用边缘提示实现跨模态肝脏分割，小样本下表现更优
Edge2Prompt: Modality-Agnostic Model for Out-of-Distribution Liver Segmentation
- 先提取跨模态边缘图，再用U-Net生成提示，引导SAM-2分割
- 在分布外数据上达86.4%平均Dice，比U-Net高27.4%
- 适合医疗影像少样本、多模态场景，临床部署潜力大
肝脏分割对肿瘤切除或移植等术前规划至关重要，但临床应用受限于模态依赖工具和数据稀缺。本文提出Edge2Prompt，一种跨模态肝脏分割新方法，可泛化至分布外（OOD）数据。该方法将经典边缘检测与基础模型结合：从输入图像中提取跨模态边缘图，经U-Net生成基于logit的提示，再由Segment Anything Model 2（SAM-2）生成2D分割结果，并重建为3D体积。在多模态CHAOS数据集上评估，该方法在分布内（ID）训练测试时表现媲美传统方法，在数据稀缺场景因引入SAM-2模块而更优。在分布外任务中，平均Dice得分为86.4%，较U-Net基线提升27.4%，优于其他自提示方法9.1%，验证了其有效性。本工作融合经典与基础模型，推动临床可用、数据高效的分割技术发展。
原文摘要 · Abstract (English)
Liver segmentation is essential for preoperative planning in interventions like tumor resection or transplantation, but implementation in clinical workflows faces challenges due to modality-specific tools and data scarcity. We propose Edge2Prompt, a novel pipeline for modality-agnostic liver segmentation that generalizes to out-of-distribution (OOD) data. Our method integrates classical edge detection with foundation models. Modality-agnostic edge maps are first extracted from input images, then processed by a U-Net to generate logit-based prompts. These prompts condition the Segment Anything Model 2 (SAM-2) to generate 2D liver segmentations, which can then be reconstructed into 3D volumes. Evaluated on the multi-modal CHAOS dataset, Edge2Prompt achieves competitive results compared to classical segmentation methods when trained and tested in-distribution (ID), and outperforms them in data-scarce scenarios due to the SAM-2 module. Furthermore, it achieves a mean Dice Score of 86.4% on OOD tasks, outperforming U-Net baselines by 27.4% and other self-prompting methods by 9.1%, demonstrating its effectiveness. This work bridges classical and foundation models for clinically adaptable, data-efficient 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。