Automated pathological brain detection system: A fast discrete curvelet transform and probabilistic neural network based approach

作者：

Highlights：

• The proposed scheme can efficiently detect pathological brain in real-time.

• FDCT via wrapping scheme is employed to capture curve features from MR images.

• The proposed PBDS is validated on several benchmark datasets.

• The proposed scheme outperforms 21 existing competent schemes.

• It has a potential to be installed on medical robots.

摘要

•The proposed scheme can efficiently detect pathological brain in real-time.•FDCT via wrapping scheme is employed to capture curve features from MR images.•The proposed PBDS is validated on several benchmark datasets.•The proposed scheme outperforms 21 existing competent schemes.•It has a potential to be installed on medical robots.

论文关键词：Computer-aided diagnosis (CAD),Magnetic resonance imaging (MRI),Pulse-coupled neural network (PCNN),Fast discrete curvelet transform (FDCT),PCA+LDA,Probabilistic neural network (PNN)

论文评审过程：Received 17 December 2016, Revised 22 June 2017, Accepted 23 June 2017, Available online 4 July 2017, Version of Record 4 August 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.06.038