SD-FSMIS：适配 Stable Diffusion 实现少样本医学图像分割
SD-FSMIS: Adapting Stable Diffusion for Few-Shot Medical Image Segmentation
把预训练 Stable Diffusion 的条件生成架构改造成少样本分割器：用 Support-Query Interaction 注入支持集特征、用 Visual-to-Textual Condition Translator 把视觉提示转成隐式文本嵌入作为生成条件，为视觉研究者提供了一条「复用生成模型先验做密集预测」的可迁移路径。
原文依据 The VTCT module translates visual cues from the support set into an implicit textual embedding that guides the diffusion model
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论少样本医学图像分割（FSMIS）旨在仅使用极少量标注样本对医学图像中的新类别目标进行分割，以应对医学成像中普遍存在的数据稀缺与域偏移这两大关键挑战。尽管扩散模型（DM）在视觉任务中表现优异，但其在 FSMIS 中的潜力仍基本未被探索。我们提出，大规模扩散模型所学到的丰富视觉先验为构建更鲁棒、更数据高效的分割方法提供了强大基础。本文提出 SD-FSMIS，一种新颖框架，旨在有效地将强大的预训练 Stable Diffusion（SD）模型适配到 FSMIS 任务上。我们的方法通过引入两个关键组件来重新利用其条件生成架构：支持-查询交互（SQI）与视觉到文本条件转换器（VTCT）。具体而言，SQI 提供了一种直接而有力的手段，将 SD 适配到 FSMIS 范式。VTCT 模块将来自支持集的视觉线索转换为隐式文本嵌入，用以引导扩散模型，从而实现对生成过程的精确条件控制。大量实验表明，SD-FSMIS 在标准设定下取得了与最优方法相比具有竞争力的结果。令人惊讶的是，它在更具挑战性的跨域场景中也展现出优异的泛化能力。这些发现凸显了适配大规模生成模型以推进数据高效且鲁棒的医学图像分割的巨大潜力。
英文原文摘要 1530 字符
Few-Shot Medical Image Segmentation (FSMIS) aims to segment novel object classes in medical images using only minimal annotated examples, addressing the critical challenges of data scarcity and domain shifts prevalent in medical imaging. While Diffusion Models (DM) excel in visual tasks, their potential for FSMIS remains largely unexplored. We propose that the rich visual priors learned by large-scale DMs offer a powerful foundation for a more robust and data-efficient segmentation approach. In this paper, we introduce SD-FSMIS, a novel framework designed to effectively adapt the powerful pre-trained Stable Diffusion (SD) model for the FSMIS task. Our approach repurposes its conditional generative architecture by introducing two key components: a Support-Query Interaction (SQI) and a Visual-to-Textual Condition Translator (VTCT). Specifically, SQI provides a straightforward yet powerful means of adapting SD to the FSMIS paradigm. The VTCT module translates visual cues from the support set into an implicit textual embedding that guides the diffusion model, enabling precise conditioning of the generation process. Extensive experiments demonstrate that SD-FSMIS achieves competitive results compared to state-of-the-art methods in standard settings. Surprisingly, it also demonstrated excellent generalization ability in more challenging cross-domain scenarios. These findings highlight the immense potential of adapting large-scale generative models to advance data-efficient and robust medical image segmentation.