Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Yao, Yang, Dong, Qiao, Zhi, Huang, Wenjian, Yang, Liuzhi, Qian, Zhen
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2509.01080
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911132065726464
author Wang, Yao
Yang, Dong
Qiao, Zhi
Huang, Wenjian
Yang, Liuzhi
Qian, Zhen
author_facet Wang, Yao
Yang, Dong
Qiao, Zhi
Huang, Wenjian
Yang, Liuzhi
Qian, Zhen
contents Abnormality detection in medical imaging is a critical task requiring both high efficiency and accuracy to support effective diagnosis. While convolutional neural networks (CNNs) and Transformer-based models are widely used, both face intrinsic challenges: CNNs have limited receptive fields, restricting their ability to capture broad contextual information, and Transformers encounter prohibitive computational costs when processing high-resolution medical images. Mamba, a recent innovation in natural language processing, has gained attention for its ability to process long sequences with linear complexity, offering a promising alternative. Building on this foundation, we present SpectMamba, the first Mamba-based architecture designed for medical image detection. A key component of SpectMamba is the Hybrid Spatial-Frequency Attention (HSFA) block, which separately learns high- and low-frequency features. This approach effectively mitigates the loss of high-frequency information caused by frequency bias and correlates frequency-domain features with spatial features, thereby enhancing the model's ability to capture global context. To further improve long-range dependencies, we propose the Visual State-Space Module (VSSM) and introduce a novel Hilbert Curve Scanning technique to strengthen spatial correlations and local dependencies, further optimizing the Mamba framework. Comprehensive experiments show that SpectMamba achieves state-of-the-art performance while being both effective and efficient across various medical image detection tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2509_01080
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SpectMamba: Integrating Frequency and State Space Models for Enhanced Medical Image Detection
Wang, Yao
Yang, Dong
Qiao, Zhi
Huang, Wenjian
Yang, Liuzhi
Qian, Zhen
Computer Vision and Pattern Recognition
Abnormality detection in medical imaging is a critical task requiring both high efficiency and accuracy to support effective diagnosis. While convolutional neural networks (CNNs) and Transformer-based models are widely used, both face intrinsic challenges: CNNs have limited receptive fields, restricting their ability to capture broad contextual information, and Transformers encounter prohibitive computational costs when processing high-resolution medical images. Mamba, a recent innovation in natural language processing, has gained attention for its ability to process long sequences with linear complexity, offering a promising alternative. Building on this foundation, we present SpectMamba, the first Mamba-based architecture designed for medical image detection. A key component of SpectMamba is the Hybrid Spatial-Frequency Attention (HSFA) block, which separately learns high- and low-frequency features. This approach effectively mitigates the loss of high-frequency information caused by frequency bias and correlates frequency-domain features with spatial features, thereby enhancing the model's ability to capture global context. To further improve long-range dependencies, we propose the Visual State-Space Module (VSSM) and introduce a novel Hilbert Curve Scanning technique to strengthen spatial correlations and local dependencies, further optimizing the Mamba framework. Comprehensive experiments show that SpectMamba achieves state-of-the-art performance while being both effective and efficient across various medical image detection tasks.
title SpectMamba: Integrating Frequency and State Space Models for Enhanced Medical Image Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.01080