Convolutional neural networks for skull-stripping in brain MR imaging using silver standard masks

作者：

Highlights：

• Validation of silver standard masks for skull-strippping CNN training.

• First deep-learning-based method to be fully trained with silver standard masks.

• Elimination of the cost associated with manual annotation.

• Our proposed method is generalizable.

• We have a completely open-source code and will be made publicly available.

摘要

•Validation of silver standard masks for skull-strippping CNN training.•First deep-learning-based method to be fully trained with silver standard masks.•Elimination of the cost associated with manual annotation.•Our proposed method is generalizable.•We have a completely open-source code and will be made publicly available.

论文关键词：Silver standard masks,Convolutional neural network (CNN),Skull-stripping,Data augmentation

论文评审过程：Received 27 August 2018, Revised 16 June 2019, Accepted 30 June 2019, Available online 23 July 2019, Version of Record 30 July 2019.

论文官网地址：https://doi.org/10.1016/j.artmed.2019.06.008