Liu Leheng, Dong Zhixia, Cheng Jinnian, Bu Xiongzhu, Qiu Kaili, Yang Chuan, Wang Jing, Niu Wenlu, Wu Xiaowan, Xu Jingxian, Mao Tiancheng, Lu Lungen, Wan Xinjian, Zhou Hui
Department of Gastroenterology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Shanghai Key Laboratory of Pancreatic Diseases, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Front Oncol. 2023 Jan 16;12:1075578. doi: 10.3389/fonc.2022.1075578. eCollection 2022.
Endoscopically visible gastric neoplastic lesions (GNLs), including early gastric cancer and intraepithelial neoplasia, should be accurately diagnosed and promptly treated. However, a high rate of missed diagnosis of GNLs contributes to the potential risk of the progression of gastric cancer. The aim of this study was to develop a deep learning-based computer-aided diagnosis (CAD) system for the diagnosis and segmentation of GNLs under magnifying endoscopy with narrow-band imaging (ME-NBI) in patients with suspected superficial lesions.
ME-NBI images of patients with GNLs in two centers were retrospectively analysed. Two convolutional neural network (CNN) modules were developed and trained on these images. CNN1 was trained to diagnose GNLs, and CNN2 was trained for segmentation. An additional internal test set and an external test set from another center were used to evaluate the diagnosis and segmentation performance.
CNN1 showed a diagnostic performance with an accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of 90.8%, 92.5%, 89.0%, 89.4% and 92.2%, respectively, and an area under the curve (AUC) of 0.928 in the internal test set. With CNN1 assistance, all endoscopists had a higher accuracy than for an independent diagnosis. The average intersection over union (IOU) between CNN2 and the ground truth was 0.5837, with a precision, recall and the Dice coefficient of 0.776, 0.983 and 0.867, respectively.
This CAD system can be used as an auxiliary tool to diagnose and segment GNLs, assisting endoscopists in more accurately diagnosing GNLs and delineating their extent to improve the positive rate of lesion biopsy and ensure the integrity of endoscopic resection.
内镜可见的胃肿瘤性病变（GNLs），包括早期胃癌和上皮内瘤变，应准确诊断并及时治疗。然而，GNLs的漏诊率较高，这增加了胃癌进展的潜在风险。本研究的目的是开发一种基于深度学习的计算机辅助诊断（CAD）系统，用于在窄带成像放大内镜检查（ME-NBI）下对疑似浅表病变患者的GNLs进行诊断和分割。
回顾性分析两个中心患有GNLs患者的ME-NBI图像。开发了两个卷积神经网络（CNN）模块并在这些图像上进行训练。CNN1用于训练诊断GNLs，CNN2用于训练分割。使用来自另一个中心的额外内部测试集和外部测试集来评估诊断和分割性能。
在内部测试集中，CNN1的诊断性能表现为：准确率、灵敏度、特异度、阳性预测值（PPV）和阴性预测值（NPV）分别为90.8%、92.5%、89.0%、89.4%和92.2%，曲线下面积（AUC）为0.928。在CNN1的辅助下，所有内镜医师的诊断准确率均高于独立诊断时。CNN2与真实情况之间的平均交并比（IOU）为0.5837，精确率、召回率和Dice系数分别为0.776、0.983和0.867。
该CAD系统可作为诊断和分割GNLs的辅助工具，协助内镜医师更准确地诊断GNLs并描绘其范围，以提高病变活检的阳性率并确保内镜切除的完整性。
