Uncertainty in multitask learning: joint representations for probabilistic MR-only radiotherapy planning

Autor:	Bragman, Felix J. S., Tanno, Ryutaro, Eaton-Rosen, Zach, Li, Wenqi, Hawkes, David J., Ourselin, Sebastien, Alexander, Daniel C., McClelland, Jamie R., Cardoso, M. Jorge
Rok vydání:	2018
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
DOI:	10.1007/978-3-030-00937-3_1
Popis:	Multi-task neural network architectures provide a mechanism that jointly integrates information from distinct sources. It is ideal in the context of MR-only radiotherapy planning as it can jointly regress a synthetic CT (synCT) scan and segment organs-at-risk (OAR) from MRI. We propose a probabilistic multi-task network that estimates: 1) intrinsic uncertainty through a heteroscedastic noise model for spatially-adaptive task loss weighting and 2) parameter uncertainty through approximate Bayesian inference. This allows sampling of multiple segmentations and synCTs that share their network representation. We test our model on prostate cancer scans and show that it produces more accurate and consistent synCTs with a better estimation in the variance of the errors, state of the art results in OAR segmentation and a methodology for quality assurance in radiotherapy treatment planning. Comment: Early-accept at MICCAI 2018, 8 pages, 4 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1806.06595 Zobrazit plný text záznamu View this record from Arxiv