Show simple item record

Files in this item


Item metadata

dc.contributor.authorNearchou, Ines P.
dc.contributor.authorUeno, Hideki
dc.contributor.authorKajiwara, Yoshiki
dc.contributor.authorLillard, Kate
dc.contributor.authorMochizuki, Satsuki
dc.contributor.authorTakeuchi, Kengo
dc.contributor.authorHarrison, David J.
dc.contributor.authorCaie, Peter D.
dc.identifier.citationNearchou , I P , Ueno , H , Kajiwara , Y , Lillard , K , Mochizuki , S , Takeuchi , K , Harrison , D J & Caie , P D 2021 , ' Automated detection and classification of desmoplastic reaction at the colorectal tumour front using deep learning ' , Cancers , vol. 13 , no. 7 , 1615 .
dc.identifier.otherPURE: 273498525
dc.identifier.otherPURE UUID: 2a65d65a-e4b2-47d0-9d71-afaaa868b5b4
dc.identifier.otherORCID: /0000-0001-9041-9988/work/91685660
dc.identifier.otherORCID: /0000-0002-0031-9850/work/91685819
dc.identifier.otherORCID: /0000-0002-1863-5413/work/91685912
dc.identifier.otherScopus: 85103314932
dc.identifier.otherWOS: 000638359100001
dc.descriptionFunding: This study was funded by Medical Research Scotland, the Japan Society for the Promotion of Science, the British Council and Indica Labs, Inc. who also provided in kind resource.en
dc.description.abstractThe categorisation of desmoplastic reaction (DR) present at the colorectal cancer (CRC) invasive front into mature, intermediate or immature type has been previously shown to have high prognostic significance. However, the lack of an objective and reproducible assessment methodology for the assessment of DR has been a major hurdle to its clinical translation. In this study, a deep learning algorithm was trained to automatically classify immature DR on haematoxylin and eosin digitised slides of stage II and III CRC cases (n = 41). When assessing the classifier’s performance on a test set of patient samples (n = 40), a Dice score of 0.87 for the segmentation of myxoid stroma was reported. The classifier was then applied to the full cohort of 528 stage II and III CRC cases, which was then divided into a training (n = 396) and a test set (n = 132). Automatically classed DR was shown to have superior prognostic significance over the manually classed DR in both the training and test cohorts. The findings demonstrated that deep learning algorithms could be applied to assist pathologists in the detection and classification of DR in CRC in an objective, standardised and reproducible manner.
dc.rightsCopyright: © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://
dc.subjectDeep learningen
dc.subjectImage analysisen
dc.subjectDesmoplastic reactionen
dc.subjectColorectal canceren
dc.subjectDigital pathologyen
dc.subjectQA75 Electronic computers. Computer scienceen
dc.subjectRC0254 Neoplasms. Tumors. Oncology (including Cancer)en
dc.titleAutomated detection and classification of desmoplastic reaction at the colorectal tumour front using deep learningen
dc.typeJournal articleen
dc.description.versionPublisher PDFen
dc.contributor.institutionUniversity of St Andrews.Cellular Medicine Divisionen
dc.contributor.institutionUniversity of St Andrews.Sir James Mackenzie Institute for Early Diagnosisen
dc.contributor.institutionUniversity of St Andrews.School of Medicineen
dc.contributor.institutionUniversity of St Andrews.Centre for Biophotonicsen
dc.description.statusPeer revieweden

This item appears in the following Collection(s)

Show simple item record