TL;DR
This work presents a Hierarchical Spectral Attention Module which combines spectral linear attention with a frequency-aware pyramid to tackle challenges of segmentation and boundary preservation.
EdgeFormer-Med is proposed, a boundary-adaptive Transformer framework designed for precise segmentation of small and low-contrast anatomical structures in brain MRI that combines multi-scale feature representation with Transformer-based contextual modeling and an edge-guided attention mechanism to preserve fine boundar...
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.
Accurate segmentation of organs and lesions in medical images is essential for clinical applications such as diagnosis, prognosis, and treatment planning. Vision transformer (ViT)-based models have demonstrated strong performance in medical image segmentation by modeling long-range dependencies through self-attention m...
NAHFormer, a medical image segmentation framework equipped with boundary-aware and redundancy-aware capabilities, is proposed, which consistently outperforms state-of-the-art methods on colonoscopy polyp and dermoscopy datasets.
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...
WFDViM is proposed, a wavelet frequency-decoupled Vision Mamba framework for weak-boundary medical image segmentation that achieves the lowest mean HD95 and ASSD across all four datasets while requiring 13.06 M parameters and 3.05 GFLOPs.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
