A Parallel Mamba Dual-U Network that adopts a cascaded dual U-Net encoder-decoder for two-stage “coarse-to-fine” segmentation refinement and outperforms state-of-the-art methods on most core metrics, verifying its effectiveness and robustness for complex medical image segmentation.
Abstract
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.
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.
Polyp segmentation in colonoscopy images plays a pivotal role in computer-aided medical diagnosis and the early prevention of colorectal cancer. However, existing methods often suffer from performance degradation when confronted with extreme polyp scale variation and polyp boundary ambiguity. To address these challenges, we propose the Staged Global-to-Local Cross-Scale Fusion Network (SGLF-Net), which adopts a novel staged global-to-local learning paradigm to progressively refine segmentation from coarse global semantics to fine-grained local details. Specifically, the Global Semantic Perception Stage integrates a Swin Transformer Encoder and a Dynamic Attentive Decoder (DAD) to construct comprehensive multi-scale contextual representations. The Local Detail Refinement Stage employs an Edge-aware Dynamic Attentive Decoder (E-DAD) to enhance structural fidelity and boundary precision through explicit edge-guided supervision. Furthermore, we introduce the Cross Spatial-Scale Feature Aggregation and Reconstitution (CSSAR) module, equipped with hybrid attention mechanisms, to facilitate efficient semantic structural interaction between the two cascaded stages. Extensive experiments on five public benchmark datasets demonstrate that SGLF-Net consistently outperforms state-of-the-art methods in both segmentation accuracy and boundary preservation.
Tan Guo, Wen-Han Zhang, Fu-Lin Luo et al.· IEEE journal of biomedical a...· 0 citations
Accurate segmentation of colorectal polyps in colonoscopy images is crucial for the early detection and prevention of colorectal cancer (CRC). However, polyp segmentation remains challenging due to variations in size, shape, texture, and boundary ambiguity caused by specular highlights, motion blur, and low contrast. In this paper, we propose MambaPolyp, a novel encoder‐decoder architecture that integrates efficient long‐sequence modeling, multi‐scale context aggregation, and fine boundary enhancement for precise colorectal polyp segmentation. The core component of our design is the MambaGate module, which leverages dynamic state‐space models (SSMs) to capture long‐range dependencies in spatial features while adaptively gating irrelevant context. To enhance multi‐scale semantic understanding, we incorporate an atrous spatial pyramid pooling (ASPP) module at the bottleneck, enabling the model to aggregate features from varying receptive fields. The decoder is equipped with a Multi‐Mamba refinement mechanism, where stacked MambaBlocks progressively refine the fused features at each resolution level. A Boundary‐Refinement Module is introduced to sharpen the polyp edges and improve boundary localization. Furthermore, a deep supervision strategy is adopted across multiple decoder stages to guide training with rich hierarchical information. The model is evaluated on five benchmark datasets, Kvasir‐SEG, CVC‐ClinicDB, CVC‐ColonDB, ETIS‐Larib, and CVC‐300, demonstrating that MambaPolyp outperforms several state‐of‐the‐art (SOTA) segmentation models in terms of Dice coefficient, Intersection over Union (IoU), and boundary‐based metrics, while maintaining lower computational efficiency, making it suitable for real‐time clinical applications during colonoscopy.
Manoj Kumar Singh, Satish Chand, K. Sahu· International journal of ima...· 0 citations
Accurate segmentation of thyroid nodules in ultrasound images is essential for thyroid cancer risk assessment and computer-aided diagnosis, yet remains challenging due to ambiguous boundaries and significant shape variations. Existing convolutional neural network (CNN)-based methods effectively capture local features but are limited in modeling long-range dependencies and complex boundary structures. To address these limitations, we propose SAFM-Net, a dual-branch CNN–GNN Network that integrates synergistic attention and frequency-domain modulation. The network adopts a dual-branch encoder, where a graph-based branch leverages a synergistic-attention dynamic graph convolution (SA-DGC) module to adaptively model global relationships among feature nodes, enhancing structural and boundary representation. In parallel, a CNN branch captures local textures and fine-grained details. To fuse complementary features, a frequency-domain modulation (FDM) module is introduced to enable cross-branch interaction and hierarchical integration, improving feature representation capability. Extensive experiments on the DDTI and TN3K datasets demonstrate the effectiveness of the proposed method. Compared with GED-Net, SAFM-Net achieves improvements of 0.54%, 1.00%, 1.68%, and 0.73% in terms of Accuracy, Dice, IoU, and Precision, respectively, on the DDTI dataset, and improvements of 0.17%, 0.43%, 0.67%, and 1.48% in terms of Accuracy, Dice, IoU, and Precision, respectively, on the TN3K dataset. These results indicate that SAFM-Net provides accurate and robust segmentation performance under challenging ultrasound imaging conditions.
Xi-Cheng Fu, Jing-Yao Lei, Qiang Wang et al.· Journal of Electronic Imagin...· 0 citations
GTUNet is proposed, a novel hybrid framework that synergistically integrates Graph Attention Networks, Transformers, and UNet for robust 3D medical image segmentation and significantly outperforms existing methods in ASSD, highlighting its precision in delineating vascular boundaries.
Mengjun Sheng, Shan-Shan He, Zhiyu Shi· Signal, Image and Video Proc...· 0 citations
U-Net remains a practical baseline for image segmentation because of its simple encoder-decoder structure and skip connections. However, the bottleneck representation is still dominated by a limited set of receptive fields, while decoder features are propagated without explicitly emphasizing the most informative channels and spatial locations. This paper presents MSCA-UNet, a U-Net-based segmentation architecture that combines multi-scale contextual aggregation at the bottleneck with channel-spatial attention refinement in the decoder. The multi-scale module uses parallel atrous convolutions to capture contextual features at different receptive fields, while Convolutional Block Attention Modules (CBAMs) progressively recalibrate decoder features. Under identical experimental settings, the baseline U-Net achieves 96.9% mIoU on a held-out test set. Adding multi-scale context improves mIoU to 97.5%, while attention alone reaches 98.4%. Combining both mechanisms yields 99.1% mIoU, a 2.2 percentage-point improvement over the baseline. Parameter analysis further shows that the attention-only variant adds approximately 0.044M parameters, whereas the multi-scale module contributes most of the additional model capacity. The results support the view that multi-scale context enrichment and attention-based feature refinement provide complementary benefits within a U-Net framework.
Sheng-Wei Chan· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
