Applications of neural network analyses to in vivo ¹H magnetic resonance spectroscopy of Parkinson disease patients

Abstract

Purpose: To apply neural network analyses to in vivo magnetic resonance spectra of controls and Parkinson disease (PD) patients for the purpose of classification. Materials and Methods:Ninety-seven in vivo proton magnetic resonance spectra of the basal ganglia were recorded from 31 patients with (PD) and 14 age-matched healthy volunteers on a 1.5-T imager. The PD patients were grouped as follows: probable PD (N ϭ 15), possible PD (N ϭ 11), and atypical PD (N ϭ 5). Total acquisition times of approximately five minutes were achieved with a TE (echo time) of 135 msec, a TR (repetition time) of 2000 msec, and 128 scan averages. Neural network (back propagation, Kohonen, probabilistic, and radial basis function) and related (generative topographic mapping) data analyses were performed.Results: Conventional data analysis showed no statistically significant differences in metabolite ratios based on measuring signal intensities. The trained networks could distinguish control from PD with considerable accuracy (true positive fraction 0.971, true negative fraction 0.933). When four classes were defined, approximately 88% of the predictions were correct. The multivariate analysis indicated metabolic changes in the basal ganglia in PD. Conclusion:A variety of neural network and related approaches can be successfully applied to both qualitative visualization and classification of in vivo spectra of PD patients.

Unsupervised feature dimension reduction for classification of MR spectra

“…Consequently, the combinatorial explosion due to the large number of features was effectively prevented when using the dynamic programming-based feature extraction. Note that data processed by our technique may be used in connection with any other optimization technique such as a genetic algorithm for feature extraction or other classification techniques, including neural networks [11], support vector machines etc. It may be also used as a preprocessing step for more sophisticated dimension reduction techniques [12].…”

MR Spectroscopy in Neurodegenerative Disease

“…Axelson and colleagues have developed an interesting alternate approach to the analysis of spectroscopic data based on pattern recognition with an artificial neural network [29]. These investigators reported that, while conventional data analysis, i.e., estimation of metabolite ratios from peak area measurements, showed no significant abnormalities in PD, trained neural networks could distinguish control from PD spectra with considerable accuracy.…”

Fast quantification of proton magnetic resonance spectroscopic imaging with artificial neural networks

“…[12]), were used to train the RBFNN. [12] where the Lorentzian peak is defined as, [13] and the Gaussian peak is defined as,…”

“…Such a goal could possibly be realized using methods based on artificial neural networks (ANN). The ability of ANN for classification of spectra for various pathologies has been demonstrated [6][7][8][9][10][11][12][13][14]. However, relatively little attention has been paid to metabolite quantification using ANN [15][16].…”