Abstract
Differentiating between Parkinson's disease (PD) and atypical parkinsonian syndromes (APS) is still a challenge, specially at early stages when the patients show similar symptoms. During last years, several computer systems have been proposed in order to improve the diagnosis of PD, but their accuracy is still limited. In this work we demonstrate a full automatic computer system to assist the diagnosis of PD using 18F-DMFP PET data. First, a few regions of interest are selected by means of a two-sample t-test. The accuracy of the selected regions to separate PD from APS patients is then computed using a support vector machine classifier. The accuracy values are finally used to train a Bayesian network that can be used to predict the class of new unseen data. This methodology was evaluated using a database with 87 neuroimages, achieving accuracy rates over 78%. A fair comparison with other similar approaches is also provided.
Highlights
One of the neuropathological hallmarks of Parkinson’s disease (PD; Greenberg et al, 2012) is a substantial decrease in the dopamine content of the striatum due to the progressive death of dopaminergic neurons of the nigrostriatal pathway
We demonstrate a method based on support vector machine (SVM) classification and Bayesian networks to separate idiopathic PD from atypical parkinsonian syndromes (APS) using 18F-DMFP PET data
Support vector machine is a supervised learning method derived from the statistical learning theory, which was developed by Vladimir Vapnik in late 90s (Vapnik, 1999)
Summary
One of the neuropathological hallmarks of Parkinson’s disease (PD; Greenberg et al, 2012) is a substantial decrease in the dopamine content of the striatum due to the progressive death of dopaminergic neurons of the nigrostriatal pathway (a neural pathway that connects the substantia nigra with the striatum). The 123I-ioupane ( known by its tradename DaTSCAN) is a widely-used radioligand that binds to the dopamine transporters in the striatum and allows visualizing the presynaptic striatal dopamine deciency state with high sensitivity. Two approaches are commonly used to learn the network structure: constraint-based and search-and-score The former starts with a fully connected graph, and remove edges if certain conditions are satisfied in the training data. The latter approach performs an exhaustive search in the space of all possible structures, which are evaluated using a predefined scoring function.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
