Investigation of Recognition Areas by Explainable AI for Colonoscopy Images of Irritable Bowel Syndrome.

IF 3 3区医学 Q2 GASTROENTEROLOGY & HEPATOLOGY

Digestion Pub Date : 2025-04-29 DOI:10.1159/000546183

Hiroshi Mihara, Shun Kuraishi, Haruka Fujinami, Takayuki Ando, Ichiro Yasuda

{"title":"Investigation of Recognition Areas by Explainable AI for Colonoscopy Images of Irritable Bowel Syndrome.","authors":"Hiroshi Mihara, Shun Kuraishi, Haruka Fujinami, Takayuki Ando, Ichiro Yasuda","doi":"10.1159/000546183","DOIUrl":null,"url":null,"abstract":"Introduction and aim: Irritable Bowel Syndrome (IBS) is a condition in which gastroenterological endoscopists cannot detect anomalies using colonoscopy, yet an artificial intelligence (AI) developed for IBS colonoscopy images has been able to distinguish between IBS and healthy individuals with high accuracy. However, it was unclear in which areas the AI identified as abnormal. The aim of this study was to elucidate how AI identifies regions typical of IBS by constructing an additional Explainable AI (XAI).Methods: Colonoscopy images of healthy individuals, patients with constipation-predominant IBS, and patients with diarrhea-predominant IBS, which are available in a repository (https://doi.org/10.5061/dryad.9s4mw6mkp), were used. After setting up a Python environment on a local PC, the XAI models for the three groups were developed. Images not used in the AI construction were then evaluated using XAI. XAI-generated images were independently assessed by two evaluators, HM and KS, to record and reconcile the characteristic differences among the three groups.Results: Images correctly identified as those of healthy individuals by XAI were evaluated as characteristics over the entire image. By contrast, for IBS, only parts of the images were evaluated as characteristic regions. For diarrhea-predominant IBS, regions characterized by clear vascular boundaries, homogeneity or erythematous tones, or narrow and somewhat dark-appearing sections of the intestinal tract were identified. For constipation-predominant IBS, regions characterized by unclear vascular boundaries, faded tones, or dark sections where the end was not visible were identified.Conclusion: An XAI for IBS was collaboratively developed by endoscopists and clinical engineers, enabling the visualization of regions characteristic of IBS and healthy individuals. The real-time display of XAI is expected to further advance the elucidation of IBS pathophysiology.","PeriodicalId":11315,"journal":{"name":"Digestion","volume":" ","pages":"1-11"},"PeriodicalIF":3.0000,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Digestion","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1159/000546183","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GASTROENTEROLOGY & HEPATOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Introduction and aim: Irritable Bowel Syndrome (IBS) is a condition in which gastroenterological endoscopists cannot detect anomalies using colonoscopy, yet an artificial intelligence (AI) developed for IBS colonoscopy images has been able to distinguish between IBS and healthy individuals with high accuracy. However, it was unclear in which areas the AI identified as abnormal. The aim of this study was to elucidate how AI identifies regions typical of IBS by constructing an additional Explainable AI (XAI).

Methods: Colonoscopy images of healthy individuals, patients with constipation-predominant IBS, and patients with diarrhea-predominant IBS, which are available in a repository (https://doi.org/10.5061/dryad.9s4mw6mkp), were used. After setting up a Python environment on a local PC, the XAI models for the three groups were developed. Images not used in the AI construction were then evaluated using XAI. XAI-generated images were independently assessed by two evaluators, HM and KS, to record and reconcile the characteristic differences among the three groups.

Results: Images correctly identified as those of healthy individuals by XAI were evaluated as characteristics over the entire image. By contrast, for IBS, only parts of the images were evaluated as characteristic regions. For diarrhea-predominant IBS, regions characterized by clear vascular boundaries, homogeneity or erythematous tones, or narrow and somewhat dark-appearing sections of the intestinal tract were identified. For constipation-predominant IBS, regions characterized by unclear vascular boundaries, faded tones, or dark sections where the end was not visible were identified.

Conclusion: An XAI for IBS was collaboratively developed by endoscopists and clinical engineers, enabling the visualization of regions characteristic of IBS and healthy individuals. The real-time display of XAI is expected to further advance the elucidation of IBS pathophysiology.

查看原文本刊更多论文

可解释AI对肠易激综合征结肠镜图像识别区域的研究。

简介和目的：肠易激综合征（IBS）是一种胃肠内窥镜医生无法使用结肠镜检查发现异常的疾病，然而为IBS结肠镜检查图像开发的人工智能（AI）已经能够以高精度区分IBS和健康个体。然而，目前还不清楚人工智能在哪些领域发现了异常。本研究的目的是通过构建一个额外的可解释AI （XAI）来阐明AI如何识别IBS的典型区域。方法：使用健康个体、便秘为主的肠易激综合征患者和腹泻为主的肠易激综合征患者的结肠镜检查图像，这些图像可在存储库（https://doi.org/10.5061/dryad.9s4mw6mkp）中获得。在本地PC上设置Python环境后，开发了三个组的XAI模型。然后使用XAI对AI构建中未使用的图像进行评估。由两位评估者HM和KS独立评估xai生成的图像，以记录和调和三组之间的特征差异。结果：通过XAI正确识别为健康个体的图像作为整个图像的特征进行评估。相比之下，对于IBS，只有部分图像被评估为特征区域。对于以腹泻为主的肠易激综合征，确定了以血管边界清晰、均匀性或红斑色调或肠道狭窄和略显黑暗部分为特征的区域。对于便秘为主的肠易激综合征，以血管边界不清、色调褪色或末端不可见的深色部分为特征的区域被确定。结论：内镜医师和临床工学技士合作开发了IBS的XAI，使IBS和健康个体的特征区域可视化。XAI的实时显示有望进一步推进IBS病理生理的阐明。

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

Digestion 医学-胃肠肝病学

CiteScore

7.90

自引率

0.00%

发文量

审稿时长

6-12 weeks

期刊介绍： ''Digestion'' concentrates on clinical research reports: in addition to editorials and reviews, the journal features sections on Stomach/Esophagus, Bowel, Neuro-Gastroenterology, Liver/Bile, Pancreas, Metabolism/Nutrition and Gastrointestinal Oncology. Papers cover physiology in humans, metabolic studies and clinical work on the etiology, diagnosis, and therapy of human diseases. It is thus especially cut out for gastroenterologists employed in hospitals and outpatient units. Moreover, the journal''s coverage of studies on the metabolism and effects of therapeutic drugs carries considerable value for clinicians and investigators beyond the immediate field of gastroenterology.