Abstract
Objectives
To construct a machine learning model for differentiating Parkinson’s disease (PD) and multiple system atrophy (MSA) by using multimodal PET/MRI radiomics and clinical characteristics.
Methods
One hundred and nineteen patients (81 with PD and 38 with MSA) underwent brain PET/CT and MRI to obtain metabolic images ([18F]FDG, [11C]CFT PET) and structural MRI (T1WI, T2WI, and T2-FLAIR). Image analysis included automatic segmentation on MRI, co-registration of PET images onto the corresponding MRI. Radiomics features were then extracted from the putamina and caudate nuclei and selected to construct predictive models. Moreover, based on PET/MRI radiomics and clinical characteristics, we developed a nomogram. Receiver operating characteristic (ROC) curves were performed to evaluate the performance of the models. Decision curve analysis (DCA) was employed to access the clinical usefulness of the models.
Results
The combined PET/MRI radiomics model of five sequences outperformed monomodal radiomics models alone. Further, PET/MRI radiomics-clinical combined model could perfectly distinguish PD from MSA (AUC = 0.993), which outperformed the clinical model (AUC = 0.923, p = 0.028) in training set, with no significant difference in test set (AUC = 0.860 vs 0.917, p = 0.390). However, no significant difference was found between PET/MRI radiomics-clinical model and PET/MRI radiomics model in training (AUC = 0.988, p = 0.276) and test sets (AUC = 0.860 vs 0.845, p = 0.632). DCA demonstrated the highest clinical benefit of PET/MRI radiomics-clinical model.
Conclusions
Our study indicates that multimodal PET/MRI radiomics could achieve promising performance to differentiate between PD and MSA in clinics.
Clinical relevance statement
This study developed an optimal radiomics signature and construct model to distinguish PD from MSA by multimodal PET/MRI imaging methods in clinics for parkinsonian syndromes, which achieved an excellent performance.
Key Points
•Multimodal PET/MRI radiomics from putamina and caudate nuclei increase the diagnostic efficiency for distinguishing PD from MSA.
•The radiomics-based nomogram was developed to differentiate between PD and MSA.
•Combining PET/MRI radiomics-clinical model achieved promising performance to identify PD and MSA.
Similar content being viewed by others
Abbreviations
- [18F]FDG:
-
18F-Fluorodeoxyglucose
- AUC:
-
Area under the curve
- DAT:
-
Dopamine transporter
- DCA:
-
Decision curve analysis
- MRI:
-
Magnetic resonance imaging
- MSA:
-
Multiple system atrophy
- PD:
-
Parkinson’s disease
- PET:
-
Positron emission tomography
- ROC:
-
Receiver operating characteristic
References
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
Peralta C, Biafore F, Depetris TS, Bastianello M (2019) Recent advancement and clinical implications of 18FDG-PET in Parkinson’s disease, atypical parkinsonisms, and other movement disorders. Curr Neurol Neurosci Rep 19:56
McKay JH, Cheshire WP (2018) First symptoms in multiple system atrophy. Clin Auton Res 28:215–221
Adler CH, Beach TG, Hentz JG et al (2014) Low clinical diagnostic accuracy of early vs advanced Parkinson disease: clinicopathologic study. Neurology 83:406–412
Fanciulli A, Wenning GK (2015) Multiple-system atrophy. N Engl J Med 372:249–263
Peeraully T (2014) Multiple system atrophy. Semin Neurol 34:174–181
Heiss WD (2016) Hybrid PET/MR imaging in neurology: present applications and prospects for the future. J Nucl Med 57:993–995
Saeed U, Compagnone J, Aviv RI et al (2017) Imaging biomarkers in Parkinson’s disease and Parkinsonian syndromes: current and emerging concepts. Transl Neurodegener 6:8
Poewe W, Wenning G (2002) The differential diagnosis of Parkinson’s disease. Eur J Neurol 9(Suppl 3):23–30
Zhao P, Zhang B, Gao S, Li X (2020) Clinical features, MRI, and 18F-FDG-PET in differential diagnosis of Parkinson disease from multiple system atrophy. Brain Behav 10:e01827
Zhu S, Deng B, Huang Z et al (2021) “Hot cross bun” is a potential imaging marker for the severity of cerebellar ataxia in MSA-C. NPJ Parkinsons Dis 7:15
Postuma RB, Berg D, Stern M et al (2015) MDS clinical diagnostic criteria for Parkinson’s disease. Mov Disord 30:1591–1601
Matthews DC, Lerman H, Lukic A et al (2018) FDG PET Parkinson’s disease-related pattern as a biomarker for clinical trials in early stage disease. Neuroimage Clin 20:572–579
Akdemir UO, Tokcaer AB, Karakus A, Kapucu LO (2014) Brain 18F-FDG PET imaging in the differential diagnosis of parkinsonism. Clin Nucl Med 39:e220-226
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
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
Aerts HJ, Velazquez ER, Leijenaar RT et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006
Sun R, Limkin EJ, Vakalopoulou M et al (2018) A radiomics approach to assess tumour-infiltrating CD8 cells and response to anti-PD-1 or anti-PD-L1 immunotherapy: an imaging biomarker, retrospective multicohort study. Lancet Oncol 19:1180–1191
Han Y, Ma Y, Wu Z et al (2021) Histologic subtype classification of non-small cell lung cancer using PET/CT images. Eur J Nucl Med Mol Imaging 48:350–360
Kirienko M, Sollini M, Corbetta M et al (2021) Radiomics and gene expression profile to characterise the disease and predict outcome in patients with lung cancer. Eur J Nucl Med Mol Imaging 48:3643–3655
Hu X, Sun X, Hu F et al (2021) Multivariate radiomics models based on (18)F-FDG hybrid PET/MRI for distinguishing between Parkinson’s disease and multiple system atrophy. Eur J Nucl Med Mol Imaging 48:3469–3481
Tupe-Waghmare P, Rajan A, Prasad S, Saini J, Pal PK, Ingalhalikar M (2021) Radiomics on routine T1-weighted MRI can delineate Parkinson’s disease from multiple system atrophy and progressive supranuclear palsy. Eur Radiol 31:8218–8227
Xu J, Xu Q, Liu S et al (2021) Computer-aided classification framework of Parkinsonian disorders using (11)C-CFT PET imaging. Front Aging Neurosci 13:792951
Sun D, Wu X, Xia Y et al (2021) Differentiating Parkinson’s disease motor subtypes: a radiomics analysis based on deep gray nuclear lesion and white matter. Neurosci Lett 760:136083
Wu Y, Jiang JH, 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 7:773
Salmanpour MR, Shamsaei M, Saberi A, Hajianfar G, Soltanian-Zadeh H, Rahmim A (2021) Robust identification of Parkinson’s disease subtypes using radiomics and hybrid machine learning. Comput Biol Med 129:104142
Gilman S, Wenning GK, Low PA et al (2008) Second consensus statement on the diagnosis of multiple system atrophy. Neurology 71:670–676
Buchert R, Lange C, Suppa P et al (2018) Magnetic resonance imaging-based hippocampus volume for prediction of dementia in mild cognitive impairment: why does the measurement method matter so little? Alzheimers Dement 14:976–978
Johnson H, Harris G, Williams K (2007) BRAINSFit: mutual information rigid registrations of whole-brain 3D images, using the Insight Toolkit. Insight J. http://hdl.handle.net/1926/1291
Ashburner J, Friston KJ (2005) Unified segmentation. Neuroimage 26:839–851
Mandal PK, Mahajan R, Dinov ID (2012) Structural brain atlases: design, rationale, and applications in normal and pathological cohorts. J Alzheimers Dis 31(Suppl 3):S169-188
Tong H, Sun J, Fang J et al (2022) A machine learning model based on PET/CT radiomics and clinical characteristics predicts tumor immune profiles in non-small cell lung cancer: a retrospective multicohort study. Front Immunol 13:859323
Ewert S, Horn A, Finkel F, Li N, Kuhn AA, Herrington TM (2019) Optimization and comparative evaluation of nonlinear deformation algorithms for atlas-based segmentation of DBS target nuclei. Neuroimage 184:586–598
Zwirner J, Mobius D, Bechmann I et al (2017) Subthalamic nucleus volumes are highly consistent but decrease age-dependently-a combined magnetic resonance imaging and stereology approach in humans. Hum Brain Mapp 38:909–922
Chakravarty MM, Steadman P, van Eede MC et al (2013) Performing label-fusion-based segmentation using multiple automatically generated templates. Hum Brain Mapp 34:2635–2654
Ruan W, Sun X, Hu X et al (2020) Regional SUV quantification in hybrid PET/MR, a comparison of two atlas-based automatic brain segmentation methods. EJNMMI Res 10:60
Brajkovic L, Kostic V, Sobic-Saranovic D et al (2017) The utility of FDG-PET in the differential diagnosis of Parkinsonism. Neurol Res 39:675–684
Meyer PT, Frings L, Rucker G, Hellwig S (2017) (18)F-FDG PET in parkinsonism: differential diagnosis and evaluation of cognitive impairment. J Nucl Med 58:1888–1898
Xian WB, Shi XC, Luo GH, Yi C, Zhang XS, Pei Z (2021) Co-registration analysis of fluorodopa and fluorodeoxyglucose positron emission tomography for differentiating multiple system atrophy parkinsonism type from Parkinson’s disease. Front Aging Neurosci 13:648531
Berardelli A, Wenning GK, Antonini A et al (2013) EFNS/MDS-ES/ENS [corrected] recommendations for the diagnosis of Parkinson’s disease. Eur J Neurol 20:16–34
Xu J, Zhang M (2019) Use of magnetic resonance imaging and artificial intelligence in studies of diagnosis of Parkinson’s disease. ACS Chem Neurosci 10:2658–2667
Funding
This work was supported by grants from the Talent Innovation Ability Training Program of Daping Hospital (2019CXLCC010, 2019CXLCB014), Science and Technology Innovation Ability Enhancement Project of Army Medical University (2022XJS29), Chongqing Science and Health Joint Medical Research Project-Young and Middle-aged High-level Talent Project (2023GDRC002), National Natural Science Foundation of China (81801672), and Chongqing Clinical Research Centre of Imaging and Nuclear Medicine (CSTC2015YFPT-gcjsyjzx0175).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Guarantor
The scientific guarantor of this publication is Xiao Chen.
Conflict of interest
Author Huan Liu was employed by GE Healthcare. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Statistics and biometry
One of the authors (Huan Liu) has significant statistical expertise.
Informed consent
The requirement of informed consent was waived by the Ethics Committee of Daping Hospital, Army Medical University, because this was a retrospective study.
Ethical approval
This retrospective study was conducted with the approval of the Ethical Committee of Daping Hospital, Army Medical University. This study’s use of human subjects complies with the Declaration of Helsinki.
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
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sun, J., Cong, C., Li, X. et al. Identification of Parkinson’s disease and multiple system atrophy using multimodal PET/MRI radiomics. Eur Radiol 34, 662–672 (2024). https://doi.org/10.1007/s00330-023-10003-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-023-10003-9