Detection of early stages of Alzheimer’s disease based on MEG activity with a randomized convolutional neural network

作者：

Highlights：

• Novel method based on a 2D-CNN randomized ensemble model.

• State-of-the-art results for the early detection of Alzheimer's disease.

• Better detection results than classic machine learning methods.

• The proposed model handles noisy and scarce training data.

• Application of a 2D-CNN to time-series of MEG activity.

摘要

•Novel method based on a 2D-CNN randomized ensemble model.•State-of-the-art results for the early detection of Alzheimer's disease.•Better detection results than classic machine learning methods.•The proposed model handles noisy and scarce training data.•Application of a 2D-CNN to time-series of MEG activity.

论文关键词：Alzheimer’s disease detection,Deep learning,Convolutional neural network,Ensemble model,Magnetoencephalography

论文评审过程：Received 16 January 2020, Revised 27 April 2020, Accepted 1 July 2020, Available online 2 July 2020, Version of Record 9 July 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2020.101924