Artificial Intelligence in Stroke Imaging: A Review of Current Applications and Limitations

Abstract

Stroke is a major global health burden, requiring time-sensitive diagnosis and treatment to improve patient outcomes. This urgency has created a compelling role for artificial intelligence in the stroke imaging workflow to accelerate diagnosis and treatment. Artificial intelligence has demonstrated a significant impact across multiple aspects of stroke care, including automated detection of acute findings, expedited triage and notification of findings, quantitative assessment of infarcts, predictive prognostication of outcomes, as well as acceleration of image acquisition. However, these advances are accompanied by important limitations including introduction of biases and challenges in the real-world clinical integration of such tools. In this review, we examine the current applications of artificial intelligence in stroke imaging and evaluate the limitations and real-world implementation challenges.

Keywords

stroke - machine learning - artificial intelligence

Publication History

Received: 15 July 2025

Accepted: 14 August 2025

Accepted Manuscript online:
14 August 2025

Article published online:
29 August 2025

• References

• 1 Stroke Facts. Accessed June 14, 2025 at: https://www.cdc.gov/stroke/data-research/facts-stats/index.html
• 2 McDonough R, Ospel J, Goyal M. State of the art stroke imaging: a current perspective. Can Assoc Radiol J 2022; 73 (02) 371-383
• 3 Sarraj A, Pujara DK, Campbell BC. Current state of evidence for neuroimaging paradigms in management of acute ischemic stroke. Ann Neurol 2024; 95 (06) 1017-1034
• 4 Kamalian S, Lev MH. Stroke imaging. Radiol Clin North Am 2019; 57 (04) 717-732
• 5 Oliveira-Filho J, Lansberg M. Neuroimaging of acute stroke. In: UpToDate; 2025. Accessed June 26, 2025 at: https://www.uptodate.com/contents/neuroimaging-of-acute-stroke
• 6 Czap AL, Sheth SA. Overview of imaging modalities in stroke. Neurology 2021; 97 (20, Suppl 2): S42-S51
• 7 Oliveira-Filho J, Samuels O. Approach to reperfusion therapy for acute ischemic stroke. In: UpToDate; 2025. Accessed June 26, 2025 at: https://www.uptodate.com/contents/approach-to-reperfusion-therapy-for-acute-ischemic-stroke
• 8 Black JE, Kueper JK, Williamson TS. An introduction to machine learning for classification and prediction. Fam Pract 2023; 40 (01) 200-204
• 9 Azad R, Aghdam EK, Rauland A. et al. Medical image segmentation review: the success of U-Net. IEEE Trans Pattern Anal Mach Intell 2024; 46 (12) 10076-10095
• 10 Flanders AE, Prevedello LM, Shih G. et al; RSNA-ASNR 2019 Brain Hemorrhage CT Annotators. Construction of a machine learning dataset through collaboration: the RSNA 2019 Brain CT Hemorrhage Challenge. Radiol Artif Intell 2020; 2 (03) e190211
• 11 Song C, Zhao Q, Li J. et al. HemSeg-200: A voxel-annotated dataset for intracerebral hemorrhages segmentation in brain CT scans. arXiv. Preprint . (e-pub ahead of print).
• 12 Wu B, Xie Y, Zhang Z. et al. BHSD: A 3D multi-class brain hemorrhage segmentation dataset. arXiv. Preprint . (e-pub ahead of print).
• 13 Hssayeni MD, Croock MS, Al-Ani A, Al-khafaji HF, Yahya ZA, Ghoraani B. Intracranial hemorrhage segmentation using deep convolutional model. arXiv. Preprint . Published October 18, 2019.
• 14 Hernandez Petzsche MR, de la Rosa E, Hanning U. et al. ISLES 2022: a multi-center magnetic resonance imaging stroke lesion segmentation dataset. Sci Data 2022; 9 (01) 762
• 15 Liew SL, Lo BP, Donnelly MR. et al. A large, curated, open-source stroke neuroimaging dataset to improve lesion segmentation algorithms. Sci Data 2022; 9 (01) 320
• 16 Trang A, Putman K, Savani D. et al. Sociodemographic biases in a commercial AI model for intracranial hemorrhage detection. Emerg Radiol 2024; 31 (05) 713-723
• 17 Bachina P, Garin SP, Kulkarni P. et al. Coarse race and ethnicity labels mask granular underdiagnosis disparities in deep learning models for chest radiograph diagnosis. Radiology 2023; 309 (02) e231693
• 18 Kamel PI, Yi PH, Sair HI, Lin CT. Prediction of coronary artery calcium and cardiovascular risk on chest radiographs using deep learning. Radiol Cardiothorac Imaging 2021; 3 (03) e200486
• 19 Yi PH, Malone PS, Lin CT, Filice RW. Deep learning algorithms for interpretation of upper extremity radiographs: laterality and technologist initial labels as confounding factors. AJR Am J Roentgenol 2022; 218 (04) 714-715
• 20 510(k) AVICENNA.AI's CINA. U.S. Food & Drug Administration. Accessed June 26, 2025 at: https://www.accessdata.fda.gov/cdrh_docs/pdf20/K200855.pdf#:~:text=CINA%20is%20a%20radiological%20computer,2%29%20LVO
• 21 510(k) MaxQ AI's AccipioIx. U.S. Food & Drug Administration. Accessed June 26, 2025 at: https://www.accessdata.fda.gov/cdrh_docs/pdf20/K201310.pdf#:~:text=suspected%20findings.%20It%20makes%20case,hemorrhage%20or%20otherwise%20preclude%20clinical
• 22 Karamian A, Seifi A. Diagnostic accuracy of deep learning for intracranial hemorrhage detection in non-contrast brain CT scans: a systematic review and meta-analysis. J Clin Med 2025; 14 (07) 2377
• 23 Yun TJ, Choi JW, Han M. et al. Deep learning based automatic detection algorithm for acute intracranial haemorrhage: a pivotal randomized clinical trial. NPJ Digit Med 2023; 6 (01) 61
• 24 Kau T, Ziurlys M, Taschwer M, Kloss-Brandstätter A, Grabner G, Deutschmann H. FDA-approved deep learning software application versus radiologists with different levels of expertise: detection of intracranial hemorrhage in a retrospective single-center study. Neuroradiology 2022; 64 (05) 981-990
• 25 Savage CH, Tanwar M, Elkassem AA. et al. Prospective evaluation of artificial intelligence triage of intracranial hemorrhage on noncontrast head CT examinations. AJR Am J Roentgenol 2024; 223 (05) e2431639
• 26 Del Gaizo AJ, Osborne TF, Shahoumian T, Sherrier R. Deep learning to detect intracranial hemorrhage in a national teleradiology program and the impact on interpretation time. Radiol Artif Intell 2024; 6 (05) e240067
• 27 Zhang K, Khosravi B, Vahdati S, Erickson BJ. FDA review of radiologic AI algorithms: process and challenges. Radiology 2024; 310 (01) e230242
• 28 Evaluation of Automatic Class III Designation for ContaCT. Accessed June 26, 2025 at: https://www.accessdata.fda.gov/cdrh_docs/reviews/DEN170073.pdf
• 29 Hassan AE, Ringheanu VM, Rabah RR, Preston L, Tekle WG, Qureshi AI. Early experience utilizing artificial intelligence shows significant reduction in transfer times and length of stay in a hub and spoke model. Interv Neuroradiol 2020; 26 (05) 615-622
• 30 Adhya J, Li C, Eisenmenger L. et al. Positive predictive value and stroke workflow outcomes using automated vessel density (RAPID-CTA) in stroke patients: one year experience. Neuroradiol J 2021; 34 (05) 476-481
• 31 Morey JR, Zhang X, Yaeger KA. et al. Real-world experience with artificial intelligence-based triage in transferred large vessel occlusion stroke patients. Cerebrovasc Dis 2021; 50 (04) 450-455
• 32 Mannix N, Penhos E, Nimjee S. et al. Real world experience with Viz.ai automated large vessel occlusion in CT angiogram (P8–5.010). Neurology 2023; 100 (17, suppl_2)
• 33 Rodrigues G, Barreira CM, Bouslama M. et al. Automated large artery occlusion detection in stroke: a single-center validation study of an artificial intelligence algorithm. Cerebrovasc Dis 2022; 51 (02) 259-264
• 34 Slater L, Ravintharan N, Goergen S. et al. RapidAI compared with human readers of acute stroke imaging for detection of intracranial vessel occlusion. Stroke Vasc Intervent Neurol 2024; 4 (02)
• 35 Barber PA, Demchuk AM, Zhang J, Buchan AM. Validity and reliability of a quantitative computed tomography score in predicting outcome of hyperacute stroke before thrombolytic therapy. ASPECTS Study Group. Alberta Stroke Programme Early CT Score. Lancet 2000; 355 (9216): 1670-1674
• 36 Chiang PL, Lin SY, Chen MH. et al. Deep learning-based automatic detection of ASPECTS in acute ischemic stroke: improving stroke assessment on CT scans. J Clin Med 2022; 11 (17) 5159
• 37 Adamou A, Beltsios ET, Bania A. et al. Artificial intelligence-driven ASPECTS for the detection of early stroke changes in non-contrast CT: a systematic review and meta-analysis. J Neurointerv Surg 2023; 15 (e2): e298-e304
• 38 Li X, Zhen Y, Liu H. et al. Automated ASPECTS in acute ischemic stroke: comparison of the overall scores and Hounsfield unit values of two software packages and radiologists with different levels of experience. Acta Radiol 2023; 64 (01) 328-335
• 39 Río Bártulos C, Pirl L, Lier D. et al. Performance evaluation of two different software programs for automated ASPECTS scoring in patients with suspected stroke. Clin Hemorheol Microcirc 2024; 86 (1–2): 109-119
• 40 Kamel P, Kanhere A, Kulkarni P. et al. Optimizing acute stroke segmentation on MRI using deep learning: self-configuring neural networks provide high performance using only DWI sequences. J Imaging Inform Med 2025; 38 (02) 717-726
• 41 Woo I, Lee A, Jung SC. et al. Fully automatic segmentation of acute ischemic lesions on diffusion-weighted imaging using convolutional neural networks: comparison with conventional algorithms. Korean J Radiol 2019; 20 (08) 1275-1284
• 42 Chen L, Bentley P, Rueckert D. Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks. Neuroimage Clin 2017; 15: 633-643
• 43 Liu CF, Hsu J, Xu X. et al; STIR and VISTA Imaging investigators. Deep learning-based detection and segmentation of diffusion abnormalities in acute ischemic stroke. Commun Med (Lond) 2021; 1: 61
• 44 Wong KK, Cummock JS, Li G. et al. Automatic segmentation in acute ischemic stroke: prognostic significance of topological stroke volumes on stroke outcome. Stroke 2022; 53 (09) 2896-2905
• 45 Olivier A, Moal O, Moal B. et al. Active learning strategy and hybrid training for infarct segmentation on diffusion MRI with a U-shaped network. J Med Imaging (Bellingham) 2019; 6 (04) 044001
• 46 Cui L, Fan Z, Yang Y. et al. Deep learning in ischemic stroke imaging analysis: a comprehensive review. BioMed Res Int 2022; 2022: 2456550
• 47 Kamel P, Khalid M, Steger R. et al. Dual energy CT for deep learning-based segmentation and volumetric estimation of early ischemic infarcts. J Imaging Inform Med 2025; 38 (03) 1484-1495
• 48 Gauriau R, Bizzo BC, Comeau DS. et al. Head CT deep learning model is highly accurate for early infarct estimation. Sci Rep 2023; 13 (01) 189
• 49 Alwood BT, Meyer DM, Ionita C. et al. Multicenter comparison using two AI stroke CT perfusion software packages for determining thrombectomy eligibility. J Stroke Cerebrovasc Dis 2024; 33 (07) 107750
• 50 Kuang H, Qiu W, Boers AM. et al. Computed tomography perfusion-based machine learning model better predicts follow-up infarction in patients with acute ischemic stroke. Stroke 2021; 52 (01) 223-231
• 51 Werdiger F, Parsons MW, Visser M. et al. Machine learning segmentation of core and penumbra from acute stroke CT perfusion data. Front Neurol 2023; 14: 1098562
• 52 Qiu W, Kuang H, Ospel JM. et al. Automated prediction of ischemic brain tissue fate from multiphase computed tomographic angiography in patients with acute ischemic stroke using machine learning. J Stroke 2021; 23 (02) 234-243
• 53 Bushnaq S, Hassan AE, Delora A. et al. A comparison of CT perfusion output of RapidAI and Viz.ai software in the evaluation of acute ischemic stroke. AJNR Am J Neuroradiol 2024; 45 (07) 863-870
• 54 Caliandro P, Lenkowicz J, Reale G. et al. Artificial intelligence to predict individualized outcome of acute ischemic stroke patients: the SIBILLA project. Eur Stroke J 2024; 9 (04) 1053-1062
• 55 Kuang Y, Zhang L, Ye K, Jiang Z, Shi C, Luo L. Clinical and imaging predictors for hemorrhagic transformation of acute ischemic stroke after endovascular thrombectomy. J Neuroimaging 2024; 34 (03) 339-347
• 56 Dagher R, Ozkara BB, Karabacak M. et al. Artificial intelligence/machine learning for neuroimaging to predict hemorrhagic transformation: systematic review/meta-analysis. J Neuroimaging 2024; 34 (05) 505-514
• 57 Cao L, Ma X, Huang W. et al. An explainable artificial intelligence model to predict malignant cerebral edema after acute anterior circulating large-hemisphere infarction. Eur Neurol 2024; 87 (02) 54-66
• 58 Yang Y, Tang L, Deng Y. et al. The predictive performance of artificial intelligence on the outcome of stroke: a systematic review and meta-analysis. Front Neurosci 2023; 17: 1256592
• 59 Lee J, Park KM, Park S. Interpretable machine learning for prediction of clinical outcomes in acute ischemic stroke. Front Neurol 2023; 14: 1234046
• 60 Kim DY, Choi KH, Kim JH. et al. Deep learning-based personalised outcome prediction after acute ischaemic stroke. J Neurol Neurosurg Psychiatry 2023; 94 (05) 369-378
• 61 Adams Jr HP, Bendixen BH, Kappelle LJ. et al. Classification of subtype of acute ischemic stroke. Definitions for use in a multicenter clinical trial. TOAST. Trial of Org 10172 in Acute Stroke Treatment. Stroke 1993; 24 (01) 35-41
• 62 Chen S, Yang X, Gu H. et al. Predictive etiological classification of acute ischemic stroke through interpretable machine learning algorithms: a multicenter, prospective cohort study. BMC Med Res Methodol 2024; 24 (01) 199
• 63 Garg R, Oh E, Naidech A, Kording K, Prabhakaran S. Automating ischemic stroke subtype classification using machine learning and natural language processing. J Stroke Cerebrovasc Dis 2019; 28 (07) 2045-2051
• 64 Turner A, Spurlock W, Harrington L. et al. A machine learning approach to automate ischemic stroke subtyping (N2.001). Neurology 2022; 98 (18, supplement)
• 65 Wu O, Winzeck S, Giese AK. et al. Big data approaches to phenotyping acute ischemic stroke using automated lesion segmentation of multi-center magnetic resonance imaging data. Stroke 2019; 50 (07) 1734-1741
• 66 Jiang J, Wei J, Zhu Y. et al. Clot-based radiomics model for cardioembolic stroke prediction with CT imaging before recanalization: a multicenter study. Eur Radiol 2023; 33 (02) 970-980
• 67 Lucero-Garófano Á, Aliena-Valero A, Vielba-Gómez I. et al. Automatic etiological classification of stroke thrombus digital photographs using a deep learning model. Front Neurol 2025; 16: 1534845
• 68 Pisu F, Williamson BJ, Nardi V. et al. Machine learning detects symptomatic plaques in patients with carotid atherosclerosis on CT angiography. Circ Cardiovasc Imaging 2024; 17 (06) e016274
• 69 Deshmane A, Gulani V, Griswold MA, Seiberlich N. Parallel MR imaging. J Magn Reson Imaging 2012; 36 (01) 55-72
• 70 Lustig M, Donoho D, Pauly JM. Sparse MRI: the application of compressed sensing for rapid MR imaging. Magn Reson Med 2007; 58 (06) 1182-1195
• 71 Heckel R, Jacob M, Chaudhari A, Perlman O, Shimron E. Deep learning for accelerated and robust MRI reconstruction. Magn Reson Mater Biol Phys Med 2024; 37 (03) 335-368
• 72 Goodfellow IJ, Pouget-Abadie J, Mirza M. et al. Generative adversarial networks. arXiv. Preprint . (e-pub ahead of print).
• 73 Yang G, Yu S, Dong H. et al. DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE Trans Med Imaging 2018; 37 (06) 1310-1321
• 74 Koetzier LR, Mastrodicasa D, Szczykutowicz TP. et al. Deep learning image reconstruction for CT: technical principles and clinical prospects. Radiology 2023; 306 (03) e221257
• 75 Yang A, Finkelstein M, Koo C, Doshi AH. Impact of deep learning image reconstruction methods on MRI throughput. Radiol Artif Intell 2024; 6 (03) e230181
• 76 Melazzini L, Bortolotto C, Brizzi L. et al. AI for image quality and patient safety in CT and MRI. Eur Radiol Exp 2025; 9 (01) 28
• 77 Haller S. AI-accelerated MRI for acute stroke: faster acquisitions, faster diagnoses. Radiology 2024; 310 (02) e240099
• 78 Altmann S, Grauhan NF, Brockstedt L. et al. Ultrafast brain MRI with deep learning reconstruction for suspected acute ischemic stroke. Radiology 2024; 310 (02) e231938
• 79 Chen RJ, Wang JJ, Williamson DFK. et al. Algorithmic fairness in artificial intelligence for medicine and healthcare. Nat Biomed Eng 2023; 7 (06) 719-742
• 80 Seyyed-Kalantari L, Zhang H, McDermott MBA, Chen IY, Ghassemi M. Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations. Nat Med 2021; 27 (12) 2176-2182
• 81 Varoquaux G, Cheplygina V. Machine learning for medical imaging: methodological failures and recommendations for the future. NPJ Digit Med 2022; 5 (01) 48