发表机构
School of Electrical Engineering and Computer Science, The University of Queensland; School of Engineering, College of Engineering, Science and Environment, University of Newcastle; School of Human Movement and Nutrition Sciences, The University of Queensland（电气工程与计算机科学学院，昆士兰大学; 工程学院，工程、科学与环境学院，纽卡斯尔大学; 人类运动与营养科学学院，昆士兰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对MRI低软组织对比度导致边界难观察的问题，提出SAMRI-3D方法，通过冻结图像编码器、微调解码器和内存模块，并引入全局体积令牌，在3D MRI分割上取得高精度，提升了基于SAM的医学模型性能。
AI 中文摘要
诸如Segment Anything Model 2（SAM2）之类的基础模型已经改变了自然图像和视频分割，近期工作开始将它们应用于医学成像。然而，这些改编大多是通用模型，将MRI视为众多模态之一。尽管MRI的低软组织对比度使许多边界在单个切片上难以有效观察到，但大规模、特定于MRI的建模和基准测试仍然有限。我们提出了SAMRI-3D，一种使用SAM2进行3D MRI分割的基准和方法。SAMRI-3D基准是迄今为止最大的仅针对MRI的评估，包含来自34个数据集（27个公开，7个内部）的10392个体积数据，涵盖12个解剖领域和10多种序列，并进行了明确的可见/不可见分割。冻结图像编码器并仅微调轻量级解码器和内存模块，使平均Dice从0.58（零样本SAM2）提高到0.76，显著超过了近期基于SAM的医学模型（SAMed-2为0.69，Medical-SAM2为0.49，SAM-Med3D为0.37）。为了处理不可见边界，我们引入了全局体积令牌（GVT）：通过截断符号距离场（TSDF）重建目标训练的持久内存令牌，在推理时被丢弃（零额外成本）。完整的SAMRI-3D模型在所有34个数据集中达到了最佳精度（0.78）和最低方差，并且在8个保留数据集中没有下降（不可见数据为0.79，可见数据为0.78）；逐序列分析证实，TSDF目标在切片对比度最弱的地方帮助最大。我们将在本文中发布基准、代码和模型。
英文摘要
Foundation models such as Segment Anything Model 2 (SAM2) have transformed natural-image and video segmentation, and recent work has begun adapting them to medical imaging. These adaptations, however, are largely general-purpose models that treat MRI as one modality among many; large-scale, MRI-specific modelling and benchmarking remain limited, even though MRI's low soft-tissue contrast leaves many boundaries effectively invisible on individual slices. We present SAMRI-3D, a benchmark and method for 3D MRI segmentation with SAM2. The SAMRI-3D benchmark is the largest MRI-only evaluation to date - 10,392 volumes from 34 datasets (27 public, 7 in-house) spanning 12 anatomical domains and 10+ sequences, with explicit seen/unseen splits. Freezing the image encoder and fine-tuning only the lightweight decoder and memory modules raises mean Dice from 0.58 (zero-shot SAM2) to 0.76, surpassing recent SAM-based medical models (SAMed-2 0.69, Medical-SAM2 0.49, SAM-Med3D 0.37) with strong statistical significance. To target invisible boundaries, we introduce Global Volume Tokens (GVT): persistent memory tokens trained with a Truncated Signed Distance Field (TSDF) reconstruction objective that is discarded at inference (zero added cost). This full model, SAMRI-3D, attains the best accuracy (0.78) and lowest variance across all 34 datasets and, uniquely, shows no drop on 8 held-out datasets (0.79 unseen vs. 0.78 seen); per-sequence analysis confirms the TSDF objective helps most where per-slice contrast is weakest. We will release the benchmark, code, and models in this paper.
