Leveraging Deep Learning for Enhanced Classification of Depres‎sion Via EEG-Derived Imagery

  • Authors

    • Maithilee Andhare E&TC Department, PCCOER-Ravet, Pune, India
    • Deepali Yewale E&TC Department, AISSMS Institute of Information Technology, Pune, India
    • Shilpa Khedkar Computer Engineering Department, MES Wadia College of Engineering, Pune, India
    • Sharad Jagtap E&TC Department, Anantrao Pawar College of Engineering and Research, Pune, India
    https://doi.org/10.14419/cnq5t832

    Received date: July 28, 2025

    Accepted date: August 31, 2025

    Published date: September 10, 2025

  • Deep Learning; Electroencephalogram (EEG); Major Depressive Disorder; Resnet50V2; Transfer learning

  • Abstract

    Depression is the most prevalent psychological disorder worldwide, affecting individuals irrespective of age and frequently associated with ‎underlying organic etiologies. Its influence extends beyond psychological health, exerting significant effects on physical well-being as well. ‎Clinically, depression is recognized as a neuropsychiatric condition linked to alterations in the brain’s neurochemistry, with its pathogenesis ‎involving a complex interaction among biological, genetic, psychological, and environmental determinants. In this study, we developed a ‎deep learning-based approach for the classification of depression using electroencephalogram (EEG)-derived imagery. Specifically, the ‎ResNet50V2 convolutional neural network architecture was employed to differentiate between EEG images of healthy controls and those ‎diagnosed with Major Depressive Disorder (MDD) based on standard diagnostic criteria. A meticulously curated dataset comprising pre-‎processed EEG images from both cohorts was used to train the model. Transfer learning was applied by leveraging the pretrained ResNet50V2 weights from the ImageNet dataset, facilitating efficient feature extraction tailored for the EEG domain. The model’s performance ‎was evaluated using multiple quantitative metrics, achieving a classification accuracy of 97.25%, indicating high discriminative capability. ‎These findings demonstrate the potential of deep learning models, particularly ResNet50V2 with transfer learning, for the reliable detection ‎of depression from EEG images, which may support timely diagnosis and intervention in clinical settings‎.

  • References

    1. J. Firth-Cozens, A perspective on stress and depression, In Understanding doctors' performance, CRC Press, (2001), pp: 22-37. https://doi.org/10.1201/9781846197062-2.
    2. E.G. Ostinelli, C. Zangani, B. Giordano, D. Maestri, O. Gambini, A. D'Agostino, T.A. Furukawa, M. Purgato, “Depressive symptoms and depres-sion in individuals with internet gaming disorder: a systematic review and meta-analysis”, Journal of Affective Disorders, Vol. 284, No. 1, (2021), pp. 136–142, available online: https://doi.org/10.1016/j.jad.2021.02.014.
    3. N. Cai, K.W. Choi, E.I. Fried, “Reviewing the genetics of heterogeneity in depression: operationalization, manifestations and etiologies”, Human Molecular Genetics, Vol. 29, No. R1, (2020), pp. R10–R18, available online: https://doi.org/10.1093/hmg/ddaa115.
    4. L.S. Wang, M.D. Zhang, X. Tao, Y.F. Zhou, X.M. Liu, R.L. Pan, Q. Chang, “LC-MS/MS-based quantification of tryptophan metabolites and neu-rotransmitters in the serum and brain of mice”, Journal of Chromatography B, Vol. 1112, No. 1, (2019), pp. 24–32, available online: https://doi.org/10.1016/j.jchromb.2019.02.021.
    5. A. Dvojkovic, M. Nikolac Perkovic, M. Sagud, G. Nedic Erjavec, A. Mihaljevic Peles, D. Svob Strac, B. Vuksan Cusa, L. Tudor, Z. Kusevic, M. Konjevod, M. Zivkovic, S. Jevtovic, N. Pivac, “Effect of vortioxetine vs. escitalopram on plasma BDNF and platelet serotonin in depressed pa-tients”, Progress in Neuro-Psychopharmacology & Biological Psychiatry, Vol. 105, No. 1, (2021), pp. 110016, available online: https://doi.org/10.1016/j.pnpbp.2020.110016.
    6. L. Meng, X. Bai, Y. Zheng, D. Chen, Y. Zheng, “Altered expression of norepinephrine transporter participate in hypertension and depression through regulated TNF-α and IL-6”, Clinical and Experimental Hypertension, Vol. 42, No. 2, (2020), pp. 181–189, available online: https://doi.org/10.1080/10641963.2019.1601205.
    7. P.M. Miguel, L.O. Pereira, P.P. Silveira, M.J. Meaney, “Early environmental influences on the development of children's brain structure and func-tion”, Developmental Medicine & Child Neurology, Vol. 61, No. 10, (2019), pp. 1127–1133, available online: https://doi.org/10.1111/dmcn.14182.
    8. Y. Zhao, L. Han, K.M. Teopiz, R.S. McIntyre, R. Ma, B. Cao, “The psychological factors mediating/moderating the association between childhood adversity and depression: A systematic review”, Neuroscience & Biobehavioral Reviews, Vol. 137, No. 1, (2022), pp. 104663, available online: https://doi.org/10.1016/j.neubiorev.2022.104663.
    9. T. Butler, P. Harvey, L. Cardozo, Y.S. Zhu, A. Mosa, E. Tanzi, F. Pervez, “Epilepsy, depression, and growth hormone”, Epilepsy & Behavior, Vol. 94, No. 1, (2019), pp. 297–300, available online: https://doi.org/10.1016/j.yebeh.2019.01.022.
    10. D.R. Cregg, J.S. Cheavens, “Gratitude interventions: Effective self-help? A meta-analysis of the impact on symptoms of depression and anxiety”, Journal of Happiness Studies: An Interdisciplinary Forum on Subjective Well-Being, Vol. 22, No. 1, (2021), pp. 413–445, available online: https://doi.org/10.1007/s10902-020-00236-6.
    11. H.P. Kapfhammer, “Somatic symptoms in depression”, Dialogues in Clinical Neuroscience, Vol. 8, No. 2, (2006), pp. 227–239, available online: https://doi.org/10.31887/DCNS.2006.8.2/hpkapfhammer.
    12. H.T. Chu, C.M. Cheng, C.S. Liang, W.H. Chang, C.H. Juan, Y.Z. Huang, J.S. Jeng, Y.M. Bai, S.J. Tsai, M.H. Chen, C.T. Li, “Efficacy and tolera-bility of theta-burst stimulation for major depression: A systematic review and meta-analysis”, Progress in Neuropsychopharmacology & Biological Psychiatry, Vol. 106, No. 1, (2021), pp. 110168, available online: https://doi.org/10.1016/j.pnpbp.2020.110168.
    13. A.E. Wong, S.R. Dirghangi, S.R. Hart, “Self-concept clarity mediates the effects of adverse childhood experiences on adult suicide behavior, de-pression, loneliness, perceived stress, and life distress”, Self and Identity, Vol. 18, No. 3, (2018), pp. 247–266, available online: https://doi.org/10.1080/15298868.2018.1439096.
    14. H. Alshikh Ahmad, A. Alkhatib, J. Luo, “Prevalence and risk factors of postpartum depression in the Middle East: a systematic review and meta–analysis”, BMC Pregnancy and Childbirth, Vol. 21, No. 542, (2021), pp. 1–12, available online: https://doi.org/10.1186/s12884-021-04016-9.
    15. Y. Dauvilliers, R.K. Bogan, I. Arnulf, T.E. Scammell, E.K. St Louis, M.J. Thorpy, “Clinical considerations for the diagnosis of idiopathic hyper-somnia”, Sleep Medicine Reviews, Vol. 66, No. 1, (2022), pp. 101709, available online: https://doi.org/10.1016/j.smrv.2022.101709.
    16. J.E.G. Charlesworth, O. Ghosn, N. Hussain, R. Mahmoud, V. Goncalves, M. Godbole, “A case report of an unusual presentation of a patient with recurrent idiopathic catatonia”, Psychiatry Research Case Reports, Vol. 2, No. 1, (2023), pp. 100111, available online: https://doi.org/10.1016/j.psycr.2023.100111.
    17. A. Castro, M. Gili, I. Ricci-Cabello, M. Roca, S. Gilbody, M.Á. Perez-Ara, A. Seguí, D. McMillan, “Effectiveness and adherence of telephone-administered psychotherapy for depression: a systematic review and meta-analysis”, Journal of Affective Disorders, Vol. 260, No. 1, (2020), pp. 514–526, available online: https://www.sciencedirect.com/science/article/pii/S0165032719311723, last visit: 16.12.2024. https://doi.org/10.1016/j.jad.2019.09.023.
    18. S. Zhang, K. Xiang, S. Li, H.F. Pan, “Physical activity and depression in older adults: the knowns and unknowns”, Psychiatry Research, Vol. 297, No. 1, (2021), pp. 113738, available online: https://doi.org/10.1016/j.psychres.2021.113738.
    19. E. Norouzi, M. Gerber, F.F. Masrour, M. Vaezmosavi, U. Pühse, S. Brand, “Implementation of a mindfulness-based stress reduction (MBSR) pro-gram to reduce stress, anxiety, and depression and to improve psychological well-being among retired Iranian football players”, Psychology of Sport and Exercise, 47, no. 1, 2020, pp. 101636, available online: https://doi.org/10.1016/j.psychsport.2019.101636.
    20. A. Priya, S. Garg, N.P. Tigga, “Predicting anxiety, depression and stress in modern life using machine learning algorithms”, Procedia Computer Science, 167, no. 1, 2020, pp. 1258–1267, available online: https://doi.org/10.1016/j.procs.2020.03.442.
    21. P. Kumar, S. Garg, A. Garg, “Assessment of anxiety, depression and stress using machine learning models”, Procedia Computer Science, 171, no. 1, 2020, pp. 1989–1998, available online: https://doi.org/10.1016/j.procs.2020.04.213.
    22. A. Sau, I. Bhakta, “Screening of anxiety and depression among seafarers using machine learning technology”, Informatics in Medicine Unlocked, 16, no. 1, 2019, pp. 100228, available online: https://doi.org/10.1016/j.imu.2018.12.004.
    23. X. Li, X. Zhang, J. Zhu, W. Mao, S. Sun, Z. Wang, B. Hu, “Depression recognition using machine learning methods with different feature genera-tion strategies”, Artificial Intelligence in Medicine, 99, no. 1, 2019, pp. 101696, available online: https://doi.org/10.1016/j.artmed.2019.07.004.
    24. E.W. McGinnis, S.P. Anderau, J. Hruschak, R.D. Gurchiek, N.L. Lopez-Duran, K. Fitzgerald, R.S. McGinnis, “Giving voice to vulnerable children: machine learning analysis of speech detects anxiety and depression in early childhood”, IEEE Journal of Biomedical and Health Informatics, 23, no. 6, 2019, pp. 2294–2301, available online: https://doi.org/10.1109/JBHI.2019.2913590.
    25. W. Mumtaz, A. Qayyum, “A deep learning framework for automatic diagnosis of unipolar depression”, International Journal of Medical Informatics, 132, no. 1, 2019, pp. 103983, available online: https://doi.org/10.1016/j.ijmedinf.2019.103983.
    26. L. Wang, L. Ye, Y. Jin, X. Pan, X. Wang, “A bibliometric analysis of the knowledge related to mental health during and post COVID-19 pandem-ic”, Frontiers in Psychology, Vol. 15, No. 1, (2024), pp. 1411340, available online: https://doi.org/10.3389/fpsyg.2024.1411340.
    27. O. Oh, K. Yun, U. Maoz, T.S. Kim, J.H. Chae, “Identifying depression in the National Health and Nutrition Examination Survey data using a deep learning algorithm”, Journal of Affective Disorders, 257, no. 1, 2019, pp. 623–631, available online: https://doi.org/10.1016/j.jad.2019.06.034.
    28. S. Ghosh, T. Anwar, “Depression intensity estimation via social media: a deep learning approach”, IEEE Transactions on Computational Social Sys-tems, 8, no. 6, 2021, pp. 1465–1474. Available online: https://doi.org/10.1109/TCSS.2021.3084154.
    29. J.W. Baek, K. Chung, “Context deep neural network model for predicting depression risk using multiple regressions”, IEEE Access, 8, no. 1, 2020, pp. 18171–18181, available online: https://doi.org/10.1109/ACCESS.2020.2968393.
    30. B. Ay, O. Yildirim, M. Talo, U.B. Baloglu, G. Aydin, S.D. Puthankattil, U.R. Acharya, “Automated depression detection using deep representa-tion and sequence learning with EEG signals”, Journal of Medical Systems, 43, no. 8, 2019, pp. 1–12, available online: https://doi.org/10.1007/s10916-019-1345-y.
    31. C. Kaur, A. Bisht, P. Singh, G. Joshi, “EEG signal denoising using hybrid approach of variational mode decomposition and wavelets for depres-sion”, Biomedical Signal Processing and Control, 65, no. 1, 2021, pp. 102337, available online: https://doi.org/10.1016/j.bspc.2020.102337.
    32. G. Sharma, A. Parashar, A.M. Joshi, “DePHNN: a novel hybrid neural network for electroencephalogram (EEG)-based screening of depression”, Biomedical Signal Processing and Control, 66, no. 1, 2021, pp. 102393, available online: https://doi.org/10.1016/j.bspc.2020.102393.
    33. A. Saeedi, M. Saeedi, A. Maghsoudi, A. Shalbaf, “Major depressive disorder diagnosis based on effective connectivity in EEG signals: a convolu-tional neural network and long short-term memory approach”, Cognitive Neurodynamics, 15, no. 2, 2021, pp. 239–252, available online: https://doi.org/10.1007/s11571-020-09619-0.
    34. N. Seneviratne, C. Espy-Wilson, “Speech based depression severity level classification using a multi-stage dilated CNN-LSTM model”, arXiv pre-print arXiv:2104.04195, vol. 1, no. 1, 2021, pp. 1–8.
    35. M.S. Shahabi, A. Shalbaf, A. Maghsoudi, “Prediction of drug response in major depressive disorder using ensemble of transfer learning with convo-lutional neural network based on EEG”, Biocybernetics and Biomedical Engineering, 41, no. 3, 2021, pp. 946–959, available online: https://doi.org/10.1016/j.bbe.2021.06.006.
    36. C.S. Deolindo, M.W. Ribeiro, M.A. Aratanha, R.F. Afonso, M. Irrmischer, E.H. Kozasa, “A critical analysis on characterizing the meditation expe-rience through the electroencephalogram”, Frontiers in Systems Neuroscience, 14, no. 53, 2020, pp. 1–10, available online: https://doi.org/10.3389/fnsys.2020.00053.
    37. V. Shankar, R. Roelofs, H. Mania, A. Fang, B. Recht, L. Schmidt, “Evaluating machine accuracy on ImageNet”, International Conference on Ma-chine Learning, vol. 119, no. 1, 2020, pp. 8634–8644, https://proceedings.mlr.press/v119/shankar20c.html.
    38. E. Bisong, Building Machine Learning and Deep Learning Models on Google Cloud Platform, Apress Berkeley, CA,(2019), pp:59-64. https://doi.org/10.1007/978-1-4842-4470-8_7.
    39. J.Moolayil, An introduction to deep learning and keras. Learn Keras for Deep Neural Networks: A Fast-Track Approach to Modern Deep Learning with Python, Apress, Berkeley, CA, (2019), pp: 1-16. https://doi.org/10.1007/978-1-4842-4240-7_1.
    40. J. Yang, Z. Zhang, P. Xiong, X. Liu, “Depression detection based on analysis of EEG signals in multi brain regions”, Journal of Integrative Neuro-science, 22, no. 4, 2023, pp. 1–9, available online: https://doi.org/10.31083/j.jin2204093.
    41. S. Mahato, S. Paul, “Analysis of region of interest (RoI) of brain for detection of depression using EEG signal”, Multimedia Tools and Applications, Vol. 83, No. 1, 2024, pp. 763–786, available online: https://doi.org/10.1007/s11042-023-15827-7.
    42. J. Yang, J. Li, S. Zhao, Y. Zhang, B. Li, X. Liu, Fusion of eyes-open and eyes-closed electroencephalography in resting state for classification of major depressive disorder, Biomedical Signal Processing and Control, 100, Part B, 2025, pp. 106964, available online: https://doi.org/10.1016/j.bspc.2024.106964.
    43. N. Ahire, EEG-derived brainwave patterns for depression diagnosis via hybrid machine learning and deep learning frameworks, Applied Neuropsy-chology: Adult, 1, no. 1, 2025, pp. 1–10, available online: https://doi.org/10.1080/23279095.2025.2457999.

  • Downloads

  • How to Cite

    Andhare, M. ., Yewale, D., Khedkar , S. ., & Jagtap, S. . (2025). Leveraging Deep Learning for Enhanced Classification of Depres‎sion Via EEG-Derived Imagery. International Journal of Basic and Applied Sciences, 14(5), 316-326. https://doi.org/10.14419/cnq5t832