Skip to content
Log in
Open access

Uncertainty-guided mamba network for efficient medical image segmentation with evidential deep learning.

Siqin Sun Chihui Long Xingbo Dong Zilu Ming Yiqing Tan Peng Ruan
Jul 2026 · Scientific Reports · 0 citations
Medicine

TL;DR

This work proposes an uncertainty-aware efficient segmentation framework synergizing Mamba state-space models with evidential deep learning, employing a 2D-adapted selective state-space mechanism to capture long-range dependencies with linear complexity O(L), overcoming transformers' quadratic scaling.

Abstract

Medical image segmentation requires balancing accuracy, computational efficiency, and uncertainty quantification for potential clinical deployment. Transformer-based architectures achieve superior performance through global context modeling but demand prohibitive computational resources (>20 GFLOPs), while lightweight convolutional networks sacrifice accuracy due to limited receptive fields. We propose an uncertainty-aware efficient segmentation framework synergizing Mamba state-space models with evidential deep learning. Our method employs a 2D-adapted selective state-space mechanism (cross-scan over four directions) to capture long-range dependencies with linear complexity O(L), overcoming transformers' quadratic scaling. The uncertainty-guided attention module (UGAM) leverages Dirichlet-parameterized evidential learning to decompose epistemic and aleatoric uncertainty, adaptively recalibrating features through spatial-channel attention conditioned on prediction confidence. Progressive multi-scale fusion with gradient-based uncertainty supervision enhances boundary delineation and calibration. Experiments on five 2D benchmarks show competitive performance: 82.67% mean Dice on Synapse (1.46% improvement over Swin-UNet, and competitive with state-space peers U-Mamba and Swin-UMamba retrained under the same 2D protocol) with only 7.8M parameters and 4.7 GFLOPs-representing [Formula: see text] parameter reduction and [Formula: see text] efficiency gain. Real-time inference at 37.2 FPS with well-calibrated uncertainty (Expected Calibration Error: 0.046) supports further evaluation of its potential value for time-sensitive clinical workflow analysis rather than direct clinical deployment. A small, single-center reader study using 150 ACDC cases and three radiologists suggested that uncertainty visualization may be associated with improved reader confidence (22.2%) and reduced decision time (18.6%); these exploratory findings require prospective, multi-reader, multi-scanner validation. We explicitly do not claim generalization to 3D volumes, high-resolution pathology, multi-phase CT/MRI, or severe class-imbalance regimes, which are left to future work.

DOI PubMed Semantic Scholar
Read PDF

Similar papers

Review Open access Jul 2026

Uncertainty Quantification in Medical Image Segmentation: A Comprehensive Survey

A comprehensive survey of UQ techniques in medical image segmentation is presented, categorizing existing approaches into Bayesian methods, deep ensembles, deterministic methods, test-time data augmentation, and hybrid models, while treating foundation-model-based UQ as a separate cross-cutting category.

Seyed Sina Ziaee, K. Ovens · 0 citations
Conference Jul 2026

Uncertainty-Quantified Mamba Architecture for Medical Image Classification

Although deep learning models achieve strong performance in medical image analysis, their clinical adoption is often limited by the lack of reliable uncertainty information and high computational costs. In this work, we propose UQ-Mamba, a novel architecture that integrates uncertainty quantification within state space models. By leveraging the linear-time complexity of Mamba blocks, the proposed approach produces efficient and well-calibrated probabilistic predictions. On the OrganMNIST dataset, UQ-Mamba achieves 89.79% test accuracy with low calibration error (ECE = 0.0202), while providing approximately 3.5× better calibration than ResNet-50 using only 466K parameters. These results demonstrate that UQ-Mamba offers a reliable and efficient solution for resource-constrained clinical environments.

Ali Güneş, Ersin Çine, Maksut Samet Çopuroğlu · 0 citations
Open access Jul 2026

Bidirectional Mamba and routing-attention synergistic network for efficient medical image segmentation

Based on U-shaped architecture for medical image segmentation faces three fundamental challenges limiting clinical deployment: (1) architectural homogeneity problems where uniform mechanism deployment overlooks distinct encoder-decoder requirements, (2) skip connection feature fusion limitations with insufficient spatial-channel attention integration, and (3) computational efficiency vs . performance trade-offs. We propose a heterogeneous U-shaped architecture that strategically deploys specialized mechanisms based on component-specific functional requirements. Our approach utilizes Vision Mamba with Non-causal State Space Duality (VSSD) in encoder/bottleneck for efficient global context extraction, Bi-Level Routing Attention (BRA) in decoder for adaptive detail recovery, and introduces Spatial-Channel Synergistic Attention (SCSA) in skip connections to optimize multi-scale feature integration with only 0.01M additional parameters. Extensive experiments across four diverse datasets demonstrate exceptional performance: for example on Synapse dataset, our model achieves 84% Dice Similarity Coefficient and 13.76 mm Hausdorff Distance with only 23.43M parameters. Details are available on https://github.com/Yuyan-Bin/Synergistic-Network .

Bo Li, YU Bin, Haijun Li et al. · 0 citations
Open access Aug 2026

WVM-UNet: A Wavelet–Vision Mamba Framework for Enhanced Medical Image Segmentation

Accurate segmentation of skin lesions and gastrointestinal polyps is essential for early diagnosis and treatment planning. Currently, Convolutional Neural Networks (CNNs) are limited by local receptive fields, missing small lesions. While Transformers model global context, their quadratic computational complexity incurs high costs. To address these limitations, we propose the Wavelet–Vision Mamba UNet (WVM-UNet), integrating State Space Models (SSMs) for linear-complexity long-range dependencies and wavelet transforms for fine-grained feature extraction. The network employs a Wavelet-based Residual State Space (WRSS) block, combining the multi-scale decomposition of discrete wavelet transforms with Vision Mamba to efficiently capture global features. A Fused Channel–Spatial Attention (FCSA) mechanism is incorporated to adaptively recalibrate feature representations. Additionally, we construct an Encoder–Decoder Semantic Connection (EDSC) to replace traditional skip connections, effectively bridging the semantic gap between cross-level features. Experimental results on multiple public datasets demonstrate the competitive performance of our method. Specifically, on the ISIC 2017 dataset, WVM-UNet achieves an mIoU of 82.94% and a DSC of 90.67%, outperforming the Mamba-based VM-UNet by 2.71% in mIoU. These results indicate our architecture effectively captures discriminative features for precise medical image segmentation.

Yulong Yang, Wenchao Gao, Zhen-Sen Wu et al. · 0 citations