Home | Publications | MRB+25

Addressing Annotation Scarcity in Hyperspectral Brain Image Segmentation With Unsupervised Domain Adaptation

MCML Authors

Abstract

This work presents a novel deep learning framework for segmenting cerebral vasculature in hyperspectral brain images. We address the critical challenge of severe label scarcity, which impedes conventional supervised training. Our approach utilizes a novel unsupervised domain adaptation methodology, completely avoiding the need for target-domain labels. The method segments the brain vasculature of the target domain using only labelled retinal images from a different dataset. Quantitative and qualitative evaluations confirm that our method significantly outperforms existing state-of-the-art approaches, demonstrating the efficacy of domain adaptation for label-scarce biomedical imaging tasks.

inproceedings MRB+25

SIPAIM 2025

21st International Symposium on Biomedical Image Processing and Analysis. Pasto, Colombia, Nov 19-21, 2025.

Authors

T. Mach • D. Rückert • A. Berger • L. Lux • I. Ezhov

Links

DOI

Research Area

 C1 | Medicine

BibTeXKey: MRB+25

#p-rueckert
Back to Top