用少量标注数据实现高光谱脑图像血管分割，突破标签稀缺瓶颈。
Addressing Annotation Scarcity in Hyperspectral Brain Image Segmentation with Unsupervised Domain Adaptation
- 基于少量专家标注+无标签数据，设计无监督域适应方法
- 在标签稀缺条件下显著优于现有最佳模型
- 适合缺乏标注的生物医学图像分割任务研究者
本文提出一种新型深度学习框架，用于高光谱脑图像中的脑血管分割。针对传统监督学习因标注数据严重稀缺而受限的问题，本方法采用新颖的无监督域适应策略，仅需少量专家标注的真实标签与大量无标签数据即可训练。定量与定性评估表明，该方法显著优于现有最先进模型，验证了域适应技术在标注稀缺的生物医学图像分割任务中的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。