# Gradient-Map-Guided Adaptive Domain Generalization for Cross Modality MRI Segmentation

arXiv: https://arxiv.org/abs/2311.09737 · HTML: https://mlsanity.com/paper/2311.09737/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 16 Nov 2023.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge](https://mlsanity.com/paper/1811.02629/) (2018)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [Demystifying Neural Style Transfer](https://mlsanity.com/paper/1701.01036/) (2017)
- [Multivariate mixture model for myocardium segmentation combining multi-source images](https://mlsanity.com/paper/1612.08820/) (2016)
- [Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains](https://mlsanity.com/paper/2007.02035/) (2020)
- [Causality-inspired Single-source Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2111.12525/) (2021)
- [A review: Deep learning for medical image segmentation using multi-modality fusion](https://mlsanity.com/paper/2004.10664/) (2020)
- [Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentation](https://mlsanity.com/paper/1907.13590/) (2019)
- [Cardiac Segmentation on Late Gadolinium Enhancement MRI: A Benchmark Study from Multi-Sequence Cardiac MR Segmentation Challenge](https://mlsanity.com/paper/2006.12434/) (2020)
- [Deep Symmetric Adaptation Network for Cross-modality Medical Image Segmentation](https://mlsanity.com/paper/2101.06853/) (2021)
- [Improving the generalizability of convolutional neural network-based segmentation on CMR images](https://mlsanity.com/paper/1907.01268/) (2019)
- [Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation](https://mlsanity.com/paper/2303.00914/) (2023)
- [Adversarial Consistency for Single Domain Generalization in Medical Image Segmentation](https://mlsanity.com/paper/2206.13737/) (2022)
- [Single-domain Generalization in Medical Image Segmentation via Test-time Adaptation from Shape Dictionary](https://mlsanity.com/paper/2206.14467/) (2022)
- [MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images](https://mlsanity.com/paper/2211.03062/) (2022)
- [Unsupervised Multi-modal Style Transfer for Cardiac MR Segmentation](https://mlsanity.com/paper/1908.07344/) (2019)
- [Adapt Everywhere: Unsupervised Adaptation of Point-Clouds and Entropy Minimisation for Multi-modal Cardiac Image Segmentation](https://mlsanity.com/paper/2103.08219/) (2021)
- [Automated Multi-sequence Cardiac MRI Segmentation Using Supervised Domain Adaptation](https://mlsanity.com/paper/1908.07726/) (2019)
- [Domain Adaptation Meets Disentangled Representation Learning and Style Transfer](https://mlsanity.com/paper/1712.09025/) (2017)

## Abstract (arXiv)

Cross-modal MRI segmentation is of great value for computer-aided medical diagnosis, enabling flexible data acquisition and model generalization. However, most existing methods have difficulty in handling local variations in domain shift and typically require a significant amount of data for training, which hinders their usage in practice. To address these problems, we propose a novel adaptive domain generalization framework, which integrates a learning-free cross-domain representation based on image gradient maps and a class prior-informed test-time adaptation strategy for mitigating local domain shift. We validate our approach on two multi-modal MRI datasets with six cross-modal segmentation tasks. Across all the task settings, our method consistently outperforms competing approaches and shows a stable performance even with limited training data.