIN, PU, AGC, and SMTs images. The CNN had image recognition time of 42 s for all the test set images.
The constructed CNN system could be used as a rapid auxiliary diagnostic instrument to detect EGC and HGIN, as well as other gastric lesions, to reduce the workload of endoscopists.
本研究旨在使用深度卷积神经网络（CNN），基于内镜图像实现早期胃癌（GC）和其他胃部病变的快速、准确的人工智能（AI）辅助诊断。
构建了一种基于 ResNet34 残差网络结构和 DeepLabv3 结构的 CNN 诊断系统，并使用 5 种胃部疾病（消化性溃疡（PU）、早期胃癌（EGC）和高级上皮内瘤变（HGIN）、晚期胃癌（AGC）、胃黏膜下肿瘤（SMT）和正常无病变胃黏膜）的 21217 张胃内镜图像对其进行训练和验证。使用包含 1091 张图像的测试数据集来评估训练好的 CNN。计算 CNN 的准确性、敏感性、特异性、阳性预测值（PPV）和阴性预测值（NPV）。将 CNN 诊断与 10 名内镜诊断经验超过 8 年的内镜医生的诊断进行比较。
对于 EGC 和 HGIN 图像，CNN 的诊断特异性和 PPV 高于内镜医生（特异性：91.2% vs. 86.7%，高 4.5%，95%CI 2.8-7.2%；PPV：55.4% vs. 41.7%，高 13.7%，95%CI 11.2-16.8%），而对于无病变、EGC 和 HGIN、PU、AGC 和 SMT 图像，CNN 的诊断准确率与内镜医生相当。该 CNN 系统对所有测试集图像的识别时间为 42 秒。
所构建的 CNN 系统可作为一种快速辅助诊断工具，用于检测 EGC 和 HGIN 以及其他胃部病变，以减轻内镜医生的工作负担。
