揭示通用3D医学分割中的模态差异与泛化幻觉
Universality Reconsidered: Rethinking the Validation of Foundation Models for General-Purpose 3D Medical Segmentation
AI总结：
本文通过UMD数据集揭示3D医学分割中模态差异与泛化幻觉问题，指出现有基础模型在实际应用中存在显著性能差异，需转向多模态训练以提升通用性。
摘要：
尽管新兴的3D医学基础模型被设想为具有通用能力的多功能工具，但其验证仍主要局限于区域和结构成像，留下显著的模态差异未被探索。为了提供严格且客观的评估，我们整理了UMD数据集，包含490例全身PET/CT和464例全身PET/MRI扫描（约675万张2D图像，约12k个3D器官注释），并对具有代表性的3D分割基础模型进行了全面评估。通过配对扫描的受试者内对照比较，我们将成像模态作为主要独立变量，以评估模型在实际应用中的鲁棒性。我们的评估揭示了文献报告的基准与实际效果之间显著的差异，特别是在从结构域转向功能域时尤为明显。这种系统性失败表明，当前的3D基础模型离真正通用化的目标还很远，需要向多模态训练和评估的范式转变，以弥合理想化基准与全面临床应用之间的差距。该数据集和分析为未来研究开发真正模态无关的医学基础模型奠定了基础。
英文摘要：
Foundation models have emerged as a transformative paradigm in 3D medical imaging, with the promise of unified quantitative analysis across diverse targets and imaging modalities. Yet the prevailing conception of universality remains incomplete. Current models are predominantly developed and evaluated on datasets largely concentrated around a limited set of imaging modalities and anatomical regions. In this Perspective, we evaluate representative 3D segmentation foundation models using paired whole-body structural and functional imaging data. Our analysis reveals a substantial gap between benchmark-reported performance and real-world generalization, with marked degradation on previously unseen data and particularly severe failures on functional imaging modalities. These findings suggest that current foundation models remain far from achieving true universality. We argue that progress requires not only scaling models and datasets, but also a reconsideration of how universality is defined and validated, extending evaluation beyond regional structural benchmarks toward whole-body structural and functional imaging. Our observations highlight the need to distinguish benchmark success from genuine clinical generalization. Bridging this gap will be essential for translating foundation models from controlled evaluation settings to real-world medical practice.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
