Ultrasound SAM Adapter: Adapting SAM for Breast Lesion Segmentation in Ultrasound Images

TL;DR

This paper introduces BUSSAM, a novel adapter-based approach that adapts the Segment Anything Model for effective breast ultrasound image segmentation, overcoming domain gap issues.

Contribution

It develops a lightweight CNN encoder and cross-branch adapter to adapt SAM for ultrasound images, significantly improving segmentation performance.

Findings

Outperforms existing medical segmentation models on AMUBUS and BUSI datasets.

Effectively integrates CNN and ViT features for ultrasound segmentation.

Demonstrates the effectiveness of adapter-based fine-tuning for domain adaptation.

Abstract

Segment Anything Model (SAM) has recently achieved amazing results in the field of natural image segmentation. However, it is not effective for medical image segmentation, owing to the large domain gap between natural and medical images. In this paper, we mainly focus on ultrasound image segmentation. As we know that it is very difficult to train a foundation model for ultrasound image data due to the lack of large-scale annotated ultrasound image data. To address these issues, in this paper, we develop a novel Breast Ultrasound SAM Adapter, termed Breast Ultrasound Segment Anything Model (BUSSAM), which migrates the SAM to the field of breast ultrasound image segmentation by using the adapter technique. To be specific, we first design a novel CNN image encoder, which is fully trained on the BUS dataset. Our CNN image encoder is more lightweight, and focuses more on features of local receptive field, which provides the complementary information to the ViT branch in SAM. Then, we design a novel Cross-Branch Adapter to allow the CNN image encoder to fully interact with the ViT image encoder in SAM module. Finally, we add both of the Position Adapter and the Feature Adapter to the ViT branch to fine-tune the original SAM. The experimental results on AMUBUS and BUSI datasets demonstrate that our proposed model outperforms other medical image segmentation models significantly. Our code will be available at: https://github.com/bscs12/BUSSAM.