用数学模型生成3D医学影像数据，让分割模型零样本泛化能力大幅提升
Synthetic Volumetric Data Generation Enables Zero-Shot Generalization of Foundation Models in 3D Medical Image Segmentation
- 通过解析建模解剖、对比度等三维变化生成合成数据
- 在11个结构上跨模态提升骰子系数，超基线显著
- 无需真实标注，适合医疗图像零样本分割场景
像Segment Anything Model 2（SAM 2）这样的基础模型在自然图像和视频上表现优异，但在医学数据上因外观统计、成像物理及三维结构差异而表现不佳。为弥合这一差距，我们提出SynthFM-3D，一个解析框架，通过数学建模解剖结构、对比度、边界定义和噪声的三维变异性，生成用于训练可提示分割模型的合成数据，无需真实标注。我们在10,000个SynthFM-3D体积上微调SAM 2，并在五个公开数据集中的三种医学成像模态（CT、MR、超声）上评估了十一种解剖结构。与预训练的SAM 2基线相比，SynthFM-3D训练带来了持续且统计显著的骰子系数提升，证明其在跨模态上的更强零样本泛化能力。与监督训练的SAM-Med3D模型在未见心脏超声数据上的对比中，SynthFM-3D实现了2-3倍更高的骰子系数，确立了解析式3D数据建模作为实现模态无关医学分割的有效路径。
原文摘要 · Abstract (English)
Foundation models such as Segment Anything Model 2 (SAM 2) exhibit strong generalization on natural images and videos but perform poorly on medical data due to differences in appearance statistics, imaging physics, and three-dimensional structure. To address this gap, we introduce SynthFM-3D, an analytical framework that mathematically models 3D variability in anatomy, contrast, boundary definition, and noise to generate synthetic data for training promptable segmentation models without real annotations. We fine-tuned SAM 2 on 10,000 SynthFM-3D volumes and evaluated it on eleven anatomical structures across three medical imaging modalities (CT, MR, ultrasound) from five public datasets. SynthFM-3D training led to consistent and statistically significant Dice score improvements over the pretrained SAM 2 baseline, demonstrating stronger zero-shot generalization across modalities. When compared with the supervised SAM-Med3D model on unseen cardiac ultrasound data, SynthFM-3D achieved 2-3x higher Dice scores, establishing analytical 3D data modeling as an effective pathway to modality-agnostic medical segmentation.
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。