Real-time and multimodal brain slice-to-volume registration using CNN

作者：

Highlights：

• The CNN is used for multimodal slice-to-volume registration.

• The classification strategy for slice-to-volume registration is first proposed.

• Multimodal brain slice-to-volume registration can be achieved in real-time.

• The proposed method reduces the three dimensions of the parameter space.

• The proposed method achieves better than state-of-the-art methods.

摘要

•The CNN is used for multimodal slice-to-volume registration.•The classification strategy for slice-to-volume registration is first proposed.•Multimodal brain slice-to-volume registration can be achieved in real-time.•The proposed method reduces the three dimensions of the parameter space.•The proposed method achieves better than state-of-the-art methods.

论文关键词：Brain slice-to-volume registration,Convolutional neural network,System,Multimodal,Real-time

论文评审过程：Received 17 July 2018, Revised 24 April 2019, Accepted 13 May 2019, Available online 13 May 2019, Version of Record 18 May 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.05.016