RUFNet: Query-Guided Support Mask Refinement and Uncertainty Fusion based on Hybrid Mamba for Few-Shot Brain Tumor Segmentation

2026-07-06

AI Summary

This work addresses key challenges in few-shot brain tumor segmentation, including noisy support masks, significant inter-patient variability, and the absence of pixel-wise confidence estimation. To tackle these issues, the authors propose RUFNet, a novel framework that integrates query-guided Attention-based Mask Refinement (AGMR) and Uncertainty-Aware Posterior Fusion (UAPF). Notably, RUFNet is the first to incorporate Hybrid Mamba into few-shot medical image segmentation, enabling efficient long-range dependency modeling with linear computational complexity. Additionally, prototype consistency optimization is introduced to enhance generalization. Evaluated on the BraTS 2020 dataset, the method achieves Dice scores of 84.3% and 86.1% under 1-shot and 5-shot settings, respectively, outperforming current state-of-the-art approaches.

Abstract

Few-shot brain tumor segmentation remains challenging due to noisy support masks, inter-patient variations between support and query images, and the lack of pixel-wise confidence estimation. This study proposes RUFNet, a Hybrid Mamba-based few-shot framework that combines support mask refinement with uncertainty-aware posterior fusion. To preserve support-query dependencies with manageable cost, RUFNet adopts a Hybrid Mamba interaction backbone with linear complexity. To reduce support-mask noise, an Attention-Guided Mask Refinement module (AGMR) uses query features to recalibrate support masks and improve prototype consistency. To handle ambiguous predictions, an Uncertainty-Aware Posterior Fusion module (UAPF) estimates pixel-wise variance and adaptively balances few-shot predictions with query-aligned priors. On the Brain Tumor Segmentation Challenge (BraTS) 2020 dataset, RUFNet achieves Dice coefficients of 84.3% and 86.1% in the 1-way 1-shot and 1-way 5-shot settings, respectively, outperforming the compared state-of-the-art methods. These results suggest that Hybrid Mamba interaction, mask refinement and uncertainty modelling can improve the robustness of few-shot medical image segmentation. The official implementation code is available at https://github.com/hdy6438/RUFNet.

Problem

• few-shot segmentation
• brain tumor segmentation
• support mask noise
• inter-patient variation
• pixel-wise uncertainty

Innovation

• Hybrid Mamba
• Mask Refinement
• Uncertainty Fusion
• Few-Shot Segmentation
• Brain Tumor Segmentation