Chiou, E;
Giganti, F;
Punwani, S;
Kokkinos, I;
Panagiotaki, E;
(2020)
Harnessing uncertainty in domain adaptation for mri prostate lesion segmentation.
In: Martel, A.L and Abolmaesumi, P and Stoyanov, D and Mateus, D and Zuluaga, M.A and Zhou, S.K and Racoceanu, D and Joskowicz, L, (eds.)
Medical Image Computing and Computer Assisted Intervention – MICCAI 2020.
(pp. pp. 510-520).
Springer: Lima, Peru.
Preview |
Text
paper2780.pdf - Published Version Download (668kB) | Preview |
Abstract
The need for training data can impede the adoption of novel imaging modalities for learning-based medical image analysis. Domain adaptation methods partially mitigate this problem by translating training data from a related source domain to a novel target domain, but typically assume that a one-to-one translation is possible. Our work addresses the challenge of adapting to a more informative target domain where multiple target samples can emerge from a single source sample. In particular we consider translating from mp-MRI to VERDICT, a richer MRI modality involving an optimized acquisition protocol for cancer characterization. We explicitly account for the inherent uncertainty of this mapping and exploit it to generate multiple outputs conditioned on a single input. Our results show that this allows us to extract systematically better image representations for the target domain, when used in tandem with both simple, CycleGAN-based baselines, as well as more powerful approaches that integrate discriminative segmentation losses and/or residual adapters. When compared to its deterministic counterparts, our approach yields substantial improvements across a broad range of dataset sizes, increasingly strong baselines, and evaluation measures.
Archive Staff Only
 |
View Item |
