U-Net deep learning model for endoscopic diagnosis of chronic atrophic gastritis and operative link for gastritis assessment staging: a prospective nested case-control study.

IF 4.3 3区材料科学 Q1 ENGINEERING, ELECTRICAL & ELECTRONIC

ACS Applied Electronic Materials Pub Date : 2023-11-02 eCollection Date: 2023-01-01 DOI:10.1177/17562848231208669

Quchuan Zhao, Qing Jia, Tianyu Chi

{"title":"U-Net deep learning model for endoscopic diagnosis of chronic atrophic gastritis and operative link for gastritis assessment staging: a prospective nested case-control study.","authors":"Quchuan Zhao, Qing Jia, Tianyu Chi","doi":"10.1177/17562848231208669","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":3,"journal":{"name":"ACS Applied Electronic Materials","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2023-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10624012/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Applied Electronic Materials","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/17562848231208669","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/1/1 0:00:00","PubModel":"eCollection","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

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.

Abstract Image

查看原文本刊更多论文

U-Net深度学习模型用于慢性萎缩性胃炎的内镜诊断和胃炎评估分期的手术环节：一项前瞻性嵌套病例对照研究。

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）患者胃癌癌症风险的分层。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估指标。设计：前瞻性嵌套病例对照研究。方法：我们的队列包括2021年7月31日至2022年1月31日的1306名患者。根据病理结果，将队列中的患者分为CAG组和慢性非萎缩性胃炎组，以评估诊断评估指标。每个萎缩病变都被自动标记，并通过模型评估萎缩的严重程度。倾向性得分匹配用于最大限度地减少选择偏差。结果：该模型的诊断评价指标和OLGA分期与病理诊断的一致性优于内镜医生[敏感性（89.31%对67.56%），特异性（90.46%对70.23%），阳性预测值（90.35%对69.41%），阴性预测值（89.43%对68.40%），准确率（89.89%对68.89%），Youden指数（79.77%对37.79%），奇数乘积（79.23对4.91），正似然比（9.36对2.27），负似然比（0.12对0.46）]，曲线下面积（AUC）（95%CI）（0.919（0.893-0.945）对0.749（0.707-0.792），p 结论：我们的研究表明，DL模型可以帮助内镜医生在胃镜检查中实时诊断CAG，并同步识别高危OLGA分期（OLGA III和IV期）患者。试验注册号：ChiCTR210044458。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

ACS Applied Electronic Materials Multiple-

CiteScore

7.20

自引率

4.30%

发文量

567