Is Foreground Prototype Sufficient? Few-Shot Medical Image Segmentation with Background-Fused Prototype

TL;DR

This paper introduces a novel background-fused prototype approach for few-shot medical image segmentation, addressing the challenge of similar foreground and background features by integrating background information into the prototype representation.

Contribution

The paper proposes a pluggable Background-fused prototype (Bro) method with feature similarity calibration and hierarchical channel adversarial attention for improved medical image segmentation.

Findings

Significant performance improvements over state-of-the-art methods

Effective background representation for medical images

Enhanced segmentation accuracy with Bro approach

Abstract

Few-shot Semantic Segmentation(FSS)aim to adapt a pre-trained model to new classes with as few as a single labeled training sample per class. The existing prototypical work used in natural image scenarios biasedly focus on capturing foreground's discrimination while employing a simplistic representation for background, grounded on the inherent observation separation between foreground and background. However, this paradigm is not applicable to medical images where the foreground and background share numerous visual features, necessitating a more detailed description for background. In this paper, we present a new pluggable Background-fused prototype(Bro)approach for FSS in medical images. Instead of finding a commonality of background subjects in support image, Bro incorporates this background with two pivot designs. Specifically, Feature Similarity Calibration(FeaC)initially reduces noise in the support image by employing feature cross-attention with the query image. Subsequently, Hierarchical Channel Adversarial Attention(HiCA)merges the background into comprehensive prototypes. We achieve this by a channel groups-based attention mechanism, where an adversarial Mean-Offset structure encourages a coarse-to-fine fusion. Extensive experiments show that previous state-of-the-art methods, when paired with Bro, experience significant performance improvements. This demonstrates a more integrated way to represent backgrounds specifically for medical image.