A novel segmentation network, MDSF-Net, consisting of two key components: the Spatial-Mamba-Frequency Feature Block (SMFB) and the Hierarchical Semantic Link (HSL) module, which outperforms current state-of-the-art segmentation methods across key quantitative metrics.
Experiments demonstrate that GeoFuse-SAM, operating in a fully automatic prompt-free mode, not only maintains leading region segmentation accuracy, but also effectively suppresses the boundary degradation phenomenon of foundation models in grayscale modalities on the core boundary metric HD95.
Qi-Yuan Wang· Poster Volume 0007 The 2026...· 0 citations
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.
Yongkang Zhu, Tianyu Yu, Hongmei Li et al.· Journal of Imaging· 0 citations
SMG-Mamba provides a highly efficient and accurate solution for text-guided medical image segmentation by mapping specific modules to computational efficiency, boundary preservation, and deep semantic alignment, and successfully balances computational overhead with precise, fine-grained cross-modal feature fusion.
Rong-Tao Li, De-Dong Yang, Zi-Yang Li et al.· Multimedia Systems· 0 citations
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.· Italian National Conference...· 0 citations
A tri-stream interaction paradigm replacing symmetric skip connections with directional fusion among semantic, spatial, and decoder-propagated streams at each decoding stage, and a Global Prototype Bank that captures dataset-level anatomical regularities via attention-based retrieval and gated EMA updates, providing pe...
Mohammed A. M. Elhassan, Qian-Fa Yuan, Zhizhong Xu et al.· Journal of King Saud Univers...· 0 citations
CDGC-Net, a 3D medical image segmentation network that combines cooperative dual-scale spatial attention with grouped hierarchical channel modeling, achieves mean DSC values on the Synapse, ACDC, BraTS, and LA datasets, indicating a favorable trade-off between segmentation accuracy and computational complexity.
Zhe-Yang Jing, Qin Lu, Jianwang Li 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.
