{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T16:08:59Z","timestamp":1769270939110,"version":"3.49.0"},"reference-count":43,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2021,12,24]],"date-time":"2021-12-24T00:00:00Z","timestamp":1640304000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Parkinson\u2019s 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.<\/jats:p>","DOI":"10.3390\/a15010005","type":"journal-article","created":{"date-parts":[[2021,12,24]],"date-time":"2021-12-24T08:38:46Z","timestamp":1640335126000},"page":"5","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Deep Transfer Learning for Parkinson\u2019s Disease Monitoring by Image-Based Representation of Resting-State EEG Using Directional Connectivity"],"prefix":"10.3390","volume":"15","author":[{"given":"Emad","family":"Arasteh","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering Department, University of Tehran, Tehran 14395-515, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ailar","family":"Mahdizadeh","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, University of Tehran, Tehran 14395-515, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maryam","family":"Mirian","sequence":"additional","affiliation":[{"name":"Pacific Parkinson\u2019s Research Centre, Djavad Mowafaghian Centre for Brain Health, University of British Columbia, Vancouver, BC V6T 2B5, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soojin","family":"Lee","sequence":"additional","affiliation":[{"name":"Pacific Parkinson\u2019s Research Centre, Djavad Mowafaghian Centre for Brain Health, University of British Columbia, Vancouver, BC V6T 2B5, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4048-0817","authenticated-orcid":false,"given":"Martin","family":"McKeown","sequence":"additional","affiliation":[{"name":"Pacific Parkinson\u2019s Research Centre, Djavad Mowafaghian Centre for Brain Health, University of British Columbia, Vancouver, BC V6T 2B5, Canada"},{"name":"Faculty of Medicine (Neurology), University of British Columbia, Vancouver, BC V6T 2B5, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,12,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1097\/00002060-200101000-00011","article-title":"Resistance training and gait function in patients with Parkinson\u2019s disease","volume":"80","author":"Scandalis","year":"2001","journal-title":"Am. J. Phys. Med. Rehabil."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/S0197-4580(02)00065-9","article-title":"Staging of brain pathology related to sporadic Parkinson\u2019s disease","volume":"24","author":"Braak","year":"2003","journal-title":"Neurobiol. Aging"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"908","DOI":"10.1016\/j.biopsych.2005.12.017","article-title":"Imaging in Parkinson\u2019s disease: The role of monoamines in behavior","volume":"59","author":"Brooks","year":"2006","journal-title":"Biol. Psychiatry"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1016\/j.conb.2006.10.002","article-title":"Basal ganglia oscillations and pathophysiology of movement disorders","volume":"16","author":"Marmor","year":"2006","journal-title":"Curr. Opin. Neurobiol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1175","DOI":"10.1093\/cercor\/bhp178","article-title":"Spatial remapping of cortico-striatal connectivity in Parkinson\u2019s disease","volume":"20","author":"Helmich","year":"2010","journal-title":"Cereb. Cortex"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1148\/radiol.12111280","article-title":"Interregional correlations in Parkinson disease and Parkinson-related dementia with resting functional MR imaging","volume":"263","author":"Seibert","year":"2012","journal-title":"Radiology"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1007\/s11571-013-9247-z","article-title":"Investigation of EEG abnormalities in the early stage of Parkinson\u2019s disease","volume":"7","author":"Han","year":"2013","journal-title":"Cogn. Neurodynamics"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"109282","DOI":"10.1016\/j.jneumeth.2021.109282","article-title":"A convolutional-recurrent neural network approach to resting-state EEG classification in Parkinson\u2019s disease","volume":"361","author":"Lee","year":"2021","journal-title":"J. Neurosci. Methods"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/j.cmpb.2014.01.019","article-title":"Spectral and complexity analysis of scalp EEG characteristics for mild cognitive impairment and early Alzheimer\u2019s disease","volume":"114","author":"McBride","year":"2014","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"52","DOI":"10.2174\/1874440000802010052","article-title":"EEG patterns in mild cognitive impairment (MCI) patients","volume":"2","author":"Baker","year":"2008","journal-title":"Open Neuroimag. J."},{"key":"ref_11","unstructured":"Vialatte, F., Cichocki, A., Dreyfus, G., Musha, T., Rutkowski, T.M., and Gervais, R. (2005, January 28). Blind source separation and sparse bump modelling of time frequency representation of EEG signals: New tools for early detection of Alzheimer\u2019s disease. Proceedings of the 2005 IEEE Workshop on Machine Learning for Signal Processing, Mystic, CT, USA."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"17017","DOI":"10.1109\/JSEN.2021.3080135","article-title":"PDCNNet: An automatic framework for the detection of Parkinson\u2019s Disease using EEG signals","volume":"21","author":"Khare","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"77905","DOI":"10.1109\/ACCESS.2019.2922047","article-title":"An efficient mixture model approach in brain-machine interface systems for extracting the psychological status of mentally impaired persons using EEG signals","volume":"7","author":"Krishna","year":"2019","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Akrofi, K., Pal, R., Baker, M.C., Nutter, B.S., and Schiffer, R.W. (2010, January 14\u201319). Classification of Alzheimer\u2019s disease and mild cognitive impairment by pattern recognition of EEG power and coherence. Proceedings of the 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, Dallas, TX, USA.","DOI":"10.1109\/ICASSP.2010.5495193"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"10927","DOI":"10.1007\/s00521-018-3689-5","article-title":"A deep learning approach for Parkinson\u2019s disease diagnosis from EEG signals","volume":"32","author":"Oh","year":"2020","journal-title":"Neural Comput. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"16009","DOI":"10.1109\/ACCESS.2020.2966834","article-title":"Multilevel feature fusion with 3d convolutional neural network for eeg-based workload estimation","volume":"8","author":"Kwak","year":"2020","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/j.neunet.2020.01.025","article-title":"The feature extraction of resting-state EEG signal from amnestic mild cognitive impairment with type 2 diabetes mellitus based on feature-fusion multispectral image method","volume":"124","author":"Wen","year":"2020","journal-title":"Neural Netw."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Omidvarnia, A.H., Azemi, G., Boashash, B., O\u2019Toole, J.M., Colditz, P., and Vanhatalo, S. (2012, January 12\u201315). Orthogonalized partial directed coherence for functional connectivity analysis of newborn EEG. Proceedings of the International Conference on Neural Information Processing, Doha, Qatar.","DOI":"10.1007\/978-3-642-34481-7_83"},{"key":"ref_19","first-page":"424","article-title":"Investigating causal relations by econometric models and cross-spectral methods","volume":"37","author":"Granger","year":"1969","journal-title":"Econom. J. Econom. Soc."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"902","DOI":"10.1109\/TBME.2007.905419","article-title":"Tracking the time-varying cortical connectivity patterns by adaptive multivariate estimators","volume":"55","author":"Astolfi","year":"2008","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"118","DOI":"10.3389\/fnhum.2019.00118","article-title":"Abnormal phase coupling in Parkinson\u2019s disease and normalization effects of subthreshold vestibular stimulation","volume":"13","author":"Lee","year":"2019","journal-title":"Front. Hum. Neurosci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1198\/TECH.2011.08118","article-title":"Sparse discriminant analysis","volume":"53","author":"Clemmensen","year":"2011","journal-title":"Technometrics"},{"key":"ref_23","first-page":"S11","article-title":"Parkinsonism: Onset, progression and mortality","volume":"57","author":"Hoehn","year":"2001","journal-title":"Neurology"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1080\/14737175.2021.1894928","article-title":"Current perspectives on galvanic vestibular stimulation in the treatment of Parkinson\u2019s disease","volume":"21","author":"Lee","year":"2021","journal-title":"Expert Rev. Neurother."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1007\/s005290050005","article-title":"Studying the interaction between brain structures via directed coherence and Granger causality","volume":"5","author":"Baccala","year":"1998","journal-title":"Appl. Signal Process."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2144","DOI":"10.1016\/j.neuroimage.2011.03.018","article-title":"Altered directional connectivity in Parkinson\u2019s disease during performance of a visually guided task","volume":"56","author":"Tropini","year":"2011","journal-title":"Neuroimage"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"680","DOI":"10.1109\/TBME.2013.2286394","article-title":"Measuring time-varying information flow in scalp EEG signals: Orthogonalized partial directed coherence","volume":"61","author":"Omidvarnia","year":"2013","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1007\/PL00007990","article-title":"Partial directed coherence: A new concept in neural structure determination","volume":"84","author":"Sameshima","year":"2001","journal-title":"Biol. Cybern."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Baccala, L.A., Sameshima, K., and Takahashi, D.Y. (2007, January 1\u20134). Generalized partial directed coherence. Proceedings of the 2007 15th International Conference on Digital Signal Processing, Cardiff, UK.","DOI":"10.1109\/ICDSP.2007.4288544"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"121","DOI":"10.3389\/fncom.2016.00121","article-title":"Volume conduction influences scalp-based connectivity estimates","volume":"10","author":"Brunner","year":"2016","journal-title":"Front. Comput. Neurosci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"884","DOI":"10.1038\/nn.3101","article-title":"Large-scale cortical correlation structure of spontaneous oscillatory activity","volume":"15","author":"Hipp","year":"2012","journal-title":"Nat. Neurosci."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., and Liu, C. (2018, January 4\u20137). A survey on deep transfer learning. Proceedings of the International Conference on Artificial Neural Networks, Rhodes, Greece.","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"ref_33","unstructured":"Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., and Darrell, T. (2014, January 21\u201326). Decaf: A deep convolutional activation feature for generic visual recognition. Proceedings of the International Conference on Machine Learning, Beijing, China."},{"key":"ref_34","unstructured":"Zeiler, M.D., and Fergus, R. (2013, January 2\u20134). Stochastic pooling for regularization of deep convolutional neural networks. Proceedings of the 1st International Conference on Learning Representations, Scottsdale, AZ, USA."},{"key":"ref_35","unstructured":"Simonyan, K., and Zisserman, A. (2015, January 7\u20139). Very Deep Convolutional Networks for Large-Scale Image Recognition. Proceedings of the The 3rd International Conference on Learning Representations, San Diego, CA, USA."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1038\/nm.4246","article-title":"Resting-state connectivity biomarkers define neurophysiological subtypes of depression","volume":"23","author":"Drysdale","year":"2017","journal-title":"Nat. Med."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"3338","DOI":"10.1016\/j.neuropsychologia.2012.09.025","article-title":"The influence of motor and cognitive impairment upon visually-guided saccades in Parkinson\u2019s disease","volume":"50","author":"MacAskill","year":"2012","journal-title":"Neuropsychologia"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J. R. Stat. Soc. Ser. B Methodol."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"759149","DOI":"10.3389\/fneur.2021.759149","article-title":"Galvanic Vestibular Stimulation Effects on EEG Biomarkers of Motor Vigor in Parkinson\u2019s Disease","volume":"12","author":"Kazemi","year":"2021","journal-title":"Front. Neurol."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1002\/mds.21386","article-title":"Interhemispheric and ipsilateral connections in Parkinson\u2019s disease: Relation to mirror movements","volume":"22","author":"Li","year":"2007","journal-title":"Mov. Disord."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1878","DOI":"10.1002\/hbm.22743","article-title":"Lateralization of brain activity pattern during unilateral movement in Parkinson\u2019s disease","volume":"36","author":"Wu","year":"2015","journal-title":"Hum. Brain Mapp."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"S44","DOI":"10.1016\/S1353-8020(13)70013-0","article-title":"The functional role of beta oscillations in Parkinson\u2019s disease","volume":"20","author":"Little","year":"2014","journal-title":"Parkinsonism Relat. Disord."},{"key":"ref_43","unstructured":"(2021, December 19). DTL-GOPDC. Available online: https:\/\/github.com\/DTL-GOPDC."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/15\/1\/5\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:52:49Z","timestamp":1760169169000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/15\/1\/5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,24]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,1]]}},"alternative-id":["a15010005"],"URL":"https:\/\/doi.org\/10.3390\/a15010005","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,24]]}}}