Arman Eshaghi1, Viktor Wottschel2, Rosa Cortese2, Massimiliano Calabrese2, Mohammad Ali Sahraian2, Alan J Thompson2, Daniel C Alexander2, Olga Ciccarelli2. 1. From the Queen Square MS Centre, Institute of Neurology (A.E., V.W., R.C., O.C.), Centre for Medical Image Computing (CMIC), Department of Computer Science (A.E., V.W., D.C.A.), and Faculty of Brain Sciences (A.J.T.), University College London, UK; MS Research Centre (A.E., M.A.S.), Neuroscience Institute, Tehran University of Medical Sciences, Iran; Advanced Neuroimaging Lab (M.C.), Neurology Clinic B, Department of Neurological and Movement Sciences, University of Verona; Neuroimaging Unit (M.C.), Euganea Medica, Padua, Italy; and National Institute of Health Research (NIHR) (A.J.T., O.C.), University College London Hospitals (UCLH) Biomedical Research Centre (BRC), London, UK. arman.eshaghi.14@ucl.ac.uk. 2. From the Queen Square MS Centre, Institute of Neurology (A.E., V.W., R.C., O.C.), Centre for Medical Image Computing (CMIC), Department of Computer Science (A.E., V.W., D.C.A.), and Faculty of Brain Sciences (A.J.T.), University College London, UK; MS Research Centre (A.E., M.A.S.), Neuroscience Institute, Tehran University of Medical Sciences, Iran; Advanced Neuroimaging Lab (M.C.), Neurology Clinic B, Department of Neurological and Movement Sciences, University of Verona; Neuroimaging Unit (M.C.), Euganea Medica, Padua, Italy; and National Institute of Health Research (NIHR) (A.J.T., O.C.), University College London Hospitals (UCLH) Biomedical Research Centre (BRC), London, UK.
Abstract
OBJECTIVE: We tested whether brain gray matter (GM) imaging measures can differentiate between multiple sclerosis (MS) and neuromyelitis optica (NMO) using random-forest classification. METHODS: Ninety participants (25 patients with MS, 30 patients with NMO, and 35 healthy controls [HCs]) were studied in Tehran, Iran, and 54 (24 patients with MS, 20 patients with NMO, and 10 HCs) in Padua, Italy. Participants underwent brain T1 and T2/fluid-attenuated inversion recovery MRI. Volume, thickness, and surface of 50 cortical GM regions and volumes of the deep GM nuclei were calculated and used to construct 3 random-forest models to classify patients as either NMO or MS, and separate each patient group from HCs. Clinical diagnosis was the gold standard against which the accuracy was calculated. RESULTS: The classifier distinguished patients with MS, who showed greater atrophy especially in deep GM, from those with NMO with an average accuracy of 74% (sensitivity/specificity: 77/72; p < 0.01). When we used thalamic volume (the most discriminating GM measure) together with the white matter lesion volume, the accuracy of the classification of MS vs NMO was 80%. The classifications of MS vs HCs and NMO vs HCs achieved higher accuracies (92% and 88%). CONCLUSIONS: GM imaging biomarkers, automatically obtained from clinical scans, can be used to distinguish NMO from MS, even in a 2-center setting, and may facilitate the differential diagnosis in clinical practice. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that GM imaging biomarkers can distinguish patients with NMO from those with MS.
OBJECTIVE: We tested whether brain gray matter (GM) imaging measures can differentiate between multiple sclerosis (MS) and neuromyelitis optica (NMO) using random-forest classification. METHODS: Ninety participants (25 patients with MS, 30 patients with NMO, and 35 healthy controls [HCs]) were studied in Tehran, Iran, and 54 (24 patients with MS, 20 patients with NMO, and 10 HCs) in Padua, Italy. Participants underwent brain T1 and T2/fluid-attenuated inversion recovery MRI. Volume, thickness, and surface of 50 cortical GM regions and volumes of the deep GM nuclei were calculated and used to construct 3 random-forest models to classify patients as either NMO or MS, and separate each patient group from HCs. Clinical diagnosis was the gold standard against which the accuracy was calculated. RESULTS: The classifier distinguished patients with MS, who showed greater atrophy especially in deep GM, from those with NMO with an average accuracy of 74% (sensitivity/specificity: 77/72; p < 0.01). When we used thalamic volume (the most discriminating GM measure) together with the white matter lesion volume, the accuracy of the classification of MS vs NMO was 80%. The classifications of MS vs HCs and NMO vs HCs achieved higher accuracies (92% and 88%). CONCLUSIONS: GM imaging biomarkers, automatically obtained from clinical scans, can be used to distinguish NMO from MS, even in a 2-center setting, and may facilitate the differential diagnosis in clinical practice. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that GM imaging biomarkers can distinguish patients with NMO from those with MS.
Authors: David W Shattuck; Mubeena Mirza; Vitria Adisetiyo; Cornelius Hojatkashani; Georges Salamon; Katherine L Narr; Russell A Poldrack; Robert M Bilder; Arthur W Toga Journal: Neuroimage Date: 2007-11-26 Impact factor: 6.556
Authors: Sean J Pittock; Brian G Weinshenker; Claudia F Lucchinetti; Dean M Wingerchuk; John R Corboy; Vanda A Lennon Journal: Arch Neurol Date: 2006-07
Authors: Massimiliano Calabrese; Roberta Magliozzi; Olga Ciccarelli; Jeroen J G Geurts; Richard Reynolds; Roland Martin Journal: Nat Rev Neurosci Date: 2015-03 Impact factor: 34.870
Authors: Brian B Avants; Paul Yushkevich; John Pluta; David Minkoff; Marc Korczykowski; John Detre; James C Gee Journal: Neuroimage Date: 2009-10-08 Impact factor: 6.556
Authors: Dean M Wingerchuk; Brenda Banwell; Jeffrey L Bennett; Philippe Cabre; William Carroll; Tanuja Chitnis; Jérôme de Seze; Kazuo Fujihara; Benjamin Greenberg; Anu Jacob; Sven Jarius; Marco Lana-Peixoto; Michael Levy; Jack H Simon; Silvia Tenembaum; Anthony L Traboulsee; Patrick Waters; Kay E Wellik; Brian G Weinshenker Journal: Neurology Date: 2015-06-19 Impact factor: 9.910