Resting-state magnetoencephalography source magnitude imaging with deep-learning neural network for classification of symptomatic combat-related mild traumatic brain injury

• Main Authors: Angeles-Quinto, A. (Author), Baker, D.G (Author), Cheng, C.-K (Author), Drake, A. (Author), Dynes, R. (Author), Foote, E. (Author), Hansen, H.B (Author), Harrington, D.L (Author), Huang, C.W (Author), Huang, J.W (Author), Huang, M.-X (Author), Ji, Z. (Author), Le, L. (Author), Lee, R.R (Author), Lerman, I. (Author), Matthews, S. (Author), Naviaux, R.K (Author), Nichols, S. (Author), Rimmele, C. (Author), Robb-Swan, A. (Author), Shen, Q. (Author), Song, T. (Author), Yurgil, K.A (Author)
• Format: Article
• Language: English
• Published: John Wiley and Sons Inc 2021
• Subjects: adult; Adult; Article; battle injury; brain concussion; Brain Concussion; clinical feature; Combat Disorders; connectome; Connectome; controlled study; deep learning; Deep Learning; Delis-Kaplan executive function system; delta rhythm; diagnostic accuracy; diagnostic imaging; diagnostic test accuracy study; female; gamma rhythm; human; Humans; machine learning; magnetoencephalography; Magnetoencephalography; major clinical study; male; Male; military service members; neuroimaging; neuropsychological test; neuropsychology; pathophysiology; posttraumatic stress disorder; priority journal; procedures; resting state magnetoencephalography; resting-state MEG; sensitivity and specificity; Sensitivity and Specificity; task performance; theta rhythm; three-dimensional imaging; traumatic brain injury; Veterans; Wechsler adult intelligence scale; young adult; Young Adult
• Online Access: View Fulltext in Publisher

 Combat-related mild traumatic brain injury (cmTBI) is a leading cause of sustained physical, cognitive, emotional, and behavioral disabilities in Veterans and active-duty military personnel. Accurate diagnosis of cmTBI is challenging since the symptom spectrum is broad and conventional neuroimaging techniques are insensitive to the underlying neuropathology. The present study developed a novel deep-learning neural network method, 3D-MEGNET, and applied it to resting-state magnetoencephalography (rs-MEG) source-magnitude imaging data from 59 symptomatic cmTBI individuals and 42 combat-deployed healthy controls (HCs). Analytic models of individual frequency bands and all bands together were tested. The All-frequency model, which combined delta-theta (1–7 Hz), alpha (8–12 Hz), beta (15–30 Hz), and gamma (30–80 Hz) frequency bands, outperformed models based on individual bands. The optimized 3D-MEGNET method distinguished cmTBI individuals from HCs with excellent sensitivity (99.9 ± 0.38%) and specificity (98.9 ± 1.54%). Receiver-operator-characteristic curve analysis showed that diagnostic accuracy was 0.99. The gamma and delta-theta band models outperformed alpha and beta band models. Among cmTBI individuals, but not controls, hyper delta-theta and gamma-band activity correlated with lower performance on neuropsychological tests, whereas hypo alpha and beta-band activity also correlated with lower neuropsychological test performance. This study provides an integrated framework for condensing large source-imaging variable sets into optimal combinations of regions and frequencies with high diagnostic accuracy and cognitive relevance in cmTBI. The all-frequency model offered more discriminative power than each frequency-band model alone. This approach offers an effective path for optimal characterization of behaviorally relevant neuroimaging features in neurological and psychiatric disorders. © 2021 The Authors. Human Brain Mapping published by Wiley Periodicals LLC.