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

Abstract

Objective. By detecting 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 a deep learning approach with diffusion MRI. Approach. In this study, the white matter structural connectivity was generated by tracking the white matter fibers in detail based on Q-ball imaging and neurite orientation dispersion and density imaging. 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. Main results. Our results showed: (a) Compared to normal control, the white matter’ neurite density of JME was significantly decreased. The most significantly abnormal fiber tracts between the two groups were found to be cortico-cortical connection tracts. (b) 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 the Inception_resnet_v2 network with a 16% transfer rate. Significance. The results revealed: (a) Through detection of the abnormal white matter changes, the white matter structural connectivity can be used as a useful biomarker for detecting JME, which helps to characterize the pathophysiology of epilepsy. (b) The proposed transfer rate, as a new hyperparameter, promotes the CNNs transfer learning performance in detecting JME.

Multilayer brain network modeling and dynamic analysis of juvenile myoclonic epilepsy

“…pathways connected to it but also affects the motor and somatosensory function (Li et al, 2020). The cuneus is usually considered to be responsible for visual functions, and it is the center of many long-range white matter fibers to support nonvisual functions (Si et al, 2021). In addition, the specific peripheral structures of the JME group are mostly located in 10.3389/fnbeh.2023.1123534 the prefrontal lobe and hippocampus.…”

Deep learning in neuroimaging of epilepsy

“…Table 1 summarize the studies that have proposed DL models to discriminate between individuals with epilepsy and healthy controls using T1/T2-weighted images [40,41], FLAIR images [42], DWI [41,43] and multimodal MRI [44].…”

“…Two studies [42,43] proposed DL models based on transfer learning with a high diagnostic accuracy of epilepsy. The first [42] used only axial slices of FLAIR sequence containing the hippocampus achieving an accuracy of 87%.…”

Computerized application for epilepsy in China: Does the era of artificial intelligence comes?

“…Similar to the above studies, Huang et al 91 predicted refractory pediatric epilepsy based on MRI and EEG characteristics by using a convolutional neural network with an accuracy of 88.1%. As for juvenile myoclonic epilepsy (JME), unlike a previous study that used functional connectivity to predict drug response, 8 Si et al 92 found that white matter structural connectivity can be a biomarker for detecting JME with the assistance of a transferred learning convolutional neural network model. For a better understanding of the pathological changes at a more microcosmic level, diffusion kurtosis images (DKIs) were applied as subjects fed to a convolutional neural network by Huang et al 93 With this approach, they achieved a 90.8% accuracy in identifying PWEs mixed with healthy controls.…”

“…Similar to the above studies, Huang et al 91 predicted refractory pediatric epilepsy based on MRI and EEG characteristics by using a convolutional neural network with an accuracy of 88.1%. As for juvenile myoclonic epilepsy (JME), unlike a previous study that used functional connectivity to predict drug response, 8 Si et al 92…”