White matter structural connectivity as a biomarker for detecting juvenile myoclonic epilepsy by transferred deep convolutional neural networks with varying transfer rates.

Researchers

Journal

Modalities

Models

Abstract

By detecting the abnormal white matter changes, diffusion magnetic resonance imaging (MRI) contributes to the detection of juvenile myoclonic epilepsy (JME). In addition, deep learning has greatly improved the detection performance of various brain disorders. However, there is almost no previous study effectively detecting JME by deep learning approach with diffusion MRI.In this study, the white matter structural connectivity was generated by tracking the white matter fibers in detail based on Q-ball imaging (QBI) and neurite orientation dispersion and density imaging (NODDI). Four advanced deep convolutional neural networks (CNNs) were deployed by using the transfer learning approach, in which the transfer rate searching strategy was proposed to achieve the best detection performance.Our results showed: (1) Compared to normal control (NC), white matter’s neurite density of JME was significantly decreased. And the most significantly abnormal fiber tracts between two groups were found to be cortico-cortical connection tracts. (2) The proposed transfer rate searching approach contributed to find each CNN’s best performance, in which the best JME detection accuracy of 92.2% was achieved by using Inception_resnet_v2 network with a 16% transfer rate.The results revealed: (1) By detecting the abnormal white matter changes, the white matter structural connectivity is a useful biomarker for detecting JME, which helps to character the pathophysiology of epilepsy. (2) The proposed transfer rate, as a new hyper-parameter, promotes the CNNs’ transfer learning performance on detecting JME.© 2021 IOP Publishing Ltd.