Show simple item record

dc.contributor.authorGehrung, Marcel
dc.contributor.authorCrispin-Ortuzar, Mireia
dc.contributor.authorBerman, Adam G
dc.contributor.authorO'Donovan, Maria
dc.contributor.authorFitzgerald, Rebecca
dc.contributor.authorMarkowetz, Florian
dc.date.accessioned2022-01-28T00:30:42Z
dc.date.available2022-01-28T00:30:42Z
dc.date.issued2021-05
dc.identifier.issn1078-8956
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/332971
dc.description.abstractDeep learning methods have been shown to achieve excellent performance on diagnostic tasks, but how to optimally combine them with expert knowledge and existing clinical decision pathways is still an open challenge. This question is particularly important for the early detection of cancer, where high-volume workflows may benefit from (semi-)automated analysis. Here we present a deep learning framework to analyze samples of the Cytosponge-TFF3 test, a minimally invasive alternative to endoscopy, for detecting Barrett's esophagus, which is the main precursor of esophageal adenocarcinoma. We trained and independently validated the framework on data from two clinical trials, analyzing a combined total of 4,662 pathology slides from 2,331 patients. Our approach exploits decision patterns of gastrointestinal pathologists to define eight triage classes of varying priority for manual expert review. By substituting manual review with automated review in low-priority classes, we can reduce pathologist workload by 57% while matching the diagnostic performance of experienced pathologists.
dc.format.mediumPrint-Electronic
dc.publisherSpringer Science and Business Media LLC
dc.rightsAll Rights Reserved
dc.rights.urihttp://www.rioxx.net/licenses/all-rights-reserved
dc.subjectAdenocarcinoma
dc.subjectBarrett Esophagus
dc.subjectCase-Control Studies
dc.subjectDecision Support Systems, Clinical
dc.subjectDeep Learning
dc.subjectEarly Detection of Cancer
dc.subjectEsophageal Neoplasms
dc.subjectEsophagus
dc.subjectHumans
dc.subjectTriage
dc.titleTriage-driven diagnosis of Barrett's esophagus for early detection of esophageal adenocarcinoma using deep learning.
dc.typeArticle
dc.publisher.departmentCancer Research Uk Cambridge Institute
dc.publisher.departmentDepartment of Oncology
dc.date.updated2022-01-26T18:09:27Z
prism.endingPage841
prism.issueIdentifier5
prism.publicationDate2021
prism.publicationNameNat Med
prism.startingPage833
prism.volume27
dc.identifier.doi10.17863/CAM.80395
dcterms.dateAccepted2021-02-17
rioxxterms.versionofrecord10.1038/s41591-021-01287-9
rioxxterms.versionAM
dc.contributor.orcidGehrung, Marcel [0000-0001-6915-9552]
dc.contributor.orcidCrispin-Ortuzar, Mireia [0000-0002-4351-3709]
dc.contributor.orcidFitzgerald, Rebecca [0000-0002-3434-3568]
dc.contributor.orcidMarkowetz, Florian [0000-0002-2784-5308]
dc.identifier.eissn1546-170X
rioxxterms.typeJournal Article/Review
pubs.funder-project-idCancer Research UK (C14478/A12088)
pubs.funder-project-idMRC (unknown)
pubs.funder-project-idNational Institute for Health Research (NIHRDH-IS-BRC-1215-20014)
pubs.funder-project-idMRC (MR/W014122/1)
pubs.funder-project-idMedical Research Council (MC_UU_12022/2)
cam.issuedOnline2021-04-15
cam.orpheus.success2022-01-27 - Embargo set during processing via Fast-track
cam.depositDate2022-01-26
pubs.licence-identifierapollo-deposit-licence-2-1
pubs.licence-display-nameApollo Repository Deposit Licence Agreement
rioxxterms.freetoread.startdate2021-10-15


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record