Classification of Parkinsonian syndromes from FDG-PET brain data using decision trees with SSM/PCA features

Abstract

Medical imaging techniques like fluorodeoxyglucose positron emission tomography (FDG-PET) have been used to aid in the differential diagnosis of neurodegenerative brain diseases. In this study, the objective is to classify FDG-PET brain scans of subjects with Parkinsonian syndromes (Parkinson's disease, multiple system atrophy, and progressive supranuclear palsy) compared to healthy controls. The scaled subprofile model/principal component analysis (SSM/PCA) method was applied to FDG-PET brain image data to obtain covariance patterns and corresponding subject scores. The latter were used as features for supervised classification by the C4.5 decision tree method. Leave-one-out cross validation was applied to determine classifier performance. We carried out a comparison with other types of classifiers. The big advantage of decision tree classification is that the results are easy to understand by humans. A visual representation of decision trees strongly supports the interpretation process, which is very important in the context of medical diagnosis. Further improvements are suggested based on enlarging the number of the training data, enhancing the decision tree method by bagging, and adding additional features based on (f)MRI data.

Figure 1

Classification steps.

Figure 2

The decision tree built from the PD-HC dataset. Oval-shaped interior nodes: features (subject scores) used to split the data. Threshold values are shown next to the arrows. Rectangular leaf nodes: the final class labels (red = PD, blue = HC).

Figure 3

The decision trees built from the MSA-HC (a) and PSP-HC (b) datasets. For details, refer to Figure 2.

Figure 4

The decision tree built from the combined PD-PSP-MSA-HC dataset.

Figure 5

The decision tree built from the disease groups compared to each other, that is, PD-PSP-MSA dataset.