Skip to main content

Advertisement

SpringerLink
Log in

Differentiation between Parkinson disease and other forms of Parkinsonism using support vector machine analysis of susceptibility-weighted imaging (SWI): initial results

  • Neuro
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

To diagnose Parkinson disease (PD) at the individual level using pattern recognition of brain susceptibility-weighted imaging (SWI).

Methods

We analysed brain SWI in 36 consecutive patients with Parkinsonism suggestive of PD who had (1) SWI at 3 T, (2) brain 123I-ioflupane SPECT and (3) extensive neurological testing including follow-up (16 PD, 67.4 ± 6.2 years, 11 female; 20 OTHER, a heterogeneous group of atypical Parkinsonism syndromes 65.2 ± 12.5 years, 6 female). Analysis included group-level comparison of SWI values and individual-level support vector machine (SVM) analysis.

Results

At the group level, simple visual analysis yielded no differences between groups. However, the group-level analyses demonstrated increased SWI in the bilateral thalamus and left substantia nigra in PD patients versus other Parkinsonism. The inverse comparison yielded no supra-threshold clusters. At the individual level, SVM correctly classified PD patients with an accuracy above 86 %.

Conclusions

SVM pattern recognition of SWI data provides accurate discrimination of PD among patients with various forms of Parkinsonism at an individual level, despite the absence of visually detectable alterations. This pilot study warrants further confirmation in a larger cohort of PD patients and with different MR machines and MR parameters.

Key Points

• Magnetic resonance imaging data offers new insights into Parkinson’s disease

• Visual susceptibility-weighted imaging (SWI) analysis could not discriminate idiopathic from atypical PD

• However, support vector machine (SVM) analysis provided highly accurate detection of idiopathic PD

• SVM analysis may contribute to the clinical diagnosis of individual PD patients

• Such information can be readily obtained from routine MR data

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Abbreviations

AD:

Alzheimer disease

DaTScan:

123I-ioflupane SPECT

DN:

dentate nucleus (of the cerebellum)

DTI:

diffusion tensor imaging

FA:

fractional anisotropy

GM:

grey matter

MCI:

mild cognitive impairment

MRI:

magnetic resonance imaging

MSA-P:

Parkinson variant of multiple system atrophy

PD:

Parkinson disease

PSP:

progressive supranuclear palsy

RBF:

radial basis function

RN:

red nucleus

ROI:

region of interest

SMO:

sequential minimal optimisation

SN:

substantia nigra

SPECT:

single-photon emission computed tomography

SVM:

support vector machine

SWI:

susceptibility-weighted imaging

TBSS:

tract-based spatial statistics

TFCE:

threshold free cluster enhancement

VBM:

voxel-based morphometry

WM:

white matter

References

  1. Aquino D, Bizzi A, Grisoli M et al (2009) Age-related iron deposition in the basal ganglia: quantitative analysis in healthy subjects. Radiology 252:165–172

    Article  PubMed  Google Scholar 

  2. Thomas M, Jankovic J (2004) Neurodegenerative disease and iron storage in the brain. Curr Opin Neurol 17:437–442

    Article  PubMed  Google Scholar 

  3. Smith MA, Zhu X, Tabaton M et al (2010) Increased iron and free radical generation in preclinical Alzheimer disease and mild cognitive impairment. J Alzheimers Dis 19:363–372

    PubMed  Google Scholar 

  4. Bishop GM, Robinson SR, Liu Q et al (2002) Iron: a pathological mediator of Alzheimer disease? Dev Neurosci 24:184–187

    Article  PubMed  CAS  Google Scholar 

  5. Haller S, Bartsch A, Nguyen D et al (2010) Cerebral microhemorrhage and iron deposition in mild cognitive impairment: susceptibility-weighted MR imaging assessment. Radiology 257:764–773

    Article  PubMed  Google Scholar 

  6. Dexter DT, Carayon A, Javoy-Agid F et al (1991) Alterations in the levels of iron, ferritin and other trace metals in Parkinson’s disease and other neurodegenerative diseases affecting the basal ganglia. Brain 114:1953–1975

    Article  PubMed  Google Scholar 

  7. Youdim MB, Ben-Shachar D, Riederer P (1993) The possible role of iron in the etiopathology of Parkinson’s disease. Mov Disord 8:1–12

    Article  PubMed  CAS  Google Scholar 

  8. Haacke EM, Xu Y, Cheng YC et al (2004) Susceptibility weighted imaging (SWI). Magn Reson Med 52:612–618

    Article  PubMed  Google Scholar 

  9. Oikawa H, Sasaki M, Tamakawa Y et al (2002) The substantia nigra in Parkinson disease: proton density-weighted spin-echo and fast short inversion time inversion-recovery MR findings. AJNR Am J Neuroradiol 23:1747–1756

    PubMed  Google Scholar 

  10. Hughes AJ, Daniel SE, Ben-Shlomo Y et al (2002) The accuracy of diagnosis of parkinsonian syndromes in a specialist movement disorder service. Brain 125:861–870

    Article  PubMed  Google Scholar 

  11. Haller S, Lovblad KO, Giannakopoulos P (2011) Principles of classification analyses in mild cognitive impairment (MCI) and Alzheimer disease. J Alzheimers Dis 26:389–394

    Article  PubMed  Google Scholar 

  12. Noble WS (2006) What is a support vector machine? Nat Biotechnol 24:1565–1567

    Article  PubMed  CAS  Google Scholar 

  13. Hoehn MM, Yahr MD (1967) Parkinsonism: onset, progression and mortality. Neurology 17:427–442

    Article  PubMed  CAS  Google Scholar 

  14. Fazekas F, Chawluk JB, Alavi A et al (1987) MR signal abnormalities at 1.5 T in Alzheimer’s dementia and normal aging. AJR Am J Roentgenol 149:351–356

    PubMed  CAS  Google Scholar 

  15. Gupta D, Saini J, Kesavadas C et al (2010) Utility of susceptibility-weighted MRI in differentiating Parkinson’s disease and atypical parkinsonism. Neuroradiology 52:1087–1094

    Article  PubMed  Google Scholar 

  16. Smith SM, Jenkinson M, Woolrich MW et al (2004) Advances in functional and structural MR image analysis and implementation as FSL. NeuroImage 23:S208–19

    Article  PubMed  Google Scholar 

  17. Smith SM, Nichols TE (2009) Threshold-free cluster enhancement: addressing problems of smoothing, threshold dependence and localisation in cluster inference. NeuroImage 44:83–98

    Article  PubMed  Google Scholar 

  18. Haller S, Nguyen D, Rodriguez C et al (2010) Individual prediction of cognitive decline in mild cognitive impairment using support vector machine-based analysis of diffusion tensor imaging data. J Alzheimers Dis 22:315–327

    PubMed  Google Scholar 

  19. Kononenko I, Šimec E, Robnik-Šikonja M (1997) Overcoming the myopia of inductive learning algorithms with RELIEFF. Appl Intell 7:39–55

    Article  Google Scholar 

  20. Platt J (1999) Sequential minimal optimization: A fast algorithm for training support vector machines. Advances in Kernel methods-support vector learning 208

  21. Scholkopf B, Sung KK, Burges CJC et al (1997) Comparing support vector machines with Gaussian kernels to radialbasis function classifiers. IEEE Trans Signal Process 45:2758–2765

    Article  Google Scholar 

  22. Wang Y, Butros S R, Shuai X et al (2011) Different iron-deposition patterns of multiple system atrophy with predominant parkinsonism and idiopathetic parkinson diseases demonstrated by phase-corrected susceptibility-weighted imaging. AJNR Am J Neuroradiol

  23. Zhang J, Zhang Y, Wang J et al (2010) Characterizing iron deposition in Parkinson’s disease using susceptibility-weighted imaging: an in vivo MR study. Brain Res 1330:124–130

    Article  PubMed  CAS  Google Scholar 

  24. Huang XM, Sun B, Xue YJ et al (2010) Susceptibility-weighted imaging in detecting brain iron accumulation of Parkinson’s disease. Zhonghua Yi Xue Za Zhi 90:3054–3058

    PubMed  Google Scholar 

  25. Rossi M, Ruottinen H, Elovaara I et al (2010) Brain iron deposition and sequence characteristics in Parkinsonism: comparison of SWI, T* maps, T-weighted-, and FLAIR-SPACE. Invest Radiol 45:795–802

    Article  PubMed  CAS  Google Scholar 

  26. Zhang W, Sun SG, Jiang YH et al (2009) Determination of brain iron content in patients with Parkinson’s disease using magnetic susceptibility imaging. Neurosci Bull 25:353–360

    Article  PubMed  CAS  Google Scholar 

  27. Grabner G, Haubenberger D, Rath J et al (2010) A population-specific symmetric phase model to automatically analyze susceptibility-weighted imaging (SWI) phase shifts and phase symmetry in the human brain. J Magn Reson Imaging 31:215–220

    Article  PubMed  Google Scholar 

  28. Pezzoli G, Canesi M, Galli C (2004) An overview of parkinsonian syndromes: data from the literature and from an Italian data-base. Sleep Med 5:181–187

    Article  PubMed  CAS  Google Scholar 

  29. Jeon HS, Han J, Yi WJ et al (2008) Classification of Parkinson gait and normal gait using spatial-temporal image of plantar pressure. Conf Proc IEEE Eng Med Biol Soc 2008:4672–4675

    PubMed  Google Scholar 

  30. Brewer BR, Pradhan S, Carvell G et al (2009) Feature selection for classification based on fine motor signs of Parkinson’s disease. Conf Proc IEEE Eng Med Biol Soc 2009:214–217

    PubMed  CAS  Google Scholar 

  31. Patel S, Lorincz K, Hughes R et al (2009) Monitoring motor fluctuations in patients with Parkinson’s disease using wearable sensors. IEEE Trans Inf Technol Biomed 13:864–873

    Article  PubMed  Google Scholar 

  32. Chan J, Leung H, Poizner H (2010) Correlation among joint motions allows classification of Parkinsonian versus normal 3-D reaching. IEEE Trans Neural Syst Rehabil Eng 18:142–149

    Article  PubMed  Google Scholar 

  33. Ozcift A (2011) SVM feature selection based rotation forest ensemble classifiers to improve computer-aided diagnosis of Parkinson disease. J Med Syst

  34. Focke NK, Helms G, Scheewe S et al (2011) Individual voxel-based subtype prediction can differentiate progressive supranuclear palsy from idiopathic parkinson syndrome and healthy controls. Hum Brain Mapp 32:1905–1915

    Article  PubMed  Google Scholar 

  35. Groschel K, Kastrup A, Litvan I et al (2006) Penguins and hummingbirds: midbrain atrophy in progressive supranuclear palsy. Neurology 66:949–950

    Article  PubMed  Google Scholar 

  36. Seppi K, Schocke MF, Esterhammer R et al (2003) Diffusion-weighted imaging discriminates progressive supranuclear palsy from PD, but not from the Parkinson variant of multiple system atrophy. Neurology 60:922–927

    Article  PubMed  CAS  Google Scholar 

  37. Schocke MF, Seppi K, Esterhammer R et al (2002) Diffusion-weighted MRI differentiates the Parkinson variant of multiple system atrophy from PD. Neurology 58:575–580

    Article  PubMed  CAS  Google Scholar 

  38. Plant C, Teipel SJ, Oswald A et al (2010) Automated detection of brain atrophy patterns based on MRI for the prediction of Alzheimer’s disease. NeuroImage 50:162–174

    Article  PubMed  Google Scholar 

  39. Haacke EM, Mittal S, Wu Z et al (2009) Susceptibility-weighted imaging: technical aspects and clinical applications, part 1. AJNR Am J Neuroradiol 30:19–30

    Article  PubMed  CAS  Google Scholar 

  40. Hopp K, Popescu BF, McCrea RP et al (2010) Brain iron detected by SWI high pass filtered phase calibrated with synchrotron X-ray fluorescence. J Magn Reson Imaging 31:1346–1354

    Article  PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Service neuro-diagnostique et neuro-interventionnel DISIM, Hôpitaux Universitaires de Genève, Rue Gabrielle Perret-Gentil 4, 1211, Genève 14, Switzerland

    S Haller & K-O Lovblad

  2. Department of Neurology, Geneva University Hospitals, Geneva, Switzerland

    S Badoud & PR Burkhard

  3. Faculty of Medicine, University of Geneva, Geneva, Switzerland

    S Badoud & PR Burkhard

  4. Centre Diagnostic Radiologique Carouge, 1b Clos de la Fonderie, 1227, Carouge, Switzerland

    D Nguyen

  5. Service de Radiologie, Geneva University Hospitals, Geneva, Switzerland

    I Barnaure

  6. Nuclear medicine and molecular imaging unit, DISIM, Geneva University Hospitals, Geneva, Switzerland

    M-L Montandon

  7. Faculty of Medicine, University of Geneva, Geneva, Switzerland

    M-L Montandon

Authors
  1. S Haller
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. S Badoud
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. D Nguyen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. I Barnaure
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. M-L Montandon
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. K-O Lovblad
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. PR Burkhard
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to S Haller.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Haller, S., Badoud, S., Nguyen, D. et al. Differentiation between Parkinson disease and other forms of Parkinsonism using support vector machine analysis of susceptibility-weighted imaging (SWI): initial results. Eur Radiol 23, 12–19 (2013). https://doi.org/10.1007/s00330-012-2579-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-012-2579-y

Keywords

Search

Navigation