Authors : Surbhi Rana; Nistha Diwedi; Durgesh Kumar

Volume/Issue : Volume 10 - 2025, Issue 10 - October

Google Scholar : https://tinyurl.com/4szwm2bp

Scribd : https://tinyurl.com/32uktwjw

DOI : https://doi.org/10.38124/ijisrt/25oct1479

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : In neuro-oncological practice, early diagnosis and accurate volumetric assessment of brain tumors are of high importance, but manual MRI segmentation is labor intensive, expensive and subject to inter-observer variability. This paper describes the design, implementation, and rigorous empirical validation of an end-to-end medical imaging platform as a Django-powered medical imaging tool tailored for the needs of the Indian health care domain. The platform is a combination of 2D attention-based U-Net for accurate tumor segmentation, large language model (LLM) for generating intelligent reports in both English and Hindi, and secure standards-based longi- tudinal patient record management solution. By taking these key components into account, the platform aims to revolutionize the way neuroimaging workflows are handled, making them more efficient and accessible. Comprehensive evaluations on the BraTS 2020 dataset and 150 real-world MRI scans from Indian hospitals reveal exceptional segmentation accuracy with Dice scores exceeding 0.90, alongside superior report fidelity and adherence to clinical standards. Furthermore, the inclusion of detailed architectural blueprints and regulatory compliance measures underscores the platform’s readiness for practical, real- world deployment in resource-constrained environments.

Keywords : Brain Tumor Segmentation, Attention U-Net, Django, LLM, Radiology Report Generation, Bilingual Reporting, FHIR, HIPAA, DISHA, BraTS 2020.

References :

1. O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, 2015, pp. 234–241.
2. F. Isensee, P. F. Jaeger, S. A. Kohl, J. Petersen, and K. H. MaierHein, “nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation,” Nature Methods, vol. 18, no. 2, pp. 203–211, 2021.
3. O. Oktay et al., “Attention U-Net: Learning where to look for the pancreas,” arXiv preprint arXiv:1804.03999, 2018.
4. B. Pang et al., “GA-UNet: A lightweight ghost and attention U-Net for medical image segmentation,” Sensors, vol. 24, no. 13, p. 4244, 2024.
5. J. Ma et al., “A review on brain tumor segmentation based on deep learning methods,” Biocybernetics and Biomedical Engineering, vol. 43, no. 3, pp. 501–519, 2023.
6. “BraTS 2020 challenge: Data, CBICA, University of Pennsylvania,” 2020.
7. T. Nakaura et al., “The impact of large language models on radiology,” Japanese Journal of Radiology, pp. 1–10, 2024.
8. S. M. Hosseini, “Pixel-wise modulated Dice loss for medical image segmentation,” arXiv preprint arXiv:2506.15744, 2025.
9. “TopK Dice loss for medical image segmentation,” in BMVC, 2024.
10. “LM-RRG: Large model driven radiology report generation with clinical quality RL,” arXiv preprint, 2024.
11. “ECQI/HL7, FHIR—About, HL7 International,” 2025.
12. T. J. Liu et al., “Building an electronic medical record system exchanged using FHIR,” Healthcare, vol. 11, no. 15, p. 2167, 2023.
13. “AI-MIRACLE: AI in multilingual interpretation and radiology communication,” 2024.
14. “Comparative evaluation of LLMs for translating radiology impressions into simple Hindi,” PubMed 39697509, 2024.
15. “U-Net-based models towards optimal MR brain image segmentation,” Diagnostics, vol. 13, no. 9, p. 1624, 2023.
16. “Brain tumor segmentation using multiscale attention U-Net with EfficientNet encoder,” Scientific Reports, vol. 15, no. 1, p. 1234, 2025.
17. “Django/DRF HIPAA best practices blog,” 2023.
18. “DISHA and HIPAA, how do they compare?” 2025.
19. “Magnetic resonance imaging image-based segmentation of brain tumors using deep learning,” Cureus, vol. 15, no. 3, 2023.
20. “BTS U-Net: A data-driven approach to brain tumor segmentation,” 2025.
21. “Generalist models in medical image segmentation: A survey and performance comparison with task-specific approaches,” ResearchGate, 2025.
22. “Multivariate technique for the prediction and classification of brain tumors,” Applied Soft Computing, 2024.
23. “Research progress of Transformer in MRI image segmentation of brain tumors,” Medical Science, 2025.
24. “Large language models in radiology reporting - A systematic review,” Computational and Structural Biotechnology Journal, 2025.
25. “Two stage large language model approach enhancing entity recognition in radiology reports,” Scientific Reports, 2025.
26. “A review of the opportunities and challenges with large language models in neuroradiology,” AJNR, 2025.
27. “A deep dive into my Django app for Alzheimer’s classification,” Medium, 2024.
28. “Building an AI-driven symptom checker using Python Django for enhanced telemedicine services,” ResearchGate, 2025.
29. “FHIR: Simplifying electronic health records (EHR) in India,” Dronapay, 2024.