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 and Matthew P. Lungren
Additional contact information
Sabri Eyuboglu: Stanford University
Geoffrey Angus: Stanford University
Bhavik N. Patel: Stanford University
Anuj Pareek: Stanford University
Guido Davidzon: Stanford University
Jin Long: Stanford University
Jared Dunnmon: Stanford University
Matthew P. Lungren: Stanford University

Nature Communications, 2021, vol. 12, issue 1, 1-15

Abstract: Abstract Computational decision support systems could provide clinical value in whole-body FDG-PET/CT workflows. However, limited availability of labeled data combined with the large size of PET/CT imaging exams make it challenging to apply existing supervised machine learning systems. Leveraging recent advancements in natural language processing, we describe a weak supervision framework that extracts imperfect, yet highly granular, regional abnormality labels from free-text radiology reports. Our framework automatically labels each region in a custom ontology of anatomical regions, providing a structured profile of the pathologies in each imaging exam. Using these generated labels, we then train an attention-based, multi-task CNN architecture to detect and estimate the location of abnormalities in whole-body scans. We demonstrate empirically that our multi-task representation is critical for strong performance on rare abnormalities with limited training data. The representation also contributes to more accurate mortality prediction from imaging data, suggesting the potential utility of our framework beyond abnormality detection and location estimation.

Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-021-22018-1 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:12:y:2021:i:1:d:10.1038_s41467-021-22018-1

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

DOI: 10.1038/s41467-021-22018-1

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 ().