arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.23116cs.CV
收藏

使用SAM2的零样本方法自动分割3DCT扫描

Automatic Segmentation of 3D CT scans with SAM2 using a zero-shot approach

Department of Computer Science, EPFL, Switzerland(瑞士联邦理工学院计算机科学系)

Miquel Lopez Escoriza, Pau Amargant Alvarez

AI总结:

本文研究了在不进行微调或领域特定训练的情况下,利用Segment Anything Model 2对体积CT数据进行自动分割的零样本方法,通过改进SAM2的视频记忆机制以适应3D数据,展示了零样本方法在医学图像分割中的可行性。

摘要:

图像分割的基础模型在自然图像中表现出强大的泛化能力,但其在3D医学影像中的应用仍受限。本文研究了在不进行微调或领域特定训练的情况下,使用Segment Anything Model 2(SAM2)对体积CT数据进行自动分割的零样本方法。我们分析了SAM2如何应用于CT体积,并识别其主要限制:缺乏固有的体积意识。为解决此问题,我们提出了一系列仅在推理阶段进行的架构和流程修改,通过将CT切片视为有序序列,将SAM2的视频基于记忆机制适应于3D数据。我们对TotalSegmentator数据集中的500个CT扫描子集进行了系统性消融研究,以评估提示策略、记忆传播方案和多轮细化方法。基于这些发现,我们选择了表现最佳的配置,并在包含2,500个CT扫描的更大TotalSegmentator数据集子集上报告最终结果。我们的结果表明,即使在冻结权重的情况下,当SAM2的推理流程被精心设计时,它也能生成连贯的3D分割,证明了完全零样本方法在体积医学图像分割中的可行性。

英文摘要:

Foundation models for image segmentation have shown strong generalization in natural images, yet their applicability to 3D medical imaging remains limited. In this work, we study the zero-shot use of Segment Anything Model 2 (SAM2) for automatic segmentation of volumetric CT data, without any fine-tuning or domain-specific training. We analyze how SAM2 should be applied to CT volumes and identify its main limitation: the lack of inherent volumetric awareness. To address this, we propose a set of inference-alone architectural and procedural modifications that adapt SAM2's video-based memory mechanism to 3D data by treating CT slices as ordered sequences. We conduct a systematic ablation study on a subset of 500 CT scans from the TotalSegmentator dataset to evaluate prompt strategies, memory propagation schemes and multi-pass refinement. Based on these findings, we select the best-performing configuration and report final results on a bigger sample of the TotalSegmentator dataset comprising 2,500 CT scans. Our results show that, even with frozen weights, SAM2 can produce coherent 3D segmentations when its inference pipeline is carefully structured, demonstrating the feasibility of a fully zero-shot approach for volumetric medical image segmentation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑