干旱区生态环境知识资源中心(Arid): GraformerDIR: Graph convolution transformer for deformable image registration

Arid

DOI	10.1016/j.compbiomed.2022.105799
	GraformerDIR: Graph convolution transformer for deformable image registration
	Yang, Tiejun; Bai, Xinhao; Cui, Xiaojuan; Gong, Yuehong; Li, Lei
通讯作者	Bai, XH
来源期刊	COMPUTERS IN BIOLOGY AND MEDICINE
ISSN	0010-4825
EISSN	1879-0534
出版年	2022
卷号	147
英文摘要	Purpose: Deformable image registration (DIR) plays an important role in assisting disease diagnosis. The emergence of the Transformer enables the DIR framework to extract long-range dependencies, which relieves the limitations of intrinsic locality caused by convolution operation. However, suffering from the interference of missing or spurious connections, it is a challenging task for Transformer-based methods to capture the highquality long-range dependencies.Methods: In this paper, by staking the graph convolution Transformer (Graformer) layer at the bottom of the feature extraction network, we propose a Graformer-based DIR framework, named GraformerDIR. The Graformer layer is consist of the Graformer module and the Cheby-shev graph convolution module. Among them, the Graformer module is designed to capture high-quality long-range dependencies. Cheby-shev graph convolution module is employed to further enlarge the receptive field.Results: The performance and generalizability of GraformerDIR have been evaluated on publicly available brain datasets including the OASIS, LPBA40, and MGH10 datasets. Compared with VoxelMorph, the GraformerDIR has obtained performance improvements of 4.6% in Dice similarity coefficient (DSC) and 0.055 mm in the average symmetric surface distance (ASD) while reducing the non-positive rate of Jacobin determinant (Npr.Jac) index about 60 times on publicly available OASIS dataset. On unseen dataset MGH10, the GraformerDIR has obtained the performance improvements of 4.1% in DSC and 0.084 mm in ASD compared with VoxelMorph, which demonstrates the GraformerDIR with better generalizability. The promising performance on the clinical cardiac dataset ACDC indicates the GraformerDIR is practicable.Conclusion: With the advantage of Transformer and graph convolution, the GraformerDIR has obtained comparable performance with the state-of-the-art method VoxelMorph.
英文关键词	Deformable image registration Graph convolution Transformer Long-range dependencies
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000827553000004
WOS关键词	LEARNING FRAMEWORK
WOS类目	Biology ; Computer Science, Interdisciplinary Applications ; Engineering, Biomedical ; Mathematical & Computational Biology
WOS研究方向	Life Sciences & Biomedicine - Other Topics ; Computer Science ; Engineering ; Mathematical & Computational Biology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/392188
推荐引用方式 GB/T 7714	Yang, Tiejun,Bai, Xinhao,Cui, Xiaojuan,et al. GraformerDIR: Graph convolution transformer for deformable image registration[J],2022,147.
APA	Yang, Tiejun,Bai, Xinhao,Cui, Xiaojuan,Gong, Yuehong,&Li, Lei.(2022).GraformerDIR: Graph convolution transformer for deformable image registration.COMPUTERS IN BIOLOGY AND MEDICINE,147.
MLA	Yang, Tiejun,et al."GraformerDIR: Graph convolution transformer for deformable image registration".COMPUTERS IN BIOLOGY AND MEDICINE 147(2022).