Attention-Enhanced MobileNetV2 for Accurate and Deployable Brain Stroke Detection

Sibel Barin Özkan

doi:10.54287/gujsa.1925900

Attention-Enhanced MobileNetV2 for Accurate and Deployable Brain Stroke Detection

Abstract

Stroke is a serious neurological condition that causes high morbidity and mortality rates worldwide. Rapid and accurate diagnosis is critical to improving patient treatment and quality of life. To address this issue, two lightweight deep learning models based on MobileNetV2 were designed for stroke diagnosis and classification. The first model combines channel and spatial attention mechanisms by integrating CBAM (Convolutional Block Attention Module) into MobileNetV2. The second model applies a multi-attention strategy using ECA (Efficient Channel Attention) and Coordinate Attention blocks. Transfer learning was applied using a pre-trained MobileNetV2 network on ImageNet for both models, preventing overfitting on small medical datasets. The results demonstrate that attention mechanisms are effective in capturing subtle differences between classes. Model 1 (99.4% accuracy) and Model 2 (99.8% accuracy) demonstrated high performance, supported by precision, recall, F1-score, and AUC values. The primary goal in selecting MobileNetV2 was to ensure that the models could be integrated into devices with limited resources, such as smartphones and embedded systems. The results were found to be promising in terms of both high accuracy and low computational cost. The proposed approach has the potential to provide scalable and real-time solutions, making a significant contribution to stroke detection.

Keywords

References

Aksoy, S., Demircioglu, P., & Bogrekci, I. (2025). An Explainable AI Framework for Stroke Classification Based on CT Brain Images. AI, 6(9), 202. https://doi.org/10.3390/ai6090202
Alomoush, W., Houssein, E. H., Alrosan, A., Abd-Alrazaq, A., Alweshah, M., & Alshinwan, M. (2024). Joint opposite selection enhanced Mountain Gazelle Optimizer for brain stroke classification. Evolutionary Intelligence, 17(4), 2865-2883. https://doi.org/10.1007/s12065-024-00917-8
Donkor, E. S. (2018). Stroke in the 21st century: a snapshot of the burden, epidemiology, and quality of life. Stroke Research and Treatment, 2018(1), 3238165. https://doi.org/10.1155/2018/3238165
Elsayed, M. S., Saleh, G. A., Saleh, A. I., & Khalil, A. T. (2025). An effective brain stroke diagnosis strategy based on feature extraction and hybrid classifier. Scientific Reports, 15(1), 29808. https://doi.org/10.1038/s41598-025-14444-8
Eshmawi, A. A., Khayyat, M., Algarni, A. D., & Hilali-Jaghdam, I. (2022). An ensemble of deep learning enabled brain stroke classification model in magnetic resonance images. Journal of Healthcare Engineering, 2022(1), 7815434. https://doi.org/10.1155/2022/7815434
Fachruddin, F., Rasywir, E., & Pratama, Y. (2024). Increasing the accuracy of brain stroke classification using random forest algorithm with mutual information feature selection. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 8(4), 555-562. https://doi.org/10.29207/resti.v8i4.5795
Feigin, V. L., Roth, G. A., Naghavi, M., Parmar, P., Krishnamurthi, R., Chugh, S., Mensah, G. A., Norrving, B., Shiue, I., Ng, M., Estep, K., Cercy, K., Murray, C. J. L., & Forouzanfar, M. H. (2016). Global burden of stroke and risk factors in 188 countries, during 1990–2013: a systematic analysis for the Global Burden of Disease Study 2013. The Lancet Neurology, 15(9), 913-924. https://doi.org/10.1016/S1474-4422(16)30073-4
Hossen, Md. S., Shuvo, E. A., Arif, S. A., Shaha, P., Saiduzzaman, Md., Nasir, M. K. (2025). An efficient deep learning framework for brain stroke diagnosis using computed tomography (CT) images. https://doi.org/10.48550/arXiv.2507.03558

Hou, Q., Zhou, D., & Feng, J. (2021). Coordinate attention for efficient mobile network design. In: Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 13708-13717), (20-25 June 2021). Nashville, TN, USA. https://doi.org/10.1109/CVPR46437.2021.01350
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. https://doi.org/10.48550/arXiv.1704.04861
Inamdar, M. A., Gudigar, A., Raghavendra, U., Salvi, M., Raj, N., Pooja, J., Hegde, A., Menon, G. R., & Acharya, U. R. (2025). Dual Attention Mechanisms with Patch-Level Significance Embedding for Ischemic Stroke Classification in Brain CT Images. Informatics in Medicine Unlocked, 101678. https://doi.org/10.1016/j.imu.2025.101678
Irfan, M., Subasi, A., Mustafa, N., Westerlund, T., & Chen, W. (2024). An evaluation of pretrained convolutional neural networks for stroke classification from brain CT images. In: A. Subasi (Eds.), Applications of Artificial Intelligence in Healthcare and Biomedicine (pp. 111-135). Academic Press. https://doi.org/10.1016/B978-0-443-22308-2.00003-2
Jayachitra, S., & Prasanth, A. (2021). Multi-feature analysis for automated brain stroke classification using weighted Gaussian naïve Bayes classifier. Journal of Circuits, Systems and Computers, 30(10), 2150178. https://doi.org/10.1142/S0218126621501784
Kaggle. (2024). Brain Stroke CT Image Dataset. Available online. https://www.kaggle.com/datasets/afridirahman/brain-stroke-ct-image-dataset (Accessed: 10/11/2025).
Kann, B. H., Thompson, R., Thomas Jr, C. R., Dicker, A., & Aneja, S. (2019). Artificial intelligence in oncology: current applications and future directions. Oncology, 33(2), 46-53.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. In: F. Pereira, C. J. Burges, L. Bottou, & K. Weinberger (Eds.), Advances in Neural Information Processing Systems 25 (NIPS 2012).
Kulathilake, C. D., Udupihille, J., & Senoo, A. (2025). Hybrid ResNet-ViT transfer learning approach for brain stroke classification on computed tomography images. IEEE Transactions on Artificial Intelligence. https://doi.org/10.1109/TAI.2025.3596534
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60-88. https://doi.org/10.1016/j.media.2017.07.005
Mohammadi, M., Rad, A. J., & Behrouzi, A. (2025). Brain stroke classification using wavelet transform and MLP neural networks on DWI MRI images. https://doi.org/10.48550/arXiv.2506.15364
Patel, C. H., Undaviya, D., Dave, H., Degadwala, S., & Vyas, D. (2023). EfficientNetB0 for brain stroke classification on computed tomography scan. In: 2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC) (pp. 713-718), (04-06 May 2023), Salem, India. IEEE. https://doi.org/10.1109/ICAAIC56838.2023.10141195
Qari, S., & Thafar, M. A. (2025). Brain Stroke Classification Using CT Scans with Transformer-Based Models and Explainable AI. Diagnostics, 15(19), 2486. https://doi.org/10.3390/diagnostics15192486
Raj, R., Mathew, J., Kannath, S. K., & Rajan, J. (2023). StrokeViT with AutoML for brain stroke classification. Engineering Applications of Artificial Intelligence, 119, 105772. https://doi.org/10.1016/j.engappai.2022.105772
Riz Kifli, N., Hidayat, H., Rahmawati, Putri Sukoco, F., Rahma Yuniarti, A., & Rizal, S. (2022). Brain stroke classification using one dimensional convolutional neural network. In 2022 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob) (pp. 1-6), (09-10 December 2022), Bandung, Indonesia. IEEE. https://doi.org/10.1109/APWiMob56856.2022.10014207
Saenger, A. K., & Christenson, R. H. (2010). Stroke biomarkers: progress and challenges for diagnosis, prognosis, differentiation, and treatment. Clinical Chemistry, 56(1), 21-33. https://doi.org/10.1373/clinchem.2009.133801
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. In: Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition (pp. 4510-4520), (18-23 June 2018), Salt Lake City, UT, USA. https://doi.org/10.1109/CVPR.2018.00474
Shen, D., Wu, G., & Suk, H.-I. (2017). Deep learning in medical image analysis. Annual Review of Biomedical Engineering, 19(1), 221-248. https://doi.org/10.1146/annurev-bioeng-071516-044442
Slimi, H., & Abid, S. (2025). Brain stroke classification using ensemble learning approaches. International Journal of Advancements in Technology, 16(2), 343.
Subashini, S. M. C., & Sakthivel, S. (2025). Optimized H-StrokeNet: A Deep Learning Network for Stroke Classification. Traitement du Signal, 42(3), 1801-1810. https://doi.org/10.18280/ts.420348
Tursynova, A., Omarov, B., Tukenova, N., Salgozha, I., Khaaval, O., Ramazanov, R., & Ospanov, B. (2023). Deep learning-enabled brain stroke classification on computed tomography images. Computers, Materials and Continua, 75(1), 1431-1446. https://doi.org/10.32604/cmc.2023.034400
Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., & Hu, Q. (2020). ECA-Net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 11531-11539), (13-19 June 2020), Seattle, WA, USA. https://doi.org/10.1109/CVPR42600.2020.01155
WHO. World Health Organization. (2024). Global Health Estimates: Leading causes of death. Geneva.
Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018). CBAM: Convolutional block attention module. In: V. Ferrari, M. Hebert, C. Sminchisescu, & Y. Weiss (Eds.), Proceedings of the European Conference on Computer Vision (ECCV) (pp. 3-19), (8-14 September 2018), Munich, Germany. https://doi.org/10.1007/978-3-030-01234-2_1
Yalçın, S., & Vural, H. (2022). Brain stroke classification and segmentation using encoder-decoder based deep convolutional neural networks. Computers in Biology and Medicine, 149, 105941. https://doi.org/10.1016/j.compbiomed.2022.105941

Details

Primary Language

English

Subjects

Deep Learning, Neural Networks

Journal Section

Research Article

Authors

Sibel Barin Özkan ^*
0000-0001-8302-7441
Türkiye

Early Pub Date

July 21, 2026

Publication Date

-

Submission Date

April 8, 2026

Acceptance Date

July 14, 2026

Published in Issue

Year 2026 Number: Advanced Online Publication

DOI

https://doi.org/10.54287/gujsa.1925900

IZ

https://izlik.org/JA62PT42PG

Cite

RIS / Bibtex

APA

Barin Özkan, S. (2026). Attention-Enhanced MobileNetV2 for Accurate and Deployable Brain Stroke Detection. Gazi University Journal of Science Part A: Engineering and Innovation, Advanced Online Publication, 941-965. https://doi.org/10.54287/gujsa.1925900

AMA

1.Barin Özkan S. Attention-Enhanced MobileNetV2 for Accurate and Deployable Brain Stroke Detection. GU J Sci, Part A. 2026;(Advanced Online Publication):941-965. doi:10.54287/gujsa.1925900

Chicago

Barin Özkan, Sibel. 2026. “Attention-Enhanced MobileNetV2 for Accurate and Deployable Brain Stroke Detection”. Gazi University Journal of Science Part A: Engineering and Innovation, no. Advanced Online Publication: 941-65. https://doi.org/10.54287/gujsa.1925900.

EndNote

Barin Özkan S (July 1, 2026) Attention-Enhanced MobileNetV2 for Accurate and Deployable Brain Stroke Detection. Gazi University Journal of Science Part A: Engineering and Innovation Advanced Online Publication 941–965.

IEEE

[1]S. Barin Özkan, “Attention-Enhanced MobileNetV2 for Accurate and Deployable Brain Stroke Detection”, GU J Sci, Part A, no. Advanced Online Publication, pp. 941–965, July 2026, doi: 10.54287/gujsa.1925900.

ISNAD

Barin Özkan, Sibel. “Attention-Enhanced MobileNetV2 for Accurate and Deployable Brain Stroke Detection”. Gazi University Journal of Science Part A: Engineering and Innovation. Advanced Online Publication (July 1, 2026): 941-965. https://doi.org/10.54287/gujsa.1925900.

JAMA

1.Barin Özkan S. Attention-Enhanced MobileNetV2 for Accurate and Deployable Brain Stroke Detection. GU J Sci, Part A. 2026;:941–965.

MLA

Barin Özkan, Sibel. “Attention-Enhanced MobileNetV2 for Accurate and Deployable Brain Stroke Detection”. Gazi University Journal of Science Part A: Engineering and Innovation, no. Advanced Online Publication, July 2026, pp. 941-65, doi:10.54287/gujsa.1925900.

Vancouver

1.Sibel Barin Özkan. Attention-Enhanced MobileNetV2 for Accurate and Deployable Brain Stroke Detection. GU J Sci, Part A. 2026 Jul. 1;(Advanced Online Publication):941-65. doi:10.54287/gujsa.1925900