Automated Categorization of Parkinsonian Syndromes Using Magnetic Resonance Imaging in a Clinical Setting.
Parkinson's disease
machine learning algorithm
multimodal magnetic resonance imaging
multiple system atrophy
progressive supranuclear palsy
Journal
Movement disorders : official journal of the Movement Disorder Society
ISSN: 1531-8257
Titre abrégé: Mov Disord
Pays: United States
ID NLM: 8610688
Informations de publication
Date de publication:
02 2021
02 2021
Historique:
received:
25
08
2020
accepted:
15
09
2020
pubmed:
3
11
2020
medline:
28
4
2021
entrez:
2
11
2020
Statut:
ppublish
Résumé
Machine learning algorithms using magnetic resonance imaging (MRI) data can accurately discriminate parkinsonian syndromes. Validation in patients recruited in routine clinical practice is missing. The aim of this study was to assess the accuracy of a machine learning algorithm trained on a research cohort and tested on an independent clinical replication cohort for the categorization of parkinsonian syndromes. Three hundred twenty-two subjects, including 94 healthy control subjects, 119 patients with Parkinson's disease (PD), 51 patients with progressive supranuclear palsy (PSP) with Richardson's syndrome, 35 with multiple system atrophy (MSA) of the parkinsonian variant (MSA-P), and 23 with MSA of the cerebellar variant (MSA-C), were recruited. They were divided into a training cohort (n = 179) scanned in a research environment and a replication cohort (n = 143) examined in clinical practice on different MRI systems. Volumes and diffusion tensor imaging (DTI) metrics in 13 brain regions were used as input for a supervised machine learning algorithm. To harmonize data across scanners and reduce scanner-dependent effects, we tested two types of normalizations using patient data or healthy control data. In the replication cohort, high accuracies were achieved using volumetry in the classification of PD-PSP, PD-MSA-C, PSP-MSA-C, and PD-atypical parkinsonism (balanced accuracies: 0.840-0.983, area under the receiver operating characteristic curves: 0.907-0.995). Performances were lower for the classification of PD-MSA-P, MSA-C-MSA-P (balanced accuracies: 0.765-0.784, area under the receiver operating characteristic curve: 0.839-0.871) and PD-PSP-MSA (balanced accuracies: 0.773). Performance using DTI was improved when normalizing by controls, but remained lower than that using volumetry alone or combined with DTI. A machine learning approach based on volumetry enabled accurate classification of subjects with early-stage parkinsonism, examined on different MRI systems, as part of their clinical assessment. © 2020 International Parkinson and Movement Disorder Society.
Sections du résumé
BACKGROUND
Machine learning algorithms using magnetic resonance imaging (MRI) data can accurately discriminate parkinsonian syndromes. Validation in patients recruited in routine clinical practice is missing.
OBJECTIVE
The aim of this study was to assess the accuracy of a machine learning algorithm trained on a research cohort and tested on an independent clinical replication cohort for the categorization of parkinsonian syndromes.
METHODS
Three hundred twenty-two subjects, including 94 healthy control subjects, 119 patients with Parkinson's disease (PD), 51 patients with progressive supranuclear palsy (PSP) with Richardson's syndrome, 35 with multiple system atrophy (MSA) of the parkinsonian variant (MSA-P), and 23 with MSA of the cerebellar variant (MSA-C), were recruited. They were divided into a training cohort (n = 179) scanned in a research environment and a replication cohort (n = 143) examined in clinical practice on different MRI systems. Volumes and diffusion tensor imaging (DTI) metrics in 13 brain regions were used as input for a supervised machine learning algorithm. To harmonize data across scanners and reduce scanner-dependent effects, we tested two types of normalizations using patient data or healthy control data.
RESULTS
In the replication cohort, high accuracies were achieved using volumetry in the classification of PD-PSP, PD-MSA-C, PSP-MSA-C, and PD-atypical parkinsonism (balanced accuracies: 0.840-0.983, area under the receiver operating characteristic curves: 0.907-0.995). Performances were lower for the classification of PD-MSA-P, MSA-C-MSA-P (balanced accuracies: 0.765-0.784, area under the receiver operating characteristic curve: 0.839-0.871) and PD-PSP-MSA (balanced accuracies: 0.773). Performance using DTI was improved when normalizing by controls, but remained lower than that using volumetry alone or combined with DTI.
CONCLUSIONS
A machine learning approach based on volumetry enabled accurate classification of subjects with early-stage parkinsonism, examined on different MRI systems, as part of their clinical assessment. © 2020 International Parkinson and Movement Disorder Society.
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
460-470Informations de copyright
© 2020 International Parkinson and Movement Disorder Society.
Références
Hughes AJ, Daniel SE, Ben-Shlomo Y, Lees AJ. The accuracy of diagnosis of parkinsonian syndromes in a specialist movement disorder service. Brain 2002;125:861-870.
Höglinger GU, Respondek G, Stamelou M, et al. Clinical diagnosis of progressive supranuclear palsy: the movement disorder society criteria. Mov Disord 2017;32:853-864.
Gilman S, Wenning GK, Low PA, et al. Second consensus statement on the diagnosis of multiple system atrophy. Neurology 2008;71:670-676.
Berardelli A, Wenning GK, Antonini A, et al. EFNS/MDS-ES/ENS [corrected] recommendations for the diagnosis of Parkinson's disease. Eur J Neurol 2013;20:16-34.
Dickson DW. Neuropathology of Parkinson disease. Parkinsonism Relat Disord 2018;46(suppl 1):S30-S33.
Dickson DW. Parkinson's disease and parkinsonism: neuropathology. Cold Spring Harb Perspect Med [online serial] 2012;2. Accessed at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3405828/. Accessed March 16, 2019.
Levin J, Kurz A, Arzberger T, Giese A, Höglinger GU. The differential diagnosis and treatment of atypical parkinsonism. Dtsch Arztebl Int 2016;113:61-69.
Kalia LV, Lang AE. Parkinson's disease. The Lancet 2015;386:896-912.
Steele JC, Richardson JC, Olszewski J. Progressive supranuclear palsy: a heterogeneous degeneration involving the brain stem, Basal Ganglia and cerebellum with vertical gaze and pseudobulbar palsy, nuchal dystonia and dementia. Semin Neurol 2014;34:129-150.
Hauw JJ, Daniel SE, Dickson D, et al. Preliminary NINDS neuropathologic criteria for Steele-Richardson-Olszewski syndrome (progressive supranuclear palsy). Neurology 1994;44:2015-2019.
Pyatigorskaya N, Yahia-Cherif L, Gaurav R, et al. Multimodal magnetic resonance imaging quantification of brain changes in progressive supranuclear palsy. Mov Disord 2020;35:161-170.
Castellani R. Multiple system atrophy. Am J Pathol 1998;153:671-676.
Whitwell JL, Höglinger GU, Antonini A, et al. Radiological biomarkers for diagnosis in PSP: where are we and where do we need to be? Mov Disord 2017;32:955-971.
Heim B, Krismer F, Seppi K. Structural imaging in atypical parkinsonism. Int Rev Neurobiol 2018;142:67-148.
Lehericy S, Vaillancourt DE, Seppi K, et al. The role of high-field magnetic resonance imaging in parkinsonian disorders: pushing the boundaries forward. Mov Disord 2017;32:510-525.
Rizzo G, Zanigni S, De Blasi R, et al. Brain MR contribution to the differential diagnosis of Parkinsonian syndromes: an update. Parkinsons Dis 2016;2016:2983638.
Kassubek J. MRI-based neuroimaging: atypical parkinsonisms and other movement disorders. Curr Opin Neurol 2018;31:425-430.
Scherfler C, Göbel G, Müller C, et al. Diagnostic potential of automated subcortical volume segmentation in atypical parkinsonism. Neurology 2016;86:1242-1249.
Huppertz H-J, Möller L, Südmeyer M, et al. Differentiation of neurodegenerative parkinsonian syndromes by volumetric magnetic resonance imaging analysis and support vector machine classification. Mov Disord 2016;31:1506-1517.
Salvatore C, Cerasa A, Castiglioni I, et al. Machine learning on brain MRI data for differential diagnosis of Parkinson's disease and progressive supranuclear palsy. J Neurosci Methods 2014;222:230-237.
Cherubini A, Morelli M, Nisticó R, et al. Magnetic resonance support vector machine discriminates between Parkinson disease and progressive supranuclear palsy. Mov Disord 2014;29:266-269.
Péran P, Barbagallo G, Nemmi F, et al. MRI supervised and unsupervised classification of Parkinson's disease and multiple system atrophy. Mov Disord 2018;33:600-608.
Morisi R, Manners DN, Gnecco G, et al. Multi-class parkinsonian disorders classification with quantitative MR markers and graph-based features using support vector machines. Parkinsonism Relat Disord 2018;47:64-70.
Du G, Lewis MM, Kanekar S, et al. Combined diffusion tensor imaging and apparent transverse relaxation rate differentiate Parkinson disease and atypical parkinsonism. AJNR Am J Neuroradiol 2017;38:966-972.
Archer DB, Bricker JT, Chu WT, Burciu RG, McCracken JL. Development and validation of the automated imaging differentiation in parkinsonism (AID-P): a multicentre machine learning study. Lancet Digit Health 2019;1(5):e222-e231.
Litvan I, Agid Y, Calne D, et al. Clinical research criteria for the diagnosis of progressive supranuclear palsy (Steele-Richardson-Olszewski syndrome): report of the NINDS-SPSP international workshop. Neurology 1996;47:1-9.
Fischl B, Salat DH, Busa E, et al. Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain. Neuron 2002;33:341-355.
Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine learning in python. J Mach Learn Res 2011;12:2825-2830.
Nigro S, Antonini A, Vaillancourt DE, et al. Automated MRI classification in progressive supranuclear palsy: a large international cohort study. Mov Disord 2020;35(6):976-983.
Messina D, Cerasa A, Condino F, et al. Patterns of brain atrophy in Parkinson's disease, progressive supranuclear palsy and multiple system atrophy. Parkinsonism Relat Disord 2011;17:172-176.
Mangesius S, Hussl A, Krismer F, et al. MR planimetry in neurodegenerative parkinsonism yields high diagnostic accuracy for PSP. Parkinsonism Relat Disord 2018;46:47-55.
Möller L, Kassubek J, Südmeyer M, et al. Manual MRI morphometry in Parkinsonian syndromes. Mov Disord 2017;32:778-782.
Quattrone A, Nicoletti G, Messina D, et al. MR imaging index for differentiation of progressive supranuclear palsy from Parkinson disease and the Parkinson variant of multiple system atrophy. Radiology 2008;246:214-221.
Whitwell JL, Master AV, Avula R, et al. Clinical correlates of white matter tract degeneration in progressive supranuclear palsy. Arch Neurol 2011;68:753-760.
Seppi K, Schocke MFH, Prennschuetz-Schuetzenau K, et al. Topography of putaminal degeneration in multiple system atrophy: a diffusion magnetic resonance study. Mov Disord 2006;21:847-852.
Pellecchia MT, Barone P, Mollica C, et al. Diffusion-weighted imaging in multiple system atrophy: a comparison between clinical subtypes. Mov Disord 2009;24:689-696.
Tsukamoto K, Matsusue E, Kanasaki Y, et al. Significance of apparent diffusion coefficient measurement for the differential diagnosis of multiple system atrophy, progressive supranuclear palsy, and Parkinson's disease: evaluation by 3.0-T MR imaging. Neuroradiology 2012;54:947-955.
Nicoletti G, Lodi R, Condino F, et al. Apparent diffusion coefficient measurements of the middle cerebellar peduncle differentiate the Parkinson variant of MSA from Parkinson's disease and progressive supranuclear palsy. Brain 2006;129:2679-2687.
Seppi K, Schocke MFH, Esterhammer R, et al. Diffusion-weighted imaging discriminates progressive supranuclear palsy from PD, but not from the parkinson variant of multiple system atrophy. Neurology 2003;60:922-927.
Focke NK, Helms G, Pantel PM, et al. Differentiation of typical and atypical Parkinson syndromes by quantitative MR imaging. Am J Neuroradiol 2011;32:2087-2092.
Sjöström H, Granberg T, Westman E, Svenningsson P. Quantitative susceptibility mapping differentiates between parkinsonian disorders. Parkinsonism Relat Disord 2017;44:51-57.