无需提示即可精准分割医学影像，支持少样本和无源域适应。
DiffuSAM: Diffusion-Based Prompt-Free SAM2 for Few-Shot and Source-Free Medical Image Segmentation
- 用扩散模型生成适配SAM2的掩码嵌入，实现免提示分割。
- 在BTCV和CHAOS数据集上少样本和无源域适应下表现优异。
- 适合医疗图像分割场景，尤其适用于标注稀缺的临床应用。
像Segment Anything Model (SAM)和SAM2这样的分割模型虽在自然图像上表现出色，但其在自然图像上的训练限制了向医学数据的迁移能力。因此，准确分割通常需要大量微调和专家设计的提示。我们提出DiffuSAM，一种基于扩散模型的SAM2免提示医学图像分割方法。该框架通过轻量级扩散先验，从预训练的冻结SAM2图像特征中合成与SAM2兼容的分割掩码类嵌入。生成的嵌入被整合到SAM2的掩码解码器中，以生成精确分割结果，从而消除对用户提示的依赖。扩散先验进一步基于先前分割的切片进行条件化，以保证体积内空间一致性。在CT和MRI的BTCV与CHAOS数据集上，在无源无监督域适应（SF-UDA）和少样本设置下评估，DiffuSAM实现了具有竞争力的性能，且训练与推理高效。代码可向通讯作者申请获取。
原文摘要 · Abstract (English)
Segmentation models such as Segment Anything Model (SAM) and SAM2 achieve strong prompt-driven zero-shot performance. However, their training on natural images limits domain transfer to medical data. Consequently, accurate segmentation typically requires extensive fine-tuning and expert-designed prompts. We propose DiffuSAM, a diffusion-based adaptation of SAM2 for prompt-free medical image segmentation. Our framework synthesizes SAM2-compatible segmentation mask-like embeddings via a lightweight diffusion-prior from off-the-shelf frozen SAM2 image features. The generated embeddings are integrated into SAM2's mask decoder to produce accurate segmentations, thereby eliminating the need for user prompts. The diffusion prior is further conditioned on previously segmented slices, enforcing spatial consistency across volumes. Evaluated on the BTCV and CHAOS datasets for CT and MRI under Source-Free Unsupervised Domain Adaptation (SF-UDA) and Few-Shot settings, DiffuSAM achieves competitive performance with efficient training and inference. Code is available upon request from the corresponding author.
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。