Automatic Classification of Early Parkinson's Disease with Multi-Modal MR Imaging

Abstract

BackgroundIn recent years, neuroimaging has been increasingly used as an objective method for the diagnosis of Parkinson's disease (PD). Most previous studies were based on invasive imaging modalities or on a single modality which was not an ideal diagnostic tool. In this study, we developed a non-invasive technology intended for use in the diagnosis of early PD by integrating the advantages of various modals.Materials and MethodsNineteen early PD patients and twenty-seven normal volunteers participated in this study. For each subject, we collected resting-state functional magnetic resonance imaging (rsfMRI) and structural images. For the rsfMRI images, we extracted the characteristics at three different levels: ALFF (amplitude of low-frequency fluctuations), ReHo (regional homogeneity) and RFCS (regional functional connectivity strength). For the structural images, we extracted the volume characteristics from the gray matter (GM), the white matter (WM) and the cerebrospinal fluid (CSF). A two-sample t-test was used for the feature selection, and then the remaining features were fused for classification. Finally a classifier for early PD patients and normal control subjects was identified from support vector machine training. The performance of the classifier was evaluated using the leave-one-out cross-validation method.ResultsUsing the proposed methods to classify the data set, good results (accuracy = 86.96%, sensitivity = 78.95%, specificity = 92.59%) were obtained.ConclusionsThis method demonstrates a promising diagnosis performance by the integration of information from a variety of imaging modalities, and it shows potential for improving the clinical diagnosis and treatment of PD.

Abnormal functional connectivity density in Parkinson's disease

“…This finding is consistent with a previous study, which reported a higher connectivity degree in the PCC and precuneus in PD patients compared with healthy controls [37]. Additionally, increased regional homogeneity and gray matter volume have been reported in the PCC and precuneus in PD patients compared with healthy controls [38,39]. However, the exact mechanism underlying the increased FCD is still unclear.…”

Decreased and increased cerebral regional homogeneity in early Parkinson's disease

“…When we estimate a candidate PD to be positive or negative with ReHo alteration, the specificity of the ReHo approach should be considered. The specificity may be improved by multi-modal imaging (Long et al, 2012) or incorporation in multi-modal classifiers (Joshi et al, 2010).…”

“…Among the various application of fMRI, regional homogeneity (ReHo), a kind of processed fMRI signal, has been utilized in automatic discrimination of early PD (Long et al, 2012). Generally, ReHo analyses were applied to the restingstate fMRI (RS-fMRI) data which records the blood oxygen level-dependent (BOLD) signals while participants lie still inside an MRI scanner.…”

Multi-modal classification of neurodegenerative disease by progressive graph-based transductive learning

“…Since an overwhelming amount of literature exits (Mueller et al, 2005; Ohtsuka et al, 2013) that relate neurodegenerative impairments to morphological abnormalities in the brain, MRI studies that reveal the structural abnormalities of the brain, or PET and SPECT studies that reveal the functional abnormalities of the brain have been widely used. Furthermore, methods that combine structural and functional neuroimaging data have been used to guide computer aided diagnosis techniques (Long et al, 2012; Ohtsuka et al, 2013; Prashanth et al, 2014; Rana et al, 2014; Salvatore et al, 2014; Weiner et al, 2013). More specifically, a technique called OPLS (orthogonal partial least squares to latent structures) is used to distinguish subjects with AD and MCI from healthy controls by combing MRI and CSF data (Westman et al, 2012).…”