Classification algorithms using multiple MRI features in mild traumatic brain injury.
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 stu...
| Publicado en: | Neurology Vol. 83; no. 14; pp. 1235 - 1241 |
|---|---|
| Autores principales: | , , , , , |
| Formato: | research Journal Article |
| Publicado: |
Lippincott Williams & Wilkins
9/30/2014
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=107802639&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 107802639 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 00283878 NRO jtl: Neurology issn: 00283878 maglogo: N pubinfo: dt: 9/30/2014 vid: 83 iid: 14 pid: 433 pub: Lippincott Williams & Wilkins place: Baltimore, Maryland artinfo: ui: 107802639 107802639 NLM25171930 2012749521 10.1212/WNL.0000000000000834 NLM25171930 PMC4180485 107802639 ppf: 1235 ppct: 6 formats: tig: atl: Classification algorithms using multiple MRI features in mild traumatic brain injury. aug: au: Lui, Yvonne W Xue, Yuanyi Kenul, Damon Ge, Yulin Grossman, Robert I Wang, Yao affil: 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. sug: subj: Classification Algorithms Brain Injuries Diagnosis Diagnosis, Computer Assisted Methods Magnetic Resonance Imaging Methods Adult Probability Brain Pathology Brain Physiopathology Brain Injuries Pathology Brain Injuries Physiopathology Female Human Male Pilot Studies Prospective Studies Sensitivity and Specificity Thalamus Pathology Thalamus Physiology Funding Source Adult: 19-44 years Female Male ab: 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. pubtype: Academic Journal doctype: research Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|