CC-SAM: SAM with Cross-feature Attention and Context for Ultrasound Image Segmentation

TL;DR

This paper enhances the Segment Anything Model (SAM) for ultrasound image segmentation by integrating a CNN branch, variational attention, and ChatGPT-generated prompts, significantly improving its performance on complex medical images.

Contribution

The paper introduces a novel fusion module, feature and position adapters, and utilizes ChatGPT for prompt generation to adapt SAM for medical imaging tasks.

Findings

Improved segmentation accuracy on ultrasound images

Effective integration of CNN and ViT encoders

ChatGPT-generated prompts enhance model understanding

Abstract

The Segment Anything Model (SAM) has achieved remarkable successes in the realm of natural image segmentation, but its deployment in the medical imaging sphere has encountered challenges. Specifically, the model struggles with medical images that feature low contrast, faint boundaries, intricate morphologies, and small-sized objects. To address these challenges and enhance SAM's performance in the medical domain, we introduce a comprehensive modification. Firstly, we incorporate a frozen Convolutional Neural Network (CNN) branch as an image encoder, which synergizes with SAM's original Vision Transformer (ViT) encoder through a novel variational attention fusion module. This integration bolsters the model's capability to capture local spatial information, which is often paramount in medical imagery. Moreover, to further optimize SAM for medical imaging, we introduce feature and position adapters within the ViT branch, refining the encoder's representations. We see that compared to current prompting strategies to fine-tune SAM for ultrasound medical segmentation, the use of text descriptions that serve as text prompts for SAM helps significantly improve the performance. Leveraging ChatGPT's natural language understanding capabilities, we generate prompts that offer contextual information and guidance to SAM, enabling it to better understand the nuances of ultrasound medical images and improve its segmentation accuracy. Our method, in its entirety, represents a significant stride towards making universal image segmentation models more adaptable and efficient in the medical domain.