# Harnessing Uncertainty in Domain Adaptation for MRI Prostate Lesion Segmentation

arXiv: https://arxiv.org/abs/2010.07411 · HTML: https://mlsanity.com/paper/2010.07411/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [End-to-end Prostate Cancer Detection in bpMRI via 3D CNNs: Effects of Attention Mechanisms, Clinical Priori and Decoupled False Positive Reduction](https://mlsanity.com/paper/2101.03244/) (2021)
- [Multimodal Machine Learning in Image-Based and Clinical Biomedicine: Survey and Prospects](https://mlsanity.com/paper/2311.02332/) (2023)
- [ProstAttention-Net: A deep attention model for prostate cancer segmentation by aggressiveness in MRI scans](https://mlsanity.com/paper/2211.13238/) (2022)
- [Combiner and HyperCombiner Networks: Rules to Combine Multimodality MR Images for Prostate Cancer Localisation](https://mlsanity.com/paper/2307.08279/) (2023)
- [The impact of using voxel-level segmentation metrics on evaluating multifocal prostate cancer localisation](https://mlsanity.com/paper/2203.16415/) (2022)
- [Unsupervised Domain Adaptation with Semantic Consistency across Heterogeneous Modalities for MRI Prostate Lesion Segmentation](https://mlsanity.com/paper/2109.09736/) (2021)
- [Beyond Deterministic Translation for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2202.07778/) (2022)
- [Semantic-guided Disentangled Representation for Unsupervised Cross-modality Medical Image Segmentation](https://mlsanity.com/paper/2203.14025/) (2022)
- [BehaviorSFT: Behavioral Token Conditioning for Clinical Agents Across the Proactivity Spectrum](https://mlsanity.com/paper/2505.21757/) (2025)

## Abstract (arXiv)

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.