EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

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

Asif Mehmood, Faisal Mehmood, Jungsuk Kim

Mathematics · 2025-10-14 · 13 (20) · 3286

DOI: 10.3390/math13203286 ↗

At a glance

Journal article in Mathematics, published online on 2025-10-14. Written by Asif Mehmood and 2 co-authors. Cited 13 times so far (Crossref); 177 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Research Foundation of Korea, The Gachon University Research Fund.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

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.

Funding

  • National Research Foundation of Korea
  • The Gachon University Research Fund

Cite

APA

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

Vancouver

Mehmood A, Mehmood F, Kim J. Towards Explainable Deep Learning in Computational Neuroscience: Visual and Clinical Applications. Mathematics. 2025;13(20):3286. doi:10.3390/math13203286

BibTeX
@article{Mehmood2025,
  author = {Mehmood, Asif and Mehmood, Faisal and Kim, Jungsuk},
  title = {Towards Explainable Deep Learning in Computational Neuroscience: Visual and Clinical Applications},
  journal = {Mathematics},
  year = {2025},
  volume = {13},
  number = {20},
  pages = {3286},
  doi = {10.3390/math13203286}
}
Start for free →