ISSN 0869-6632 (Print)
ISSN 2542-1905 (Online)

The article published as Early Access!

This is an open access article distributed under the terms of Creative Commons Attribution 4.0 International License (CC-BY 4.0).
Full text PDF(Ru):
PDF icon and_2025-1_shusharina_ranniy_dostup.pdf
(downloads: 0)
Language: 
Russian
Heading: 
Nonlinear Dynamics and Neuroscience
Article type: 
Article
UDC: 
004.78
DOI: 
10.18500/0869-6632-003126
EDN: 
BMEUDZ

Comparative analysis of transfer learning performance on generalised EEG data for use in a depression diagnosis task

Autors: 
Shusharina Natalia Nikolaevna, Immanuel Kant Baltic Federal University
Abstract: 

The purpose of this work was to analyse the performance of different deep learning methods in the task of depression diagnosis based on bioelectrical brain activity data. In particular, to study the potential of transfer learning using an artificial neural network trained on a significant amount of “generalised” electroencephalography data in the task of diagnosing depression from non-invasive electroencephalogram signals.

Methods. Deep learning approaches such as transfer learning and contrastive learning were used in the present study. Artificial neural networks were trained on the public HBN EO/EC task dataset containing recordings of electroencephalogram signals. The 1D CNN and EEGNet architectures were used as auxiliary artificial networks for transfer learning. In order to test the quality of contrastive learning, the dataset was augmented and the following algorithms were selected as the donor network: SimCLR, MoCo, NNCLR, BarlowTwins, DINO.

Results. It was found that the EEGNet architecture used as a auxiliary network, due to its small size, does not give the full potential of contrastive learning algorithms. Therefore, EEGNet was replaced by a 1D CNN architecture with a larger number of parameters, which led to an increase in the quality performance of the models.

Conclusion. Although the considered method of transient learning looks promising, the specificity of electroencephalogram signals and problems solved on their basis requires large-scale adaptation of algorithms and contrastive optimisation techniques for effective training of the target task. It is also worth noting the crucial role of the representativeness of the data set for training the donor network, since it is the completeness of real observations that increases the effectiveness of augmentation, which leads to an increase in the number of “useful” features in the latent space of the network and the best conditions for transfer learning in the target task. If we talk about the diagnosis of depression, the data should maximally represent examples of electroencephalograms of depressed patients.
 

Key words: 
diagnosis
depression
electroencephalography
artificial neural network
transfer learning
contrastive learning
Acknowledgments: 
This work was supported by grant RSF (project No. 23-71-30010)
Reference: 
  1. Karpov OE, Khramov AE. Information technologies, computing systems and artificial intelligence in medicine. Moscow: DPK Press; 2022. 479 p.
  2. Karpov O. E., Pitsik E. N., Kurkin S. A., Maksimenko V. A., Gusev A. V., Shusharina N. N., Hramov A. E. Analysis of publication activity and research trends in the field of aI medical applications: Network approach // International Journal of Environmental Research and Public Health. 2023. Vol. 20, iss. 7. С. 5335. DOI: 10.3390/ijerph20075335.
  3. Yuan J., Ran X., Liu K., Yao C., Yao Y., Wu H., Liu Q. Machine learning applications on neuroimaging for diagnosis and prognosis of epilepsy: A review // Journal of Neuroscience Methods. 2022. Vol. 15, iss. 368. P. 109441. DOI: 10.1016/j.jneumeth.2021.109441.
  4. Karpov O. E., Grubov V. V., Maksimenko V. A., Kurkin S. A., Smirnov N. M., Utyashev N. P., Andrikov D. A., Shusharina N. N., Hramov A. E. Extreme value theory inspires explainable machine learning approach for seizure detection // Scientific Reports. 2022. Vol. 12. P. 11474. DOI: 10.1038/s41598-022-15675-9.
  5. Karpov O. E., Afinogenov S., Grubov V. V., Maksimenko V., Korchagin S., Utyashev N., Hramov A. E. Detecting epileptic seizures using machine learning and interpretable features of human EEG // The European Physical Journal Special Topics. 2023. Vol. 232, no. 5. P. 673–682. DOI: 10.1140/epjs/s11734-022-00714-3.
  6. Erguzel T. T., Sayar G. H., Tarhan N. Artificial intelligence approach to classify unipolar and bipolar depressive disorders // Neural Computing and Applications. 2016. Vol. 27, iss. 6. P. 1607-1616. DOI: 10.1007/s00521-015-1959-z.
  7. Andreev A. V., Kurkin S. A., Stoyanov D., Badarin A. A., Paunova R., Hramov A. E. Toward interpretability of machine learning methods for the classification of patients with major depressive disorder based on functional network measures // Chaos. 2023. Vol. 33, iss. 6. P. 063140. DOI: 10.1063/5.0155567.
  8. Stoyanov D., Khorev V., Paunova R., Kandilarova S., Simeonova D., Badarin A., Hramov A., Kurkin S. Resting-state functional connectivity impairment in patients with major depressive episode // International Journal of Environmental Research and Public Health. 2022. Vol. 19, iss. 21. P. 14045. DOI: 10.3390/ijerph192114045.
  9. Chaddad A., Li J., Lu Q., Li Y., Okuwobi I. P., Tanougast C., Desrosiers C., Niazi T. Can autism Be diagnosed with artificial intelligence? A narrative review // Diagnostics. 2021. Vol. 11, iss. 11. P. 2032. DOI: 10.3390/diagnostics11112032.
  10. Song D. Y., Kim S. Y., Bong G., Kim J. M., Yoo H. J. The use of artificial intelligence in screening and diagnosis of autism spectrum disorder: a literature review // Journal of the Korean Academy of Child and Adolescent Psychiatry. 2019. Vol. 30. iss. 4. P. 145-152. DOI: 10.5765/jkacap.190027.
  11. Sysoeva O., Maximenko V., Kuc A., Voinova V., Martynova O., Hramov A. Abnormal spectral and scale-free properties of resting-state EEG in girls with Rett syndrome // Scientific Reports. 2023. Vlo. 13. P. 12932. DOI: 10.1038/s41598-023-39398-7.
  12. Zhang Z., Li G., Xu Y., Tang X. Application of artificial intelligence in the MRI classification task of human brain neurological and psychiatric diseases: A scoping review // Diagnostics. 2021. Vol. 11, iss. 8. P. 1402. DOI: 10.3390/diagnostics11081402.
  13. Pitsik E. N., Maximenko V. A., Kurkin S. A., Sergeev A. P., Stoyanov D., Paunova R., Kandilarova S., Simeonova D., Hramov A. E. The topology of fMRI-based networks defines the performance of a graph neural network for the classification of patients with major depressive disorder // Chaos, Solitons & Fractals. 2023. Vol. 167. P. 113041. DOI: 10.1016/j.chaos.2022.113041.
  14. Ramzan F., Khan M. U., Rehmat A., Iqbal S., Saba T., Rehman A., Mehmood Z. A deep learning approach for automated diagnosis and multi-class classification of Alzheimer’s disease stages using resting-state fMRI and residual neural networks // Journal of Medical Systems. 2020. Vol. 44. P. 1-6. DOI: 10.1007/s10916-019-1475-2.
  15. Alorf A., Khan M. U. Multi-label classification of Alzheimer’s disease stages from resting-state fMRI-based correlation connectivity data and deep learning // Computers in Biology and Medicine. 2022. Vol. 151, iss. 6. P. 106240. DOI: 10.1016/j.compbiomed.2022.106240.
  16. Subha D. P., Joseph P. K., Acharya U. R., Lim C. M. EEG signal analysis: a survey // Journal of Medical Systems. 2010. Vol. 34, iss. 2. P. 195-212. DOI: 10.1007/s10916-008-9231-z.
  17. Lotte F., Congedo M., Lecuyer A., Fabrice L., Arnaldi B. A review of classification algorithms for EEG-based brain–computer interfaces // Journal of Neural Engineering. 2007. Vol. 4, iss. 2. P. R1. DOI: 10.1088/1741-2560/4/2/R01.
  18. Kang H., Nam Y., Choi S. Composite common spatial pattern for subject-to-subject transfer // IEEE Signal Processing Letters. 2009. Vol. 16, iss. 8. P. 683-686. DOI: 10.1109/LSP.2009.2022557.
  19. Wan Z., Yang R., Huang M., Zeng N., Liu X. A review on transfer learning in EEG signal analysis // Neurocomputing. 2021. Vol. 421. P. 1-14. DOI: 10.1016/j.neucom.2020.09.017.
  20. Wu D., Xu Y., Lu B.-L. Transfer Learning for EEG-Based Brain-Computer Interfaces: A Review of Progress Made Since 2016 // IEEE Trans. on Cognitive and Developmental Systems. 2022. Vol. 14, iss. 1. P. 4-19. DOI: 10.1109/TCDS.2020.3007453.
  21. Kuc A., Korchagin S., Maksimenko V. A., Shusharina N., Hramov A. E. Combining statistical analysis and machine learning for EEG scalp topograms classification // Frontiers in Systems Neuroscience. 2021. Vol. 15. DOI: 10.3389/fnsys.2021.716897.
  22. Luo Y., Lu B.-L. EEG data augmentation for emotion recognition using a conditional Wasserstein GAN // 2018 40th annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEE, 2018. P. 2535-2538. DOI: 10.1109/EMBC.2018.8512865.
  23. Weiss K., Khoshgoftaar T. M., Wang D. D. A survey of transfer learning // Journal of Big data. 2016. Vol. 3, iss. 1. P. 1-40. DOI: 10.1186/s40537-016-0043-6.
  24. Azab A. M., Ahmadi H., Mihaylova L., Arvaneh M. Dynamic time warping-based transfer learning for improving common spatial patterns in brain–computer interface // Journal of Neural Engineering. 2020. Vol. 17, iss. 1. P. 016061. DOI: 10.1088/1741-2552/ab64a0.
  25. Raghu S., Natarajan S., Temel Y., Rao S. V., Kubben P. EEG based multi-class seizure type classification using convolutional neural network and transfer learning // Neural Networks. 2020. Vol. 124. P. 202-212. DOI: 10.1016/j.neunet.2020.01.017.
  26. Nejedly P., Cimbalnik J., Klimes P., Plesinger F., Halamek J., Kremen V., Viscor I., Brinkmann B. H., Pail M., Brazdil M., Worrell G., Jurak P. Intracerebral EEG artifact identification using convolutional neural networks // Neuroinformatics. 2019. Vol. 17, iss. 3. P. 225-234. DOI: 10.1007/s12021-018-9397-6.
  27. Hramov A. E., Maksimenko V. A., Pisarchik A. N. Physical principles of brain-computer interfaces and their applications for rehabilitation, robotics and control of human brain states // Physics Reports. 2021. Vol. 918. P. 1-133. DOI: 10.1016/j.physrep.2021.03.002.
  28. Shen X., Liu X., Hu X., Zhang D., Song S., Contrastive learning of subject-invariant EEG representations for cross-subject emotion recognition // IEEE Transactions on Affective Computing. 2023. Vol. 14, no. 3. P. 2496-2511. DOI: 10.1109/TAFFC.2022.3164516.
  29. Chen T., Kornblith S., Norouzi M., Hinton G. A simple framework for contrastive learning of visual representations // International conference on machine learning (PMLR). 2020. P. 1597-1607. arXiv:2002.05709. DOI: 10.48550/arXiv.2002.05709.
  30. Jaiswal A., Babu A. R., Zadeh M. Z., Banerjee D., Makedon F. A survey on contrastive selfsupervised learning // Technologies. 2020. Vol. 9, iss. 1. P. 2. DOI: 10.3390/technologies9010002.
  31. Zygierewicz J., Janik R. A., Podolak I. T., Drozd A., Malinowska U., Poziomska M., Wojciechowski J., Ogniewski P., Niedbalski P., Terczynska I., Rogala J. Decoding working memory-related information from repeated psychophysiological EEG experiments using convolutional and contrastive neural networks // Journal of Neural Engineering. 2022. Vol. 19, iss. 4. P. 046053. DOI: 10.1088/1741- 2552/ac8b38.
  32. Hadsell R., Chopra S., LeCun Y. Dimensionality reduction by learning an invariant mapping // 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2 (CVPR’06). IEEE, 2006. P. 1735-1742. DOI: 10.1109/CVPR.2006.100.
  33. He K., Fan H., Wu Y., Xie S., Girshick R. Momentum contrast for unsupervised visual representation learning // Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020. P. 9729-9738. DOI: 10.1109/CVPR42600.2020.00975.
  34. Dwibedi D., Aytar Y., Tompson J., Sermanet P., Zisserman A. With a little help from my friends: Nearest-neighbor contrastive learning of visual representations // Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada, 2021. P. 9588-9597. DOI: 10.1109/ICCV48922.2021.00945.
  35. Zbontar J., Jing L., Misra I., LeCun Y., Deny S. Barlow twins: Self-supervised learning via redundancy reduction // International Conference on Machine Learning (PMLR), 2021. P. 12310- 12320. arXiv:2103.03230. DOI: 10.48550/arXiv.2103.03230.
  36. Caron M., Touvron H., Misra I., Jegou H., Mairal J., Bojanowski P., Joulin A. Emerging properties in self-supervised vision transformers // Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021. С. 9650-9660. arXiv:2104.14294. DOI: 10.48550/arXiv.2104.14294
  37. Self-supervised Contrastive Learning for Image Classification with Keras [Electronic resource]. https://github.com/beresandras/contrastive-classification-keras (Date of reference: 16.01.2024).
  38. Alexander L. M., Escalera J., Ai L., Andreotti C., Febre K., Mangone A., Vega-Potler N., Langer N., Alexander A., Kovacs M., Litke S., OHagan B., Andersen J., Bronstein B., Bui A., Bushey M., Butler H., Castagna V., Camacho N., Chan E., Citera D., Clucas J., Cohen S., Dufek S., Eaves M., Fradera B., Gardner J., Grant-Villegas N., Green G., Gregory C., Hart E., Harris S., Horton M., Kahn D., Kabotyanski K., Karmel B., Kelly S. P., Kleinman K., Koo B., Kramer E., Lennon E., Lord C., Mantello G., Margolis A., Merikangas K. R., Milham J., Minniti G., Neuhaus R., Levine A., Osman Y., Parra L. C., Pugh K. R., Racanello A., Restrepo A., Saltzman T., Septimus B., Tobe R., Waltz R., Williams A., Yeo A., Castellanos F. X., Klein A., Paus T., Leventhal B. L., Craddock R. C., Koplewicz H. S., Milham M. P. HBN EO/EC task. OpenNeuro Accession Number ds004186. DOI: doi:10.18112/openneuro.ds004186.v2.0.0.
  39. Gramfort A., Luessi M., Larson E., Engemann D. A., Strohmeier D., Brodbeck C., Goj R., Jas M., Brooks T., Parkkonen L., Hamalainen M. MEG and EEG data analysis with MNE-Python // Frontiers in Neuroscience. 2013. Vol. 7. P. 267. DOI: 10.3389/fnins.2013.00267. 
  40. Mumtaz W. MDD Patients and Healthy Controls EEG Data (New). Dataset. 2016. DOI: 10.6084/ m9.figshare.4244171.v2
  41. Cavanagh J. F. EEG: Depression rest. Dataset. 2021. DOI: 10.18112/openneuro.ds003478.v1.1.0.
  42. Cai H., Gao Y., Sun S., Li N., Tian F., Xiao H., Hu B. MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis. arXiv:2002.09283. 2020. http://modma.lzu.edu.cn/data/application/.
  43. van Dijk H., van Wingen G. A., Denys D., Olbrich S., van Ruth R., Arns M. The two decades brainclinics research archive for insights in neurophysiology (TDBRAIN) database // Scientific Data. 2022. Vol. 9, iss. 1. P. 1-10. DOI: 10.1038/s41597-022-01409-z.
  44. Maaten L., Hinton G. Visualizing data using t-sne // Journal of Machine Learning Research. 2008. Vol. 9. P. 2579-2605.
  45. Sandheep P., Vineeth S., Poulose M., Subha D. P. Performance analysis of deep learning CNN in classification of depression EEG signals // TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON), Kochi, India. IEEE, 2019. P. 1339-1344. DOI: 10.1109/TENCON.2019.8929254.
  46. Lawhern V. J., Solon A. J., Waytowich N., Gordon S. M., Hung C. P., Lance B. J. EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces // Journal of neural engineering. 2018. Vol. 15, iss. 5. P. 056013. DOI: 10.1088/1741-2552/aace8c.
  47. LeCun Y. A., Bottou L., Orr G. B., Muller K.-R. Efficient BackProp // In: Montavon G., Orr G. B., Muller K. R. (eds) Neural Networks: Tricks of the Trade. Lecture Notes in Computer Science, vol. 7700. Berlin, Heidelberg: Springer, 2012. P. 9-48.
  48. van Dijk H., Koppenberg M., Arns M. Towards robust, reproducible, and clinically actionable EEG biomarkers: Large open access EEG Database for discovery and out-of-sample validation // Clinical EEG and Neuroscience. 2022. Vol. 54, iss. 2. DOI: 10.1177/15500594221120516.
  49. Darvishi-Bayazi M.-J., Ghaemi M. S., Lesort T., Arefin Md R., Faubert J., Rish I. Amplifying pathological detection in EEG signaling pathways through cross-dataset transfer learning. arXiv:2309.10910. DOI: 10.48550/arXiv.2309.10910
  50. Zeng H., Li X., Borghini G., Zhao Y., Arico P., Di Flumeri G., Sciaraffa N., Zakaria W., Kong W., Babiloni F. An EEG-based transfer learning method for cross-subject fatigue mental state prediction // Sensors. 2021. Vol. 21, iss. 7. P. 2369. DOI: 10.3390/s21072369.
  51. Zhang K., Xu G., Zheng X., Li H., Zhang S., Yu Y., Liang R. Application of transfer learning in EEG decoding based on brain-computer interfaces: A review // Sensors. 2020. Vol. 20, iss. 21. P. 1-25. DOI: 10.3390/s20216321.
  52. Deep Learning Applications. Vol. 4 / M. Arif Wani, Vasile Palade (eds.). Advances in Intelligent Systems and Computing, Vol. 1434. Singapore: Springer, 2023. 384 p. DOI: 10.1007/978-981- 19-6153-3
  53. Seal A., Bajpai R., Agnihotri J., Yazidi A., Herrera-Viedma E., Krejcar O. DeprNet: A deep convolution neural network framework for detecting depression using EEG // IEEE Transactions on Instrumentation and Measurement. 2021. Vol. 70. P. 1-13. 2505413. DOI: 10.1109/TIM.2021.3053999.
  54. Sharma G., Parashar A., Joshi A. M. DepHNN: A novel hybrid neural network for electroencephalogram (EEG)-based screening of depression // Biomedical Signal Processing and Control. 2021. Vol. 66. P. 102393. DOI: 10.1016/j.bspc.2020.102393.
  55. Uran A., van Gemeren C., van Diepen R., Chavarriaga R., del R. Millan J. Applying transfer learning to deep learned models for EEG analysis. arXiv:1907.01332. DOI: 10.48550/ arXiv.1907.01332.
  56. Osman Berke Guney, Huseyin Ozkan Transfer Learning of an Ensemble of DNNs for SSVEP BCI Spellers without User-Specific Training. arXiv:2209.01511. DOI: 10.48550/arXiv.2209.01511.
  57. Ju C., Gao D., Mane R., Tan B., Liu Y., Guan C. Federated Transfer Learning for EEG Signal Classification // 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada, 2020. P. 3040-3045. DOI: 10.1109/EMBC44109.2020.9175344.
  58. Khosla P., Teterwak P., Wang C., Sarna A., Tian Y., Isola Ph., Maschinot A., Liu C., Krishnan D. Supervised contrastive learning // Advances in Neural Information Processing Systems. 2020. Vol. 33. P. 18661-18673. ArXiv:abs/2004.11362. https://api.semanticscholar.org/CorpusID:216080787.
  59. Lv Z., Zhang J., Epota Oma E. A novel method of emotion recognition from multi-band EEG topology maps based on ERENet // Appl. Sci. 2022. Vol. 12. 10273. DOI: https://doi.org/10.3390/app122010273.
  60. Xiao J., Provenzaa N. R., Asfouric J., Myersa J., Mathuraa R. K., Metzgera B., Adkinsona J. A., Allawalad A.B., Pirtlea V., Oswalta D., Shoftya B., Robinsona M.E., Mathewe S.J., Goodmane W.K., Pouratianf N., Schraterg P. R., Patel A. B., Tolias A. S., Bijankia K. R., Pitkowb X., Sheth S. A. Decoding depression severity from intracranial neural activity // Biological Psychiatry. 2023. Vol. 94, iss. 6. P. 445-453. DOI: 10.1016/j.biopsych.2023.01.020.
Received: 
02.02.2024
Accepted: 
26.06.2024
Available online: 
09.10.2024
  • 190 reads