Tri-Plane Mamba：高效适配Segment Anything Model用于3D医学图像
Tri-Plane Mamba: Efficiently Adapting Segment Anything Model for 3D Medical Images
AI总结：
针对3D医学图像适配SAM时特征难共享、计算成本高的问题，提出带多尺度3D卷积适配器和三平面mamba模块的TP-Mamba，在稀缺数据下仍实现3D CT器官分割SOTA性能。
摘要：
3D医学图像分割的通用网络近年来得到了广泛探索。这些网络出色性能的背后，是对大量像素级标注数据的巨大需求，而这类数据的标注既耗时又费力。Segment Anything Model（SAM，分割一切模型）的出现，使得该模型能够通过参数高效和数据高效的特征适配，在2D医学图像分割任务中取得优异性能。然而，3D医学图像中额外深度通道的引入，不仅阻碍了2D预训练特征的共享，还导致适配SAM的计算成本呈二次方增长。为克服这些挑战，我们提出了专为SAM定制的Tri-Plane Mamba（TP-Mamba，三平面Mamba）适配器，它具备两大创新点：1）多尺度3D卷积适配器，经优化可高效处理局部深度层面的信息；2）三平面mamba模块，旨在不显著增加计算成本的前提下捕获长距离深度层面表征。该方法在3D CT器官分割任务中达到了当前最优性能。值得注意的是，即便在训练数据稀缺的情况下，该方法仍能保持这种优异性能。具体而言，仅使用BTCV数据集中的3个CT训练样本，它就超越了传统3D分割网络，Dice系数最高提升了12%。
英文摘要：
General networks for 3D medical image segmentation have recently undergone extensive exploration. Behind the exceptional performance of these networks lies a significant demand for a large volume of pixel-level annotated data, which is time-consuming and labor-intensive. The emergence of the Segment Anything Model (SAM) has enabled this model to achieve superior performance in 2D medical image segmentation tasks via parameter- and data-efficient feature adaptation. However, the introduction of additional depth channels in 3D medical images not only prevents the sharing of 2D pre-trained features but also results in a quadratic increase in the computational cost for adapting SAM. To overcome these challenges, we present the Tri-Plane Mamba (TP-Mamba) adapters tailored for the SAM, featuring two major innovations: 1) multi-scale 3D convolutional adapters, optimized for efficiently processing local depth-level information, 2) a tri-plane mamba module, engineered to capture long-range depth-level representation without significantly increasing computational costs. This approach achieves state-of-the-art performance in 3D CT organ segmentation tasks. Remarkably, this superior performance is maintained even with scarce training data. Specifically using only three CT training samples from the BTCV dataset, it surpasses conventional 3D segmentation networks, attaining a Dice score that is up to 12% higher.
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。
