Web application for brain tumor diagnosis based on convolutional neural networks

M.R. Kiyasov, I.A. Pshenokova

---

Abstract. The clinical relevance of this research lies in the necessity of introducing web-based applications to enhance the efficiency of brain tumor diagnosis via MRI data. This application provides preprocessing and standardization of input images, high-precision recognition of the presence and type of tumor, presentation of results in a physician-friendly format, and the ability to scale and further refine the model as new data accumulates. The proposed application ensures automated preprocessing and standardization of input images, high-accuracy tumor detection and classification, and clear visualization of results for clinical decision support; furthermore, the system architecture supports scalability and continuous model refinement as new data is accumulated.
Aim. The study aims to design a functional web-based system for medical diagnosis featuring an accessible user interface.
Research methods. The core approach involves machine learning based on convolutional neural networks and robust software development technologies.
Results. A fully functional web application integrated with convolutional neural networks was successfully developed and deployed for automated brain tumor diagnosis. The system utilizes a MobileNet model for MRI image classification and recognition, while a U-Net architecture is deployed for precise semantic segmentation of tumor regions. The frontend framework was implemented using React and TypeScript, while the backend infrastructure was constructed in Python.
Conclusions. The tests conducted show that the developed application demonstrates high accuracy in tumor recognition and segmentation, ensuring its effectiveness in medical diagnostics. The validation tests confirm that the developed application yields high accuracy in tumor detection and segmentation, ensuring robust performance in real-world medical imaging tasks.

Keywords: web application, brain tumor diagnostics, deep learning, convolutional neural networks, image analysis, artificial intelligence, medical data

For citation. Kiyasov M.R., Pshenokova I.A. Web application for brain tumor diagnosis based on convolutional neural networks News of the Kabardino-Balkarian Scientific Center of RAS. 2026. Vol. 28. No. 3. Pp. 71–83. DOI: 10.35330/1991-6639-2026-28-3-71-83

©   Kiyasov M.R., Pshenokova I.A., 2026

References

1. Aguiar-Ibanez R., Mbous Y.P.V., Sharma S. Chawla E. Assessing the clinical, humanistic, and economic impact of early cancer diagnosis: a systematic literature review. Frontiers in
   Oncology. 2025. Vol. 3. DOI: 10.3389/fonc.2025.1546447
2. Wang C., Shi Z., Li Y. et al. Protocol for brain magnetic resonance imaging and extraction of imaging-derived phenotypes from the china phenobank project. Phenomics. 2023. Vol. 3. No. 6. Pp. 642–656. DOI: 10.1007/s43657-022-00083-w
3. Jiang X., Hu Z., Wang S., Zhang Y. Deep learning for medical image-based cancer diagnosis. Cancers. 2023. Vol. 15. No. 14. DOI: 10.3390/cancers15143608
4. Solopov M.V., Kavelina A.S., Popandopulo A.G. at al. Prospects for the application of convolutional neural networks in cytological diagnostics of thyroid nodules. Problems of Endocrinology. 2025. No. 71. Pp. 4–13. DOI: 10.14341/probl13475. (In Russian)
5. Loghmani N., Moqadam R., Allahverdy A. Brain tumor segmentation using multimodal MRI and convolutional neural network. 30th International Conference on Electrical Engineering (ICEE). Tehran. Iran. 2022. Pp. 227–230. DOI: 10.1109/ICEE55646.2022.9827274
6. Rastogi D., Johri P., Donelli M. et al. Brain tumor detection and prediction in MRI images utilizing a Fine-Tuned transfer learning model integrated within deep learning frameworks. Life. 2025. Vol. 15. No. 3. P. 327. DOI: 10.3390/life15030327
7. Balch J.A., Ruppert M.M., Loftus T.J. at al. Machine learning-enabled clinical information systems using fast healthcare interoperability resources data standards: Scoping review. JMIR Medical Information. 2023. Vol. 11. DOI: 10.2196/48297
8. Ottoni M., Kasperczuk A., Tavora L.M.N. Machine learning in MRI brain imaging: a review of methods, challenges, and future directions. Diagnostics. 2025. Vol. 15. No. 21. DOI: 10.3390/diagnostics15212692
9. Alzubaidi A.K. Analysis of requirements for confidentiality and sharing of digital healthcare data. Medical Ethics. 2023. Vol. 11. No. 4. Pp. 27–31. DOI: 10.24075/medet.2023.030. (In Russian)
10. Vu H.A. Integrating preprocessing methods and convolutional neural networks for effective tumor detection in medical imaging. arXiv preprint arXiv:2402.16221. 2024.
11. Pshenokova I.A., Kiyasov M.R. Models and methods of deep learning in medical image recognition and classification tasks. News of the Kabardino-Balkarian Scientific Center of RAS. Vol. 27. No. 2. Pp. 103–112. DOI: 10.35330/1991-6639-2025-27-2-103-112. (In Russian)
12. Bash S., Tanenbaum L.N., Segovis C., Chen M. CPT codes for quantitative MRI of the brain: what it means for neuroradiology. American Journal of Neuroradiology. 2024. 45(7) E19.
    DOI: 10.3174/ajnr.A8286

Information about the authors

Murat R. Kiyasov, Undergraduate Student majoring in Computer Science and Engineering, Kabardino-Balkarian State University named after Kh.M. Berbekov;
173, Chernyshevsky street, Nalchik, 360004, Russia;
myrat7450@mail.ru
Inna A. Pshenokova, Candidate of Physical and Mathematical Sciences, Head of the Department Multi-Agent Systems, Institute of Computer Science and Problems of Regional Management – branch of Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences;
37-a, I. Armand street, Nalchik, 360000, Russia;
Associate Professor, Department of Computer Technology and Information Security, KabardinoBalkarian State University named after Kh.M. Berbekov;
173, Chernyshevsky street, Nalchik, 360004, Russia;
pshenokova_inna@mail.ru, ORCID: https://orcid.org/0000-0003-3394-7682, SPIN-code: 3535-2963

Funding

The study was performed without external funding.