用一张标注图即可让医学图像分割模型快速适应新场景。
Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation
- 用解剖图谱生成上下文感知提示，提升模型理解能力。
- 在六组数据上实现显著提升，小器官分割效果最佳。
- 轻量级设计适合临床实际部署，尤其适合罕见病场景。
准确分割医学图像中的解剖结构对诊断与治疗规划至关重要。尽管近期交互式分割基础模型通过大规模多模态预训练提升了泛化能力，但仍依赖精确提示，且在少样本临床场景（如小器官）中表现不佳。我们提出AtlasSegFM，一种基于图谱引导的框架，仅需一个标注样本即可将现成基础模型定制到新临床场景。该方法包括：1）通过图谱查询注册生成上下文感知提示；2）利用冻结的基础模型进行分割优化；3）采用轻量级自适应融合模块，结合图谱先验与基础模型输入及输出。在六组公开与内部数据集（涵盖放疗与血管场景）上的实验显示，该方法持续取得提升，尤其在小而精细结构上表现最佳。AtlasSegFM为真实临床流程中基础模型的一次性定制提供轻量、可部署的解决方案。
原文摘要 · Abstract (English)
Accurate segmentation of anatomical structures in medical images is essential for diagnosis and treatment planning. While recent interactive segmentation foundation models enhance generalization through large-scale multimodal pretraining, they still depend on precise prompts and can fail in underrepresented clinical contexts (e.g., small organs-at-risk). We present AtlasSegFM, an atlas-guided framework that customizes off-the-shelf foundation models to new clinical contexts with a single annotated example. AtlasSegFM 1) performs atlas-query registration to generate context-aware prompts, 2) refines the segmentation with a frozen foundation model, and 3) applies a lightweight adaptive fusion module to combine atlas priors with foundation-model inputs and predictions. Extensive experiments on six public and in-house datasets across radiotherapy and vascular scenarios show consistent gains, with the largest improvements on small and delicate structures. AtlasSegFM provides a lightweight, deployable solution for one-shot customization of segmentation foundation models in real-world clinical workflows.
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。