Diagnostic Accuracy of Parkinson Disease by Support Vector Machine (SVM) Analysis of 123I-FP-CIT Brain SPECT Data

Abstract

Brain single-photon-emission-computerized tomography (SPECT) with 123I-ioflupane (123I-FP-CIT) is useful to diagnose Parkinson disease (PD). To investigate the diagnostic performance of 123I-FP-CIT brain SPECT with semiquantitative analysis by Basal Ganglia V2 software (BasGan), we evaluated semiquantitative data of patients with suspect of PD by a support vector machine classifier (SVM), a powerful supervised classification algorithm.123I-FP-CIT SPECT with BasGan analysis was performed in 90 patients with suspect of PD showing mild symptoms (bradykinesia-rigidity and mild tremor). PD was confirmed in 56 patients, 34 resulted non-PD (essential tremor and drug-induced Parkinsonism). A clinical follow-up of at least 6 months confirmed diagnosis. To investigate BasGan diagnostic performance we trained SVM classification models featuring different descriptors using both a “leave-one-out” and a “five-fold” method. In the first study we used as class descriptors the semiquantitative radiopharmaceutical uptake values in the left (L) and right (R) putamen (P) and in the L and R caudate nucleus (C) for a total of 4 descriptors (CL, CR, PL, PR). In the second study each patient was described only by CL and CR, while in the third by PL and PR descriptors. Age was added as a further descriptor to evaluate its influence in the classification performance.123I-FP-CIT SPECT with BasGan analysis reached a classification performance higher than 73.9% in all the models. Considering the “Leave-one-out” method, PL and PR were better predictors (accuracy of 91% for all patients) than CL and CR descriptors; using PL, PR, CL, and CR diagnostic accuracy was similar to that of PL and PR descriptors in the different groups. Adding age as a further descriptor accuracy improved in all the models. The best results were obtained by using all the 5 descriptors both in PD and non-PD subjects (CR and CL + PR and PL + age = 96.4% and 94.1%, respectively). Similar results were observed for the “five-fold” method.123I-FP-CIT SPECT with BasGan analysis using SVM classifier was able to diagnose PD. Putamen was the most discriminative descriptor for PD and the patient age influenced the classification accuracy.

Discriminating among degenerative parkinsonisms using advanced 123 I-ioflupane SPECT analyses

“…Two previous investigations by Palumbo et al and by Segovia et al assessed classification performance of PD versus controls ( Palumbo et al, 2014 , Segovia et al, 2012 ). Note that the classification accuracies of 73.9% and 94.7%, respectively, exceed the classification accuracy of the current investigation due to the fact that the discrimination of a disease condition associated with a clear dopaminergic depletion versus a healthy control group is much easier than the classification of several disease conditions which significantly affect the dopaminergic system.…”

“…Previous investigations applying support vector machines (SVM), a type of Multi Voxel Pattern Analysis (MVPA), successfully discriminated PD from APS patients based on MRI diffusion tensor imaging (DTI) ( Haller et al, 2012 ), MRI susceptibility weighted imaging (SWI) ( Haller et al, 2013 ) and gait analysis ( Tahir and Manap, 2012 ). This SVM classification technique was also applied to 123 I-ioflupane SPECT data to discriminate 95 PD versus 94 controls ( Segovia et al, 2012 ) and to discriminate 56 PD versus 34 non-PD (essential tremor and drug-induced parkinsonism) patients ( Palumbo et al, 2014 ). A comparison between PD and APS was not performed as yet.…”

Parkinson's Disease Detection Using Isosurfaces-Based Features and Convolutional Neural Networks

“…This is addressed by sampling the 3D images using fractal curves in order to transform the 3D DatSCAN images into 1D signals, preserving the neighborhood relationship among voxels. Striatal binding ratios for both caudates and putamina were used in Prashanth et al (2014), Palumbo et al (2014), and Bhalchandra et al (2015). Martínez-Murcia et al (2014b) proposed the extraction of 3D textural-based features (Haralick texture features) for the characterization of the dopamine transporters concentration in the image.…”

A Shape Approximation for Medical Imaging Data

“…For instance, Ziegler et al [ 6 ] used multispectral structural magnetic resonance imaging (MRI) tools to measure substantia nigra volume loss before basal forebrain degeneration in early PD. Palumbo et al [ 7 ] proposed a volumetric 3D region of interest (ROI) of putamen and caudate nucleus by BasGan software. Prashanth et al [ 8 ] proposed to draw ‘indirect 3D features’ by building a regression surface of an ROI based on the 2D-combined image.…”

“…Most of the aforementioned studies of drawing 3D features focused on computing the volumes of the ROI and applying the quantities derived from the volumes of the ROI to PD identification [ 6 , 7 , 9 , 10 , 11 ]. Although the geometric features such as volume and the volume-related quantities are valuable proxies representing the 3D shapes of the ROI, they still cannot fully capture the desired shapes since different shapes of the ROI could have the same volumes or volume-related quantities.…”