Yvonne W Lui1, Yuanyi Xue2, Damon Kenul2, Yulin Ge2, Robert I Grossman2, Yao Wang2. 1. From the Department of Radiology (Y.W.L., D.K., Y.G., R.I.G.), New York University School of Medicine, New York; and Department of Electrical Engineering (Y.X., Y.W.), New York University Polytechnic School of Engineering, Brooklyn. Yvonne.lui@nyumc.org. 2. From the Department of Radiology (Y.W.L., D.K., Y.G., R.I.G.), New York University School of Medicine, New York; and Department of Electrical Engineering (Y.X., Y.W.), New York University Polytechnic School of Engineering, Brooklyn.
Abstract
OBJECTIVE: The purpose of this study was to develop an algorithm incorporating MRI metrics to classify patients with mild traumatic brain injury (mTBI) and controls. METHODS: This was an institutional review board-approved, Health Insurance Portability and Accountability Act-compliant prospective study. We recruited patients with mTBI and healthy controls through the emergency department and general population. We acquired data on a 3.0T Siemens Trio magnet including conventional brain imaging, resting-state fMRI, diffusion-weighted imaging, and magnetic field correlation (MFC), and performed multifeature analysis using the following MRI metrics: mean kurtosis (MK) of thalamus, MFC of thalamus and frontal white matter, thalamocortical resting-state networks, and 5 regional gray matter and white matter volumes including the anterior cingulum and left frontal and temporal poles. Feature selection was performed using minimal-redundancy maximal-relevance. We used classifiers including support vector machine, naive Bayesian, Bayesian network, radial basis network, and multilayer perceptron to test maximal accuracy. RESULTS: We studied 24 patients with mTBI and 26 controls. Best single-feature classification uses thalamic MK yielding 74% accuracy. Multifeature analysis yields 80% accuracy using the full feature set, and up to 86% accuracy using minimal-redundancy maximal-relevance feature selection (MK thalamus, right anterior cingulate volume, thalamic thickness, thalamocortical resting-state network, thalamic microscopic MFC, and sex). CONCLUSION: Multifeature analysis using diffusion-weighted imaging, MFC, fMRI, and volumetrics may aid in the classification of patients with mTBI compared with controls based on optimal feature selection and classification methods. CLASSIFICATION OF EVIDENCE: This study provides Class III evidence that classification algorithms using multiple MRI features accurately identifies patients with mTBI as defined by American Congress of Rehabilitation Medicine criteria compared with healthy controls.
OBJECTIVE: The purpose of this study was to develop an algorithm incorporating MRI metrics to classify patients with mild traumatic brain injury (mTBI) and controls. METHODS: This was an institutional review board-approved, Health Insurance Portability and Accountability Act-compliant prospective study. We recruited patients with mTBI and healthy controls through the emergency department and general population. We acquired data on a 3.0T Siemens Trio magnet including conventional brain imaging, resting-state fMRI, diffusion-weighted imaging, and magnetic field correlation (MFC), and performed multifeature analysis using the following MRI metrics: mean kurtosis (MK) of thalamus, MFC of thalamus and frontal white matter, thalamocortical resting-state networks, and 5 regional gray matter and white matter volumes including the anterior cingulum and left frontal and temporal poles. Feature selection was performed using minimal-redundancy maximal-relevance. We used classifiers including support vector machine, naive Bayesian, Bayesian network, radial basis network, and multilayer perceptron to test maximal accuracy. RESULTS: We studied 24 patients with mTBI and 26 controls. Best single-feature classification uses thalamic MK yielding 74% accuracy. Multifeature analysis yields 80% accuracy using the full feature set, and up to 86% accuracy using minimal-redundancy maximal-relevance feature selection (MK thalamus, right anterior cingulate volume, thalamic thickness, thalamocortical resting-state network, thalamic microscopic MFC, and sex). CONCLUSION: Multifeature analysis using diffusion-weighted imaging, MFC, fMRI, and volumetrics may aid in the classification of patients with mTBI compared with controls based on optimal feature selection and classification methods. CLASSIFICATION OF EVIDENCE: This study provides Class III evidence that classification algorithms using multiple MRI features accurately identifies patients with mTBI as defined by American Congress of Rehabilitation Medicine criteria compared with healthy controls.
Authors: Jonathan D Power; Kelly A Barnes; Abraham Z Snyder; Bradley L Schlaggar; Steven E Petersen Journal: Neuroimage Date: 2011-10-14 Impact factor: 6.556
Authors: Lin Tang; Yulin Ge; Daniel K Sodickson; Laura Miles; Yongxia Zhou; Joseph Reaume; Robert I Grossman Journal: Radiology Date: 2011-07-20 Impact factor: 11.105
Authors: Paul McMahon; Allison Hricik; John K Yue; Ava M Puccio; Tomoo Inoue; Hester F Lingsma; Sue R Beers; Wayne A Gordon; Alex B Valadka; Geoffrey T Manley; David O Okonkwo Journal: J Neurotrauma Date: 2013-10-31 Impact factor: 5.269
Authors: Laura Miles; Robert I Grossman; Glyn Johnson; James S Babb; Leonard Diller; Matilde Inglese Journal: Brain Inj Date: 2008-02 Impact factor: 2.311
Authors: Jens H Jensen; Kamila Szulc; Caixia Hu; Anita Ramani; Hanzhang Lu; Liang Xuan; Maria F Falangola; Ramesh Chandra; Edmond A Knopp; John Schenck; Earl A Zimmerman; Joseph A Helpern Journal: Magn Reson Med Date: 2009-02 Impact factor: 4.668
Authors: Shervin Minaee; Yao Wang; Alp Aygar; Sohae Chung; Xiuyuan Wang; Yvonne W Lui; Els Fieremans; Steven Flanagan; Joseph Rath Journal: IEEE Trans Med Imaging Date: 2019-03-18 Impact factor: 10.048
Authors: Arman Eshaghi; Viktor Wottschel; Rosa Cortese; Massimiliano Calabrese; Mohammad Ali Sahraian; Alan J Thompson; Daniel C Alexander; Olga Ciccarelli Journal: Neurology Date: 2016-11-02 Impact factor: 9.910
Authors: Shervin Minaee; Yao Wang; Anna Choromanska; Sohae Chung; Xiuyuan Wang; Els Fieremans; Steven Flanagan; Joseph Rath; Yvonne W Lui Journal: Annu Int Conf IEEE Eng Med Biol Soc Date: 2018-07
Authors: David B Douglas; Michael Iv; Pamela K Douglas; Ariana Anderson; Sjoerd B Vos; Roland Bammer; Michael Zeineh; Max Wintermark Journal: Top Magn Reson Imaging Date: 2015-10
Authors: Andrew R Mayer; Faith M Hanlon; Andrew B Dodd; Josef M Ling; Stefan D Klimaj; Timothy B Meier Journal: Hum Brain Mapp Date: 2015-08-19 Impact factor: 5.038
Authors: Hannah M Lindsey; Cooper B Hodges; Kaitlyn M Greer; Elisabeth A Wilde; Tricia L Merkley Journal: Neuropsychol Rev Date: 2021-03-15 Impact factor: 6.940