Share：
Share this content in WeChat
X
[Chinese] [PDF] 9 1
• Review •
Advances in artificial intelligence for MRI of carotid artery vulnerable plaques​
ZHOU Jinglin  LU Jie 

DOI:10.12015/issn.1674-8034.2026.01.028.


[Abstract] Ischemic stroke has high incidence, high disability rate, and high mortality rate. Globally, approximately 18% to 30% of ischemic stroke events are attributable to thromboembolism caused by ruptured carotid vulnerable plaques. However, the precise identification of carotid vulnerable plaques in current clinical practice faces significant challenges, as traditional imaging techniques have limitations in insufficient sensitivity. Multi-parameter magnetic resonance imaging (MRI), with its high soft-tissue contrast, serves as the gold standard for assessing plaque vulnerability, yet manual analysis has limitations such as large inter-observer differences and insufficient characterization of feature correlations. This article reviews research advances in artificial intelligence (AI) technology for MRI evaluation of carotid vulnerable plaques from the following aspects: innovations in automated plaque segmentation and quantitative analysis algorithms, deep learning-based predictive models for vulnerability biomarkers, and intelligent methods for clinical outcome assessment and treatment response prediction. The limitations of the current research are clarified, and potential directions for future investigations are proposed. This study deeply integrates the potential of AI technologies to accelerate their clinical translation in the identification of carotid vulnerable plaques, thereby enhancing the detection efficiency of vulnerable plaques and facilitating the early prevention and treatment of ischemic stroke.
[Keywords] cerebrovascular disease；ischemic stroke；vulnerable carotid artery plaque；artificial intelligence；magnetic resonance imaging；deep learning

ZHOU Jinglin1, 2   LU Jie1, 2*  

1 Department of Radiology and Nuclear Medicine, Xuanwu Hospital Capital Medical University, Beijing 100053, China

2 Beijing Key Lab of MRI and Brain Informatics, Beijing 100053, China

Corresponding author: LU J, E-mail: imaginglu@hotmail.com

Conflicts of interest   None.

Received  2025-06-23
Accepted  2025-12-23
DOI: 10.12015/issn.1674-8034.2026.01.028
DOI:10.12015/issn.1674-8034.2026.01.028.

[1]
PU L Y, WANG L, ZHANG R J, et al. Projected global trends in ischemic stroke incidence, deaths and disability-adjusted life years from 2020 to 2030[J]. Stroke, 2023, 54(5): 1330-1339. DOI: 10.1161/STROKEAHA.122.040073.
[2]
ZHANG Y, LU J. Research progresses in evaluating the stability of carotid atherosclerotic plaque with positron emission tomography/computed tomography[J]. J Cap Med Univ, 2021, 42(1): 31-36. DOI: 10.3969/j.issn.1006-7795.2021.01.006.
[3]
SABA L, NARDI V, CAU R, et al. Carotid artery plaque calcifications: lessons from histopathology to diagnostic imaging[J]. Stroke, 2022, 53(1): 290-297. DOI: 10.1161/STROKEAHA.121.035692.
[4]
ZHENG W Q, WEI H, BAI F, et al. Stroke mechanism subtypes and prognosis in patients with symptomatic intracranial atherosclerosis based on multiparametric MRI[J]. J Magn Reson Imaging, 2025, 62(3): 917-927. DOI: 10.1002/jmri.29813.
[5]
JAIN P K, DUBEY A, SABA L, et al. Attention-based UNet deep learning model for plaque segmentation in carotid ultrasound for stroke risk stratification: an artificial intelligence paradigm[J/OL]. J Cardiovasc Dev Dis, 2022, 9(10): 326 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/36286278/. DOI: 10.3390/jcdd9100326.
[6]
KOPALLI S R, SHUKLA M, JAYAPRAKASH B, et al. Artificial intelligence in stroke rehabilitation: From acute care to long-term recovery[J/OL]. Neuroscience, 2025, 572: 214-231 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/40068721/. DOI: 10.1016/j.neuroscience.2025.03.017.
[7]
LUO Y, GAO K, ZHOU Y, et al. Differentiating calcifications from cerebral microbleeds using quantitative susceptibility mapping[J]. Eur Radiol, 2025, 35(4): 2043-2052. DOI: 10.1007/s00330-024-10889-z.
[8]
LIU Y S, HUI P J. Progress of radiomics combined with artificial intelligence in the diagnosis of carotid atherosclerotic plaque and ischemic stroke[J]. Int J Med Radiol, 2024, 47(2): 154-159. DOI: 10.19300/j.2024.Z21097.
[9]
HUANG L X, WU X B, LIU Y A, et al. High-resolution magnetic resonance vessel wall imaging in ischemic stroke and carotid artery atherosclerotic stenosis: a review[J/OL]. Heliyon, 2024, 10(7): e27948 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/38571643/. DOI: 10.1016/j.heliyon.2024.e27948.
[10]
ZHANG R Y, ZHANG Q W, JI A H, et al. Identification of high-risk carotid plaque with MRI-based radiomics and machine learning[J]. Eur Radiol, 2021, 31(5): 3116-3126. DOI: 10.1007/s00330-020-07361-z.
[11]
SCICOLONE R, VACCA S, PISU F, et al. Radiomics and artificial intelligence: General notions and applications in the carotid vulnerable plaque[J/OL]. Eur J Radiol, 2024, 176: 111497 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/38749095/. DOI: 10.1016/j.ejrad.2024.111497.
[12]
AYOUB M, LIAO Z F, LI L F, et al. HViT: Hybrid vision inspired transformer for the assessment of carotid artery plaque by addressing the cross-modality domain adaptation problem in MRI[J/OL]. Comput Med Imaging Graph, 2023, 109: 102295 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/37717365/. DOI: 10.1016/j.compmedimag.2023.102295.
[13]
LIN G H, SONG J X, HUANG T D, et al. Relationship between the stroke mechanism of symptomatic middle cerebral artery atherosclerotic diseases and culprit plaques based on high-resolution vessel wall imaging[J/OL]. Front Neurol, 2022, 13: 968417 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/36188409/. DOI: 10.3389/fneur.2022.968417.
[14]
YANG R W, YUAN J, CHEN X E, et al. Vessel wall magnetic resonance imaging of symptomatic middle cerebral artery atherosclerosis: a systematic review and meta-analysis[J/OL]. Clin Imaging, 2022, 90: 90-96 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/35952437/. DOI: 10.1016/j.clinimag.2022.08.001.
[15]
ZHU C L, WANG X Y, TENG Z Z, et al. Cascaded residual U-Net for fully automatic segmentation of 3D carotid artery in high-resolution multi-contrast MR images[J/OL]. Phys Med Biol, 2021, 66(4): 045033 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/33333499/. DOI: 10.1088/1361-6560/abd4bb.
[16]
XU W J, YANG X, LI Y K, et al. Deep learning-based automated detection of arterial vessel wall and plaque on magnetic resonance vessel wall images[J/OL]. Front Neurosci, 2022, 16: 888814 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/35720719/. DOI: 10.3389/fnins.2022.888814.
[17]
LI R, ZHENG J, ZAYED M A, et al. Carotid atherosclerotic plaque segmentation in multi-weighted MRI using a two-stage neural network: advantages of training with high-resolution imaging and histology[J/OL]. Front Cardiovasc Med, 2023, 10: 1127653 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/37293278/. DOI: 10.3389/fcvm.2023.1127653.
[18]
WANG J, YU F, ZHANG M Z, et al. A 3D framework for segmentation of carotid artery vessel wall and identification of plaque compositions in multi-sequence MR images[J/OL]. Comput Med Imag Graph, 2024, 116: 102402 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/38810486/. DOI: 10.1016/j.compmedimag.2024.102402.
[19]
VAN ENGELEN A, VAN DIJK A C, TRUIJMAN M T B, et al. Multi-center MRI carotid plaque component segmentation using feature normalization and transfer learning[J]. IEEE Trans Med Imag, 2015, 34(6): 1294-1305. DOI: 10.1109/TMI.2014.2384733.
[20]
TAO X T, SHEN S, YANG L, et al. Clinically oriented deep learning framework for automated vessel wall segmentation in black-blood MRI: a multi-center study[J/OL]. Eur Radiol, 2025 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/41273425/. DOI: 10.1007/s00330-025-12161-4.
[21]
FU Y H, LIU J F, SHI J. TSCA-Net: Transformer based spatial-channel attention segmentation network for medical images[J/OL]. Comput Biol Med, 2024, 170: 107938 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/38219644/. DOI: 10.1016/j.compbiomed.2024.107938.
[22]
FERREIRA A, LI J N, POMYKALA K L, et al. GAN-based generation of realistic 3D volumetric data: a systematic review and taxonomy[J/OL]. Med Image Anal, 2024, 93: 103100 [2025-06-22] https://pubmed.ncbi.nlm.nih.gov/38340545/.. DOI: 10.1016/j.media.2024.103100.
[23]
SAEED M U, BIN W, SHENG J F, et al. MSFF: an automated multi-scale feature fusion deep learning model for spine fracture segmentation using MRI[J/OL]. Biomed Signal Process Control, 2024, 91: 105943 [2025-06-22]. https://linkinghub.elsevier.com/retrieve/pii/S1746809424000016. DOI: 10.1016/j.bspc.2024.105943.
[24]
LIN M Q, CUI H, CHEN W F, et al. Longitudinal assessment of carotid plaque texture in three-dimensional ultrasound images based on semi-supervised graph-based dimensionality reduction and feature selection[J/OL]. Comput Biol Med, 2020, 116: 103586 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/32425160/. DOI: 10.1016/j.compbiomed.2019.103586.
[25]
BLASER M C, BUFFOLO F, HALU A, et al. Multiomics of tissue extracellular vesicles identifies unique modulators of atherosclerosis and calcific aortic valve stenosis[J]. Circulation, 2023, 148(8): 661-678. DOI: 10.1161/CIRCULATIONAHA.122.063402.
[26]
GAO Y, LI Z A, ZHAI X Y, et al. MRI-based habitat radiomics combined with vision transformer for identifying vulnerable intracranial atherosclerotic plaques and predicting stroke events: a multicenter, retrospective study[J/OL]. EClinicalMedicine, 2025, 82: 103186 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/40235946/. DOI: 10.1016/j.eclinm.2025.103186.
[27]
GUO Y, AKCICEK E Y, HIPPE D S, et al. Long-term carotid plaque progression and the role of intraplaque hemorrhage: a deep learning-based analysis of longitudinal vessel wall imaging[J/OL]. medRxiv, 2025 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/39711698/. DOI: 10.1101/2024.12.09.24318661.
[28]
E Y M, YAO Z C, GE M L, et al. Development and validation of a machine learning model for predicting vulnerable carotid plaques using routine blood biomarkers and derived indicators: insights into sex-related risk patterns[J/OL]. Cardiovasc Diabetol, 2025, 24(1): 326 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/40784899/. DOI: 10.1186/s12933-025-02867-6.
[29]
SKANDHA S S, NICOLAIDES A, GUPTA S K, et al. A hybrid deep learning paradigm for carotid plaque tissue characterization and its validation in multicenter cohorts using a supercomputer framework[J/OL]. Comput Biol Med, 2022, 141: 105131 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/34922173/. DOI: 10.1016/j.compbiomed.2021.105131.
[30]
YAO W H, CHEN H B, HUANG K M, et al. Atherosclerotic plaque evolution predicts cerebral ischemic events in patients with intracranial atherosclerosis: a multicentre longitudinal study using high-resolution MRI[J]. Eur Radiol, 2025, 35(6): 3238-3248. DOI: 10.1007/s00330-024-11248-8.
[31]
PAKIZER D, KOZEL J, ELMERS J, et al. Diagnostics accuracy of magnetic resonance imaging in detection of atherosclerotic plaque characteristics in carotid arteries compared to histology: a systematic review[J]. J Magn Reson Imaging, 2025, 61(3): 1067-1093. DOI: 10.1002/jmri.29522.
[32]
GUI C Z, CAO C, ZHANG X, et al. Radiomics and artificial neural networks modelling for identification of high-risk carotid plaques[J/OL]. Front Cardiovasc Med, 2023, 10: 1173769 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/37485276/. DOI: 10.3389/fcvm.2023.1173769.
[33]
DIMITRIADIS K, PYRPYRIS N, THEOFILIS P, et al. Computed tomography angiography identified high-risk coronary plaques: from diagnosis to prognosis and future management[J/OL]. Diagnostics, 2024, 14(15): 1671 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/39125547/. DOI: 10.3390/diagnostics14151671.
[34]
JAMTHIKAR A D, GUPTA D, MANTELLA L E, et al. Multiclass machine learning vs. conventional calculators for stroke/CVD risk assessment using carotid plaque predictors with coronary angiography scores as gold standard: a 500 participants study[J]. Int J Cardiovasc Imaging, 2021, 37(4): 1171-1187. DOI: 10.1007/s10554-020-02099-7.
[35]
SUN X H, WU C Q, KANG J P, et al. Development and validation of a risk prediction model for short-term progression of carotid atherosclerosis among early middle age adults[J/OL]. Atherosclerosis, 2024, 397: 118557 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/39180959/. DOI: 10.1016/j.atherosclerosis.2024.118557.
[36]
HAN N, MA Y R, LI Y, et al. Imaging and hemodynamic characteristics of vulnerable carotid plaques and artificial intelligence applications in plaque classification and segmentation[J/OL]. Brain Sci, 2023, 13(1): 143 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/36672124/. DOI: 10.3390/brainsci13010143.
[37]
HE L, YANG Z K, WANG Y D, et al. A deep learning algorithm to identify carotid plaques and assess their stability[J/OL]. Front Artif Intell, 2024, 7: 1321884 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/38952409/. DOI: 10.3389/frai.2024.1321884.
[38]
STEINMETZ E, COTTENET J, MARIET A S, et al. Editor's choice–stroke and death following carotid endarterectomy or carotid artery stenting: a ten year nationwide study in France[J]. Eur J Vasc Endovasc Surg, 2025, 69(3): 359-370. DOI: 10.1016/j.ejvs.2024.10.031.
[39]
YANG Q S, ZHU M L, WOO P Y M, et al. Progressive distillation with optimal transport for federated incomplete multi-modal learning of brain tumor segmentation[J]. IEEE J Biomed Health Inform, 2025, 29(5): 3159-3170. DOI: 10.1109/JBHI.2025.3525854.
[40]
XU C C, ZHANG T, ZHANG D, et al. Deep generative adversarial reinforcement learning for semi-supervised segmentation of low-contrast and small objects in medical images[J]. IEEE Trans Med Imag, 2024, 43(9): 3072-3084. DOI: 10.1109/TMI.2024.3383716.
[41]
ZHANG J H, SUN B B, WANG H Y, et al. Intracranial atherosclerotic plaque features on vessel wall imaging predict first ever and recurrence of stroke: a meta-analysis[J]. Eur Radiol, 2025, 35(8): 5017-5026. DOI: 10.1007/s00330-025-11451-1.
[42]
TATTERSALL M C, HANSEN S L, MCCLELLAND R L, et al. Importance of age and sex in carotid artery plaque detection and cardiovascular disease risk[J]. JAMA Cardiol, 2025, 10(5): 487-491. DOI: 10.1001/jamacardio.2024.5702.
[43]
LYU J H, FU Y, YANG M L, et al. Generative adversarial network-based noncontrast CT angiography for aorta and carotid arteries[J/OL]. Radiology, 2023, 309(2): e230681 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/37962500/. DOI: 10.1148/radiol.230681.
[44]
CHIEN A C, BOYLE N, FINN P, et al. Abstract TP238: Sequential cardiac and brain 4D Flow MRI in healthy individuals show positive correlation between aortic blood flow and cerebral blood flow pulsatility in internal carotid arteries and basilar artery[J/OL]. Stroke, 2025, 56(Suppl_1) [2025-06-22]. https://www.ahajournals.org/doi/10.1161/str.56.suppl_1.TP238. DOI: 10.1161/str.56.suppl_1.tp238.
[45]
PINTO M S, PAOLELLA R, BILLIET T, et al. Harmonization of brain diffusion MRI: concepts and methods[J/OL]. Front Neurosci, 2020, 14: 396 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/32435181/. DOI: 10.3389/fnins.2020.00396.
[46]
HUANG H Y, MO J Y, DING Z G, et al. Deep learning to simulate contrast-enhanced MRI for evaluating suspected prostate cancer[J/OL]. Radiology, 2025, 314(1): e240238 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/39807983/. DOI: 10.1148/radiol.240238.
[47]
LI X X, GU Y F, DVORNEK N, et al. Multi-site fMRI analysis using privacy-preserving federated learning and domain adaptation: ABIDE results[J/OL]. Med Image Anal, 2020, 65: 101765 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/32679533/. DOI: 10.1016/j.media.2020.101765.
[48]
TANG X J, ZHANG L N, HE D, et al. Automatic generation and risk stratification of carotid plaque in virtual shear wave elastography using a generative adversarial network[J/OL]. Comput Med Imag Graph, 2025, 124: 102600 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/40845689/. DOI: 10.1016/j.compmedimag.2025.102600.
[49]
GARG M, KARPINSKI M, MATELSKA D, et al. Disease prediction with multi-omics and biomarkers empowers case-control genetic discoveries in the UK Biobank[J]. Nat Genet, 2024, 56(9): 1821-1831. DOI: 10.1038/s41588-024-01898-1.
[50]
VACCA S, SCICOLONE R, GUPTA A, et al. Atherosclerotic carotid artery disease Radiomics: a systematic review with meta-analysis and radiomic quality score assessment[J/OL]. Eur J Radiol, 2024, 177: 111547 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/38852329/. DOI: 10.1016/j.ejrad.2024.111547.

PREV Research progress in multimodal MRI radiomics for predicting molecular typing of gliomas
NEXT Research progress in predicting axillary lymph node metastasis in breast cancer using dynamic contrast-enhanced magnetic resonance imaging-based radiomics
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn