Authors : Shivam Kaintyura; Kamal Ahmad; Dr. Manmohan Singh Yadav

Volume/Issue : Volume 10 - 2025, Issue 12 - December

Google Scholar : https://tinyurl.com/mr24wvzk

Scribd : https://tinyurl.com/2f62979k

DOI : https://doi.org/10.38124/ijisrt/25dec850

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 : Early diagnosis and precise segmentation of brain tumors play a crucial role in neuro-oncology, yet traditional manual MRI analysis is often time-consuming, costly, and subject to significant inter-observer variability. This review paper presents a comprehensive analysis of deep learning methodologies employed for brain tumor detection,emphasizing state- of-the-art segmentation techniques such as attention-based U-Net, convolutional neural networks (CNNs), and transformer- based architectures. The paper thoroughly examines benchmarks on datasets like BraTS, exploring performance metrics— including Dice similarity coefficient and accuracy—across diverse neural network models. Additionally, key challenges such as data scarcity, model interpretability, and domain adaptation for heterogeneous MRI sources are discussed. Recent advances in automated feature extraction, multi-modal data integration, and explainable AI are highlighted, outlining their potential to enhance clinical decision-making. By systematically evaluating both technical developments and practical deployment barriers, this review provides researchers and practitioners with actionable insights into future directions for deep learning-driven brain tumor detection systems.

Keywords : Brain Tumor Detection, Deep Learning, Attention U-Net, CNN, MRI Segmentation, Medical Image Analysis, Explainable AI, BraTS.

References :

1. O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in MICCAI, 2015, pp. 234–241.Detection-Of-Brain-Tumor-Stages-Using-deep-learning.docx​
2. F. Isensee et al., “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: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. [Online]. Available: https://www.med.upenn.edu/cbica/brats2020/data.html
7. T. Nakaura et al., “The impact of large language models on radiology,” Japanese Journal of Radiology, 2024.
8. S. M. Hosseini, “Pixel-wise modulated Dice loss for medical image segmentation,” 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. [Online]. Available: https://www.hl7.org/fhir/
12. “AI-MIRACLE: AI in multilingual interpretation and radiology communication,” 2024.
13. “Comparative evaluation of LLMs for translating radiology impressions into simple Hindi,” PubMed 39697509, 2024.
14. “U-Net-based models towards optimal MR brain image segmentation,” Diagnostics, vol. 13, no. 9, p. 1624, 2023.
15. “Brain tumor segmentation using multiscale attention U-Net with EfficientNet encoder,” Scientific Reports, vol. 15, no. 1, p. 1234, 2025.
16. “Django/DRF HIPAA best practices blog,” 2023.
17. “DISHA and HIPAA, how do they compare?” 2025.
18. “Generalist models in medical image segmentation: A survey and performance comparison with task-specific approaches,” 2025.
19. “Research progress of Transformer in MRI image segmentation of brain tumors,” Medical Science, 2025.
20. “Large language models in radiology reporting - A systematic review,” Computational and Structural Biotechnology Journal, 2025.
21. “Two stage large language model approach enhancing entity recognition in radiology reports,” Scientific Reports, 2025.
22. “A review of the opportunities and challenges with large language models in neuroradiology,” AJNR, 2025.
23. “A deep dive into my Django app for Alzheimer’s classification,” Medium, 2024.
24. “Building an AI-driven symptom checker using Python Django for enhanced telemedicine services,” 2025.