Cerebrovascular segmentation network based on fast fourier convolution and Mamba.
Saved in:
| Title: | Cerebrovascular segmentation network based on fast fourier convolution and Mamba. |
|---|---|
| Authors: | Yang C; School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, People's Republic of China.; College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, People's Republic of China., Cao M; College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, People's Republic of China., Zhu J; Department of Anesthesiology, Weifang People's Hospital, Weifang 261000, People's Republic of China., Liu P; College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, People's Republic of China., Qiao S; School of Software, Tiangong University, Tianjin 300387, People's Republic of China., Li Z; College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, People's Republic of China. |
| Source: | Biomedical physics & engineering express [Biomed Phys Eng Express] 2025 Oct 16; Vol. 11 (6). Date of Electronic Publication: 2025 Oct 16. |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: IOP Publishing Ltd Country of Publication: England NLM ID: 101675002 Publication Model: Electronic Cited Medium: Internet ISSN: 2057-1976 (Electronic) Linking ISSN: 20571976 NLM ISO Abbreviation: Biomed Phys Eng Express Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Bristol : IOP Publishing Ltd., [2015]- |
| MeSH Terms: | Magnetic Resonance Angiography*/methods , Fourier Analysis* , Image Processing, Computer-Assisted*/methods , Brain*/diagnostic imaging , Brain*/blood supply , Cerebrovascular Disorders*/diagnostic imaging, Humans ; Algorithms ; Neural Networks, Computer |
| Abstract: | Purpose. Cerebrovascular segmentation is crucial for the diagnosis and treatment of cerebrovascular diseases. However, accurately extracting cerebral vessels from Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) remains challenging due to the topological complexity and anatomical variability. Methods. This paper presents a novel Y-shaped segmentation network with fast Fourier convolution and Mamba, termed F-Mamba-YNet. The network employs a dual-encoder architecture that effectively leverages the complementarity of spectral and spatial domains for achieving the fusion of multi-level features. The spectral encoder features the Fast Fourier Convolution Module, which captures high-frequency changes in vessel edges, improving segmentation completeness and connectivity. The spatial encoder incorporates a Spatial Mamba Module, which captures long-range dependencies while enhancing the spatial feature representation of cerebral vessels. Additionally, a Multi-scale Feature Selection Module in the decoder adaptively enhances discriminative features, enabling improved feature reuse. Results. Experiments demonstrate that the proposed F-Mamba-YNet achieved 86.28% and 72.24% Dice Similarity Coefficient (DSC) on the IXI-A-SegAN dataset and MIDAS dataset. Conclusions. Compared with existing algorithms, F-Mamba-YNet provided more connected and continuous segmentation results and achieved competitive performance in terms of generalization. (© 2025 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.) |
| Contributed Indexing: | Keywords: 3D cerebrovascular segmentation; Mamba; TOF-MRA; fast fourier convolution; feature selection |
| Entry Date(s): | Date Created: 20250908 Date Completed: 20251016 Latest Revision: 20251016 |
| Update Code: | 20251016 |
| DOI: | 10.1088/2057-1976/ae0483 |
| PMID: | 40921181 |
| Database: | MEDLINE |
Nájsť tento článok vo Web of Science | Abstract: | Purpose. Cerebrovascular segmentation is crucial for the diagnosis and treatment of cerebrovascular diseases. However, accurately extracting cerebral vessels from Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) remains challenging due to the topological complexity and anatomical variability. Methods. This paper presents a novel Y-shaped segmentation network with fast Fourier convolution and Mamba, termed F-Mamba-YNet. The network employs a dual-encoder architecture that effectively leverages the complementarity of spectral and spatial domains for achieving the fusion of multi-level features. The spectral encoder features the Fast Fourier Convolution Module, which captures high-frequency changes in vessel edges, improving segmentation completeness and connectivity. The spatial encoder incorporates a Spatial Mamba Module, which captures long-range dependencies while enhancing the spatial feature representation of cerebral vessels. Additionally, a Multi-scale Feature Selection Module in the decoder adaptively enhances discriminative features, enabling improved feature reuse. Results. Experiments demonstrate that the proposed F-Mamba-YNet achieved 86.28% and 72.24% Dice Similarity Coefficient (DSC) on the IXI-A-SegAN dataset and MIDAS dataset. Conclusions. Compared with existing algorithms, F-Mamba-YNet provided more connected and continuous segmentation results and achieved competitive performance in terms of generalization.<br /> (© 2025 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.) |
|---|---|
| ISSN: | 2057-1976 |
| DOI: | 10.1088/2057-1976/ae0483 |