Prompting Segment Anything Model with Domain-Adaptive Prototype for Generalizable Medical Image Segmentation

TL;DR

This paper introduces DAPSAM, a novel framework that fine-tunes the Segment Anything Model with domain-adaptive prototypes and self-learning prompts, significantly improving generalization in medical image segmentation across different domains.

Contribution

The paper proposes a new domain-adaptive prompt framework with prototype-based prompt generation for large models, enhancing medical image segmentation under domain shift.

Findings

Achieves state-of-the-art results on two SDG medical segmentation tasks.

Utilizes a self-learning prototype-based prompt generator for improved generalization.

Incorporates a domain-adaptive memory bank for robust prompt construction.

Abstract

Deep learning based methods often suffer from performance degradation caused by domain shift. In recent years, many sophisticated network structures have been designed to tackle this problem. However, the advent of large model trained on massive data, with its exceptional segmentation capability, introduces a new perspective for solving medical segmentation problems. In this paper, we propose a novel Domain-Adaptive Prompt framework for fine-tuning the Segment Anything Model (termed as DAPSAM) to address single-source domain generalization (SDG) in segmenting medical images. DAPSAM not only utilizes a more generalization-friendly adapter to fine-tune the large model, but also introduces a self-learning prototype-based prompt generator to enhance model's generalization ability. Specifically, we first merge the important low-level features into intermediate features before feeding to each adapter, followed by an attention filter to remove redundant information. This yields more robust image embeddings. Then, we propose using a learnable memory bank to construct domain-adaptive prototypes for prompt generation, helping to achieve generalizable medical image segmentation. Extensive experimental results demonstrate that our DAPSAM achieves state-of-the-art performance on two SDG medical image segmentation tasks with different modalities. The code is available at https://github.com/wkklavis/DAPSAM.