Multi-task weak supervision enables anatomically-resolved abnormality detection in whole-body FDG-PET/CT

Sabri Eyuboglu; Geoffrey Angus; Bhavik N. Patel; Anuj Pareek; Guido Davidzon; Jin Long; Jared Dunnmon; Matthew P. Lungren

doi:10.1038/s41467-021-22018-1

Nature Communications (Mar 2021)

Multi-task weak supervision enables anatomically-resolved abnormality detection in whole-body FDG-PET/CT

Sabri Eyuboglu,
Geoffrey Angus,
Bhavik N. Patel,
Anuj Pareek,
Guido Davidzon,
Jin Long,
Jared Dunnmon,
Matthew P. Lungren

Affiliations

Sabri Eyuboglu: Department of Computer Science, Stanford University
Geoffrey Angus: Department of Computer Science, Stanford University
Bhavik N. Patel: Department of Radiology, Stanford University
Anuj Pareek: Department of Radiology, Stanford University
Guido Davidzon: Department of Radiology, Stanford University
Jin Long: Center for Artificial Intelligence in Medicine and Imaging, Stanford University
Jared Dunnmon: Department of Computer Science, Stanford University
Matthew P. Lungren: Department of Radiology, Stanford University

DOI: https://doi.org/10.1038/s41467-021-22018-1
Journal volume & issue: Vol. 12, no. 1
pp. 1 – 15

Abstract

Read online

Computational decision support systems could provide clinical value in whole-body FDG PET/CT workflows, but labeled data is scarce and PET/CT imaging exams are cumbersome. Here, the authors describe a weak supervision framework that extracts regional abnormality labels from free-text radiology reports.

Published in Nature Communications

ISSN: 2041-1723 (Online)
Publisher: Nature Portfolio
Country of publisher: United Kingdom
LCC subjects: Science
Website: https://www.nature.com/ncomms/

About the journal