Skip to main content

Radiomics on routine T1-weighted MRI can delineate Parkinson’s disease from multiple system atrophy and progressive supranuclear palsy

Abstract

Objectives

This study aimed to explore the feasibility of radiomics features extracted from T1-weighted MRI images to differentiate Parkinson’s disease (PD) from atypical parkinsonian syndromes (APS).

Methods

Radiomics features were computed from T1 images of 65 patients with PD, 61 patients with APS (31: progressive supranuclear palsy and 30: multiple system atrophy), and 75 healthy controls (HC). These features were extracted from 19 regions of interest primarily from subcortical structures, cerebellum, and brainstem. Separate random forest classifiers were applied to classify different groups based on a reduced set of most important radiomics features for each classification as determined by the random forest–based recursive feature elimination by cross-validation method.

Results

The PD vs HC classifier illustrated an accuracy of 70%, while the PD vs APS classifier demonstrated a superior test accuracy of 92%. Moreover, a 3-way PD/MSA/PSP classifier performed with 96% accuracy. While first-order and texture-based differences like Gray Level Co-occurrence Matrix (GLCM) and Gray Level Difference Matrix for the substantia nigra pars compacta and thalamus were highly discriminative for PD vs HC, textural features mainly GLCM of the ventral diencephalon were highlighted for APS vs HC, and features extracted from the ventral diencephalon and nucleus accumbens were highlighted for the classification of PD and APS.

Conclusions

This study establishes the utility of radiomics to differentiate PD from APS using routine T1-weighted images. This may aid in the clinical diagnosis of PD and APS which may often be indistinguishable in early stages of disease.

Key Points

• Radiomics features were extracted from T1-weighted MRI images.

• Parkinson’s disease and atypical parkinsonian syndromes were classified at an accuracy of 92%.

• This study establishes the utility of radiomics to differentiate Parkinson’s disease and atypical parkinsonian syndromes using routine T1-weighted images.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Abbreviations

AAO:

Age at onset

ANTs:

Advanced normalization tools

APS:

Atypical parkinsonian syndromes

AU-ROC:

Area under receiver operating characteristics

CV:

Cross-validation

DAT-SPECT:

Dopamine transporter single-photon emission computed tomography

FDG PET:

Fluorodeoxyglucose positron emission tomography

GLCM:

Gray Level Co-occurrence Matrix

GLDM:

Gray Level Dependence Matrix

GLRLM:

Gray Level Run Length Matrix

GLSZM:

Gray Level Size Zone Matrix

GM:

Gray matter

GRE:

Gradient echo

HC:

Healthy controls

MRI:

Magnetic resonance imaging

MSA:

Multiple system atrophy

MSA-C:

Multiple system atrophy-cerebellar type

MSA-P:

Multiple system atrophy-parkinsonian type

NGTDM:

Neighboring Gray Tone Difference Matrix

PD:

Parkinson’s disease

PSP:

Progressive supranuclear palsy

PSP-P:

Progressive supranuclear palsy-parkinsonism

PSP-RS:

Progressive supranuclear palsy-Richardson syndrome

QSM:

Quantitative susceptibility mapping

RF:

Random forest

RF-RFECV:

Random forest–based recursive feature elimination with cross-validation

ROC:

Receiver operating characteristics

ROI:

Regions of interest

rs-fMRI:

Resting-state functional MRI

SNc:

Substantia nigra pars compacta

SPIR:

Spectral pre-saturation inversion with recovery

TE:

Echo time

TR:

Repetition time

UPDRS-III:

Unified Parkinson’s Disease Rating Scale Part III

WM:

White matter

References

  1. Williams DR, Litvan I (2013) Parkinsonian syndromes. Continuum (Minneap Minn) 19:1189–1212

    Google Scholar 

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

    Article  Google Scholar 

  3. Broski SM, Hunt CH, Johnson GB, Morreale RF, Lowe VJ, Peller PJ (2014) Structural and functional imaging in parkinsonian syndromes. Radiographics 34:1273–1292

    Article  Google Scholar 

  4. Ohtsuka C, Sasaki M, Konno K et al (2014) Differentiation of early-stage parkinsonisms using neuromelanin-sensitive magnetic resonance imaging. Parkinsonism Relat Disord 20:755–760

    Article  Google Scholar 

  5. Sjostrom H, Granberg T, Westman E, Svenningsson P (2017) Quantitative susceptibility mapping differentiates between parkinsonian disorders. Parkinsonism Relat Disord 44:51–57

    Article  Google Scholar 

  6. Yao Q, Zhu D, Li F et al (2017) Altered functional and causal connectivity of cerebello-cortical circuits between multiple system atrophy (parkinsonian type) and Parkinson’s disease. Front Aging Neurosci 9:266

    Article  Google Scholar 

  7. Baggio HC, Abos A, Segura B et al (2019) Cerebellar resting-state functional connectivity in Parkinson’s disease and multiple system atrophy: characterization of abnormalities and potential for differential diagnosis at the single-patient level. Neuroimage: Clin 22:101720

    Article  Google Scholar 

  8. Sako W, Abe T, Furukawa T et al (2019) Differences in the intra-cerebellar connections and graph theoretical measures between Parkinson’s disease and multiple system atrophy. J Neurol Sci 400:129–134

    Article  Google Scholar 

  9. Franciotti R, Delli Pizzi S, Perfetti B et al (2015) Default mode network links to visual hallucinations: a comparison between Parkinson’s disease and multiple system atrophy. Mov Disord 30:1237–1247

    Article  Google Scholar 

  10. Abos A, Baggio HC, Segura B et al (2019) Differentiation of multiple system atrophy from Parkinson’s disease by structural connectivity derived from probabilistic tractography. Sci Rep 9:1–12

    CAS  Article  Google Scholar 

  11. Planetta PJ, Ofori E, Pasternak O et al (2016) Free-water imaging in Parkinson’s disease and atypical parkinsonism. Brain 139:495–508

    Article  Google Scholar 

  12. Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749–762

    Article  Google Scholar 

  13. van Timmeren JE, Cester D, Tanadini-Lang S, Alkadhi H, Baessler B (2020) Radiomics in medical imaging-“how-to” guide and critical reflection. Insights Imaging 11:91

    Article  Google Scholar 

  14. Salvatore C, Castiglioni I, Cerasa A (2019) Radiomics approach in the neurodegenerative brain. Aging Clin Exp Res. https://doi.org/10.1007/s40520-019-01299-z

  15. Shinde S, Prasad S, Saboo Y et al (2019) Predictive markers for Parkinson’s disease using deep neural nets on neuromelanin sensitive MRI. Neuroimage Clin 22:101748

    Article  Google Scholar 

  16. Cheng Z, Zhang J, He N et al (2019) Radiomic features of the nigrosome-1 region of the substantia nigra: using quantitative susceptibility mapping to assist the diagnosis of idiopathic Parkinson’s disease. Front Aging Neurosci 11:167

    Article  Google Scholar 

  17. Xiao B, He N, Wang Q et al (2019) Quantitative susceptibility mapping based hybrid feature extraction for diagnosis of Parkinson’s disease. Neuroimage Clin 24:102070

    Article  Google Scholar 

  18. Wu Y, Jiang J-H, Chen L et al (2019) Use of radiomic features and support vector machine to distinguish Parkinson’s disease cases from normal controls. Ann Transl Med 7(23):773. https://doi.org/10.21037/atm.2019.11.26

  19. Cao X, Wang X, Xue C, Zhang S, Huang Q, Liu W (2020) A radiomics approach to predicting Parkinson’s disease by incorporating whole-brain functional activity and gray matter structure. Front Neurosci 14:751

    Article  Google Scholar 

  20. Liu P, Wang H, Zheng S, Zhang F, Zhang X (2020) Parkinson’s disease diagnosis using neostriatum radiomic features based on t2-weighted magnetic resonance imaging. Front Neurol 11:248

    Article  Google Scholar 

  21. Naduthota RM, Bharath RD, Jhunjhunwala K et al (2017) Imaging biomarker correlates with oxidative stress in Parkinson’s disease. Neurol India 65:263–268

    Article  Google Scholar 

  22. Dash SK, Stezin A, Takalkar T et al (2019) Abnormalities of white and grey matter in early multiple system atrophy: comparison of parkinsonian and cerebellar variants. Eur Radiol 29:716–724

    Article  Google Scholar 

  23. Saini J, Bagepally BS, Sandhya M et al (2013) Subcortical structures in progressive supranuclear palsy: vertex-based analysis. Eur J Neurol 20:493–501

    CAS  Article  Google Scholar 

  24. Hughes AJ, Daniel SE, Kilford L, Lees AJ (1992) Accuracy of clinical diagnosis of idiopathic Parkinson’s disease: a clinico-pathological study of 100 cases. J Neurol Neurosurg Psychiatry 55:181–184

    CAS  Article  Google Scholar 

  25. Gilman S, Wenning GK, Low PA et al (2008) Second consensus statement on the diagnosis of multiple system atrophy. Neurology 71:670–676

    CAS  Article  Google Scholar 

  26. Litvan I, Agid Y, Calne D et al (1996) Clinical research criteria for the diagnosis of progressive supranuclear palsy (Steele-Richardson-Olszewski syndrome): report of the NINDS-SPSP international workshop. Neurology 47:1–9

    CAS  Article  Google Scholar 

  27. Hoglinger GU, Respondek G, Stamelou M et al (2017) Clinical diagnosis of progressive supranuclear palsy: the movement disorder society criteria. Mov Disord 32:853–864

    Article  Google Scholar 

  28. Fischl B, van der Kouwe A, Destrieux C et al (2004) Automatically parcellating the human cerebral cortex. Cereb Cortex 14:11–22

    Article  Google Scholar 

  29. Desikan RS, Segonne F, Fischl B et al (2006) An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest. Neuroimage 31:968–980

    Article  Google Scholar 

  30. Smith SM, Jenkinson M, Woolrich MW et al (2004) Advances in functional and structural MR image analysis and implementation as FSL. Neuroimage 23(Suppl 1):S208–S219

    Article  Google Scholar 

  31. Safai A, Prasad S, Chougule T, Saini J, Pal PK, Ingalhalikar M (2020) Microstructural abnormalities of substantia nigra in Parkinson’s disease: a neuromelanin sensitive MRI atlas based study. Hum Brain Mapp 41:1323–1333

    Article  Google Scholar 

  32. Avants BB, Tustison N, Song G (2009) Advanced normalization tools (ANTS). Insight J 2:1–35

    Google Scholar 

  33. van Griethuysen JJ, Fedorov A, Parmar C et al (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Res 77:e104–e107

    Article  Google Scholar 

  34. Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830

    Google Scholar 

  35. Chougar L, Pyatigorskaya N, Degos B, Grabli D, Lehéricy S (2020) The role of magnetic resonance imaging for the diagnosis of atypical parkinsonism. Front Neurol 11:665. https://doi.org/10.3389/fneur.2020.00665

  36. Dickson DW (2012) Parkinson’s disease and parkinsonism: neuropathology. Cold Spring Harb Perspect Med 2:a009258

    Article  Google Scholar 

  37. Zwanenburg A, Vallières M, Abdalah MA et al (2020) The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology 295:328–338

    Article  Google Scholar 

Download references

Funding

This study has received partial funding by the Department of Science and Technology – Science and Engineering Research Board (DST-SERB) (ECR/2016/000808) and (DST-SERB EMR/2017/004523).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Madhura Ingalhalikar.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Madhura Ingalhalikar.

Conflict of interest

The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was obtained from all subjects (patients) in this study.

Ethical approval

Institutional Review Board approval was obtained.

Study subjects or cohorts overlap

Some study subjects who were part of the cohort have been part of previous studies from our group:

Shinde S, Prasad S, Saboo Y, et al Predictive markers for Parkinson’s disease using deep neural nets on neuromelanin sensitive MRI. Neuroimage Clin. 2019;22:101748.

Naduthota RM, Bharath RD, Jhunjhunwala K, et al Imaging biomarker correlates with oxidative stress in Parkinson’s disease. Neurol India. 2017;65(2):263-268.

Dash SK, Stezin A, Takalkar T, et al Abnormalities of white and gray matter in early multiple system atrophy: comparison of parkinsonian and cerebellar variants. European radiology. 2019;29(2):716-724.

Methodology

• Retrospective

• Case-control study

• Performed at one institution

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

ESM 1

(DOCX 389 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Tupe-Waghmare, P., Rajan, A., Prasad, S. et al. Radiomics on routine T1-weighted MRI can delineate Parkinson’s disease from multiple system atrophy and progressive supranuclear palsy. Eur Radiol 31, 8218–8227 (2021). https://doi.org/10.1007/s00330-021-07979-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-021-07979-7

Keywords

  • Parkinson’s disease
  • Parkinsonism
  • Magnetic resonance imaging
  • Multiple system atrophy
  • Progressive supranuclear palsy