A deep learning approach to case prioritisation of colorectal biopsies.

IF 3.9 2区 医学 Q2 CELL BIOLOGY Histopathology Pub Date : 2024-10-03 DOI:10.1111/his.15331
Ciara D White, Runjan Chetty, John Weldon, Maria E Morrissey, Rob Sykes, Corina Gîrleanu, Mirko Colleuori, Jenny Fitzgerald, Adam Power, Ajaz Ahmad, Seán Carmody, Pierre Moulin, Donal O'Shea, Muhammad Aslam, Mahomed A Dada, Maurice B Loughrey, Martine C McManus, Klaudia M Nowak, Kristopher McCombe, Sinead Hutton, Máirín Rafferty, Niall Mulligan
{"title":"A deep learning approach to case prioritisation of colorectal biopsies.","authors":"Ciara D White, Runjan Chetty, John Weldon, Maria E Morrissey, Rob Sykes, Corina Gîrleanu, Mirko Colleuori, Jenny Fitzgerald, Adam Power, Ajaz Ahmad, Seán Carmody, Pierre Moulin, Donal O'Shea, Muhammad Aslam, Mahomed A Dada, Maurice B Loughrey, Martine C McManus, Klaudia M Nowak, Kristopher McCombe, Sinead Hutton, Máirín Rafferty, Niall Mulligan","doi":"10.1111/his.15331","DOIUrl":null,"url":null,"abstract":"<p><strong>Aims: </strong>To create and validate a weakly supervised artificial intelligence (AI) model for detection of abnormal colorectal histology, including dysplasia and cancer, and prioritise biopsies according to clinical significance (severity of diagnosis).</p><p><strong>Materials and methods: </strong>Triagnexia Colorectal, a weakly supervised deep learning model, was developed for the classification of colorectal samples from haematoxylin and eosin (H&E)-stained whole slide images. The model was trained on 24 983 digitised images and assessed by multiple pathologists in a simulated digital pathology environment. The AI application was implemented as part of a point and click graphical user interface to streamline decision-making. Pathologists assessed the accuracy of the AI tool, its value, ease of use and integration into the digital pathology workflow.</p><p><strong>Results: </strong>Validation of the model was conducted on two cohorts: the first, on 100 single-slide cases, achieved micro-average model specificity of 0.984, micro-average model sensitivity of 0.949 and micro-average model F1 score of 0.949 across all classes. A secondary multi-institutional validation cohort, of 101 single-slide cases, achieved micro-average model specificity of 0.978, micro-average model sensitivity of 0.931 and micro-average model F1 score of 0.931 across all classes. Pathologists reflected their positive impressions on the overall accuracy of the AI in detecting colorectal pathology abnormalities.</p><p><strong>Conclusions: </strong>We have developed a high-performing colorectal biopsy AI triage model that can be integrated into a routine digital pathology workflow to assist pathologists in prioritising cases and identifying cases with dysplasia/cancer versus non-neoplastic biopsies.</p>","PeriodicalId":13219,"journal":{"name":"Histopathology","volume":" ","pages":""},"PeriodicalIF":3.9000,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Histopathology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/his.15331","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CELL BIOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Aims: To create and validate a weakly supervised artificial intelligence (AI) model for detection of abnormal colorectal histology, including dysplasia and cancer, and prioritise biopsies according to clinical significance (severity of diagnosis).

Materials and methods: Triagnexia Colorectal, a weakly supervised deep learning model, was developed for the classification of colorectal samples from haematoxylin and eosin (H&E)-stained whole slide images. The model was trained on 24 983 digitised images and assessed by multiple pathologists in a simulated digital pathology environment. The AI application was implemented as part of a point and click graphical user interface to streamline decision-making. Pathologists assessed the accuracy of the AI tool, its value, ease of use and integration into the digital pathology workflow.

Results: Validation of the model was conducted on two cohorts: the first, on 100 single-slide cases, achieved micro-average model specificity of 0.984, micro-average model sensitivity of 0.949 and micro-average model F1 score of 0.949 across all classes. A secondary multi-institutional validation cohort, of 101 single-slide cases, achieved micro-average model specificity of 0.978, micro-average model sensitivity of 0.931 and micro-average model F1 score of 0.931 across all classes. Pathologists reflected their positive impressions on the overall accuracy of the AI in detecting colorectal pathology abnormalities.

Conclusions: We have developed a high-performing colorectal biopsy AI triage model that can be integrated into a routine digital pathology workflow to assist pathologists in prioritising cases and identifying cases with dysplasia/cancer versus non-neoplastic biopsies.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
结直肠活检病例优先排序的深度学习方法。
目的:创建并验证一种弱监督人工智能(AI)模型,用于检测异常结直肠组织学,包括发育不良和癌症,并根据临床意义(诊断严重程度)确定活检的优先次序:Triagnexia Colorectal是一种弱监督深度学习模型,用于从血红素和伊红(H&E)染色的整张切片图像中对结肠直肠样本进行分类。该模型在 24 983 张数字化图像上进行了训练,并由多名病理学家在模拟数字病理环境中进行了评估。人工智能应用是作为点选式图形用户界面的一部分实施的,以简化决策过程。病理学家对人工智能工具的准确性、价值、易用性以及与数字病理工作流程的整合进行了评估:在两个队列中对模型进行了验证:第一个队列对 100 个单张病例进行了验证,在所有类别中,模型特异性的微观平均值为 0.984,模型灵敏度的微观平均值为 0.949,模型 F1 的微观平均值为 0.949。由 101 个单滑动病例组成的二级多机构验证队列的微观平均模型特异性为 0.978,微观平均模型灵敏度为 0.931,所有类别的微观平均模型 F1 得分为 0.931。病理学家对人工智能检测结直肠病理异常的整体准确性给予了积极评价:我们开发了一种高效的结直肠活检人工智能分检模型,可将其整合到常规数字病理工作流程中,协助病理学家确定病例的优先次序,并识别发育不良/癌症病例与非肿瘤性活检病例。
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
Histopathology
Histopathology 医学-病理学
CiteScore
10.20
自引率
4.70%
发文量
239
审稿时长
1 months
期刊介绍: Histopathology is an international journal intended to be of practical value to surgical and diagnostic histopathologists, and to investigators of human disease who employ histopathological methods. Our primary purpose is to publish advances in pathology, in particular those applicable to clinical practice and contributing to the better understanding of human disease.
期刊最新文献
Evolution of morphological changes in donor livers undergoing normothermic machine perfusion. Recurrent GRHL fusions in a subset of sebaceoma: microscopic and molecular characterisation of eight cases. Sinonasal adenosquamous carcinomas arising in seromucinous hamartoma or respiratory epithelial adenomatoid hamartoma with atypical features: Report of five detailed clinicopathological and molecular characterisation of rare entity. Can patient ancestry influence molecular classifications in myeloid neoplasms? Dedicated diagnostic approaches for mature B-cell non-Hodgkin lymphomas occurring in children, adolescents, and young adults.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1