Skip to content
Conference

MSHA-Net: learning with multiscale hierarchical discriminative attention for few-shot medical segmentation

Sep 2026 · Asia Conference onAsia Conference on Advances in Image Processing · Vol 14375, pp. 1437507 - 1437507-12 · 0 citations · 28 references
Engineering

TL;DR

Unlike existing single-scale attention-based few-shot segmentation methods that struggle to balance global semantics and local boundary details, MSHA-Net introduces a hierarchical discriminative attention framework that explicitly decouples and fuses multi-scale features through three specialized modules.

Abstract

Few-shot medical image segmentation, which aims to achieve accurate segmentation with limited labeled data, faces challenges including 1) the model’s need for strong generalization ability and 2) simultaneous extraction of global semantics and local boundaries. To address these issues, we propose MSHA-NET, a framework based on Multi-Scale Hierarchical Discriminative Attention for few-shot medical segmentation. MSHA-Net consists of three core components: a Triple-Branch Feature Extraction Module (TBFEM), a Two-Stream Attention Module (TSAM), and a Threshold-based Multi-scale Fusion Module (TMFM). First, TBFEM effectively extracts global semantics and local boundary details across multiple scales from support and query images. Then, TSAM harnesses self-attention and cross-attention mechanisms to adequately enhance and fuse multi-scale support and query features. Finally, via the features containing both global semantics and boundary details, TMFM adaptively generates and then integrates prediction masks from different scales to get the final segmentation map. To train MSHA-NET, super voxel-based self-supervised training process based on generating auxiliary data is developed to enhance the model’s generalization ability under data-scarce conditions. Unlike existing single-scale attention-based few-shot segmentation methods that struggle to balance global semantics and local boundary details, MSHA-Net introduces a hierarchical discriminative attention framework that explicitly decouples and fuses multi-scale features through three specialized modules. Experiments on the public ABD-CT and ABD-MR datasets show that MSHA-Net surpasses state-of-the-art methods by up to 10.62% in Dice scores, demonstrating its superior ability to handle diverse organ sizes and cross-modality generalization.

View source

Similar papers

Aug 2026

GLNet: global-to-local aware hybrid framework for medical image segmentation

GLNet adopts a dual-branch encoder that combines a CNN-based Local Detail Perception Branch with a Mamba-based Global Context Modeling Branch, enabling the joint extraction of fine-grained local features and long-range semantic representations.

Dengdi Sun, Long-Long Liu, Xiao-Wei Zhao et al. · 0 citations
Conference Aug 2026

PFT-Net: prototypes filtering and transformation for few-shot medical image segmentation

A Prototypes Filtering and Transformation Network (PFT-Net) to alleviate the intra-class variation problem and integrates the optimal transport algorithm to convert initially filtered support prototypes into query-adapted representations, allowing them to better align with the feature distribution of the query image.

Rui-Fa Zhou, Guo-Heng Huang, Lin-Hui Wu et al. · 0 citations
Open access Aug 2026

MGA-UNet: A Frequency-Aware Multi-Scale Mamba U-Net for Medical Image Segmentation

MGA-UNet, a frequency-aware multi-scale encoder–decoder segmentation framework that integrates wavelet-based frequency decomposition with Mamba-based long-range dependency modelling, demonstrates that frequency-domain decomposition and state-space modelling can complement each other for accurate medical image segmentat...

Shuai-Kang Qiu, Xuan Wang, Kai-Le Su et al. · 0 citations
Sep 2026

EPPNet: Edge Prototype Purification with Auxiliary Supervision for Few-Shot Medical Image Segmentation.

An Auxiliary Supervision-guided Edge Prototype Purification Network (EPPNet) is proposed, which introduces a novel Prototype Purification Module (PPM) and selectively integrates high-confidence edge prototypes via a learnable adaptive threshold, aiming to substantially alleviate boundary feature contamination.

Wen-Jie Meng, Kai Liu, Minghui Wang · 0 citations
Conference Aug 2026

AG-HFFNet: Attention-Guided Hierarchical Feature Fusion for Ultrasound Image Segmentation

Accurate ultrasound image segmentation is essential for computer-aided diagnosis, enabling reliable localization and characterization of anatomical structures and lesions. However, it remains challenging due to speckle noise, low contrast, and complex structural variations that hinder precise feature extraction. To add...

Sushmitha Heerekar, Y. Devi, Suresh Pabboju · 0 citations
Open access Aug 2026

Shared multi-branch framework and enhanced feature fusion for few-shot semantic segmentation

Experimental results demonstrate that the method significantly narrows the performance gap in data-constrained scenarios, achieving a mean Intersection over Union increase of 4.6% in one-shot and 5.5% in five-shot settings over the baseline.

Jin-Ming Guo, Li-Hsuan Chen, Yi-Chong Zeng et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.