Volume 10 • Issue 1 • PP: 20–27 • 2025
Brain Stroke Detection in CT Images Using Transfer Learning and Deep Learning Models
Open Access & Copyright
© 2025 The Author(s). Published by ASPG. This article is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
Editorial responsibility:
This article was handled by an independent editor. The author serving on the Editorial Board had no involvement in the peer-review process or the final editorial decision.
View PDF Abstract
A brain stroke represents a deadly health condition that emerges from poor blood flow to the brain. Brain tissue affected by a stroke will completely cease regular operations. Immediate detection of a brain stroke leads to better treatment success. Images from computed tomography (CT) provide a quick diagnosis of stroke. But time is passing quickly as physicians examine each brain CT scan. This situation could cause therapy to be delayed and mistakes to be made. Thus, we focused on using a practical artificial intelligence algorithm for stroke detection. This paper proposes several deep neural network models, such as DenseNet121, ResNet50, Xception, and EfficientNetV2S, for transfer learning to study the features of stroke lesions and achieve complete intelligent automatic detection by classifying CT images into two categories (stroke and normal). The dataset comprises 437 testing, 235 validation, and 1843 training photos. Using the same dataset, the experimental findings outperform all state-of-the-art. The optimal model utilizing the EfficientNetV2S model for transfer learning has an overall accuracy of 99.57% and the same value for precision and recall.
Keywords
References
[1] GBD 2021 Stroke Risk Factor Collaborators, “Global, regional, and national burden of stroke and its risk fac-tors, 1990–2021: a systematic analysis for the Global Burden of Disease Study 2021,” The Lancet Neurology, vol. 23, no. 10, pp. 973–1003, 2024.
[2] A. Sarraj, D. K. Pujara, and B. C. V. Campbell, “Cur-rent state of evidence for neuroimaging paradigms in management of acute ischemic stroke,” Annals of Neu-rology, vol. 95, no. 6, pp. 1017–1034, 2024.
[3] Y. Liu, Z. Wen, Y. Wang, Y. Zhong, J. Wang, Y. Hu, P. Zhou, and S. Guo, “Artificial intelligence in ischemic stroke images: current applications and future direc-tions,” Frontiers in Neurology, vol. 15, art. 1418060, 2024.
[4] J. Luo, P. Dai, Y. Wu, Z. He, C. M. Huang, Z. Huang, S. Liao, and K. Liu, “Deep learning models for ischemic stroke lesion segmentation in medical images: a sur-vey,” Computers in Biology and Medicine, vol. 175, art. 108509, 2024.
[5] Ö. Polat, Z. Dokur, and T. Ölmez, “Classification of brain strokes using divergence-based convolutional neu-ral networks,” Biomedical Signal Processing and Con-trol, vol. 93, art. 106193, 2024.
[6] M. J. Ferdous and R. Shahriyar, “An ensemble convolu-tional neural network model for brain stroke prediction using brain computed tomography images,” Healthcare Analytics, vol. 6, art. 100368, 2024.
[7] W.-C. Wang et al., “Automated delineation of acute ischemic stroke lesions on non-contrast CT using 3D deep learning: a promising step towards efficient diag-nosis and treatment,” Biomedical Signal Processing and Control, vol. 93, art. 106139, 2024.
[8] P. Hu et al., “Deep learning-assisted detection and seg-mentation of intracranial hemorrhage in noncontrast computed tomography scans of acute stroke patients: a systematic review and meta-analysis,” International Journal of Surgery, vol. 110, no. 6, pp. 3839–3847, 2024.
[9] S. M. Mäenpää and M. Korja, “Diagnostic test accuracy of externally validated convolutional neural network (CNN) artificial intelligence (AI) models for emergencyhead CT scans–A systematic review,” International Jour-nal of Medical Informatics, vol. 189, art. 105523, 2024.
[10] Q. Gao, H. Fu, X. Zhao, and Z. Ge, “Additive margin networks with adaptive feature recalibration and its ap-plications in brain stroke CT image classification,” IET Image Processing, vol. 18, no. 3, pp. 731–740, 2024.
[11] R. Singh, S. Kaur, G. Singh, M. Kaur, and P. Kaur, “Optimizing early diagnosis by integrating multiple clas-sifiers for predicting brain stroke and critical diseases,” Scientific Reports, vol. 14, art. 28429, 2024.
[12] F. Chollet, “Xception: deep learning with depthwise separable convolutions,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recogni-tion, pp. 1251–1258, 2017.
[13] G. Huang, Z. Liu, L. van der Maaten, and K. Q. Wein-berger, “Densely connected convolutional networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708, 2017.
[14] M. Tan and Q. V. Le, “EfficientNetV2: smaller models and faster training,” in Proceedings of the 38th Interna-tional Conference on Machine Learning, vol. 139, pp. 10096–10106, 2021.
[15] K. He, X. Zhang, S. Ren, and J. Sun, “Deep resid-ual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778, 2016.
[16] H. Kim et al., “Automated segmentation of MRI white matter hyperintensities in 8421 patients with acute is-chemic stroke,” American Journal of Neuroradiology, vol. 45, no. 12, pp. 1885–1894, 2024.
[17] Z. Wu et al., “A feature-enhanced network for stroke le-sion segmentation from brain MRI images,” Computers in Biology and Medicine, vol. 174, art. 108326, 2024.
[18] B. P. Garcia-Salgado et al., “Enhanced ischemic stroke lesion segmentation in MRI using attention U-Net with generalized Dice focal loss,” Applied Sciences, vol. 14, no. 18, art. 8183, 2024.
[19] J. Sun et al., “Pathological asymmetry-guided progres-sive learning for acute ischemic stroke infarct segmenta-tion,” IEEE Transactions on Medical Imaging, vol. 43, no. 12, pp. 4146–4160, 2024.
[20] K. Kirillov et al., “Segmentation of 3D non-contrast CT brain images using transformer neural networks,” in Proceedings of the 2024 IEEE International Multi-Conference on Engineering, Computer and Information Sciences, pp. 173–177, 2024.
[21] J. Sun et al., “Multi-grained contrastive representation learning for label-efficient lesion segmentation and on-set time classification of acute ischemic stroke,” Medical Image Analysis, vol. 97, art. 103250, 2024.
[22] Z. Wang et al., “Hybrid offline and self-knowledge dis-tillation for acute ischemic stroke lesion segmentation from non-contrast CT scans,” Computers in Biology and Medicine, vol. 183, art. 109312, 2024.
[23] Y. Peng et al., “Deep learning-assisted diagnosis of large vessel occlusion in acute ischemic stroke based on four-dimensional computed tomography angiography,” Frontiers in Neuroscience, vol. 18, art. 1329718, 2024.
[24] H. Qu et al., “Target-based deep learning network surveillance of non-contrast computed tomography for small infarct core of acute ischemic stroke,” Frontiers in Neurology, vol. 15, art. 1477811, 2024.
[25] Y.-H. Huang et al., “The value of CT-based radiomics in predicting hemorrhagic transformation in acute is-chemic stroke patients without recanalization therapy,” Frontiers in Neurology, vol. 15, art. 1255621, 2024.
[26] Q. Li et al., “CT-based radiomics models predict spon-taneous intracerebral hemorrhage expansion and are comparable with CT angiography spot sign,” Frontiers in Neurology, vol. 15, art. 1332509, 2024.
[27] A. Fontanella et al., “Development of a deep learning method to identify acute ischaemic stroke lesions on brain CT,” Stroke and Vascular Neurology, art. svn-2024-003372, 2024.
[28] J. Sommer et al., “Deep learning for prediction of post-thrombectomy outcomes based on admission CT an-giography in large vessel occlusion stroke,” Frontiers in Artificial Intelligence, vol. 7, art. 1369702, 2024.
[29] Y. Liu et al., “Prediction of ischemic stroke functional outcomes from acute-phase noncontrast CT and clinical information,” Radiology, vol. 313, no. 1, art. e240137, 2024.
[30] B. Borsos, C. G. Allaart, and A. van Halteren, “Predict-ing stroke outcome: a case for multimodal deep learning methods with tabular and CT perfusion data,” Artificial Intelligence in Medicine, vol. 147, art. 102719, 2024.
[31] A. Gutierrez et al., “Annotation-free prediction of treatment-specific tissue outcome from 4D CT perfu-sion imaging in acute ischemic stroke,” Computerized Medical Imaging and Graphics, vol. 114, art. 102376, 2024.
[32] F. Palsson et al., “Prediction of tissue outcome in acute ischemic stroke based on single-phase CT angiogra-phy at admission,” Frontiers in Neurology, vol. 15, art. 1330497, 2024.
[33] J. H. Han et al., “Automated identification of thrombec-tomy amenable vessel occlusion on computed tomog-raphy angiography using deep learning,” Frontiers in Neurology, vol. 15, art. 1442025, 2024.
[34] Q. Huang et al., “Machine learning is an effective method to predict the 3-month prognosis of patients with acute ischemic stroke,” Frontiers in Neurology, vol. 15, art. 1407152, 2024.
[35] S. Zhi et al., “An exploration on the machine-learning-based stroke prediction model,” Frontiers in Neurology, vol. 15, art. 1372431, 2024.
[36] Y. Yang and Y. Guo, “Ischemic stroke outcome pre-diction with diversity features from whole brain tissue using deep learning network,” Frontiers in Neurology, vol. 15, art. 1394879, 2024.
[37] H. Wei et al., “Explainable machine learning for predict-ing neurological outcome in hemorrhagic and ischemic stroke patients in critical care,” Frontiers in Neurology, vol. 15, art. 1385013, 2024.
[38] C. Gui et al., “St-RegSeg: an unsupervised registration-based framework for multimodal magnetic resonance imaging stroke lesion segmentation,” Quantitative Imag-ing in Medicine and Surgery, vol. 14, no. 12, pp. 9459–9476, 2024.
[39] T. Li et al., “SrSNet: accurate segmentation of stroke lesions by a two-stage segmentation framework with asymmetry information,” Expert Systems with Applica-tions, art. 124329, 2024.
[40] B. B. Ozkara et al., “Utilizing imaging parameters for functional outcome prediction in acute ischemic stroke: a machine learning study,” Journal of Neuroimaging, vol. 34, no. 3, pp. 356–365, 2024.
[41] T.-H. Yang et al., “Magnetic resonance imaging-based deep learning imaging biomarker for predicting func-tional outcomes after acute ischemic stroke,” European Journal of Radiology, vol. 174, art. 111405, 2024.
[42] Y. He et al., “Construction of a machine learning-based prediction model for unfavorable discharge outcomes in patients with ischemic stroke,” Heliyon, vol. 10, no. 17, art. e37179, 2024.
[43] T. Kaewlek et al., “Comparative analysis of deep learn-ing techniques for accurate stroke detection,” Journal of Associated Medical Sciences, vol. 57, no. 2, pp. 49–55, 2024.
Cite This Article
Choose your preferred format
Publisher's Note
The statements, opinions, and data presented in this article are solely those of the author(s) and do not necessarily represent those of ASPG, the journal, or its editors. ASPG and the editors disclaim responsibility for any harm arising from the use of any ideas, methods, instructions, or products described in this article, to the fullest extent permitted by applicable law.