Towards Explainable Deep Learning in Computational Neuroscience: Visual and Clinical Applications

Asif Mehmood; Faisal Mehmood; Jungsuk Kim

doi:10.3390/math13203286

journal article Open Access Oct 14, 2025

Towards Explainable Deep Learning in Computational Neuroscience: Visual and Clinical Applications

Asif Mehmood

Faisal Mehmood

Jungsuk Kim

Mathematics Vol. 13 No. 20 pp. 3286 · MDPI AG

View at Publisher Save 10.3390/math13203286

Abstract

Deep learning has emerged as a powerful tool in computational neuroscience, enabling the modeling of complex neural processes and supporting data-driven insights into brain function. However, the non-transparent nature of many deep learning models limits their interpretability, which is a significant barrier in neuroscience and clinical contexts where trust, transparency, and biological plausibility are essential. This review surveys structured explainable deep learning methods, such as saliency maps, attention mechanisms, and model-agnostic interpretability frameworks, that bridge the gap between performance and interpretability. We then explore explainable deep learning’s role in visual neuroscience and clinical neuroscience. By surveying literature and evaluating strengths and limitations, we highlight explainable models’ contribution to both scientific understanding and ethical deployment. Challenges such as balancing accuracy, complexity and interpretability, absence of standardized metrics, and scalability are assessed. Finally, we propose future directions, which include integrating biological priors, implementing standardized benchmarks, and incorporating human-intervention systems. The research study highlights the position of explainable deep learning, not only as a technical advancement but represents it as a necessary paradigm for transparent, responsible, auditable, and effective computational neuroscience. In total, 177 studies were reviewed as per PRISMA, which provided evidence across both visual and clinical computational neuroscience domains.

Topics

No keywords indexed for this article. Browse by subject →

References

177

[1]

Guimarães, K., and Duarte, A. (2023). A Network-Level Stochastic Model for Pacemaker GABAergic Neurons in Substantia Nigra Pars Reticulata. Mathematics, 11. 10.3390/math11173778

[2]

Iwama "EEG decoding with spatiotemporal convolutional neural network for visualization and closed-loop control of sensorimotor activities: A simultaneous EEG-fMRI study" Hum. Brain Mapp. (2024) 10.1002/hbm.26767

[3]

Huang "Data-driven natural computational psychophysiology in class" Cogn. Neurodynamics (2024) 10.1007/s11571-024-10126-9

[4]

Elmoznino, E., and Bonner, M.F. (2024). High-performing neural network models of visual cortex benefit from high latent dimensionality. PLoS Comput. Biol., 20. 10.1371/journal.pcbi.1011792

[5]

Attention mechanisms in computer vision: A survey

Meng-Hao Guo, Tian-Xing Xu, Jiang-Jiang Liu et al.

Computational Visual Media 2022 10.1007/s41095-022-0271-y

[6]

Watanabe "Multimodal deep neural decoding reveals highly resolved spatiotemporal profile of visual object representation in humans" NeuroImage (2023) 10.1016/j.neuroimage.2023.120164

[7]

Farzmahdi "Emergence of brain-like mirror-symmetric viewpoint tuning in convolutional neural networks" eLife (2024) 10.7554/elife.90256

[8]

Transparency of deep neural networks for medical image analysis: A review of interpretability methods

Zohaib Salahuddin, Henry C. Woodruff, Avishek Chatterjee et al.

Computers in Biology and Medicine 10.1016/j.compbiomed.2021.105111

[9]

Danks "Causal inference in cognitive neuroscience" Wiley Interdiscip. Rev. Cogn. Sci. (2023) 10.1002/wcs.1650

[10]

Kokol "Trusting AI made decisions in healthcare by making them explainable" Sci. Prog. (2024) 10.1177/00368504241266573

[11]

Freyer, N., Groß, D., and Lipprandt, M. (2024). The ethical requirement of explainability for AI-DSS in healthcare: A systematic review of reasons. BMC Med. Ethics, 25. 10.1186/s12910-024-01103-2

[12]

Brima, Y., and Atemkeng, M. (2024). Saliency-driven explainable deep learning in medical imaging: Bridging visual explainability and statistical quantitative analysis. BioData Min., 17. 10.1186/s13040-024-00370-4

[13]

Yang "Explainable multimodal deep dictionary learning to capture developmental differences from three fMRI paradigms" IEEE Trans. Biomed. Eng. (2023) 10.1109/tbme.2023.3244921

[14]

Sattiraju, A., Ellis, C.A., Miller, R.L., and Calhoun, V.D. (2023, January 4–6). An explainable and robust deep learning approach for automated electroencephalography-based schizophrenia diagnosis. Proceedings of the 2023 IEEE 23rd International Conference on Bioinformatics and Bioengineering (BIBE), Dayton, OH, USA. 10.1109/bibe60311.2023.00048

[15]

Mauricio "Explainable Machine Learning Models for Brain Diseases: Insights from a Systematic Review" Neurol. Int. (2024) 10.3390/neurolint16060098

[16]

Hussain, T., and Shouno, H. (2023). Explainable deep learning approach for multi-class brain magnetic resonance imaging tumor classification and localization using gradient-weighted class activation mapping. Information, 14. 10.3390/info14120642

[17]

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł, and Polosukhin, I. (2017). Attention is all you need. arXiv.

[18]

Li "Neurobolt: Resting-state eeg-to-fmri synthesis with multi-dimensional feature mapping" Adv. Neural Inf. Process. Syst. (2024)

[19]

Song "A hybrid spatiotemporal deep belief network and sparse representation-based framework reveals multilevel core functional components in decoding multitask fMRI signals" Netw. Neurosci. (2023) 10.1162/netn_a_00334

[20]

Hu "Interpretable multimodal fusion networks reveal mechanisms of brain cognition" IEEE Trans. Med. Imaging (2021) 10.1109/tmi.2021.3057635

[21]

Ji "A multiview deep learning method for brain functional connectivity classification" Comput. Intell. Neurosci. (2022) 10.1155/2022/5782569

[22]

Germann, J., Zadeh, G., Mansouri, A., Kucharczyk, W., Lozano, A.M., and Boutet, A. (2022). Untapped neuroimaging tools for neuro-oncology: Connectomics and spatial transcriptomics. Cancers, 14. 10.3390/cancers14030464

[23]

Luo "Statistical Multiscore Functional Atlas Creation for Image-Guided Deep Brain Stimulation" IEEE Trans. Neural Syst. Rehabil. Eng. (2025) 10.1109/tnsre.2025.3542395

[24]

Li, R. (2025). Integrative diagnosis of psychiatric conditions using ChatGPT and fMRI data. BMC Psychiatry, 25. 10.1186/s12888-025-06586-w

[25]

Khan, S., Kallis, L., Mee, H., El Hadwe, S., Barone, D., Hutchinson, P., and Kolias, A. (2025). Invasive Brain–Computer Interface for Communication: A Scoping Review. Brain Sci., 15. 10.3390/brainsci15040336

[26]

Baniqued "Brain–computer interface robotics for hand rehabilitation after stroke: A systematic review" J. Neuroeng. Rehabil. (2021) 10.1186/s12984-021-00820-8

[27]

Zhang "A novel brain-controlled prosthetic hand method integrating AR-SSVEP augmentation, asynchronous control, and machine vision assistance" Heliyon (2024) 10.1016/j.heliyon.2024.e26521

[28]

Berezutskaya "Direct speech reconstruction from sensorimotor brain activity with optimized deep learning models" J. Neural Eng. (2023) 10.1088/1741-2552/ace8be

[29]

Lai "Interpretable medical imagery diagnosis with self-attentive transformers: A review of explainable AI for health care" BioMedInformatics (2024) 10.3390/biomedinformatics4010008

[30]

Sinz "Engineering a less artificial intelligence" Neuron (2019) 10.1016/j.neuron.2019.08.034

[31]

Stringer "High-dimensional geometry of population responses in visual cortex" Nature (2019) 10.1038/s41586-019-1346-5

[32]

Räuker, T., Ho, A., Casper, S., and Hadfield-Menell, D. (2023, January 8–10). Toward transparent ai: A survey on interpreting the inner structures of deep neural networks. Proceedings of the 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SATML), Raleigh, NC, USA. 10.1109/satml54575.2023.00039

[33]

Retzlaff "Post-hoc vs ante-hoc explanations: xAI design guidelines for data scientists" Cogn. Syst. Res. (2024) 10.1016/j.cogsys.2024.101243

[34]

Salih "A review of evaluation approaches for explainable AI with applications in cardiology" Artif. Intell. Rev. (2024) 10.1007/s10462-024-10852-w

[35]

Liu "Spatial-temporal convolutional attention for discovering and characterizing functional brain networks in task fMRI" NeuroImage (2024) 10.1016/j.neuroimage.2024.120519

[36]

"Conceptglassbox: Guided concept-based explanation for deep neural networks" Cogn. Comput. (2024) 10.1007/s12559-024-10262-8

[37]

A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts

Gesina Schwalbe, Bettina Finzel

Data Mining and Knowledge Discovery 2024 10.1007/s10618-022-00867-8

[38]

Wang "Multi-objective feature attribution explanation for explainable machine learning" ACM Trans. Evol. Learn. Optim. (2024) 10.1145/3617380

[39]

Lee, S., and Lee, K.S. (2024). Predictive and Explainable Artificial Intelligence for Neuroimaging Applications. Diagnostics, 14. 10.3390/diagnostics14212394

[40]

Preferred reporting items for systematic reviews and meta-analyses: The PRISMA statement

David Moher, Alessandro Liberati, Jennifer Tetzlaff et al.

International Journal of Surgery 2010 10.1016/j.ijsu.2010.02.007

[41]

Kemp "Analysis of a sleep-dependent neuronal feedback loop: The slow-wave microcontinuity of the EEG" IEEE Trans. Biomed. Eng. (2000) 10.1109/10.867928

[42]

LaMontagne, P.J., Benzinger, T.L., Morris, J.C., Keefe, S., Hornbeck, R., Xiong, C., Grant, E., Hassenstab, J., Moulder, K., and Vlassenko, A.G. (2019). OASIS-3: Longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and Alzheimer disease. medRxiv. 10.1101/2019.12.13.19014902

[43]

Markiewicz "The OpenNeuro resource for sharing of neuroscience data" eLife (2021) 10.7554/elife.71774

[44]

Mehmood, A., Ko, J., Kim, H., and Kim, J. (2024). Optimizing Image Enhancement: Feature Engineering for Improved Classification in AI-Assisted Artificial Retinas. Sensors, 24. 10.3390/s24092678

[45]

The Measurement of Observer Agreement for Categorical Data

J. Richard Landis, Gary G. Koch

Biometrics 10.2307/2529310

[46]

Lai-Dang, Q.V., Kang, T., and Son, S. (2025, January 24–28). Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in Transformers. Proceedings of the The Thirteenth International Conference on Learning Representations, Singapore.

[47]

Dayan, P., and Abbott, L.F. (2005). Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems, MIT Press.

[48]

Koch, C., and Segev, I. (1988). Methods in Neuronal Modeling: From Synapses to Networks, MIT Press. Computational Neuroscience.

[49]

Moshruba, A., Poursiami, H., and Parsa, M. (2025). Izhikevich-Inspired Temporal Dynamics for Enhancing Privacy, Efficiency, and Transferability in Spiking Neural Networks. arXiv. 10.56553/popets-2025-0060

[50]

Wojcik, G.M., Masiak, J., Kawiak, A., Kwasniewicz, L., Schneider, P., Polak, N., and Gajos-Balinska, A. (2018). Mapping the human brain in frequency band analysis of brain cortex electroencephalographic activity for selected psychiatric disorders. Front. Neuroinform., 12. 10.3389/fninf.2018.00073

Showing 50 of 177 references

Metrics

5

Citations

177

References

Details

Published: Oct 14, 2025
Vol/Issue: 13(20)
Pages: 3286
License: View

Authors

A

Asif Mehmood

Department of Biomedical Engineering, College of IT Convergence, Gachon University, Sujeong-gu, Seongnam-si 13120, Republic of Korea

F

Faisal Mehmood

Department of AI and Software, College of IT Convergence, Gachon University, Sujeong-gu, Seongnam-si 13120, Republic of Korea

J

Jungsuk Kim

Department of Biomedical Engineering, College of IT Convergence, Gachon University, Sujeong-gu, Seongnam-si 13120, Republic of Korea

Funding

National Research Foundation of Korea Award: RS-2024-0041926912982076870101

The Gachon University Research Fund Award: 2023 (GCU-202303650001)

Cite This Article

Asif Mehmood, Faisal Mehmood, Jungsuk Kim (2025). Towards Explainable Deep Learning in Computational Neuroscience: Visual and Clinical Applications. Mathematics, 13(20), 3286. https://doi.org/10.3390/math13203286

Towards Explainable Deep Learning in Computational Neuroscience: Visual and Clinical Applications

You May Also Like