Medical Image Analysis for Brain Tumor Detection Using Deep Learning on MRI Scans

International Journal of Emerging Research in Science, Engineering, and Management
Vol. 2, Issue 3, pp. 386-395, March 2026.

https://doi.org/10.58482/ijersem.v2i3.49

This work is licensed under a Creative Commons Attribution 4.0 International License.

Medical Image Analysis for Brain Tumor Detection Using Deep Learning on MRI Scans

S Savitha

V K Dinesh

M Gopi Krishna

P C Adithya

M Divya Sree

Department of CSE, Siddharth Institute of Engineering & Technology, Puttur, AP, India.

Full Text PDF

Abstract: Brain tumors are among the most aggressive and deadliest neurological disorders in the world, hence the need for quick and accurate diagnostic interventions. The gold standard for non-invasive diagnosis is Magnetic Resonance Imaging (MRI). However, manual interpretation by radiologists is prone to inter-observer variability, fatigue-based error, and delays in treatment planning. A deep-learning model named NeuroDetectNet, incorporating the Squeeze-and-Excitation attention block (SE) and a customised Convolutional Neural Network (CNN), is proposed for automatic detection and classification of brain tumours. Unlike traditional CNNs that treat all spatial features with equal importance, the proposed model dynamically recalibrates channel-specific responses, focusing on tumour-relevant regions while suppressing background noise. The network was trained and tested using a multi-class MRI dataset consisting of glioma, meningioma, pituitary tumours, and non-tumour images. Experimental evaluation demonstrates that NeuroDetectNet achieves a classification accuracy of 98.7%, with sensitivity of 98.2% and specificity of 99.1%, outperforming existing architectures such as VGG-19 and ResNet-50. The proposed system significantly reduces diagnostic time per scan to less than 45 ms, indicating strong potential as an effective clinical decision-support tool for radiologists.

Keywords: Brain Tumour Detection, Deep Learning, Medical Image Analysis, Convolutional Neural Network, Attention Mechanisms.

References: 

  1. T. A. Fahim, F. B. Alam, and M. A. Hossain, “Brain tumor detection, classification and segmentation by deep learning models from MRI images: Recent approaches, challenges and future directions,” Array, vol. 28, p. 100571, Nov. 2025, doi: 10.1016/j.array.2025.100571.

  2. K. S. Prabhas et al., “A Deep learning framework for brain tumor detection using CNNs and transfer learning on MRI scans,” Systems and Soft Computing, vol. 7, p. 200389, Sep. 2025, doi: 10.1016/j.sasc.2025.200389.

  3. H. Sadr, M. Nazari, S. Yousefzadeh-Chabok, H. Emami, R. Rabiei, and A. Ashraf, “Enhancing brain tumor classification in MRI images: A deep learning-based approach for accurate diagnosis,” Image and Vision Computing, vol. 159, p. 105555, Apr. 2025, doi: 10.1016/j.imavis.2025.105555.

  4. R. Khan et al., “High-precision brain tumor classification from MRI images using an advanced hybrid deep learning method with minimal radiation exposure,” Journal of Radiation Research and Applied Sciences, vol. 18, no. 4, p. 101858, Aug. 2025, doi: 10.1016/j.jrras.2025.101858.

  5. A. Rath, B. S. P. Mishra, and D. K. Bagal, “ResNet50-based Deep Learning model for accurate brain tumor detection in MRI scans,” Next Research., vol. 2, no. 1, p. 100104, Dec. 2024, doi: 10.1016/j.nexres.2024.100104.

  6. A. Alamri, S. Abdel-Khalek, A. A. Bahaddad, and A. M. Alghamdi, “Innovative deep learning and quantum entropy techniques for brain tumor MRI image edge detection and classification model,” Alexandria Engineering Journal, vol. 122, pp. 588–604, Mar. 2025, doi: 10.1016/j.aej.2025.03.038.

  7. M. S. Hasan, M. M. R. Komol, F. Fahim, J. Islam, T. Pervin, and M. M. Hasan, “DEEP Q-NAS: A new algorithm based on neural architecture search and reinforcement learning for brain tumor identification from MRI,” Computers in Biology and Medicine, vol. 196, no. Pt B, p. 110767, Jul. 2025, doi: 10.1016/j.compbiomed.2025.110767.

  8. R. B. Sumona, J. P. Biswas, A. Shafkat, M. M. Rahman, M. O. Faruk, and Y. Majeed, “An integrated deep learning approach for enhancing brain tumor diagnosis,” Healthcare Analytics, vol. 8, p. 100421, Sep. 2025, doi: 10.1016/j.health.2025.100421.

  9. F. Alshomrani, “Challenges and Advances in Classifying Brain Tumors: An Overview of Machine, Deep Learning, and Hybrid Approaches with Future Perspectives in Medical Imaging,” Current Medical Imaging Formerly Current Medical Imaging Reviews, vol. 21, p. e15734056365191, Jun. 2025, doi: 10.2174/0115734056365191250602124819.

  10. E. Chamseddine, L. Tlig, L. Chaari, and M. Sayadi, “A Gabor-enhanced deep learning approach with dual-attention for 3D MRI brain tumor segmentation,” Computers in Biology and Medicine, vol. 197, no. Pt B, p. 111047, Sep. 2025, doi: 10.1016/j.compbiomed.2025.111047.

  11. N. Raju, K. Srinivas, C. Rajesh, and B. M. Chintakindi, “Advanced brain tumor detection using YOLO- β 11 in MRI images,” Alexandria Engineering Journal, vol. 132, pp. 181–190, Oct. 2025, doi: 10.1016/j.aej.2025.10.019.

  12. B. Jiang et al., “Deep learning for brain tumor segmentation in multimodal MRI images: A review of methods and advances,” Image and Vision Computing, vol. 156, p. 105463, Mar. 2025, doi: 10.1016/j.imavis.2025.105463.

Download PDF

This article is part of Volume 2, Issue 3 (March 2026)