Organ segmentation from PET/CT is critical for quantitative analysis and radiotherapy planning in oncology. To ease the high annotation cost of PET/CT segmentation, semi-supervised learning (SSL) provides a practical and effective solution for developing deep models with limited labeled data. Recent developments in visual foundation models have demonstrated remarkable adaptability with improved efficiency. In this work, we propose a mutual distillation framework that seamlessly exploits both structural and functional foundation models, which act as modality-specific generalists for distilling knowledge from structural CT and metabolic PET imaging. By bridging the gap between the task-specific precision of student models and the segmentation priors of generalist foundation models, we propose \textbf{MuDuo}, a mutual distillation framework that synergistically leverages SAM-Med3D for CT and SegAnyPET for PET to distill their knowledge into a lightweight student network. Our approach eliminates the need for manual prompts while maximizing the utility of unlabeled data for automatic segmentation, achieving state-of-the-art performance on the AutoPET dataset with only 5 labeled cases. Our source code is available at https://github.com/Wu-beining/MuDuo.

翻译：PET/CT器官分割对于肿瘤学定量分析和放疗规划至关重要。为降低PET/CT分割的高标注成本，半监督学习（SSL）为利用有限标注数据开发深度模型提供了实用且有效的解决方案。视觉基础模型的最新发展展现了卓越的适应性和更高效率。在本工作中，我们提出了一种互蒸馏框架，无缝利用结构性和功能性基础模型——这些模型作为模态专用通才，分别从结构CT和代谢PET成像中蒸馏知识。通过弥合学生模型的任务特异性精度与通才基础模型的分割先验之间的差距，我们提出\textbf{MuDuo}——一种互蒸馏框架，协同利用SAM-Med3D（针对CT）和SegAnyPET（针对PET）将其知识蒸馏至轻量级学生网络。该方法无需人工提示，同时最大化未标注数据在自动分割中的效用，在仅使用5例标注样本的AutoPET数据集上实现了最先进性能。我们的源代码已开源至https://github.com/Wu-beining/MuDuo。