MFDiff: multiscale feature diffusion model for segmentation of 3D intracranial aneurysm from CT images

doi:10.1007/s10044-024-01266-z

	MFDiff: multiscale feature diffusion model for segmentation of 3D intracranial aneurysm from CT images
	Pei, Xinyu 1; Ren, Yande 2; Tang, Yueshan 2; Wang, Yuanquan 1; Zhang, Lei 1; Wei, Jin 3; Zhao, Di 4
	2024-06-01
发表期刊	PATTERN ANALYSIS AND APPLICATIONS
ISSN	1433-7541
卷号	27 期号:2 页码:13
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.
关键词	Diffusion model Swin transformer CT Intracranial aneurysm Image segmentation
DOI	10.1007/s10044-024-01266-z
收录类别	SCI
语种	英语
资助项目	National Science Foundation of China[61976241] ; National Science Foundation of China (NSFC)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001227402600001
出版者	SPRINGER
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40091
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.