Support-Query Prototype Fusion Network for Few-shot Medical Image Segmentation
Xiaoxiao Wu, Zhenguo Gao, Xiaowei Chen, Yakai Wang, Shulei Qu, Na Li
TL;DR
This work tackles the data-scarcity challenge in medical image segmentation by proposing SQPFNet, a few-shot framework that fuses information from both support and query sets. It constructs multiple regional prototypes from the support foreground, builds a coarse query prototype guided by that mask, and then fuses the two into a final prototype $p_{\text{final}} = \alpha p_s + \beta p_q$ to segment the query image. Extensive experiments on the SABS and CMR datasets demonstrate state-of-the-art performance, with ablations showing clear gains from using multiple supporting prototypes and incorporating a query prototype, while maintaining a lightweight model. The approach reduces reliance on the support set by leveraging query information during prototype construction, offering practical benefits for rapid, accurate medical image segmentation in data-limited settings.
Abstract
In recent years, deep learning based on Convolutional Neural Networks (CNNs) has achieved remarkable success in many applications. However, their heavy reliance on extensive labeled data and limited generalization ability to unseen classes pose challenges to their suitability for medical image processing tasks. Few-shot learning, which utilizes a small amount of labeled data to generalize to unseen classes, has emerged as a critical research area, attracting substantial attention. Currently, most studies employ a prototype-based approach, in which prototypical networks are used to construct prototypes from the support set, guiding the processing of the query set to obtain the final results. While effective, this approach heavily relies on the support set while neglecting the query set, resulting in notable disparities within the model classes. To mitigate this drawback, we propose a novel Support-Query Prototype Fusion Network (SQPFNet). SQPFNet initially generates several support prototypes for the foreground areas of the support images, thus producing a coarse segmentation mask. Subsequently, a query prototype is constructed based on the coarse segmentation mask, additionally exploiting pattern information in the query set. Thus, SQPFNet constructs high-quality support-query fused prototypes, upon which the query image is segmented to obtain the final refined query mask. Evaluation results on two public datasets, SABS and CMR, show that SQPFNet achieves state-of-the-art performance.