Artificial intelligence improves submucosal vessel detection during third space endoscopy.

IF 11.5 1区医学 Q1 GASTROENTEROLOGY & HEPATOLOGY

Endoscopy Pub Date : 2025-02-05 DOI:10.1055/a-2534-1164

Markus Wolfgang Scheppach, Robert Mendel, Anna Muzalyova, David Rauber, Andreas Probst, Sandra Nagl, Christoph Römmele, Hon Chi Yip, Ho Shing Louis Lau, Stefan Karl Gölder, Arthur Schmidt, Konstantinos Kouladouros, Mohamed Abdelhafez, Benjamin M Walter, Michael Meinikheim, Philip Wai Yan Chiu, Christoph Palm, Helmut Messmann, Alanna Ebigbo

{"title":"Artificial intelligence improves submucosal vessel detection during third space endoscopy.","authors":"Markus Wolfgang Scheppach, Robert Mendel, Anna Muzalyova, David Rauber, Andreas Probst, Sandra Nagl, Christoph Römmele, Hon Chi Yip, Ho Shing Louis Lau, Stefan Karl Gölder, Arthur Schmidt, Konstantinos Kouladouros, Mohamed Abdelhafez, Benjamin M Walter, Michael Meinikheim, Philip Wai Yan Chiu, Christoph Palm, Helmut Messmann, Alanna Ebigbo","doi":"10.1055/a-2534-1164","DOIUrl":null,"url":null,"abstract":"Background and study aims: While artificial intelligence (AI) shows high potential in decision support for diagnostic gastrointestinal endoscopy, its role in therapeutic endoscopy remains unclear. Third space endoscopic procedures pose the risk of intraprocedural bleeding. Therefore, we aimed to develop an AI algorithm for intraprocedural blood vessel detection.Patients and methods: Using a test dataset with 101 standardized video clips containing 200 predefined submucosal blood vessels, 19 endoscopists were evaluated for the vessel detection rate (VDR) and time (VDT) with and without support of an AI algorithm. Test subjects were grouped according to experience in ESD.Results: With AI support, endoscopists VDR increased from 56.4% [CI 54.1-58.6] to 72.4% [CI 70.3-74.4]. Endoscopists' VDT dropped from 6.7sec [CI 6.2-7.1] to 5.2sec [CI 4.8-5.7]. False positive (FP) readings appeared in 4.5% of frames and were marked significantly shorter than true positives (6.0sec [CI 5.28-6.70] vs. 0.7sec [CI 0.55-0.87]).Conclusions: AI improved the vessel detection rate and time of endoscopists during third space endoscopy. While these data need to be corroborated by clinical trials, AI may prove to be an invaluable tool for the improvement of endoscopic interventions.","PeriodicalId":11516,"journal":{"name":"Endoscopy","volume":" ","pages":""},"PeriodicalIF":11.5000,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Endoscopy","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1055/a-2534-1164","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GASTROENTEROLOGY & HEPATOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background and study aims: While artificial intelligence (AI) shows high potential in decision support for diagnostic gastrointestinal endoscopy, its role in therapeutic endoscopy remains unclear. Third space endoscopic procedures pose the risk of intraprocedural bleeding. Therefore, we aimed to develop an AI algorithm for intraprocedural blood vessel detection.

Patients and methods: Using a test dataset with 101 standardized video clips containing 200 predefined submucosal blood vessels, 19 endoscopists were evaluated for the vessel detection rate (VDR) and time (VDT) with and without support of an AI algorithm. Test subjects were grouped according to experience in ESD.

Results: With AI support, endoscopists VDR increased from 56.4% [CI 54.1-58.6] to 72.4% [CI 70.3-74.4]. Endoscopists' VDT dropped from 6.7sec [CI 6.2-7.1] to 5.2sec [CI 4.8-5.7]. False positive (FP) readings appeared in 4.5% of frames and were marked significantly shorter than true positives (6.0sec [CI 5.28-6.70] vs. 0.7sec [CI 0.55-0.87]).

Conclusions: AI improved the vessel detection rate and time of endoscopists during third space endoscopy. While these data need to be corroborated by clinical trials, AI may prove to be an invaluable tool for the improvement of endoscopic interventions.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Endoscopy 医学-外科

CiteScore

5.80

自引率

11.80%

发文量

1401

审稿时长

2 months

期刊介绍： Endoscopy is a leading journal covering the latest technologies and global advancements in gastrointestinal endoscopy. With guidance from an international editorial board, it delivers high-quality content catering to the needs of endoscopists, surgeons, clinicians, and researchers worldwide. Publishing 12 issues each year, Endoscopy offers top-quality review articles, original contributions, prospective studies, surveys of diagnostic and therapeutic advances, and comprehensive coverage of key national and international meetings. Additionally, articles often include supplementary online video content.