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":null,"pages":null},"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.
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.