Linked Color Imaging with Artificial Intelligence Improves the Detection of Early Gastric Cancer.

IF 4.6 Q2 MATERIALS SCIENCE, BIOMATERIALS ACS Applied Bio Materials Pub Date : 2024-08-05 DOI:10.1159/000540728

Youshen Zhao, Osamu Dohi, Tsugitaka Ishida, Naohisa Yoshida, Tomoko Ochiai, Hiroki Mukai, Mayuko Seya, Katsuma Yamauchi, Hajime Miyazaki, Hayato Fukui, Takeshi Yasuda, Naoto Iwai, Ken Inoue, Yoshito Itoh, Xinkai Liu, Ruiyao Zhang, Xin Zhu

{"title":"Linked Color Imaging with Artificial Intelligence Improves the Detection of Early Gastric Cancer.","authors":"Youshen Zhao, Osamu Dohi, Tsugitaka Ishida, Naohisa Yoshida, Tomoko Ochiai, Hiroki Mukai, Mayuko Seya, Katsuma Yamauchi, Hajime Miyazaki, Hayato Fukui, Takeshi Yasuda, Naoto Iwai, Ken Inoue, Yoshito Itoh, Xinkai Liu, Ruiyao Zhang, Xin Zhu","doi":"10.1159/000540728","DOIUrl":null,"url":null,"abstract":"Introduction: Esophagogastroduodenoscopy is the most important tool to detect gastric cancer (GC). In this study, we developed a computer-aided detection (CADe) system to detect GC with white light imaging (WLI) and linked color imaging (LCI) modes and aimed to compare the performance of CADe with that of endoscopists.Methods: The system was developed based on the deep learning framework from 9,021 images in 385 patients between 2017 and 2020. A total of 116 LCI and WLI videos from 110 patients between 2017 and 2023 were used to evaluate per-case sensitivity and per-frame specificity.Results: The per-case sensitivity and per-frame specificity of CADe with a confidence level of 0.5 in detecting GC were 78.6% and 93.4% for WLI and 94.0% and 93.3% for LCI, respectively (p < 0.001). The per-case sensitivities of nonexpert endoscopists for WLI and LCI were 45.8% and 80.4%, whereas those of expert endoscopists were 66.7% and 90.6%, respectively. Regarding detectability between CADe and endoscopists, the per-case sensitivities for WLI and LCI were 78.6% and 94.0% in CADe, respectively, which were significantly higher than those for LCI in experts (90.6%, p = 0.004) and those for WLI and LCI in nonexperts (45.8% and 80.4%, respectively, p < 0.001); however, no significant difference for WLI was observed between CADe and experts (p = 0.134).Conclusions: Our CADe system showed significantly better sensitivity in detecting GC when used in LCI compared with WLI mode. Moreover, the sensitivity of CADe using LCI is significantly higher than those of expert endoscopists using LCI to detect GC.","PeriodicalId":2,"journal":{"name":"ACS Applied Bio Materials","volume":null,"pages":null},"PeriodicalIF":4.6000,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Applied Bio Materials","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1159/000540728","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, BIOMATERIALS","Score":null,"Total":0}

引用次数: 0

Abstract

Introduction: Esophagogastroduodenoscopy is the most important tool to detect gastric cancer (GC). In this study, we developed a computer-aided detection (CADe) system to detect GC with white light imaging (WLI) and linked color imaging (LCI) modes and aimed to compare the performance of CADe with that of endoscopists.

Methods: The system was developed based on the deep learning framework from 9,021 images in 385 patients between 2017 and 2020. A total of 116 LCI and WLI videos from 110 patients between 2017 and 2023 were used to evaluate per-case sensitivity and per-frame specificity.

Results: The per-case sensitivity and per-frame specificity of CADe with a confidence level of 0.5 in detecting GC were 78.6% and 93.4% for WLI and 94.0% and 93.3% for LCI, respectively (p < 0.001). The per-case sensitivities of nonexpert endoscopists for WLI and LCI were 45.8% and 80.4%, whereas those of expert endoscopists were 66.7% and 90.6%, respectively. Regarding detectability between CADe and endoscopists, the per-case sensitivities for WLI and LCI were 78.6% and 94.0% in CADe, respectively, which were significantly higher than those for LCI in experts (90.6%, p = 0.004) and those for WLI and LCI in nonexperts (45.8% and 80.4%, respectively, p < 0.001); however, no significant difference for WLI was observed between CADe and experts (p = 0.134).

Conclusions: Our CADe system showed significantly better sensitivity in detecting GC when used in LCI compared with WLI mode. Moreover, the sensitivity of CADe using LCI is significantly higher than those of expert endoscopists using LCI to detect GC.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

人工智能关联彩色成像提高了早期胃癌的检测率。

简介食管胃十二指肠镜检查（EGD）是检测胃癌（GC）最重要的工具。在这项研究中，我们开发了一种计算机辅助系统（CADe），利用白光成像（WLI）和联动彩色成像（LCI）模式检测胃癌（GC），并将 CADe 的性能与内镜医师的性能进行比较：该系统是基于深度学习框架从2017年至2020年间385名患者的9021张图像中开发出来的。2017年至2023年间，共有110名患者的116个LCI和WLI视频被用于评估每例灵敏度和每帧特异性：在置信度为 0.5 的情况下，CADe 检测 GC 的每例灵敏度和每帧特异性分别为：WLI 78.6% 和 93.4%，LCI 94.0% 和 93.3%（P <0.001）。非专业内镜医师对WLI和LCI的每例敏感度分别为45.8%和80.4%，而专业内镜医师的敏感度分别为66.7%和90.6%。关于CADe与内镜医师之间的可检测性，CADe对WLI和LCI的每例敏感度分别为78.6%和94.0%，显著高于内镜医师对LCI的敏感度（90.6%，P = 0.004）和非内镜医师对WLI和LCI的敏感度（分别为45.8%和80.4%，P <0.0001）；然而，CADe与内镜医师对WLI的敏感度无显著差异（P = 0.134）：我们的 CADe 系统在 LCI 模式下检测 GC 的灵敏度明显高于 WLI 模式。此外，使用 LCI 的 CADe 的灵敏度明显高于使用 LCI 的内镜专家。

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分钟内获得全文去求助

来源期刊