Enhanced ResNet-Vision Transformer using Optimization Techniques for Brain Stroke Detection
view PDF
view PDF

How to Cite

S., Jacophine Susmi, Gunavathie M.A., Kavya S., and Priya J. 2026. “Enhanced ResNet-Vision Transformer Using Optimization Techniques for Brain Stroke Detection”. Journal of Innovative Image Processing 8 (4): 1599-1619. https://doi.org/10.36548/jiip.2026.4.013.

Keywords

Stroke Detection
Hybrid Deep Learning
ResNet50
Vision Transformer (ViT)
Enhanced Black-winged Kite Optimization (EBKO).

Abstract

Early recognition of brain stroke is the key to prompt clinical management and better outcomes. Accurate identification of stroke-affected tissue from normal brain tissue structures in Computed Tomography (CT) images, however, is still a difficult task because of its subtle intensity differences and complex anatomical characteristics. In this regard, this paper proposes an Enhanced Black-winged Kite Optimized ResNet–Vision Transformer Network (HBK-ResViTNet) for automated brain stroke detection. The first step in the CT processing includes detailed noise removal, image normalization, skull stripping, and contrast enhancement in order to improve the image quality and highlight regions of interest for diagnostic purposes. Then, ResNet50 is used to generate a discriminative local spatial representation, and Vision Transformer (ViT) is used to understand the long-range contextual information and achieve global feature interaction. The complementary features generated by these two networks are effectively merged to acquire a powerful feature representation for stroke identification. Additionally, the Enhanced Black-winged Kite Optimization (EBKO) algorithm is used to tune the network hyperparameters for better convergence speed and classification accuracy. Finally, the optimized feature representations are fed into fully connected layers to classify CT images into multiple classes. The proposed framework is evaluated using the RSNA Intracranial Hemorrhage Detection Dataset, a large-scale, multi-institutional brain CT dataset containing expert annotations for five major intracranial haemorrhage subtypes. The experimental outcomes show that it attains higher accuracy, precision, recall, and F1-score than traditional deep learning techniques. The results suggest that the suggested HBK-ResViTNet provides a dependable, efficient, and scalable computer-aided system for early diagnosis of brain stroke, which would be useful in clinical decision-making and management of stroke patients.

References

  1. Abdi, Hassan, Mian Usman Sattar, Raza Hasan, Vishal Dattana, and Salman Mahmood. “Stroke Detection in Brain CT Images Using Convolutional Neural Networks: Model Development, Optimization And Interpretability.” Information 16, no. 5 (2025): 345.
  2. Elsayed, Maha Samir, Gehad Ahmed Saleh, Ahmed I. Saleh, and Abeer Twakol Khalil. “An Effective Brain Stroke Diagnosis Strategy based on Feature Extraction and Hybrid Classifier.” Scientific Reports 15, no. 1 (2025): 29808.
  3. Kulathilake, Chathura D., Jeevani Udupihille, and Atsushi Senoo. “Hybrid Resnet-vit Transfer Learning Approach for Brain Stroke Classification on Computed Tomography Images.” IEEE Transactions on Artificial Intelligence (2025).
  4. Mousavi, Sayyed Saleh Sayyed, and Mohammad Saeed Majedi. “Reconstruction and Classification of Brain Strokes Using Deep Learning-Based Microwave Imaging.” IEEE Access 13 (2025): 27024-27036.
  5. Karimzadeh, Mahsa, Hadi Seyedarabi, Ata Jodeiri, and Reza Afrouzian. “Enhanced Brain Stroke Lesion Segmentation in MRI Using a 2.5 D Transformer Backbone U-Net Model.” Brain Sciences 15, no. 8 (2025): 778.
  6. Hazarika, Hrishikesh, Rion Barua, Mahendra Kumar Gourisaria, Junali Jasmine Jena, Suchismita Das, and Sudhansu Shekhar Patra. “Detection of Glioma from Brain CT Scan Images Using Explainable AI based Ensemble Feature Extraction.” Procedia Computer Science 258 (2025): 1877-1887.
  7. Wang, Zhi, Ao Dong, Junli Zhao, Zhenkuan Pan, Hui Li, and Yi Li. “ISFPN: A Medical Detection Model for Ischemic Stroke Based on Feature Pyramid Network and Swin Transformer.” Biomedical Signal Processing and Control 109 (2025): 108064.
  8. Inamdar, Mahesh Anil, Anjan Gudigar, U. Raghavendra, Massimo Salvi, Raja Rizal Azman Bin Raja Aman, Nadia Fareeda Muhammad Gowdh, Izzah Amirah Binti Mohd Ahir et al. “A Dual-Stream Deep Learning Architecture with Adaptive Random Vector Functional Link for Multi-Center Ischemic Stroke Classification.” IEEE Access 13 (2025): 46638-46658.
  9. Srinivas, A., and Joseph Prakash Mosiganti. “A Brain Stroke Detection Model Using Soft Voting Based Ensemble Machine Learning Classifier.” Measurement: Sensors 29 (2023): 100871.
  10. Ozaltin, Oznur, Orhan Coskun, Ozgur Yeniay, and Abdulhamit Subasi. “A Deep Learning Approach for Detecting Stroke from Brain CT Images Using OzNet.” Bioengineering 9, no. 12 (2022): 783.
  11. Ahmed, Md Mahfuz, Md Maruf Hossain, Md Rakibul Hasan Rakib, Ronok Hashan, Md Touhid Hasan Nirob, and Md Khairul Islam. “A Hybrid Swin Transformer–BiLSTM Framework and Ensemble Learning For Multimodal Brain Stroke Detection and Risk Prediction.” Computers in Biology and Medicine 204 (2026): 111518.
  12. Mostafapour, Ehsan, Mehdi Memarian, Farshad Ebrahimi, Nematollah Ezzati, and Amir Aminfar. “Brain Stroke Detection from MRI Images Using Convolutional Neural Networks and XGBoost.” Biomedical Signal Processing and Control 113 (2026): 109049.
  13. Mandhare, Rajani M., and D. B. Kshirsagar. “Elk Herd Taylor Optimizer-based Deep Kronecker Network for Stroke Detection Using Brain Computed Tomography Images.” Biomedical Signal Processing and Control 112 (2026): 108450.
  14. Shangguan, Hong, Hongrui Zhao, Xiong Zhang, Jie Yang, Yue Sun, Zhanlong Li, and Yina Guo. “A Multi-Stage Progressive Feature Fusion Network for Brain Stroke Lesion Segmentation.” Biomedical Signal Processing and Control 112 (2026): 108581.
  15. Hossain, Md Maruf, Md Mahfuz Ahmed, Abdullah Al Nomaan Nafi, Md Rakibul Islam, Md Shahin Ali, Jahurul Haque, Md Sipon Miah, Md Mahbubur Rahman, and Md Khairul Islam. “A Novel Hybrid ViT-LSTM Model with Explainable AI for Brain Stroke Detection and Classification in CT Images: A Case Study of Rajshahi Region.” Computers in Biology and Medicine 186 (2025): 109711.
  16. Thakre, Gayatri, Rohini Raut, Chetan Puri, and Prateek Verma. “A Hybrid Deep Learning Approach for Improved Detection and Prediction Of Brain Stroke.” Applied Sciences 15, no. 9 (2025): 4639.
  17. Sabir, Muhammad Ayub, and Fatima Ashraf. “Development of a Novel Deep Convolutional Neural Network Model for Early Detection of Brain Stroke Using CT Scan Images.” Multimedia Tools and Applications 84, no. 10 (2025): 7931-7955.
  18. Abumihsan, Ahmad, Amani Yousef Owda, Majdi Owda, Mobarak Abumohsen, Lampros Stergioulas, and Mohammad Ahmad Abu Amer. “A Novel Hybrid Model for Brain Ischemic Stroke Detection Using Feature Fusion and Convolutional Block Attention Module.” IEEE Access (2025).
  19. Li, Yancang, Binli Shi, Weitao Qiao, and Zunfeng Du. “A Black-Winged Kite Optimization Algorithm Enhanced by Osprey Optimization and Vertical and Horizontal Crossover Improvement.” Scientific Reports 15, no. 1 (2025): 6737.
  20. Dataset Link: https://www.kaggle.com/c/rsna-intracranial-hemorrhage-detection?utm_source=chatgpt.com
  21. Ghosal, Rhea, Ronok Ghosal, and Eileen Lou. “Low Dose CT for Stroke Diagnosis: A Dual Pipeline Deep Learning Framework for Portable Neuroimaging.” arXiv preprint arXiv:2603.26764 (2026).
  22. Lu, Zhicheng, Shahadat Uddin, Sergio Uribe, Sam White, Rodrigo Tomazini Martins, Shayne Chau, Abu Syed Md Mosaddek et al. “Clinically Generalisable End-to-End Graph Learning for CT Image-Based Multitask Stroke Diagnosis.” medRxiv (2026): 2026-08.
  23. Gençtürk, Tuğrul Hakan, İsmail Kaya, and Fidan Kaya Gülağız. “Deepening the Diagnosis: Detection of Midline Shift Using an Advanced Deep Learning Architecture.” Applied Sciences 16, no. 2 (2026): 890.
  24. Morshed, Atik, Rifah Jahan Tamanna, Fareha Alam, Ishrat Jahan Lamia, and A. B. M. Danial. “A Hybrid Deep Learning Framework for Multi-Class ICH Detection and Severity Assessment from CT Scans.” PhD diss., Brac University, 2026.
  25. Habek, Gül Cihan, and Fatih Basciftci. “A Randomized Multi-Window 3D Deep Learning Approach for Intracranial Hemorrhage Detection on Non-Contrast Head CT.” Medical & Biological Engineering & Computing (2026): 1-21.