用医学知识图谱和概率模型提升分割模型在医疗影像中的准确性和可靠性
Encoding Structural Constraints into Segment Anything Models via Probabilistic Graphical Models
- 融合医学知识图谱与能量型条件随机场，约束解剖结构一致性
- 在前列腺、腹部多模态影像上分别取得82.69%和78.05%~79.68%的Dice分数
- 适合需高精度与不确定度评估的临床医学图像分割场景
尽管分割一切模型（SAM）在图像分割中取得显著成果，但其直接应用于医学影像仍面临边界模糊、解剖关系建模不足及缺乏不确定性量化等根本挑战。为此，我们提出KG-SAM——一种融合医学先验知识的框架，协同实现边界精炼与不确定性估计。具体包括：(i) 利用医学知识图谱编码细粒度解剖关系；(ii) 采用基于能量的条件随机场（CRF）强制预测符合解剖一致性；(iii) 设计不确定性感知融合模块以提升高风险临床场景下的可靠性。在多个中心医学数据集上的实验证明，该方法表现优异：在前列腺分割中平均获得82.69%的Dice分数，在腹部分割中分别达到MRI的78.05%和CT的79.68%。结果表明，KG-SAM是一种鲁棒且可泛化的医疗图像分割框架。
原文摘要 · Abstract (English)
While the Segment Anything Model (SAM) has achieved remarkable success in image segmentation, its direct application to medical imaging remains hindered by fundamental challenges, including ambiguous boundaries, insufficient modeling of anatomical relationships, and the absence of uncertainty quantification. To address these limitations, we introduce KG-SAM, a knowledge-guided framework that synergistically integrates anatomical priors with boundary refinement and uncertainty estimation. Specifically, KG-SAM incorporates (i) a medical knowledge graph to encode fine-grained anatomical relationships, (ii) an energy-based Conditional Random Field (CRF) to enforce anatomically consistent predictions, and (iii) an uncertainty-aware fusion module to enhance reliability in high-stakes clinical scenarios. Extensive experiments across multi-center medical datasets demonstrate the effectiveness of our approach: KG-SAM achieves an average Dice score of 82.69% on prostate segmentation and delivers substantial gains in abdominal segmentation, reaching 78.05% on MRI and 79.68% on CT. These results establish KG-SAM as a robust and generalizable framework for advancing medical image 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。