Leap-mamba: locality-enhanced feature calibration with pixel-region dual-stream vision mamba UNet for medical image segmentation

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

DIG-MambaNet: A Dual-Path Interactive Guided Mamba Network for Medical Image Segmentation

Reliable medical image segmentation remains challenging because models must preserve fine boundary details while maintaining global semantic consistency. CNNs capture local structures effectively but have limited long-range modeling ability, whereas Transformer-based methods improve global context at high computational cost. Mamba-based state space models offer efficient long-range modeling, but may weaken high-frequency textures and boundary cues. To address these limitations, we propose DIG-MambaNet, a Dual-path Interactive Guided Mamba Network for medical image segmentation. The network introduces a dual-path complementary modeling block (DCM Block), where a cross-feature spatial interaction module (CSIM) adaptively integrates CNN-based local features and Mamba-based global features. A source image-guided module (SIGM) injects high-frequency information from the original image to compensate for downsampling-induced detail loss, while an inter-layer detail refinement fusion module (IDRFM) improves encoder–decoder feature alignment during reconstruction. Experiments on 2018DSB, ISIC2018, JSUAH-Cerebellum, and CVC-ClinicDB, covering nuclei segmentation in microscopy images, skin lesion segmentation in dermoscopic images, fetal cerebellum segmentation in ultrasound images, and polyp segmentation in colonoscopy images, demonstrate that DIG-MambaNet achieves consistent and competitive performance across diverse target structures and imaging conditions, with improved boundary delineation and favorable overlap-based accuracy compared with representative CNN-, Transformer-, and Mamba-based methods.

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.

MamNet-PT: A Mamba-enhanced hybrid architecture with selective state-space modeling for uncertainty-aware brain tumor segmentation

Precise segmentation of brain tumors from MRI remains a challenging problem in medical image analysis because tumor regions exhibit substantial size variability, diffuse and infiltrative boundaries, and severe foreground-background imbalance. To address these challenges, we propose MamNet-PT, a hybrid segmentation architecture that integrates efficient long-range dependency modeling, multi-resolution feature aggregation, and uncertainty-aware prediction within a unified framework. First, a selective state-space model is embedded into the U-Net-based feature pathway to capture long-range spatial dependencies with linear computational complexity, which is particularly important for irregular and spatially extended tumor regions. Second, a pre-trained ResNet-50 encoder is used to improve feature robustness under limited annotated medical data. Third, a gated feature interaction mechanism adaptively balances Mamba-derived global contextual features and CNN-derived local boundary features, avoiding simple feature concatenation or uncontrolled module stacking. In addition, a multi-resolution pyramid fusion module strengthens scale-aware representation of small enhancing foci and extensive edema, while Monte Carlo Dropout-based uncertainty estimation provides spatial confidence maps for retrospective confidence characterization and failure-mode analysis. On the BraTS2020 benchmark, MamNet-PT achieves a Dice score of 96.7% and an Intersection over Union of 95.4%, outperforming representative CNN-Transformer and Mamba-based segmentation baselines. Ablation experiments further confirm that the performance gain is attributable to the complementary effects of selective state-space modeling, gated global-local fusion, multi-resolution aggregation, and uncertainty-aware inference. These results suggest that MamNet-PT is a promising research framework for accurate and efficient brain tumor segmentation under retrospective benchmark evaluation.

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

Medical image segmentation is a critical task in computer-assisted diagnosis, but accurate delineation remains challenging in sensor-captured dermoscopic and endoscopic images because of low contrast, blurred boundaries, acquisition artifacts, and large appearance variations. Although CNN-based methods are effective in capturing local texture and boundary cues, they often struggle to explicitly model long-range dependencies and global structural relationships. Transformer-based architectures can capture global context, but their self-attention mechanism may become computationally costly when processing high-resolution feature maps. To address these challenges, we propose MGA-UNet, a frequency-aware multi-scale encoder–decoder segmentation framework that integrates wavelet-based frequency decomposition with Mamba-based long-range dependency modelling. Specifically, the Wavelet-Mamba feature extraction backbone (WMB) decomposes features into low- and high-frequency components to enhance boundary-aware representation, the Gated Multi-scale Aggregation Module (GMAM) aggregates parallel multi-scale encoder features and applies a content-dependent gate to the fused response, and the Adaptive Sparse Attention Module (ASAM) refines bottleneck representations with sparse attention for global semantic modelling. Across three independent runs with random seeds 42, 123, and 2026, MGA-UNet achieves mean Dice Similarity Coefficients of 88.92±0.04%, 88.01±0.07%, and 85.91±0.04% on ISIC2018, ISIC2017, and Kvasir-SEG, respectively. These results demonstrate competitive segmentation performance among the compared representative CNN-based, Transformer-based, and Mamba-based methods, including the recent H-VMUNet baseline. These results indicate that frequency-domain decomposition and state-space modelling can complement each other for accurate medical image segmentation, particularly in images with ambiguous boundaries and complex background interference.

PM-DUnet: Fusing long-range dependencies and attention in a dual-U architecture for thyroid nodule segmentation

For medical image segmentation, accurately balancing local details and global long-range dependencies is critical to tackling thyroid nodule challenges (variable sizes, ambiguous boundaries, complex context). Traditional CNNs excel at local feature extraction but are constrained by local receptive fields, hindering efficient global dependency modeling. To address this, we propose a Parallel Mamba Dual-U Network (PM-DUNet). It adopts a cascaded dual U-Net encoder-decoder for two-stage “coarse-to-fine” segmentation refinement. We design a Multi-Path Parallel Mamba (MPM) module—using State Space Models (SSMs)—to efficiently model global context with linear complexity. Additionally, Squeeze-Excitation Downsampling (SED) and Spatial Attention Upsampling (SAU) modules are integrated to adaptively enhance key features in encoding/decoding. Results show PM-DUNet achieves highly competitive performance and outperforms state-of-the-art methods on most core metrics, verifying its effectiveness and robustness for complex medical image segmentation. Our code is available on https://github.com/Andrevict/MPDUNet.