eprintid: 13991
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/39/91
datestamp: 2023-11-10 03:28:33
lastmod: 2023-11-10 03:28:33
status_changed: 2023-11-10 01:52:28
type: article
metadata_visibility: show
creators_name: Rasheed, W.
creators_name: Tang, T.B.
title: Anomaly Detection of Moderate Traumatic Brain Injury Using Auto-Regularized Multi-Instance One-Class SVM
ispublished: pub
keywords: Brain; Brain mapping; Decision making; Diagnosis; Learning systems; Magnetic resonance imaging; Magnetoencephalography; Support vector machines, Brain activity patterns; Clinical decision making; Detection and quantifications; Magnitude squared coherences; Neural imaging; Neurorehabilitation; One-class support vector machine; Traumatic Brain Injuries, Anomaly detection, adult; amnesia; Article; clinical article; consciousness; controlled study; diagnostic test accuracy study; female; Glasgow coma scale; histogram; human; machine learning; magnetoencephalography; magnetometry; male; mathematical model; nerve cell network; nuclear magnetic resonance imaging; one class support vector machine; outlier detection; performance; sensitivity and specificity; traumatic brain injury; adolescent; algorithm; automation; beta rhythm; brain; diagnostic imaging; factual database; nerve tract; pathophysiology; support vector machine; traumatic brain injury; young adult, Adolescent; Adult; Algorithms; Automation; Beta Rhythm; Brain; Brain Injuries, Traumatic; Databases, Factual; Female; Glasgow Coma Scale; Humans; Magnetic Resonance Imaging; Magnetoencephalography; Male; Neural Pathways; Sensitivity and Specificity; Support Vector Machine; Young Adult
note: cited By 15
abstract: Detection and quantification of functional deficits due to moderate traumatic brain injury (mTBI) is crucial for clinical decision-making and timely commencement of functional therapy. In this work, we explore magnetoencephalography (MEG) based functional connectivity features i.e. magnitude squared coherence (MSC) and phase lag index (PLI) to quantify synchronized brain activity patterns as a means to detect functional deficits. We propose a multi-instance one-class support vector machine (SVM) model generated from a healthy control population. Any dispersion from the decision boundary of the model would be identified as an anomaly instance of mTBI case (Glasgow Coma Scale, GCS score between 9 and 13). The decision boundary was optimized by considering the closest anomaly (GCS =13) from the negative class as a support vector. Validated against magnetic resonance imaging (MRI) data, the proposed model at high beta band yielded an accuracy of 94.19 and a sensitivity of 90.00, when tested with our mTBI dataset. The results support the suggestion of multi-instance one-class SVM for the detection of mTBI. © 2001-2011 IEEE.
date: 2020
publisher: Institute of Electrical and Electronics Engineers Inc.
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85078348215&doi=10.1109%2fTNSRE.2019.2948798&partnerID=40&md5=d4a3bb30c0f85fc80fda5d5dd0cd2a50
id_number: 10.1109/TNSRE.2019.2948798
full_text_status: none
publication: IEEE Transactions on Neural Systems and Rehabilitation Engineering
volume: 28
number: 1
pagerange: 83-93
refereed: TRUE
issn: 15344320
citation:   Rasheed, W. and Tang, T.B.  (2020) Anomaly Detection of Moderate Traumatic Brain Injury Using Auto-Regularized Multi-Instance One-Class SVM.  IEEE Transactions on Neural Systems and Rehabilitation Engineering, 28 (1).  pp. 83-93.  ISSN 15344320