Work

Dual-Filter Cross Attention and Onion Pooling Network for Enhanced Few-Shot Medical Image Segmentation

Year: 2025

Type: article

Abstract: Few-shot learning has demonstrated remarkable performance in medical image segmentation. However, existing few-shot medical image segmentation (FSMIS) models often struggle to fully utilize query image information, leading to prototype bias and limited generalization ability. To address these issues, we propose the dual-filter cross attention and onion pooling network (DCOP-Net) for FSMIS. DCOP-Net consists of a prototype learning stage and a segmentation stage. During the prototype learning stage, we introduce a dual-filter cross attention (DFCA) module to avoid entanglement between query background features and support foreground features, effectively integrating query foreground features into support prototypes. Additionally, we design an onion pooling (OP) module that combines eroding mask operations with masked average pooling to generate multiple prototypes, preserving contextual information and mitigating prototype bias. In the segmentation stage, we present a parallel threshold perception (PTP) module to generate robust thresholds for foreground and background differentiation and a query self-reference regularization (QSR) strategy to enhance model accuracy and consistency. Extensive experiments on three publicly available medical image datasets demonstrate that DCOP-Net outperforms state-of-the-art methods, exhibiting superior segmentation and generalization capabilities.

Source: Sensors

DOI: 10.3390/s25072176

Authors: Lina Ni, Yang Liu, Zekun Zhang, Yongtao Li, Jinquan Zhang

Institutions: Tongji University, Shandong University of Science and Technology, University of Glasgow

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: gold

Estimated APC paid: $3,137