Differential diagnosis of multiple system atrophy with predominant parkinsonism and Parkinson's disease using neural networks

Published:April 10, 2019DOI:https://doi.org/10.1016/j.jns.2019.04.014


      • Neural network (NN) deep learning differentiated MSA-P from PD in earlier stages.
      • Analysis by NN was carried out using the data of VBM and MRS.
      • Neuronal loss and gliosis in the globus pallidus were observed in both MSA-P and PD.
      • Enhanced pattern recognition is a potential significant clinical application of NN.
      • NN data can provide feedback to review clinical diagnosis and neurological findings.


      Differential diagnosis between Parkinson's disease (PD) and atypical parkinsonism, such as multiple system atrophy (MSA), can be difficult, especially in the early stages of the disease. Deep learning using neural networks (NNs) makes possible the prediction of the diagnosis using various types of biomarkers, unlike conventional linear statistics. We aimed to differentiate the Parkinson's variant of MSA (MSA-P) from PD both in the early stages by clinical utilization of NN analyses before the hot cross-bun and putaminal rim imaging features of MSA appeared. Analysis by NN involved the data of voxel-based morphometry (VBM) that indicate morphological changes and magnetic resonance spectroscopy (MRS) that indicate qualitative changes. VBM analysis showed that compared with PD patients, MSA-P patients showed atrophy in the superior cerebellar peduncle, middle cerebellar peduncle, cerebellar hemisphere, pons, midbrain, and putamen, but not in the globus pallidus. Proton MRS on the globus pallidus in the diseased hemisphere, lacking atrophy as observed with VBM, revealed decreased neurons and gliosis in both groups. Clinical differentiation of MSA-P from PD using NN analysis, involved measuring the prediction potential using the area under the receiver operator characteristic (ROC) curves (AUC). Using both VBM and MRS data, NNs contributed adequately to the clinical diagnosis.


      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic and Personal


      Subscribe to Journal of the Neurological Sciences
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Chelban V.
        • Bocchetta M.
        • Hassanein S.
        • Haridy N.A.
        • Houlden H.
        • Rohrer J.D.
        An update on advances in magnetic resonance imaging of multiple system atrophy.
        J. Neurol. 2018 Nov 20; https://doi.org/10.1007/s00415-018-9121-3
        • Stamelou M.
        • Bhatia K.P.
        Atypical parkinsonism: diagnosis and treatment.
        Neurol. Clin. 2015; 33: 39-56https://doi.org/10.1016/j.ncl.2014.09.012
        • Rizzo G.
        • Copetti M.
        • Arcuti S.
        • Martino D.
        • Fontana A.
        • Logroscino G.
        Accuracy of clinical diagnosis of Parkinson disease: a systematic review and meta-analysis.
        Neurology. 2016; 86: 566-576https://doi.org/10.1212/WNL.0000000000002350
        • Koga S.
        • Aoki N.
        • Uitti R.J.
        • van Gerpen J.A.
        • Cheshire W.P.
        • Josephs K.A.
        • Wszolek Z.K.
        • Langston J.W.
        • Dickson D.W.
        When DLB, PD, and PSP masquerade as MSA: an autopsy study of 134 patients.
        Neurology. 2015; 85: 404-412https://doi.org/10.1212/WNL.0000000000001807
        • Gilman S.
        • Wenning G.K.
        • Low P.A.
        • Brooks D.J.
        • Mathias C.J.
        • Trojanowski J.Q.
        • Wood N.W.
        • Colosimo C.
        • Dürr A.
        • Fowler C.J.
        • Kaufmann H.
        • Klockgether T.
        • Lees A.
        • Poewe W.
        • Quinn N.
        • Revesz T.
        • Robertson D.
        • Sandroni P.
        • Seppi K.
        • Vidailhet M.
        Second consensus statement on the diagnosis of multiple system atrophy.
        Neurology. 2008; 71: 670-676https://doi.org/10.1212/01.wnl.0000324625.00404.15
        • Heim B.
        • Krismer F.
        • De Marzi R.
        • Seppi K.
        Magnetic resonance imaging for the diagnosis of Parkinson's disease.
        J. Neural Transm. 2017; 124: 915-964https://doi.org/10.1007/s00702-017-1717-8
        • Oliveira R.V.
        • Pereira J.S.
        The role of diffusion magnetic resonance imaging in Parkinson's disease and in the differential diagnosis with atypical parkinsonism.
        Radiol. Bras. 2017; 50: 250-257https://doi.org/10.1590/0100-3984.2016-0073
        • LeCun Y.
        • Bengio Y.
        • Hinton G.
        Deep learning.
        Nature. 2015; 521: 436-444
        • Ashburner J.
        • Friston K.J.
        Voxel-based morphometry-the methods.
        Neuroimage. 2000; 11: 805-821https://doi.org/10.1006/nimg.2000.0582
        • Ciurleo R.
        • Lorenzo G.D.
        • Bramanti P.
        • Marino S.
        Magnetic resonance spectroscopy: an in vivo molecular imaging biomarker for Parkinson's disease?.
        Biomed. Res. Int. 2014; 2014: 519816https://doi.org/10.1155/2014/519816
        • Emir U.E.
        • Tuite P.J.
        • Öz G.
        Elevated pontine and putamenal GABA levels in mild-moderate Parkinson disease detected by 7 tesla proton MRS.
        PLoS ONE. 2012; 7e30918https://doi.org/10.1371/journal.pone.0030918
        • Wenning G.K.
        • Tison F.
        • Seppi K.
        • Sampaio C.
        • Diem A.
        • Yekhlef F.
        • Ghorayeb I.
        • Ory F.
        • Galitzky M.
        • Scaravilli T.
        • Bozi M.
        • Colosimo C.
        • Gilman S.
        • Shults C.W.
        • Quinn N.P.
        • Rascol O.
        • Poewe W.
        Multiple system atrophy study group, development and validation of the unified multiple system atrophy rating scale (UMSARS).
        Mov. Disord. 2004; 19: 1391-1402https://doi.org/10.1002/mds.20255
        • Goetz C.G.
        • Tilley B.C.
        • Shaftman S.R.
        • Stebbins G.T.
        • Fahn S.
        • Martinez-Martin P.
        • Poewe W.
        • Sampaio C.
        • Stern M.B.
        • Dodel R.
        • Dubois B.
        • Holloway R.
        • Jankovic J.
        • Kulisevsky J.
        • Lang A.E.
        • Lees A.
        • Leurgans S.
        • LeWitt P.A.
        • Nyenhuis D.
        • Olanow C.W.
        • Rascol O.
        • Schrag A.
        • Teresi J.A.
        • van Hilten J.J.
        • LaPelle N.
        Movement Disorder Society UPDRS revision task force., movement disorder society-sponsored revision of the unified Parkinson's disease rating scale (MDS-UPDRS): scale presentation and clinimetric testing results.
        Mov. Disord. 2008; 23: 2129-2170https://doi.org/10.1002/mds.22340
        • Hoehn M.
        • Yahr M.
        Parkinsonism: onset, progression and mortality.
        Neurology. 1967; 17: 427-442https://doi.org/10.1212/wnl.17.5.427
        • Tzourio-Mazoyer N.
        • Landeau B.
        • Papathanassiou D.
        • Crivello F.
        • Etard O.
        • Delcroix N.
        • Mazoyer B.
        • Joliot M.
        Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain.
        Neuroimage. 2002; 15: 273-289https://doi.org/10.1006/nimg.2001.0978
        • Watanabe H.
        • Fukatsu H.
        • Katsuno M.
        • Sugiura M.
        • Hamada K.
        • Okada Y.
        • Hirayama M.
        • Ishigaki T.
        • Sobue G.
        Multiple regional 1H-MR spectroscopy in multiple system atrophy: NAA/Cr reduction in pontine base as a valuable diagnostic marker.
        J. Neurol. Neurosurg. Psychiatry. 2004; 75: 103-109
        • Wu G.
        • Shen Y.J.
        • Huang M.H.
        • Xing Z.
        • Liu Y.
        • Chen J.
        Proton MR spectroscopy for monitoring pathologic changes in the substantia nigra and globus pallidus in Parkinson disease.
        Am. J. Roentgenol. 2016; 206: 385-389https://doi.org/10.2214/AJR.14.14052
        • Tsuda M.
        • Asano S.
        • Kato Y.
        • Murai K.
        • Miyazaki M.
        A study of the globus pallidus of patients with Parkinson disease by magnetic resonance spectroscopy using artificial intelligence (neural network).
        Neurol. Med. 2017; 86: 628-631
        • Ruiz A.
        • Teruel P.E. L'opez-de
        Nonlinear kernel-based statistical pattern analysis.
        IEEE Trans. Neural Netw. 2001; 12: 16-32https://doi.org/10.1109/72.896793
        • Metz C.E.
        Basic principles of ROC analysis.
        Semin. Nucl. Med. 1978; 8: 283-298
        • Ozawa T.
        • Paviour D.
        • Quinn P.
        • Keith A.
        • Josephs A.
        • Sangha H.
        • Kilford L.
        • Healy D.G.
        • Wood W.N.
        • Lees A.J.
        • Holton J.L.
        • Revesz T.
        The spectrum of pathological involvement of the striatonigral and olivopontocerebellar systems in multiple system atrophy: clinicopathological correlations.
        Brain. 2004; 127: 2657-2671https://doi.org/10.1093/brain/awh303
        • Brenneis C.
        • Egge K.
        • Scherner C.
        • Seppi K.
        • Schocke M.
        • Poewe W.
        • Wenning G.K.
        Progression of brain atrophy in multiple system atrophy. A longitudinal VBM study.
        J. Neurol. 2007; 254: 191-196https://doi.org/10.1007/s00415-006-0325-6
        • Shigemoto Y.
        • Matsuda H.
        • Kamiya K.
        • Maikusa N.
        • Nakata Y.
        • Ito K.
        • Ota M.
        • Matsunaga N.
        • Sato N.
        In vivo evaluation of gray and white matter volume loss in the parkinsonian variant of multiple system atrophy using SPM8 plus DARTEL for VBM.
        Neuroimage Clin. 2013; 2: 491-496https://doi.org/10.1016/j.nicl.2013.03.017
        • Milosevic L.
        • Gramer R.
        • Kim T.H.
        • Algarni M.
        • Fasano A.
        • Kalia S.K.
        • Hodaie M.
        • Lozano A.M.
        • Popovic M.R.
        • Hutchison W.D.
        Modulation of inhibitory plasticity in basal ganglia output nuclei of patients with Parkinson's disease.
        Neurobiol. Dis. 2018; 124 (pii: S0969-9961(18)30593-X): 46-56
        • Shin H.
        • Roberts K.
        • Lu L.
        • Demnur-Fushman D.
        • Yao J.
        • Summers R.
        Learning to read chest-rays: recurrent neural cascade model for automated image annotation.
        arXiv. 2016; (1603.08486)https://doi.org/10.1109/CVPR.2016.274
        • Cruz-Roa A.A.
        • Ovalle J.E.
        • Madabhushi A.
        • Osorio F.A.
        A deep learning architecture for image representation, visual interpretability and automated basal-cell carcinoma cancer detection.
        Med. Image Comput. Comput. Assist. Interv. 2013; 16: 403-410