干旱区生态环境知识资源中心(Arid): Reverse-Net: Few-Shot Learning with Reverse Teaching for Deformable Medical Image Registration

Arid

DOI	10.3390/app13021040
	Reverse-Net: Few-Shot Learning with Reverse Teaching for Deformable Medical Image Registration
	Zhang, Xin; Yang, Tiejun; Zhao, Xiang; Yang, Aolin
通讯作者	Yang, TJ
来源期刊	APPLIED SCIENCES-BASEL
EISSN	2076-3417
出版年	2023
卷号	13 期号:2
英文摘要	Multimodal medical image registration has an important role in monitoring tumor growth, radiotherapy, and disease diagnosis. Deep-learning-based methods have made great progress in the past few years. However, its success depends on large training datasets, and the performance of the model decreases due to overfitting and poor generalization when only limited data are available. In this paper, a multimodal medical image registration framework based on few-shot learning is proposed, named reverse-net, which can improve the accuracy and generalization ability of the network by using a few segmentation labels. Firstly, we used the border enhancement network to enhance the ROI (region of interest) boundaries of T1 images to provide high-quality data for the subsequent pixel alignment stage. Secondly, through a coarse registration network, the T1 image and T2 image were roughly aligned. Then, the pixel alignment network generated more smooth deformation fields. Finally, the reverse teaching network used the warped T1 segmentation labels and warped images generated by the deformation field to teach the border enhancement network more structural knowledge. The performance and generalizability of our model have been evaluated on publicly available brain datasets including the MRBrainS13DataNii-Pro, SRI24, CIT168, and OASIS datasets. Compared with VoxelMorph, the reverse-net obtained performance improvements of 4.36% in DSC on the publicly available MRBrainS13DataNii-Pro dataset. On the unseen dataset OASIS, the reverse-net obtained performance improvements of 4.2% in DSC compared with VoxelMorph, which shows that the model can obtain better generalizability. The promising performance on dataset CIT168 indicates that the model is practicable.
英文关键词	multimodal registration few-shot learning generalizability reverse teaching
类型	Article
语种	英语
开放获取类型	gold
收录类别	SCI-E
WOS记录号	WOS:000914339100001
WOS关键词	FRAMEWORK
WOS类目	Chemistry, Multidisciplinary ; Engineering, Multidisciplinary ; Materials Science, Multidisciplinary ; Physics, Applied
WOS研究方向	Chemistry ; Engineering ; Materials Science ; Physics
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/395358
推荐引用方式 GB/T 7714	Zhang, Xin,Yang, Tiejun,Zhao, Xiang,et al. Reverse-Net: Few-Shot Learning with Reverse Teaching for Deformable Medical Image Registration[J],2023,13(2).
APA	Zhang, Xin,Yang, Tiejun,Zhao, Xiang,&Yang, Aolin.(2023).Reverse-Net: Few-Shot Learning with Reverse Teaching for Deformable Medical Image Registration.APPLIED SCIENCES-BASEL,13(2).
MLA	Zhang, Xin,et al."Reverse-Net: Few-Shot Learning with Reverse Teaching for Deformable Medical Image Registration".APPLIED SCIENCES-BASEL 13.2(2023).