Artificial intelligence capabilities for automated diagnosis and prediction of acute stroke outcomes based on magnetic resonance imaging

Acute stroke is one of the leading causes of death and disability worldwide. Millions of people experience this disease every year, with significant consequences for both patients and health systems. Diagnosis and treatment of stroke require fast and accurate decision-making, as time is a critical factor for a successful outcome. However, existing diagnostic methods such as magnetic resonance imaging, although they provide high imaging accuracy, require significant time and human resources. This creates the need to develop new approaches that can improve the effectiveness of diagnosis and prediction of stroke outcomes.

Artificial intelligence is actively developing and finding applications in various fields of medicine, including medical image analysis. The use of artificial intelligence to process MRI data opens up new possibilities for automated diagnosis and prediction of disease outcomes such as stroke. This improves diagnostic accuracy and reduces data analysis time, which is especially important in emergency situations. 

1. Isakova EV, Ryabtseva AA, Kotov SV. The state of the microcirculatory system in patients with ischemic stroke. Russian Medical Journal. 2015;12:680–682. (In Russ.)

2. Gusev EI. Neurology. National guide. Vol. 1. Moscow: GEOTAR-Media; 2018. 299 p. (In Russ.)

3. Yoshimura S, Sakai N, Yamagami H, et al. Endovascular therapy for acute stroke with a large ischemic region. N Engl J Med. 2022;386(14):1303–1313. https://doi.org/10.1056/NEJMoa2118191

4. Regenhardt R, Bretzner M, Zanon Zotin C, et al. Radiomic signature of DWI-FLAIR mismatch in large vessel occlusion stroke. Neuroimaging. 2022;32(1):63–67. https://doi.org/10.1111/jon.12928

5. Fokin VA. Yanishevskij SN, Trufanov AG. Magnetic resonance imaging in the diagnosis of ischemic stroke: a textbook. Voenno-medicinskaya akademiya im. S. M. Kirova. Saint Petersburg: ELBI-SPb; 2012. 96 p. (In Russ.)

6. Jiang B, Pham N, van Staalduinen EK. Deep learning applications in imaging of acute ischemic stroke: a systematic review and narrative summary. Radiology. 2025; 315(1):е240775. https://doi.org/10.1148/radiol.240775

7. Clinical protocol «Reperfusion therapy of ischemic stroke». Society for Evidence Neurology; 2019 [cited 2025 Mar 18]. Available from: https://evidence-neurology.ru/evidentiary-medicine/protokoli/protokol-reperfuzionnoi-terapi/

8. Alaya IB, Limam H, Kraiem T. Applications of artificial intelligence for DWI and PWI data processing in acute ischemic stroke: Current practices and future directions. Clin Imaging. 2022;81:79–86. https://doi.org/10.1016/j.clinimag.2021.09.015

9. Prokhorikhin AA, Baistrukov VI, Boikov AA, et al. Comparative study of a system of contrast-free CT diagnostics of acute ischemic stroke based on deep learning neural networks. Russian electronic journal of radiology. 2020;10(3):36–45. (In Russ.) https://doi.org/10.21569/2222-7415-2020-10-3-36-45

10. Yalçın S, Vural H. Brain stroke classification and segmentation using encoder-decoder based deep convolutional neural networks. Comput Biol Med. 2022;149:105941. https://doi.org/10.1016/j.compbiomed.2022.105941

11. Dasari Y, Duffin J, Sayin ES, et al. Convolutional neural networks to assess steno-occlusive disease using cerebrovascular reactivity. Healthcare. 2023;11(16):2231. https://doi.org/10.3390/healthcare11162231

12. Lai YL, Wu YD, Yeh HJ, et al. Using convolutional neural network to analyze brain MRI images for predicting functional outcomes of stroke. Med Biol Eng Comput. 2022;60(10):2841–2849. https://doi.org/10.1007/s11517-022-02636-7

13. Herzog L, Murina E, Dürr O, et al. Integrating uncertainty in deep neural networks for MRI based stroke analysis. Med Image Anal. 2020;65:101790. https://doi.org/10.1016/j.media.2020.101790

14. Adlung A, Paschke NK, Golla AK, et al. 23 Na MRI in ischemic stroke: Acquisition time reduction using postprocessing with convolutional neural networks. NMR Biomed. 2021;34(4):4474. https://doi.org/10.1002/nbm.4474

15. Rava RA, Podgorsak AR, Waqas M, et al. Investigation of convolutional neural networks using multiple computed tomography perfusion maps to identify infarct core in acute ischemic stroke patients. J Med Imaging. 2021;8(1):014505. https://doi.org/10.1117/1.JMI.8.1.014505

16. Choo YJ, Chang MC. Use of Machine Learning in Stroke Rehabilitation: A Narrative Review. Brain Neurorehabil. 2022;15(3):26. https://doi.org/10.12786/bn.2022.15.e26

17. Murat F, Sadak F, Yildirim O, et al. Review of deep learning-based atrial fibrillation detection studies. Int. J. Environ Res Public Health. 2021;18(21):11302. https://doi.org/10.3390/ijerph182111302

18. Gheibi Y, Shirini K, Razavi SN, et al. CNN-Res: deep learning framework for segmentation of acute ischemic stroke lesions on multimodal MRI images. BMC Med Inform Decis Mak. 2023;23(1):192. https://doi.org/10.1186/s12911-023-02289-y

19. Debs N, Cho TH, Rousseau D, et al. Impact of the reperfusion status for predicting the final stroke infarct using deep learning. Neuroimage Clin. 2021;29:102548. https://doi.org/10.1016/j.nicl.2020.102548

20. Lekoubou A, Ba DM, Nguyen C, et al. Poststroke Seizures and the Risk of Dementia Among Young Stroke Survivors. Neurology. 2022;99(4):385–392. https://doi.org/10.1212/wnl.0000000000200736

21. Galovic M, Ferreira-Atuesta C, Abraira L, et al. Seizures and Epilepsy After Stroke: Epidemiology, Biomarkers and Management. Drugs Aging. 2021;38(4):285– 299. https://doi.org/10.1007/s40266-021-00837-7

22. Moon HS, Heffron L, Mahzarnia A, et al. Automated multimodal segmentation of acute ischemic stroke lesions on clinical MR images. Magn. Reson. Imaging. 2022;92:45–57. https://doi.org/10.1016/j.mri.2022.06.001

23. Luciw NJ, Shirzadi Z, Black SE, et al. Automated generation of cerebral blood flow and arterial transit time maps from multiple delay arterial spin-labeled MRI. Magn. Reson. Med. 2022;88(1):406–417. https://doi.org/10.1002/mrm.29193

24. Li X, Zhao Y, Jiang J, et al. White matter hyperintensities segmentation using an ensemble of neural networks. Hum Brain Mapp. 2022;43(3):929–939. https://doi.org/10.1002/hbm.25695

25. Figurelle ME, Meyer DM, Perrinez ES, et al. Implementation of stroke augmented intelligence and communications platform to improve indicators and outcomes for a comprehensive stroke center and network. AJNR Am J Neuroradiol. 2023;44(1):47–53.