Accurate segmentation of brain vessels is crucial for cerebrovascular disease
diagnosis and treatment. However, existing methods face challenges in capturing
small vessels and handling datasets that are partially or ambiguously
annotated. In this paper, we propose an adaptive semi-supervised approach to
address these challenges. Our approach incorporates innovative techniques
including progressive semi-supervised learning, adaptative training strategy,
and boundary enhancement. Experimental results on 3DRA datasets demonstrate the
superiority of our method in terms of mesh-based segmentation metrics. By
leveraging the partially and ambiguously labeled data, which only annotates the
main vessels, our method achieves impressive segmentation performance on
mislabeled fine vessels, showcasing its potential for clinical applications.

准确分割脑血管对于脑血管疾病的诊断和治疗至关重要。本文提出了一种自适应半监督方法，通过创新的技术，包括渐进式半监督学习、自适应训练策略和边界增强，解决了存在的小血管捕捉和部分或模糊标注数据处理的挑战。实验结果表明，我们的方法在基于网格的分割度量方面具有优越性。通过利用部分和模糊标记的数据对主要血管进行标注，我们的方法在错标细小血管的分割性能方面取得了令人瞩目的成果，展示了其在临床应用中的潜力。