Enabling large-scale screening of Barrett’s esophagus using weakly supervised deep learning in histopathology

Kenza Bouzid, Harshita Sharma, Sarah Killcoyne, Daniel C. Castro, Anton Schwaighofer, Max Ilse, Valentina Salvatelli, Ozan Oktay, Sumanth Murthy, Lucas Bordeaux, Luiza Moore, Maria O’Donovan, Anja Thieme, Aditya Nori, Marcel Gehrung () and Javier Alvarez-Valle ()
Additional contact information
Kenza Bouzid: Microsoft Health Futures
Harshita Sharma: Microsoft Health Futures
Sarah Killcoyne: Cyted Ltd
Daniel C. Castro: Microsoft Health Futures
Anton Schwaighofer: Microsoft Health Futures
Max Ilse: Microsoft Health Futures
Valentina Salvatelli: Microsoft Health Futures
Ozan Oktay: Microsoft Health Futures
Sumanth Murthy: Cyted Ltd
Lucas Bordeaux: Cyted Ltd
Luiza Moore: Cambridge University NHS Foundation Trust
Maria O’Donovan: Cyted Ltd
Anja Thieme: Microsoft Health Futures
Aditya Nori: Microsoft Health Futures
Marcel Gehrung: Cyted Ltd
Javier Alvarez-Valle: Microsoft Health Futures

Nature Communications, 2024, vol. 15, issue 1, 1-15

Abstract: Abstract Timely detection of Barrett’s esophagus, the pre-malignant condition of esophageal adenocarcinoma, can improve patient survival rates. The Cytosponge-TFF3 test, a non-endoscopic minimally invasive procedure, has been used for diagnosing intestinal metaplasia in Barrett’s. However, it depends on pathologist’s assessment of two slides stained with H&E and the immunohistochemical biomarker TFF3. This resource-intensive clinical workflow limits large-scale screening in the at-risk population. To improve screening capacity, we propose a deep learning approach for detecting Barrett’s from routinely stained H&E slides. The approach solely relies on diagnostic labels, eliminating the need for expensive localized expert annotations. We train and independently validate our approach on two clinical trial datasets, totaling 1866 patients. We achieve 91.4% and 87.3% AUROCs on discovery and external test datasets for the H&E model, comparable to the TFF3 model. Our proposed semi-automated clinical workflow can reduce pathologists’ workload to 48% without sacrificing diagnostic performance, enabling pathologists to prioritize high risk cases.

Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-46174-2 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-46174-2

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-024-46174-2

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().