Unsupervised Domain Adaptation for Brain Vessel Segmentation through Transwarp Contrastive Learning

Fengming Lin, Yan Xia, Michael MacRaild, Yash Deo, Haoran Dou +4 more
2/23/2024
cs.CVcs.LG

No official code found. Best implementation: fmlinks/domain (7 stars, last commit 2024-09-15).

Abstract

Unsupervised domain adaptation (UDA) aims to align the labelled source distribution with the unlabelled target distribution to obtain domain-invariant predictive models. Since cross-modality medical data exhibit significant intra and inter-domain shifts and most are unlabelled, UDA is more important while challenging in medical image analysis. This paper proposes a simple yet potent contrastive learning framework for UDA to narrow the inter-domain gap between labelled source and unlabelled target distribution. Our method is validated on cerebral vessel datasets. Experimental results show that our approach can learn latent features from labelled 3DRA modality data and improve vessel segmentation performance in unlabelled MRA modality data.

View on arXivView PDF

Code Implementations(1)

fmlinks/domainCommunity100%
70PythonFeb 18, 20242 years ago

Similar Papers

RemInD: Remembering Anatomical Variations for Interpretable Domain Adaptive Medical Image Segmentation

85% match2025

Joint semi-supervised and contrastive learning enables domain generalization and multi-domain segmentation

85% match2024

HyDA: Hypernetworks for Test Time Domain Adaptation in Medical Imaging Analysis

85% match2025

DRL-STNet: Unsupervised Domain Adaptation for Cross-modality Medical Image Segmentation via Disentangled Representation Learning

85% match2024

Cross-Modal Domain Adaptation in Brain Disease Diagnosis: Maximum Mean Discrepancy-based Convolutional Neural Networks

84% match2024

M3DA: Benchmark for Unsupervised Domain Adaptation in 3D Medical Image Segmentation

84% match2 repos82025

Cite this paper

@article{lin2024unsupervised,
  title  = {Unsupervised Domain Adaptation for Brain Vessel Segmentation through Transwarp Contrastive Learning},
  author = {Fengming Lin and Yan Xia and Michael MacRaild and Yash Deo and Haoran Dou and Qiongyao Liu and Kun Wu and Nishant Ravikumar and Alejandro F. Frangi},
  year   = {2024},
  eprint = {2402.15237},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.15237v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.15237.svg)](https://codeofpaper.com/paper/2402.15237)

Discussion