Deep Learning Applications for Mental Health Disorder DiagnosisUsing Medical Imaging

Abstract

Mental health disorders such as depression, schizophrenia, and bipolar disorder remain difficult to diagnose objectively. Medical imaging techniques—such as MRI, fMRI, PET, and EEG—offer valuable insights into brain structure and function, revealing biomarkers linked to psychiatric conditions. Deep learning has recently transformed the analysis of these complex data by automatically extracting meaningful features from high-dimensional images.  This review summarizes recent advances in applying deep learning models, including convolutional, recurrent, and graph neural networks, to mental health diagnosis. It highlights key imaging modalities, representative applications,  and current limitations such as small datasets and limited interpretability. Emerging directions, including multimodal fusion and explainable AI, promise to enhance clinical reliability and understanding. Deep learning thus holds strong potential for improving early detection and personalized treatment in mental health care.

References

[1] Vigo D, Thornicroft G, Atun R. Estimating the true global burden of mental illness. The Lancet Psychiatry. 2016 Feb 1;3(2):171-8.

[2] Greicius MD, Flores BH, Menon V, Glover GH, Solvason HB, Kenna H, Reiss AL, Schatzberg AF. Resting-state functional connectivity in major depression: abnormally increased contributions from subgenual cingulate cortex and thalamus. Biological psychiatry. 2007 Sep 1;62(5):429-37.

[3] Diwadkar VA, Burgess A, Hong E, Rix C, Arnold PD, Hanna GL, Rosenberg DR. Dysfunctional activation and brain network profiles in youth with obsessive-compulsive disorder: a focus on the dorsal anterior cingulate during working memory. Frontiers in human neuroscience. 2015 Mar 17;9:149.

[4] Chen J, Liu Y, Wei S, Bian Z, Subramanian S, Carass A, Prince JL, Du Y. A survey on deep learning in medical image registration: New technologies, uncertainty, evaluation metrics, and beyond. Medical Image Analysis. 2025 Feb 1;100:103385.

[5] Rohani, M. M., Sharifi, S., & Durson, S. (2025). Deep learning in medical imaging for disease diagnosis. World Journal of Advanced Research and Reviews, 25(2), 2522–2526. https://doi.org/10.30574/wjarr.2025.25.2.0558

[6] Wang J, Wang S, Zhang Y. Deep learning on medical image analysis. CAAI Transactions on Intelligence Technology. 2025 Feb;10(1):1-35.

[7] Hosseinabadi F, Ghasemi Y. Artificial Intelligence in Radiology: Concepts and Applications. International Journal of Applied Data Science in Engineering and Health. 2025 Jun 18;1(3).

[8] Halkiopoulos C, Gkintoni E, Aroutzidis A, Antonopoulou H. Advances in neuroimaging and deep learning for emotion detection: A systematic review of cognitive neuroscience and algorithmic innovations. Diagnostics. 2025 Feb 13;15(4):456.

[9] Westlin C, Guthrie AJ, Paredes-Echeverri S, Maggio J, Finkelstein S, Godena E, Millstein D, MacLean J, Ranford J, Freeburn J, Adams C. Machine learning classification of functional neurological disorder using structural brain MRI features. Journal of Neurology, Neurosurgery & Psychiatry. 2025 Mar 1;96(3):249-57.

[10] Ktena SI, Parisot S, Ferrante E, Rajchl M, Lee M, Glocker B, Rueckert D. Metric learning with spectral graph convolutions on brain connectivity networks. NeuroImage. 2018 Apr 1;169:431-42.

[11] Lu D, Popuri K, Ding GW, Balachandar R, Beg MF. Alzheimer’s Disease Neuroimaging I. Multimodal and multiscale deep neural networks for the early diagnosis of Alzheimer’s disease using structural MR and FDG-PET images. Sci Rep. 2018;8(1):5697.

[12] Craik A, He Y, Contreras-Vidal JL. Deep learning for electroencephalogram (EEG) classification tasks: a review. Journal of neural engineering. 2019 Apr 9;16(3):031001.

[13] Skaramagkas V, Pentari A, Kefalopoulou Z, Tsiknakis M. Multi-modal deep learning diagnosis of Parkinson’s disease—a systematic review. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2023 May 18;31:2399-423.

[14] Vieira S, Pinaya WH, Mechelli A. Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: Methods and applications. Neuroscience & Biobehavioral Reviews. 2017 Mar 1;74:58-75.

[15] Sarraf S, Tofighi G. Alzheimer’s Disease Neuroimaging InitiativDeepAD: Alzheimer’s disease classification via deep convolutional neural networks using MRI and fMRI. BioRxiv. 2016;4:070441.

[16] Alves CL, Thaise GD, Porto JA, de Carvalho Aguiar PM, de Sena EP, Rodrigues FA, Pineda AM, Thielemann C. Analysis of functional connectivity using machine learning and deep learning in different data modalities from individuals with schizophrenia. Journal of neural engineering. 2023 Sep 28;20(5):056025.

[17] Suk HI, Shen D. Deep learning-based feature representation for AD/MCI classification. InInternational conference on medical image computing and computer-assisted intervention 2013 Sep 22 (pp. 583-590). Berlin, Heidelberg: Springer Berlin Heidelberg.

18] Bravo-Ortiz, M.A., Holguin-Garcia, S.A., Quiñones-Arredondo, S., Mora-Rubio, A., Guevara-Navarro, E., Arteaga-Arteaga, H.B., Ruz, G.A. and Tabares-Soto, R., 2024. A systematic review of vision transformers and convolutional neural networks for Alzheimer’s disease classification using 3D MRI images. Neural Computing and Applications, 36(35), pp.21985-22012.

[19] Mwangi B, Hasan KM, Soares JC. Prediction of individual subject's age across the human lifespan using diffusion tensor imaging: a machine learning approach. Neuroimage. 2013 Jul 15;75:58-67.

[20] Udayakumar P, Subhashini R. Connectome-based schizophrenia prediction using structural connectivity-Deep Graph Neural Network (sc-DGNN). Journal of X-Ray Science and Technology. 2024 Jul;32(4):1041-59.

[21] Abrol A, Damaraju E, Miller RL, Stephen JM, Claus ED, Mayer AR, Calhoun VD. Replicability of time-varying connectivity patterns in large resting state fMRI samples. Neuroimage. 2017 Dec 1;163:160-76.

[22] Heinsfeld AS, Franco AR, Craddock RC, Buchweitz A, Meneguzzi F. Identification of autism spectrum disorder using deep learning and the ABIDE dataset. NeuroImage: clinical. 2018 Jan 1;17:16-23.

[23] Lu D, Popuri K, Ding GW, Balachandar R, Beg MF. Alzheimer’s Disease Neuroimaging I. Multimodal and multiscale deep neural networks for the early diagnosis of Alzheimer’s disease using structural MR and FDG-PET images. Sci Rep. 2018;8(1):5697.