无需训练的医学图像分割跨模态适配方法，保护数据隐私同时提升精度。
HEAL: Learning-Free Source Free Unsupervised Domain Adaptation for Cross-Modality Medical Image Segmentation
- 通过无学习机制与分层去噪、边缘引导等策略应对无源数据挑战
- 在多模态医学图像上实现当前最优分割性能，超越已有SOTA方法
- 特别适合医疗数据隐私敏感场景下的模型部署与迁移
临床数据隐私需求和存储限制推动了无源无监督域适应（SFUDA）的发展。SFUDA在不访问源域数据且目标域无标签的情况下，将模型从源域适配到未知目标域。然而，其面临两大挑战：源域数据缺失及目标域缺乏标签监督。为此，我们提出HEAL框架，融合分层去噪、边缘引导选择、尺寸感知融合与无学习特征提取。大规模跨模态实验表明，该方法显著优于现有SFUDA方法，达到当前最佳性能。代码已公开于https://github.com/derekshiii/HEAL。
原文摘要 · Abstract (English)
Growing demands for clinical data privacy and storage constraints have spurred advances in Source Free Unsupervised Domain Adaptation (SFUDA). SFUDA addresses the domain shift by adapting models from the source domain to the unseen target domain without accessing source data, even when target-domain labels are unavailable. However, SFUDA faces significant challenges: the absence of source domain data and label supervision in the target domain due to source free and unsupervised settings. To address these issues, we propose HEAL, a novel SFUDA framework that integrates Hierarchical denoising, Edge-guided selection, size-Aware fusion, and Learning-free characteristic. Large-scale cross-modality experiments demonstrate that our method outperforms existing SFUDA approaches, achieving state-of-the-art (SOTA) performance. The source code is publicly available at: https://github.com/derekshiii/HEAL.
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。