Multi-task Bayesian model combining FDG-PET/CT imaging and clinical data for interpretable high-grade prostate cancer prognosis

Multi-task Bayesian model combining FDG-PET/CT imaging and clinical data for interpretable high-grade prostate cancer prognosis

Abstract We propose a fully automatic multi-task Bayesian model, named Bayesian Sequential Network (BSN), for predicting high-grade (Gleason  $$\ge$$ ≥  8) prostate cancer (PCa) prognosis using pre-prostatectomy FDG-PET/CT images and clinical data. BSN performs one classification task and five survi...

Full description

Saved in:
Bibliographic Details
Main Authors: Maxence Larose, Louis Archambault, Nawar Touma, Raphaël Brodeur, Félix Desroches, Nicolas Raymond, Daphnée Bédard-Tremblay, Danahé LeBlanc, Fatemeh Rasekh, Hélène Hovington, Bertrand Neveu, Martin Vallières, Frédéric Pouliot
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Prostate cancer
Prognosis
Multi-task
Multi-modal
FDG-PET/CT
Segmentation
Online Access:https://doi.org/10.1038/s41598-024-77498-0
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://doi.org/10.1038/s41598-024-77498-0

Similar Items