Deep Transfer Learning for Parkinson’s Disease Monitoring by Image-Based Representation of Resting-State EEG Using Directional Connectivity
Open Access
- 24 December 2021
- journal article
- research article
- Published by MDPI AG in Algorithms
- Vol. 15 (1) , 5
Abstract
Parkinson’s disease (PD) is characterized by abnormal brain oscillations that can change rapidly. Tracking neural alternations with high temporal resolution electrophysiological monitoring methods such as EEG can lead to valuable information about alterations observed in PD. Concomitantly, there have been advances in the high-accuracy performance of deep neural networks (DNNs) using few-patient data. In this study, we propose a method to transform resting-state EEG data into a deep latent space to classify PD subjects from healthy cases. We first used a general orthogonalized directed coherence (gOPDC) method to compute directional connectivity (DC) between all pairwise EEG channels in four frequency bands (Theta, Alpha, Beta, and Gamma) and then converted the DC maps into 2D images. We then used the VGG-16 architecture (trained on the ImageNet dataset) as our pre-trained model, enlisted weights of convolutional layers as initial weights, and fine-tuned all layer weights with our data. After training, the classification achieved 99.62% accuracy, 100% precision, 99.17% recall, 0.9958 F1 score, and 0.9958 AUC averaged for 10 random repetitions of training/evaluating on the proposed deep transfer learning (DTL) network. Using the latent features learned by the network and employing LASSO regression, we found that latent features (as opposed to the raw DC values) were significantly correlated with five clinical indices routinely measured: left and right finger tapping, left and right tremor, and body bradykinesia. Our results demonstrate the power of transfer learning and latent space derivation for the development of oscillatory biomarkers in PD.Keywords
This publication has 37 references indexed in Scilit:
- Interregional Correlations in Parkinson Disease and Parkinson-related Dementia with Resting Functional MR ImagingRadiology, 2012
- Sparse Discriminant AnalysisTechnometrics, 2011
- Altered directional connectivity in Parkinson's disease during performance of a visually guided taskNeuroImage, 2011
- EEG Patterns in Mild Cognitive Impairment (MCI) PatientsThe Open Neuroimaging Journal, 2008
- Interhemispheric and ipsilateral connections in Parkinson's disease: Relation to mirror movementsMovement Disorders, 2007
- Basal ganglia oscillations and pathophysiology of movement disordersCurrent Opinion in Neurobiology, 2006
- Imaging in Parkinson’s Disease: The Role of Monoamines in BehaviorBiological Psychiatry, 2006
- Staging of brain pathology related to sporadic Parkinson’s diseaseNeurobiology of Aging, 2003
- Studying the Interaction Between Brain Structures via Directed Coherence and Granger CausalityApplied Signal Processing, 1998
- Investigating Causal Relations by Econometric Models and Cross-spectral MethodsEconometrica, 1969