Concentrate on Weakness: Mining Hard Prototypes for Few-Shot Medical Image Segmentation

TL;DR

This paper introduces a novel few-shot medical image segmentation method that emphasizes weak boundary features by generating hard prototypes and fusing similarity maps, leading to improved segmentation accuracy.

Contribution

The paper proposes a new approach focusing on weak features for better boundary delineation in FSMIS, using modules for weak feature identification, hard prototype generation, and dual-path similarity fusion.

Findings

Achieves state-of-the-art results on three medical datasets.

Effectively enhances boundary segmentation accuracy.

Outperforms existing prototype-based FSMIS methods.

Abstract

Few-Shot Medical Image Segmentation (FSMIS) has been widely used to train a model that can perform segmentation from only a few annotated images. However, most existing prototype-based FSMIS methods generate multiple prototypes from the support image solely by random sampling or local averaging, which can cause particularly severe boundary blurring due to the tendency for normal features accounting for the majority of features of a specific category. Consequently, we propose to focus more attention to those weaker features that are crucial for clear segmentation boundary. Specifically, we design a Support Self-Prediction (SSP) module to identify such weak features by comparing true support mask with one predicted by global support prototype. Then, a Hard Prototypes Generation (HPG) module is employed to generate multiple hard prototypes based on these weak features. Subsequently, a Multiple Similarity Maps Fusion (MSMF) module is devised to generate final segmenting mask in a dual-path fashion to mitigate the imbalance between foreground and background in medical images. Furthermore, we introduce a boundary loss to further constraint the edge of segmentation. Extensive experiments on three publicly available medical image datasets demonstrate that our method achieves state-of-the-art performance. Code is available at https://github.com/jcjiang99/CoW.