Gray matter MRI differentiates neuromyelitis optica from multiple sclerosis using random forest. Eshaghi, A., Wottschel, V., Cortese, R., Calabrese, M., Sahraian, M. A., Thompson, A. J., Alexander, D. C., & Ciccarelli, O. Neurology, 87(23):2463–2470, December, 2016. Publisher: Wolters Kluwer Health, Inc. on behalf of the American Academy of Neurology Section: ArticlePaper doi abstract bibtex 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 \textless 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.
@article{eshaghi_gray_2016,
title = {Gray matter {MRI} differentiates neuromyelitis optica from multiple sclerosis using random forest},
volume = {87},
copyright = {© 2016 American Academy of Neurology},
issn = {0028-3878, 1526-632X},
url = {https://n.neurology.org/content/87/23/2463},
doi = {10.1212/WNL.0000000000003395},
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 {\textless} 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.},
language = {en},
number = {23},
urldate = {2020-04-30},
journal = {Neurology},
author = {Eshaghi, Arman and Wottschel, Viktor and Cortese, Rosa and Calabrese, Massimiliano and Sahraian, Mohammad Ali and Thompson, Alan J. and Alexander, Daniel C. and Ciccarelli, Olga},
month = dec,
year = {2016},
pmid = {27807185},
note = {Publisher: Wolters Kluwer Health, Inc. on behalf of the American Academy of Neurology
Section: Article},
pages = {2463--2470},
}
Downloads: 0
{"_id":"DsonCb4viFB3dKqWh","bibbaseid":"eshaghi-wottschel-cortese-calabrese-sahraian-thompson-alexander-ciccarelli-graymattermridifferentiatesneuromyelitisopticafrommultiplesclerosisusingrandomforest-2016","authorIDs":[],"author_short":["Eshaghi, A.","Wottschel, V.","Cortese, R.","Calabrese, M.","Sahraian, M. A.","Thompson, A. J.","Alexander, D. C.","Ciccarelli, O."],"bibdata":{"bibtype":"article","type":"article","title":"Gray matter MRI differentiates neuromyelitis optica from multiple sclerosis using random forest","volume":"87","copyright":"© 2016 American Academy of Neurology","issn":"0028-3878, 1526-632X","url":"https://n.neurology.org/content/87/23/2463","doi":"10.1212/WNL.0000000000003395","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 \\textless 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.","language":"en","number":"23","urldate":"2020-04-30","journal":"Neurology","author":[{"propositions":[],"lastnames":["Eshaghi"],"firstnames":["Arman"],"suffixes":[]},{"propositions":[],"lastnames":["Wottschel"],"firstnames":["Viktor"],"suffixes":[]},{"propositions":[],"lastnames":["Cortese"],"firstnames":["Rosa"],"suffixes":[]},{"propositions":[],"lastnames":["Calabrese"],"firstnames":["Massimiliano"],"suffixes":[]},{"propositions":[],"lastnames":["Sahraian"],"firstnames":["Mohammad","Ali"],"suffixes":[]},{"propositions":[],"lastnames":["Thompson"],"firstnames":["Alan","J."],"suffixes":[]},{"propositions":[],"lastnames":["Alexander"],"firstnames":["Daniel","C."],"suffixes":[]},{"propositions":[],"lastnames":["Ciccarelli"],"firstnames":["Olga"],"suffixes":[]}],"month":"December","year":"2016","pmid":"27807185","note":"Publisher: Wolters Kluwer Health, Inc. on behalf of the American Academy of Neurology Section: Article","pages":"2463–2470","bibtex":"@article{eshaghi_gray_2016,\n\ttitle = {Gray matter {MRI} differentiates neuromyelitis optica from multiple sclerosis using random forest},\n\tvolume = {87},\n\tcopyright = {© 2016 American Academy of Neurology},\n\tissn = {0028-3878, 1526-632X},\n\turl = {https://n.neurology.org/content/87/23/2463},\n\tdoi = {10.1212/WNL.0000000000003395},\n\tabstract = {Objective: We tested whether brain gray matter (GM) imaging measures can differentiate between multiple sclerosis (MS) and neuromyelitis optica (NMO) using random-forest classification.\nMethods: 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.\nResults: 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 {\\textless} 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\\%).\nConclusions: 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.\nClassification of evidence: This study provides Class II evidence that GM imaging biomarkers can distinguish patients with NMO from those with MS.},\n\tlanguage = {en},\n\tnumber = {23},\n\turldate = {2020-04-30},\n\tjournal = {Neurology},\n\tauthor = {Eshaghi, Arman and Wottschel, Viktor and Cortese, Rosa and Calabrese, Massimiliano and Sahraian, Mohammad Ali and Thompson, Alan J. and Alexander, Daniel C. and Ciccarelli, Olga},\n\tmonth = dec,\n\tyear = {2016},\n\tpmid = {27807185},\n\tnote = {Publisher: Wolters Kluwer Health, Inc. on behalf of the American Academy of Neurology\nSection: Article},\n\tpages = {2463--2470},\n}\n\n","author_short":["Eshaghi, A.","Wottschel, V.","Cortese, R.","Calabrese, M.","Sahraian, M. A.","Thompson, A. J.","Alexander, D. C.","Ciccarelli, O."],"key":"eshaghi_gray_2016","id":"eshaghi_gray_2016","bibbaseid":"eshaghi-wottschel-cortese-calabrese-sahraian-thompson-alexander-ciccarelli-graymattermridifferentiatesneuromyelitisopticafrommultiplesclerosisusingrandomforest-2016","role":"author","urls":{"Paper":"https://n.neurology.org/content/87/23/2463"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/m.shamimkaiser","creationDate":"2021-02-19T18:04:08.999Z","downloads":0,"keywords":[],"search_terms":["gray","matter","mri","differentiates","neuromyelitis","optica","multiple","sclerosis","using","random","forest","eshaghi","wottschel","cortese","calabrese","sahraian","thompson","alexander","ciccarelli"],"title":"Gray matter MRI differentiates neuromyelitis optica from multiple sclerosis using random forest","year":2016,"dataSources":["yda423vBhGBN7Q3WB"]}