Self-Prompt SAM: Medical Image Segmentation via Automatic Prompt SAM Adaptation

TL;DR

This paper introduces Self-Prompt-SAM, a novel framework that adapts the SAM model for medical image segmentation by generating prompts automatically and incorporating 3D information, achieving state-of-the-art results.

Contribution

It proposes a self-prompting mechanism and a 3D depth-fused adapter to adapt SAM for medical images without extra manual prompts.

Findings

Outperforms nnUNet by 2.3% on AMOS2022

Achieves 1.6% improvement on ACDC dataset

Attains 0.5% higher accuracy on Synapse dataset

Abstract

Segment Anything Model (SAM) has demonstrated impressive zero-shot performance and brought a range of unexplored capabilities to natural image segmentation tasks. However, as a very important branch of image segmentation, the performance of SAM remains uncertain when applied to medical image segmentation due to the significant differences between natural images and medical images. Meanwhile, it is harsh to meet the SAM's requirements of extra prompts provided, such as points or boxes to specify medical regions. In this paper, we propose a novel self-prompt SAM adaptation framework for medical image segmentation, named Self-Prompt-SAM. We design a multi-scale prompt generator combined with the image encoder in SAM to generate auxiliary masks. Then, we use the auxiliary masks to generate bounding boxes as box prompts and use Distance Transform to select the most central points as point prompts. Meanwhile, we design a 3D depth-fused adapter (DfusedAdapter) and inject the DFusedAdapter into each transformer in the image encoder and mask decoder to enable pre-trained 2D SAM models to extract 3D information and adapt to 3D medical images. Extensive experiments demonstrate that our method achieves state-of-the-art performance and outperforms nnUNet by 2.3% on AMOS2022, 1.6% on ACDCand 0.5% on Synapse datasets.