Tri-Plane Mamba: Efficiently Adapting Segment Anything Model for 3D Medical Images

TL;DR

This paper introduces Tri-Plane Mamba adapters for the Segment Anything Model, enabling efficient 3D medical image segmentation with limited data and achieving state-of-the-art results in CT organ segmentation.

Contribution

The paper proposes novel multi-scale 3D convolutional adapters and a tri-plane mamba module to adapt SAM for 3D medical images efficiently.

Findings

Achieves state-of-the-art performance in 3D CT organ segmentation.

Maintains high accuracy even with scarce training data.

Surpasses conventional 3D segmentation networks with only three training samples.

Abstract

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.