{"ID":2879087,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.16934","arxiv_id":"2508.16934","title":"Addressing Annotation Scarcity in Hyperspectral Brain Image Segmentation with Unsupervised Domain Adaptation","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, using a small, expert-annotated ground truth alongside unlabeled data. 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.","short_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, using a small, exper...","url_abs":"https://arxiv.org/abs/2508.16934","url_pdf":"https://arxiv.org/pdf/2508.16934v1","authors":"[\"Tim Mach\",\"Daniel Rueckert\",\"Alex Berger\",\"Laurin Lux\",\"Ivan Ezhov\"]","published":"2025-08-23T07:55:42Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"q-bio.QM\"]","methods":"[]","has_code":false}