Background The operative link for the gastritis assessment (OLGA) system can objectively reflect the stratification of gastric cancer risk in patients with chronic atrophic gastritis (CAG). Objectives We developed a real-time video monitoring model for the endoscopic diagnosis of CAG and OLGA staging based on U-Net deep learning (DL). To further validate and improve its performance, we designed a study to evaluate the diagnostic evaluation indices. Design A prospective nested case-control study. Methods Our cohort consisted of 1306 patients from 31 July 2021 to 31 January 2022. According to the pathological results, patients in the cohort were divided into the CAG group and the chronic non-atrophic gastritis group to evaluate the diagnostic evaluation indices. Each atrophy lesion was automatically labeled and the atrophy severity was assessed by the model. Propensity score matching was used to minimize selection bias. Results The diagnostic evaluation indices and the consistency between OLGA staging and pathological diagnosis of the model were superior to those of endoscopists [sensitivity (89.31% versus 67.56%), specificity (90.46% versus 70.23%), positive predictive value (90.35% versus 69.41%), negative predictive value (89.43% versus 68.40%), accuracy rate (89.89% versus 68.89%), Youden index (79.77% versus 37.79%), odd product (79.23 versus 4.91), positive likelihood ratio (9.36 versus 2.27), negative likelihood ratio (0.12 versus 0.46)], areas under the curves (AUC) (95% CI) (0.919 (0.893-0.945) versus 0.749 (0.707-0.792), p < 0.001) and kappa (0.816 versus 0.291)]. Conclusion Our study demonstrated that the DL model can assist endoscopists in real-time diagnosis of CAG during gastroscopy and synchronous identification of high-risk OLGA stage (OLGA stages III and IV) patients. Trial registration ChiCTR2100044458.

中文翻译：

---

用于慢性萎缩性胃炎内镜诊断的U-Net深度学习模型和胃炎评估分期的操作环节：一项前瞻性巢式病例对照研究。

背景胃炎评估（OLGA）系统的操作环节可以客观反映慢性萎缩性胃炎（CAG）患者胃癌风险分层。目标 我们开发了基于 U-Net 深度学习 (DL) 的内镜诊断 CAG 和 OLGA 分期的实时视频监控模型。为了进一步验证和提高其性能，我们设计了一项研究来评估诊断评价指标。设计前瞻性巢式病例对照研究。方法纳入2021年7月31日至2022年1月31日期间的1306例患者。根据病理结果将队列患者分为CAG组和慢性非萎缩性胃炎组，评估诊断评价指标。每个萎缩病变都会自动标记，并通过模型评估萎缩严重程度。倾向评分匹配用于最大限度地减少选择偏差。结果模型的诊断评价指标以及OLGA分期与病理诊断的一致性均优于内镜医师[敏感度（89.31%比67.56%）、特异度（90.46%比70.23%）、阳性预测值（90.35%比69.41 %）、阴性预测值（89.43% vs 68.40%）、准确率（89.89% vs 68.89%）、Youden 指数（79.77% vs 37.79%）、奇积（79.23 vs 4.91）、阳性似然比（9.36 vs 2.27） ，阴性似然比（0.12 与 0.46）]，曲线下面积 (AUC)（95% CI）（0.919 (0.893-0.945) 与 0.749 (0.707-0.792)，p < 0.001）和 kappa（0.816 与 0.291）] 。结论 我们的研究表明，DL模型可以辅助内镜医师在胃镜检查过程中实时诊断CAG并同步识别高危OLGA分期（OLGA III期和IV期）患者。试用注册ChiCTR2100044458。