从掩码引导自监督学习中学习通用的3D医学图像表示
Learning Generalizable 3D Medical Image Representations from Mask-Guided Self-Supervision
AI总结：
本文提出MASS方法，通过掩码引导自监督学习，学习通用的医学图像表示，实现了在不同数据集上的高效分割和分类任务。
摘要：
基础模型通过从大规模未标记数据中学习通用表示，改变了视觉和语言领域，但3D医学影像缺乏类似方法。现有自监督方法依赖低级重建或对比目标，无法捕捉医学影像分析中至关重要的解剖学语义，限制了其在下游任务中的迁移。本文提出MASS（MAsk-guided Self-Supervision），将上下文分割作为预训练任务，学习通用的医学影像表示。MASS的核心思想是自动生成的类无关掩码提供了足够的结构监督，以学习语义丰富的表示。通过在数千个多样化的掩码提案上训练，涵盖解剖结构和病理发现，MASS学习了医学结构的语义定义：外观、形状、空间上下文和解剖关系的综合。我们展示了在不同数据集上的有效性：从小规模预训练（20-200扫描）到大规模多模态预训练（5K CT、MRI和PET体积），均无需标注。MASS展示了：（i）在新结构上的少样本分割，（ii）仅使用20-40%标注数据即可匹配全监督，且在低数据条件下比自监督基线高出20分以上的Dice得分，（iii）冻结编码器分类未见过的病理，其效果可与成千上万样本的全监督训练相媲美。掩码引导的自监督预训练捕捉了广泛可推广的知识，为无需专家标注的3D医学影像基础模型开辟了道路。代码可获取：https://github.com/Stanford-AIMI/MASS。
英文摘要：
Foundation models have transformed vision and language by learning general-purpose representations from large-scale unlabeled data, yet 3D medical imaging lacks analogous approaches. Existing self-supervised methods rely on low-level reconstruction or contrastive objectives that fail to capture the anatomical semantics critical for medical image analysis, limiting transfer to downstream tasks. We present MASS (MAsk-guided Self-Supervised learning), which treats in-context segmentation as the pretext task for learning general-purpose medical imaging representations. MASS's key insight is that automatically generated class-agnostic masks provide sufficient structural supervision for learning semantically rich representations. By training on thousands of diverse mask proposals spanning anatomical structures and pathological findings, MASS learns what semantically defines medical structures: the holistic combination of appearance, shape, spatial context, and anatomical relationships. We demonstrate effectiveness across data regimes: from small-scale pretraining on individual datasets (20-200 scans) to large-scale multi-modal pretraining on 5K CT, MRI, and PET volumes, all without annotations. MASS demonstrates: (i) few-shot segmentation on novel structures, (ii) matching full supervision with only 20-40\% labeled data while outperforming self-supervised baselines by over 20 in Dice score in low-data regimes, and (iii) frozen-encoder classification on unseen pathologies that matches full supervised training with thousands of samples. Mask-guided self-supervised pretraining captures broadly generalizable knowledge, opening a path toward 3D medical imaging foundation models without expert annotations. Code is available: https://github.com/Stanford-AIMI/MASS.
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。
