中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
MFDiff: multiscale feature diffusion model for segmentation of 3D intracranial aneurysm from CT images

文献类型:期刊论文

作者Pei, Xinyu1; Ren, Yande2; Tang, Yueshan2; Wang, Yuanquan1; Zhang, Lei1; Wei, Jin3; Zhao, Di4
刊名PATTERN ANALYSIS AND APPLICATIONS
出版日期2024-06-01
卷号27期号:2页码:13
关键词Diffusion model Swin transformer CT Intracranial aneurysm Image segmentation
ISSN号1433-7541
DOI10.1007/s10044-024-01266-z
英文摘要Intracranial aneurysm is a common life-threatening disease, and the rupture of an intracranial aneurysm carries a high risk of morbidity and mortality. Due to their small size in images, it remains a challenging task to accurately extract the intracranial aneurysms in CT images. In this paper, we propose a multi-scale feature diffusion model, named as MFDiff in short, for segmentation of 3D intracranial aneurysm. The proposed MFDiff includes a feature extraction module and a diffusion model. The feature extraction module is designed to extract features of the original image, and the features act as conditional priors to guide the diffusion model to gradually generate segmentation maps. The diffusion model takes a structure similar to U-Net as backbone, and there is a residual multi-scale feature fusion attention module (RMFA) in the diffusion model, which can adapt to intracranial aneurysms of different size due to multi-scale features. A local CT image dataset is employed for experiment, there are both ruptured and unruptured intracranial aneurysms in the images, and the size of intracranial aneurysms is various, even less than 3 mm. Compared with other popular methods, such as U-Net, GLIA-Net, UNETR++ , LinTransUNet, Swin UNETR, the proposed MFDiff shows better performance in intracranial aneurysm segmentation, the segmentation precision is 82.91% when the aneurysms of just size larger than 3 mm are taken into account, and the precision is 75.53% when considering aneurysms of all size.
资助项目National Science Foundation of China[61976241] ; National Science Foundation of China (NSFC)
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001227402600001
出版者SPRINGER
源URL[http://119.78.100.204/handle/2XEOYT63/40090]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Wang, Yuanquan; Zhang, Lei
作者单位1.Hebei Univ Technol HeBUT, Sch Artificial Intelligence, Tianjin 300401, Peoples R China
2.Qingdao Univ, Dept Radiol, Affiliated Hosp, Qingdao, Shandong, Peoples R China
3.Third Cent Hosp Tianjin, Tianjin 300171, Peoples R China
4.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Pei, Xinyu,Ren, Yande,Tang, Yueshan,et al. MFDiff: multiscale feature diffusion model for segmentation of 3D intracranial aneurysm from CT images[J]. PATTERN ANALYSIS AND APPLICATIONS,2024,27(2):13.
APA Pei, Xinyu.,Ren, Yande.,Tang, Yueshan.,Wang, Yuanquan.,Zhang, Lei.,...&Zhao, Di.(2024).MFDiff: multiscale feature diffusion model for segmentation of 3D intracranial aneurysm from CT images.PATTERN ANALYSIS AND APPLICATIONS,27(2),13.
MLA Pei, Xinyu,et al."MFDiff: multiscale feature diffusion model for segmentation of 3D intracranial aneurysm from CT images".PATTERN ANALYSIS AND APPLICATIONS 27.2(2024):13.

入库方式: OAI收割

来源:计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。