To provide an automated classification method for degenerative parkinsonian syndromes (PS) based on semiquantitative 123I-FP-CIT SPECT striatal indices and support-vector-machine (SVM) analysis.
123I-FP-CIT SPECT was performed at a single-center level on 370 individuals with PS, including 280 patients with Parkinson’s disease (PD), 21 with multiple system atrophy-parkinsonian type (MSA-P), 41 with progressive supranuclear palsy (PSP) and 28 with corticobasal syndrome (CBS) (mean age 70.3 years, 47% female, mean disease duration at scan 1.4 year), as well as 208 age- and gender-matched control subjects. Striatal volumes-of-interest (VOIs) uptake, VOIs asymmetry indices (AIs) and caudate/putamen (C/P) ratio were used as input for SVM individual classification using fivefold cross-validation.
Univariate analyses showed significantly lower VOIs uptake, higher striatal AI and C/P ratio for each PS in comparison to controls (all p < 0.001). Among PS, higher degree of striatal impairment was observed in MSA-P and PSP, while CBS showed moderate uptake reduction and higher AI. Binary SVM classification showed 92.9% accuracy in distinguishing PS from controls. Classification based on each binary combination of PS ranged 62.9–83.7% accuracy with the most satisfactory results when separating CBS from the other PS. Sensitivity and specificity values were high and balanced ranging from 60 to 80% for all analyses with > 70% accuracy. Overall, striatal AI and C/P ratio on the more affected side had the highest weighting factors.
Semiquantitative 123I-FP-CIT SPECT striatal evaluation combined with SVM represents a promising approach to disentangle PD from non-degenerative conditions and from atypical PS at the early stage.
Postuma RB, Berg B, Stern M, Poewe W, Olanow CW, Oertel W et al (2015) MDS clinical diagnostic criteria for Parkinson's disease. Mov Disord 30:1591–1601 CrossRef
Nicastro N, Garibotto V, Burkhard PR (2018) The role of molecular imaging in assessing degenerative parkinsonism—an updated review. Swiss Med Wkly 148:w14621 PubMed
Tissingh G, Bergmans P, Booij J, Winogrodzka A, Stoof JC, Wolters EC, Van Royen EA (1997) [123I]beta-CIT single-photon emission tomography in Parkinson's disease reveals a smaller decline in dopamine transporters with age than in controls. Eur J Nucl Med 24:1171–1174 PubMed
Antonini A, Benti R, De Notaris R, Tesei S, Zecchinelli A, Sacilotto G, Meucci N, Canesi M, Mariani C, Pezzoli G, Gerundini P (2003) 123I-Ioflupane/SPECT binding to striatal dopamine transporter (DAT) uptake in patients with Parkinson's disease, multiple system atrophy, and progressive supranuclear palsy. Neurol Sci 24:149–150 CrossRefPubMed
Huppertz HJ, Moller L, Sudmeyer M, Hilker R, Hattingen E, Egger K et al (2016) Differentiation of neurodegenerative parkinsonian syndromes by volumetric magnetic resonance imaging analysis and support vector machine classification. Mov Disord 31:1506–1517 CrossRef
Castillo-Barnes D, Ramirez J, Segovia F, Martinez-Murcia FJ, Salas-Gonzalez D, Gorriz JM (2018) Robust ensemble classification methodology for I123-Ioflupane SPECT images and multiple heterogeneous biomarkers in the diagnosis of Parkinson's disease. Front Neuroinform 12:53 CrossRefPubMedPubMedCentral
Martinez-Murcia F, Górriz J, Ramírez J, Illan IA, Ortiz A (2014) Automatic detection of Parkinsonism using significance measures and component analysis in datscan imaging. Neurocomputing 126(Suppl. C):58–70 CrossRef
Lunardon N, Menardi G, Torelli N (2014) Rose—a package for binary imbalanced learning. R J 6:79–89 CrossRef
Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th international joint conference on artificial intelligence vol 2, pp 1137–1145
- Classification of degenerative parkinsonism subtypes by support-vector-machine analysis and striatal 123I-FP-CIT indices
Maria Giulia Preti
Dimitri Van de Ville
Pierre R. Burkhard
- Springer Berlin Heidelberg
Neu im Fachgebiet Neurologie
Meistgelesene Bücher in der Neurologie
Mail Icon II