Advancing Ischemic Stroke Detection Through an In-depth Evaluation of YOLOv10 Models on Diffusion-Weighted Imaging Data

Bilal Bayram; Suat Ince; Serhat Kilicarslan; Erkan Veziroglu; Omer Celik; Ishak Pacal

doi:10.31181/jscda41202680

Authors

Bilal Bayram Department of Neurology, University of Health Sciences, Van Education and Research Hospital, 65000 Van, Turkey Author https://orcid.org/0000-0003-1952-2581
Suat Ince Department of Radiology, University of Health Sciences, Van Education and Research Hospital, 65000 Van, Turkey Author https://orcid.org/0009-0002-6873-7984
Serhat Kilicarslan Department of Software Engineering, Faculty of Engineering, Bandirma Onyedi Eylül University, Balıkesir 10010, Türkiye Author https://orcid.org/0000-0001-9483-4425
Erkan Veziroglu Department of Computer Technologies, Simav Vocational School, Kutahya Dumlupinar University, 43500, Simav, Kutahya, Turkey Author https://orcid.org/0000-0002-3358-8467
Omer Celik Department of Healthcare Management, Igdir University, Igdir University, 76002 Igdir, Turkey Author https://orcid.org/0000-0001-9342-5443
Ishak Pacal Department of Computer Engineering, Faculty of Engineering, Igdir University, 76002 Igdir, Turkey Author https://orcid.org/0000-0001-6670-2169

DOI:

https://doi.org/10.31181/jscda41202680

Keywords:

Ischemic stroke detection, Deep learning, YOLOv10, Medical imaging analysis

Abstract

Rapid, accurate detection of acute ischemic stroke (AIS) is vital for patient outcomes. This study evaluates YOLOv10 variants using Diffusion-Weighted Imaging (DWI) data from the ISLES 2022 dataset to identify a model that optimally balances diagnostic accuracy, speed, and computational efficiency for clinical deployment. Methods: YOLOv10 variants were trained on 1652 preprocessed DWI images using transfer learning and data augmentation. Performance was assessed using precision, recall, mAP50, and inference time to evaluate each model comprehensively. Results: The YOLOv10l variant achieved the best performance with 0.933 precision, 0.783 recall, and 0.887 mAP50. YOLOv10n was fastest (0.8 ms) but less accurate, highlighting a trade-off between speed and precision. A key challenge across models was the reliable detection of smaller, less distinct stroke lesions. These findings underscore the importance of balancing accuracy and efficiency. YOLOv10l is optimal for high-precision hospital diagnostics, whereas YOLOv10n suits real-time, resource-limited settings. Future work must focus on improving the detection of small lesions to enhance clinical utility and ensure comprehensive diagnostic support. YOLOv10 is a powerful tool for automated stroke detection, with the YOLOv10l model providing a balanced solution for clinical use. Integrating such models can significantly enhance diagnostic workflows, aid clinical decisions, and ultimately improve patient outcomes in stroke care.

Downloads

Download data is not yet available.

References

Spence, J. D. (2009). Stroke: Atrial fibrillation, stroke prevention therapy and aging. Nature Reviews Cardiology, 6(8), 448–450. https://doi.org/10.1038/nrcardio.2009.98

Langlois, J. A., Rutland-Brown, W., & Wald, M. M. (2006). The epidemiology and impact of traumatic brain injury: A brief overview. Journal of Head Trauma Rehabilitation, 21(5), 375–378. https://doi.org/10.1097/00001199-200609000-00001

He, Q., Wang, Y., Fang, C., Feng, Z., Yin, M., Huang, J., & Ma, Y., Mo, Z. (2024). Advancing stroke therapy: A deep dive into early phase of ischemic stroke and recanalization. CNS Neuroscience & Therapeutics, 30(4), e14634. https://doi.org/10.1111/cns.14634

Feigin, V. L., Barker-Collo, S., Krishnamurthi, R., Theadom, A., & Starkey, N. (2010). Epidemiology of ischaemic stroke and traumatic brain injury. Best Practice & Research Clinical Anaesthesiology, 24(4), 485–494. https://doi.org/10.1016/j.bpa.2010.10.006

Lo, E. H., Dalkara, T., & Moskowitz, M. A. (2003). Mechanisms, challenges and opportunities in stroke. Nature Reviews Neuroscience, 4(5), 399–414. https://doi.org/10.1038/nrn1106

Campbell, B. C. V. (2024). Hyperacute ischemic stroke care—Current treatment and future directions. International Journal of Stroke, 19(7), 718–726. https://doi.org/10.1177/17474930241267353

Majumder, D. (2024). Ischemic stroke: Pathophysiology and evolving treatment approaches. Neuroscience Insights, 19. https://doi.org/10.1177/26331055241292600

Liu, Y., Wen, Z., Wang, Y., Zhong, Y., Wang, J., Hu, Y., Zhou, P., & Guo, S. (2024). Artificial intelligence in ischemic stroke images: Current applications and future directions. Frontiers in Neurology, 15, 1418060. https://doi.org/10.3389/fneur.2024.1418060

Hill, M. D., & Hachinski, V. (1998). Stroke treatment: Time is brain. The Lancet, 352(SIII), 10–14. https://doi.org/10.1016/S0140-6736(98)90088-5

Jiang, B., Pham, N., van Staalduinen, E. K., Liu, Y., Nazari-Farsani, S., Sanaat, A., van Voorst, H., Fettahoglu, A., Kim, D., Ouyang, J., Kumar, A., Srivatsan, A., Hussein, R., Lansberg, M. G., Boada, F., & Zaharchuk, G. (2025). Deep learning applications in imaging of acute ischemic stroke: A systematic review and narrative summary. Radiology, 315(2). https://doi.org/10.1148/radiol.240775

Pacal, I. (2024). MaxCerVixT: A novel lightweight vision transformer-based approach for precise cervical cancer detection. Knowledge-Based Systems, 289, 111482. https://doi.org/10.1016/j.knosys.2024.111482

Ganie, S. M., Pramanik, P. K. D., & Zhao, Z. (2024). Improved liver disease prediction from clinical data through an evaluation of ensemble learning approaches. BMC Medical Informatics and Decision Making, 24(1), 160. https://doi.org/10.1186/s12911-024-02550-y

Ganie, S. M., Malik, M. B., Aadil, M., Muteeb, G., Farhan, M., & Aatif, M. (2025). Explainable AI based hybrid DRM-Net transfer learning model for breast cancer detection and classification using ultrasound images. Scientific Reports, 15(1), 44170. https://doi.org/10.1038/s41598-025-27934-6

Ganie, S. M., & Pramanik, P. K. D. (2025). Interpretable lung cancer risk prediction using ensemble learning and XAI based on lifestyle and demographic data. Computational Biology and Chemistry, 117, 108438. https://doi.org/10.1016/j.compbiolchem.2025.108438

Banerjee, T. (2025). Towards automated and reliable lung cancer detection in histopathological images using DY-FSPAN: A feature-summarized pyramidal attention network for explainable AI. Computational Biology and Chemistry, 118, 108500. https://doi.org/10.1016/j.compbiolchem.2025.108500

Banerjee, T., & Pacal, I. (2026). Towards accurate and interpretable brain tumor diagnosis: T-FSPANNet with tri-attribute and pyramidal attention-based feature fusion. Biomedical Signal Processing and Control, 113, 108852. https://doi.org/10.1016/j.bspc.2025.108852

Pacal, I. (2024). A novel Swin transformer approach utilizing residual multi-layer perceptron for diagnosing brain tumors in MRI images. International Journal of Machine Learning and Cybernetics. Advance online publication. https://doi.org/10.1007/s13042-024-02110-w

Pacal, I. (2025). Chaotic learning rate scheduling for improved CNN-based breast cancer ultrasound classification. Chaos Theory and Applications, 7(1), 297–306. https://doi.org/10.51537/chaos.1807694

Banerjee, T., & Paçal, İ. (2025). A systematic review of machine learning in heart disease prediction. Turkish Journal of Biology, 49(1), 600–634. https://doi.org/10.55730/1300-0152.2766

Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. arXiv. https://arxiv.org/abs/1505.04597

Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., & Han, J., Ding, G. (2024). YOLOv10: Real-time end-to-end object detection. arXiv. https://doi.org/10.48550/arXiv.2405.14458

Redmon, J., Divvala, S., Girshick, A., & Farhadi, R. (2016). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779–788. https://doi.org/10.1109/CVPR.2016.91

Chen, S., Duan, J., Zhang, N., Qi, M., Li, J., Wang, H., Wang, R., Ju, R., Duan, Y., & Qi, S. (2023). MSA-YOLOv5: Multi-scale attention-based YOLOv5 for automatic detection of acute ischemic stroke from multi-modality MRI images. Computers in Biology and Medicine, 165, 107471. https://doi.org/10.1016/j.compbiomed.2023.107471

Elhanashi, A., Dini, P., Saponara, S., & Zheng, Q. (2024). TeleStroke: Real-time stroke detection with federated learning and YOLOv8 on edge devices. Journal of Real-Time Image Processing, 21(3), 70. https://doi.org/10.1007/s11554-024-01500-1

Ince, S., Kunduracioglu, I., Algarni, A., Bayram, B., & Pacal, I. (2025). Deep learning for cerebral vascular occlusion segmentation: A novel ConvNeXtV2 and GRN-integrated U-Net framework for diffusion-weighted imaging. Neuroscience, 574, 42–53. https://doi.org/10.1016/j.neuroscience.2025.04.010

Chen, S., Duan, J., Wang, H., Wang, R., Li, J., Qi, M., Duan, Y., & Qi, S. (2022). Automatic detection of stroke lesion from diffusion-weighted imaging via the improved YOLOv5. Computers in Biology and Medicine, 150, 106120. https://doi.org/10.1016/j.compbiomed.2022.106120

Zhang, K., Zhu, Y., Li, H., Zeng, Z., Liu, Y., & Zhang, Y. (2024). MDANet: Multimodal difference aware network for brain stroke segmentation. Biomedical Signal Processing and Control, 95, 106383. https://doi.org/10.1016/j.bspc.2024.106383

Wu, Z., Zhang, X., Li, F., Wang, S., & Li, J. (2024). A feature-enhanced network for stroke lesion segmentation from brain MRI images. Computers in Biology and Medicine, 174, 108326. https://doi.org/10.1016/j.compbiomed.2024.108326

Li, L., Liu, J., Chen, S., Wang, J., Li, Y., Liao, Q., Zhang, L., Peng, X., & Pu, X. (2025). Segmentation of acute ischemic stroke lesions based on deep feature fusion. Information Fusion, 114, 102724. https://doi.org/10.1016/j.inffus.2024.102724

Kaya, B., & Önal, M. (2023). A CNN transfer learning-based approach for segmentation and classification of brain stroke from noncontrast CT images. International Journal of Imaging Systems and Technology, 33(5), 1335–1352. https://doi.org/10.1002/ima.22864

Chen, Y. F., Chen, Z. J., Lin, Y. Y., Lin, Z. Q., Chen, C. N., Yang, M. L., Zhang, J. Y., Li, Y. Z., Wang, Y., & Huang, Y. H. (2023). Stroke risk study based on deep learning-based magnetic resonance imaging carotid plaque automatic segmentation algorithm. Frontiers in Cardiovascular Medicine, 10, 1101765. https://doi.org/10.3389/fcvm.2023.1101765

Uzun, S., & Okuyar, M. (2024). A new deep learning-based GUI design and implementation for automatic detection of brain strokes with CT images. The European Physical Journal Special Topics. Advance online publication. https://doi.org/10.1140/epjs/s11734-024-01423-9

Sinha, S., Bhatt, M., Anand, A., Areeckal, A. S., & Aparna, V. (2024). EnigmaNet: A novel attention-enhanced segmentation framework for ischemic stroke lesion detection in brain MRI. IEEE Access, 12, 91480–91498. https://doi.org/10.1109/ACCESS.2024.3422025

Li, T., An, X., Di, Y., Gui, C., Yan, Y., Liu, S., & Ming, D. (2024). SrSNet: Accurate segmentation of stroke lesions by a two-stage segmentation framework with asymmetry information. Expert Systems with Applications, 254, 124329. https://doi.org/10.1016/j.eswa.2024.124329

Hernandez Petzsche, M. R., de la Rosa, E., Hanning, U., Wiest, R., Valenzuela, W., Reyes, M., Meyer, M., Liew, S. L., Kofler, F., Ezhov, I., Robben, D., Hutton, A., Friedrich, T., Zarth, T., Bürkle, J., Baran, T. A., Menze, G., Broocks, G., Meyer, L., ... Ikenberg, B., & Wiestler, B., Kirschke, J. S. (2022). ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset. Scientific Data, 9(1), 762. https://doi.org/10.1038/s41597-022-01875-5

Global Burden of Cardiovascular Diseases and Risks 2023 Collaborators. (2025). Global, regional, and national burden of cardiovascular diseases and risk factors in 204 countries and territories, 1990-2023. Journal of the American College of Cardiology, 86(22), 2167-2243. https://doi.org/10.1016/j.jacc.2025.08.015

Zaher, H. F., & Roy, J. K. (2025). Decentralized finance and sustainability analysis of global research patterns and emerging themes. Discover Sustainability. 7, 72. https://doi.org/10.1007/s43621-025-02311-5

Anikó, N., Tarek, A., Arshad, S., Nóra, G., Miklós, N., Mirzaei, M., ... & Mohammed, S. (2025). Real-time monitoring of ammonia emissions from cereal crops using LoRaWAN-based sensing technology. Scientific Reports. 16, 1446. https://doi.org/10.1038/s41598-025-31661-3