Brain Stroke Detection Using Deep Learning and Grad-CAM Explainability Framework

Year : 2026 | Volume : 16 | Issue : 02 | Page : 8 14
By

Vibhav Dadhich,

Shruti Mathur,

Dimpal Sharma,

  1. M. Tech Scholar, Department of Computer Science, Jaipur Engineering College and Research Centre (JECRC), JECRC University, Jaipur, Rajasthan, India
  2. Assistant Professor, Department of Computer Science, Jaipur Engineering College and Research Centre (JECRC), JECRC University, Jaipur, Rajasthan, India
  3. Assistant Professor, Department of Computer Science, Jaipur Engineering College and Research Centre (JECRC), JECRC University, Jaipur, Rajasthan, India

Abstract

Seconds matter when a brain stroke occurs; it is a race against time where rapid, precise intervention is the only way to preserve a patient’s quality of life. This research introduces a deep learning framework designed to act as a vital ally for clinicians, providing automated, high-speed stroke detection through brain MRI analysis. At the heart of our approach is EfficientNetB0, a sophisticated neural network chosen for its ability to recognize complex medical patterns with remarkable efficiency. However, we believe that for AI to be truly effective in a hospital, it cannot be a “black box.” To bridge the gap between data and trust, we integrated Grad-CAM (Gradient-weighted Class Activation Mapping). This feature translates the model’s internal logic into visual heatmaps, pinpointing the exact regions of the brain that triggered a stroke diagnosis. By classifying scans into “Stroke” and “Normal” categories with 98% accuracy, our system offers a reliable second opinion. These visual explanations don’t just provide an answer – they provide a rationale, fostering the confidence doctors need to make life-saving decisions. Ultimately, this tool serves as a critical support system in clinical settings, particularly in underserved areas where immediate access to specialist radiologists may be limited.

Keywords: Brain stroke, deep learning, efficientNetB0, Grad-CAM, explainable AI, MRI

[This article belongs to Research and Reviews: A Journal of Neuroscience ]

How to cite this article: Vibhav Dadhich, Shruti Mathur, Dimpal Sharma. Brain Stroke Detection Using Deep Learning and Grad-CAM Explainability Framework. Research and Reviews: A Journal of Neuroscience. 2026; 16(02):8-14.
How to cite this URL: Vibhav Dadhich, Shruti Mathur, Dimpal Sharma. Brain Stroke Detection Using Deep Learning and Grad-CAM Explainability Framework. Research and Reviews: A Journal of Neuroscience. 2026; 16(02):8-14. Available from: https://journals.stmjournals.com/rrjons/article=2026/view=253604

References

  1. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV); 2017. p. 618–626. doi: 1109/ICCV.2017.74.
  2. Hossain S, Hossain MS, Muhammad G, Amin SU, Alhamid MF, Alamri A. Vision transformers and explainable artificial intelligence for brain tumor detection and classification. IEEE J Biomed Health Inform. 2023;27(8):3891–3902.
  3. Rahman M, Islam MZ, Hasan MM, Hossain MS, Alsharif MH, Islam MR, et al. GliomaCNN: A lightweight convolutional neural network model for glioma classification using brain MRI images. Comput Model Eng Sci. 2024;139(1):1–22.
  4. Mahesh TR, Reddy PS, Kumar AS, Rao GS. An XAI-enhanced EfficientNetB0 framework for brain imaging classification and interpretation. J Neurosci Methods. 2024;401:110003.
  5. Mastoi QUA, Shaikh ZA, Memon MH, Memon S, Alvi AH, Ahmed S, et al. Explainable artificial intelligence in medical imaging: a federated learning approach. Front Neurosci. 2025;19:1456789.
  6. Tan M, Le QV. EfficientNet: Rethinking model scaling for convolutional neural networks. In: Proceedings of the 36th International Conference on Machine Learning (ICML). PMLR. 2019;97:6105–6114.
  7. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems. 2012;25:1097–1105.
  8. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016. p. 770–778. doi: 1109/CVPR.2016.90.
  9. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: Proceedings of the International Conference on Learning Representations (ICLR); 2015.
  10. Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60–88. doi: 1016/j.media.2017.07.005.
  11. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115–118. doi: 1038/nature21056.
  12. Chilamkurthy S, Ghosh R, Tanamala S, Biviji M, Campeau NG, Venugopal VK, et al. Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study. Lancet. 2018;392(10162):2388–2396. doi: 1016/S0140-6736(18)31645-3.
  13. Rajpurkar P, Irvin J, Zhu K, Yang B, Mehta H, Duan T, et al. CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv [Preprint]. 2017. arXiv:1711.05225.
  14. Kamnitsas K, Ledig C, Newcombe VFJ, Simpson JP, Kane AD, Menon DK, et al. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal. 2017;36:61–78. doi: 1016/j.media.2016.10.004.
  15. Pereira S, Pinto A, Alves V, Silva CA. Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans Med Imaging. 2016;35(5):1240–1251. doi: 1109/TMI.2016.2538465.
  16. Ribeiro MT, Singh S, Guestrin C. “Why should I trust you?” Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD); 2016. p. 1135–1144. doi: 1145/2939672.2939778.
  17. Lundberg SM, Lee SI. A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems. 2017;30:4765–4774.
  18. Bach S, Binder A, Montavon G, Klauschen F, Müller KR, Samek W. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS One. 2015;10(7):e0130140. doi: 1371/journal.pone.0130140.
  19. Montavon G, Samek W, Müller KR. Methods for interpreting and understanding deep neural networks. Digit Signal Process. 2018;73:1–15. doi: 1016/j.dsp.2017.10.011.
  20. Samek W, Wiegand T, Müller KR. Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models. ITU J ICT Discov. 2017;1(1):39–48.
  21. Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et al. An image is worth 16×16 words: Transformers for image recognition at scale. In: Proceedings of the International Conference on Learning Representations (ICLR); 2021.
  22. Hatamizadeh A, Tang Y, Nath V, Yang D, Myronenko A, Landman BA, et al. UNETR: Transformers for 3D medical image segmentation. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV); 2022. p. 574–584.
  23. Azad R, Khan A, Khan MU, Rehman A, Awan MJ, Alharbi A, et al. Advances in medical image segmentation using deep learning: a comprehensive review. Front Neuroinform. 2022;16:923524.
  24. Shamshad F, Khan S, Zamir SW, Khan MH, Hayat M, Khan FS, et al. Transformers in medical imaging: a survey. Med Image Anal. 2023;88:102802. doi: 1016/j.media.2023.102802.
  25. Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A. Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016. p. 2921–2929.
  26. Liew SL, Anglin JM, Banks NW, Sondag M, Ito KL, Kim H, et al. A large, open source dataset of stroke anatomical brain images and manual lesion segmentations. Sci Data. 2018;5:180011. doi: 1038/sdata.2018.11.
  27. Winzeck S, Hakim A, McKinley R, Pinto JA, Alves V, Silva C, et al. ISLES 2016 and 2017 benchmarking ischemic stroke lesion outcome prediction based on multispectral MRI. Med Image Anal. 2018;48:103–116. doi: 1016/j.media.2018.05.001.
  28. Chen L, Bentley P, Mori K, Misawa K, Fujiwara M, Rueckert D. Deep learning for stroke prediction and diagnosis: A systematic review. IEEE Access. 2020;8:56806–56820. doi: 1109/ACCESS.2020.2981082.
  29. Pinto A, Brunese L, Pinto F, Reali R, Daniele S, Romano L. The role of artificial intelligence in radiology: Current status and future directions. Radiol Med. 2021;126(1):58–69.
  30. Topol EJ. High-performance medicine: The convergence of human and artificial intelligence. Nat Med. 2019;25(1):44–56. doi: 1038/s41591-018-0300-7.
Regular Issue Subscription Original Research
Volume 16
Issue 02
Received 04/02/2026
Accepted 15/05/2026
Published 31/08/2026
Publication Time 208 Days

Login

My IP

PlumX Metrics

Support