Abstract
Accurate segmentation of 3D medical images is critical for clinical applications like disease assessment and treatment planning. While the Segment Anything Model 2 (SAM2) has shown remarkable success in video object segmentation by leveraging temporal cues, its direct application to 3D medical images faces two fundamental domain gaps: 1) the bidirectional anatomical continuity between slices contrasts sharply with the unidirectional temporal flow in videos, and 2) precise boundary delineation, crucial for morphological analysis, is often underexplored in video tasks. To bridge these gaps, we propose SAM2-3dMed, an adaptation of SAM2 for 3D medical imaging. Our framework introduces two key innovations: 1) a Slice Relative Position Prediction (SRPP) module explicitly models bidirectional inter-slice dependencies by guiding SAM2 to predict the relative positions of different slices in a self-supervised manner; 2) a Boundary Detection (BD) module enhances segmentation accuracy along critical organ and tissue boundaries. Extensive experiments on three diverse medical datasets (the Lung, Spleen, and Pancreas in the Medical Segmentation Decathlon (MSD) dataset) demonstrate that SAM2-3dMed significantly outperforms state-of-the-art methods, achieving superior performance in segmentation overlap and boundary precision. Our approach not only advances 3D medical image segmentation performance but also offers a general paradigm for adapting video-centric foundation models to spatial volumetric data.
Abstract (translated)
准确分割三维医学图像对于疾病评估和治疗计划等临床应用至关重要。虽然Segment Anything Model 2 (SAM2) 在视频对象分割中通过利用时间线索取得了显著的成功，但在将其直接应用于3D医学图像时面临两个根本性的领域差异：1）切片之间的双向解剖连续性与视频中的单向时间流形成鲜明对比；2）对于形态学分析至关重要的精确边界划分在视频任务中往往被忽视。为了弥合这些差距，我们提出了SAM2-3dMed，这是对SAM2用于三维医学成像的一种适应。我们的框架引入了两个关键创新：1）一个切片相对位置预测（SRPP）模块通过引导SAM2以自监督的方式预测不同切片之间的相对位置来明确建模双向跨切片依赖关系；2）边界检测（BD）模块增强了在重要器官和组织界限上的分割精度。我们在三个多样化的医学数据集上进行了广泛的实验（Medical Segmentation Decathlon (MSD) 数据集中的肺、脾脏和胰腺），结果表明SAM2-3dMed显著优于最先进的方法，在分割重叠度和边界精确度方面表现出色。我们的方法不仅提升了三维医学图像的分割性能，还为将视频中心的基础模型适应于空间体积数据提供了一般范式。
URL
https://arxiv.org/abs/2510.08967
