Faculty, Staff and Student Publications
Publication Date
6-8-2024
Journal
Communications Medicine
Abstract
BACKGROUND: Radiotherapy is a core treatment modality for oropharyngeal cancer (OPC), where the primary gross tumor volume (GTVp) is manually segmented with high interobserver variability. This calls for reliable and trustworthy automated tools in clinician workflow. Therefore, accurate uncertainty quantification and its downstream utilization is critical.
METHODS: Here we propose uncertainty-aware deep learning for OPC GTVp segmentation, and illustrate the utility of uncertainty in multiple applications. We examine two Bayesian deep learning (BDL) models and eight uncertainty measures, and utilize a large multi-institute dataset of 292 PET/CT scans to systematically analyze our approach.
RESULTS: We show that our uncertainty-based approach accurately predicts the quality of the deep learning segmentation in 86.6% of cases, identifies low performance cases for semi-automated correction, and visualizes regions of the scans where the segmentations likely fail.
CONCLUSIONS: Our BDL-based analysis provides a first-step towards more widespread implementation of uncertainty quantification in OPC GTVp segmentation.
Keywords
Medical imaging, Cancer imaging
DOI
10.1038/s43856-024-00528-5
PMID
38851837
PMCID
PMC11162474
PubMedCentral® Posted Date
6-8-2024
PubMedCentral® Full Text Version
Post-print
Published Open-Access
yes
Included in
Bioinformatics Commons, Biomedical Informatics Commons, Genetic Phenomena Commons, Medical Genetics Commons, Oncology Commons