Applications of artificial intelligence-based models in vulnerable carotid plaque

Abstract

Carotid atherosclerotic disease is a widely acknowledged risk factor for ischemic stroke, making it a major concern on a global scale. To alleviate the socio-economic impact of carotid atherosclerotic disease, crucial objectives include prioritizing prevention efforts and early detection. So far, the degree of carotid stenosis has been regarded as the primary parameter for risk assessment and determining appropriate therapeutic interventions. Histopathological and imaging-based studies demonstrated important differences in the risk of cardiovascular events given a similar degree of luminal stenosis, identifying plaque structure and composition as key determinants of either plaque vulnerability or stability. The application of Artificial Intelligence (AI)-based techniques to carotid imaging can offer several solutions for tissue characterization and classification. This review aims to present a comprehensive overview of the main concepts related to AI. Additionally, we review the existing literature on AI-based models in ultrasound (US), computed tomography (CT), and Magnetic Resonance Imaging (MRI) for vulnerable plaque detection, and we finally examine the advantages and limitations of these AI approaches.

Keywords

Cardiovascular imaging / carotid / AI / vulnerable plaque

References

[1] Roth GA,Abajobir A.Global, regional, and national burden of cardiovascular diseases for 10 causes, 1990 to 2015.J Am Coll Cardiol2017;70:1-25

[2] Mathers CD.Projections of global mortality and burden of disease from 2002 to 2030.PLoS Med2006;3:e442 PMCID:PMC1664601

[3] Dai H,Maor E.Global, regional, and national burden of ischaemic heart disease and its attributable risk factors, 1990-2017: results from the Global Burden of Disease Study 2017.Eur Heart J Qual Care Clin Outcomes2022;8:50-60 PMCID:PMC8728029

[4] Song P,Wang H.Global and regional prevalence, burden, and risk factors for carotid atherosclerosis: a systematic review, meta-analysis, and modelling study.Lancet Glob Health2020;8:e721-9

[5] Kolominsky-Rabas PL,Gefeller O,Heuschmann PU.Epidemiology of ischemic stroke subtypes according to TOAST criteria: incidence, recurrence, and long-term survival in ischemic stroke subtypes: a population-based study.Stroke2001;32:2735-40

[6] Schindler A,Altaf N.Prediction of stroke risk by detection of hemorrhage in carotid plaques: meta-analysis of individual patient data.JACC Cardiovasc Imaging2020;13:395-406

[7] Bos D,Gupta A.Advances in multimodality carotid plaque imaging: AJR expert panel narrative review.AJR Am J Roentgenol2021;217:16-26

[8] Cau R,Kooi ME.Pearls and pitfalls of carotid artery imaging: ultrasound, computed tomography angiography, and MR imaging.Radiol Clin N Am2023;61:405-13

[9] Saba L,Cau R.Review of imaging biomarkers for the vulnerable carotid plaque.JVS Vasc Sci2021;2:149-58 PMCID:PMC8489200

[10] Saba L,Hatsukami TS.Vessel Wall Imaging Study Group of the American Society of NeuroradiologyCarotid artery wall imaging: perspective and guidelines from the ASNR Vessel Wall Imaging Study Group and expert consensus recommendations of the American Society of Neuroradiology.Am J Neuroradiol2018;39:E9-E31 PMCID:PMC7410574

[11] Muscogiuri G,Cau R.Application of AI in cardiovascular multimodality imaging.Heliyon2022;8:e10872 PMCID:PMC9576885

[12] Petersen SE,Leiner T.Artificial intelligence will transform cardiac imaging-opportunities and challenges.Front Cardiovasc Med2019;6:133 PMCID:PMC6746883

[13] Dey D,Leeson P.Artificial intelligence in cardiovascular imaging: JACC state-of-the-art review.J Am Coll Cardiol2019;73:1317-35 PMCID:PMC6474254

[14] Xu B,Grimm R,Cheng F.Applications of artificial intelligence in multimodality cardiovascular imaging: a state-of-the-art review.Prog Cardiovasc Dis2020;63:367-76

[15] Cau R,Mannelli L.Artificial intelligence in computed tomography plaque characterization: a review.Eur J Radiol2021;140:109767

[16] Cau R,Micheletti G.Potential role of artificial intelligence in cardiac magnetic resonance imaging: can it help clinicians in making a diagnosis?.J Thorac Imaging2021;36:142-8

[17] Cau R,Nardi V.Long-COVID diagnosis: from diagnostic to advanced AI-driven models.Eur J Radiol2022;148:110164 PMCID:PMC8791239

[18] Cau R,Suri JS.Artificial intelligence applications in cardiovascular magnetic resonance imaging : are we on the path to avoiding the administration of contrast media?.Diagnostics2023;13:2061 PMCID:PMC10297403

[19] Goodfellow I,Courville A. Deep Learning. Cambridge: MIT Press; 2016.

[20] Leiner T,Suinesiaputra A.Machine learning in cardiovascular magnetic resonance: basic concepts and applications.J Cardiovasc Magn Reson2019;21:61 PMCID:PMC6778980

[21] Soffer S,Shimon O,Greenspan H.Convolutional neural networks for radiologic images: a radiologist's guide.Radiology2019;290:590-606

[22] Ronneberger O,Brox T.U-Net: convolutional networks for biomedical image segmentation BT - medical image computing and computer-assisted intervention - MICCAI 2015. In: Navab N, Hornegger J, Wells WM, Frangi AF, editors. Berlin: Springer; 2015. pp. 234-41.

[23] Han N,Li Y.Imaging and hemodynamic characteristics of vulnerable carotid plaques and artificial intelligence applications in plaque classification and segmentation.Brain Sci2023;13:143 PMCID:PMC9856903

[24] Siddique N,Elkin CP.U-Net and its variants for medical image segmentation: a review of theory and applications.IEEE Access2021;9:82031-57

[25] Isensee F,Kohl SAA,Maier-Hein KH.nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation.Nat Methods2021;18:203-11

[26] He K,Li Z.Transformers in medical image analysis.Intell Med2023;3:59-78

[27] Dosovitskiy A,Kolesnikov A. An image is worth 16 × 16 words: Transformers for image recognition at scale. Available from: https://arxiv.org/abs/2010.11929 [Last accessed on 14 Sep 2023]

[28] Lin Y,Xu W,Xu W.Method for carotid artery 3-D ultrasound image segmentation based on CSWin transformer.Ultrasound Med Biol2023;49:645-56

[29] Petch J,Nelson W.Opening the black box: the promise and limitations of explainable machine learning in cardiology.Can J Cardiol2022;38:204-13

[30] Linardatos P,Kotsiantis S.Explainable AI: a review of machine learning interpretability methods.Entropy2020;23:18 PMCID:PMC7824368

[31] Guthikonda S.Homocysteine: role and implications in atherosclerosis.Curr Atheroscler Rep2006;8:100-6

[32] Hegele RA.The genetic basis of atherosclerosis.Int J Clin Lab Res1997;27:2-13

[33] von Eckardstein A. Risk factors for atherosclerotic vascular disease. In: von Eckardstein A, editor. Atherosclerosis: diet and drugs. Berlin: Springer; 2005. pp. 71-105.

[34] Singh RB,Xu Y-J,Dhalla NS.Pathogenesis of atherosclerosis: a multifactorial process.Exp Clin Cardiol2002;7:40-53 PMCID:PMC2716189

[35] Saba L,Jäger HR.Imaging biomarkers of vulnerable carotid plaques for stroke risk prediction and their potential clinical implications.Lancet Neurol2019;18:559-72

[36] Sillesen H,Sandholt B,Mehran R.Carotid plaque thickness and carotid plaque burden predict future cardiovascular events in asymptomatic adult Americans.Eur Heart J Cardiovasc Imaging2018;19:1042-50

[37] Kakkos SK,Nicolaides AN.Asymptomatic Carotid Stenosis and Risk of Stroke (ACSRS) Study GroupThe size of juxtaluminal hypoechoic area in ultrasound images of asymptomatic carotid plaques predicts the occurrence of stroke.J Vasc Surg2013;57:609-618

[38] Nicolaides AN.Atherosclerotic disease risk stratification using ultrasonographic measurements of plaque.JACC Cardiovasc Imaging2022;15:1136-8

[39] Nicolaides AN,Griffin M.Arterial ultrasound testing to predict atherosclerotic cardiovascular events.J Am Coll Cardiol2022;79:1969-82

[40] Cademartiri F,Cau R.Insight from imaging on plaque vulnerability: similarities and differences between coronary and carotid arteries-implications for systemic therapies.Cardiovasc Diagn Ther2020;10:1150-62 PMCID:PMC7487399

[41] Saba L,Saam T.Vessel wall-imaging biomarkers of carotid plaque vulnerability in stroke prevention trials: a viewpoint from the carotid imaging consensus group.JACC Cardiovasc Imaging2020;13:2445-56

[42] Gupta A,Schweitzer AD.Carotid plaque MRI and stroke risk: a systematic review and meta-analysis.Stroke2013;44:3071-7

[43] Saba L,Sanfilippo R.Imaging of the carotid artery.Atherosclerosis2012;220:294-309

[44] Saba L,Weikert T.State-of-the-art CT and MR imaging and assessment of atherosclerotic carotid artery disease: the reporting-a consensus document by the European Society of Cardiovascular Radiology (ESCR).Eur Radiol2023;33:1088-101 PMCID:PMC9889425

[45] Cademartiri F,Pistoia L.Dual-source photon-counting computed tomography - Part I : clinical overview of cardiac ct and coronary CT angiography applications.J Clin Med2023;12:3627 PMCID:PMC10253312

[46] Meloni A,Pistoia L.Dual-source photon-counting computed tomography - Part III : clinical overview of vascular applications beyond cardiac and neuro imaging.J Clin Med2023;12:3798 PMCID:PMC10253892

[47] Cademartiri F,Pistoia L.Dual source photon-counting computed tomography - Part II : clinical overview of neurovascular applications.J Clin Med2023;12:3626 PMCID:PMC10253695

[48] Saba L,Gupta A.International Union of Angiology (IUA) consensus paper on imaging strategies in atherosclerotic carotid artery imaging: from basic strategies to advanced approaches.Atherosclerosis2022;354:23-40

[49] Johri AM,Naqvi TZ.Recommendations for the assessment of carotid arterial plaque by ultrasound for the characterization of atherosclerosis and evaluation of cardiovascular risk: from the American Society of Echocardiography.J Am Soc Echocardiogr2020;33:917-33

[50] Saba L,Marincola BC.Imaging of the carotid artery vulnerable plaque.Cardiovasc Intervent Radiol2014;37:572-85

[51] Adla T.Multimodality imaging of carotid stenosis.Int J Angiol2015;24:179-84 PMCID:PMC4572013

[52] Jain PK,Giannopoulos AA,Nicolaides A.Hybrid deep learning segmentation models for atherosclerotic plaque in internal carotid artery B-mode ultrasound.Comput Biol Med2021;136:104721

[53] Menchón-Lara RM,Morales-Sánchez J.Automatic detection of the intima-media thickness in ultrasound images of the common carotid artery using neural networks.Med Biol Eng Comput2014;52:169-81

[54] Zhou T,Pan X,Li J.Fully automatic deep learning trained on limited data for carotid artery segmentation from large image volumes.Quant Imaging Med Surg2021;11:67-83 PMCID:PMC7719941

[55] Huang W,Hou C,Wang X.Simultaneous vessel segmentation and unenhanced prediction using self-supervised dual-task learning in 3D CTA (SVSUP).Comput Methods Programs Biomed2022;224:107001

[56] Bortsova G,Dubost F.Automated segmentation and volume measurement of intracranial internal carotid artery calcification at noncontrast CT.Radiol Artif Intell2021;3:e200226 PMCID:PMC8489463

[57] Dos Santos FL, Kolasa M, Terada M, Salenius J, Eskola H, Paci M. VASIM: an automated tool for the quantification of carotid atherosclerosis by computed tomography angiography.Int J Cardiovasc Imaging2019;35:1149-59

[58] Wu J,Yang X.Deep morphology aided diagnosis network for segmentation of carotid artery vessel wall and diagnosis of carotid atherosclerosis on black-blood vessel wall MRI.Med Phys2019;46:5544-61

[59] Ziegler M,Bustamante M.Automated segmentation of the individual branches of the carotid arteries in contrast-enhanced MR angiography using DeepMedic.BMC Med Imaging2021;21:38 PMCID:PMC7912466

[60] Jain PK,Saba L.Unseen artificial intelligence-deep learning paradigm for segmentation of low atherosclerotic plaque in carotid ultrasound: a multicenter cardiovascular study.Diagnostics2021;11:2257 PMCID:PMC8699942

[61] Zhang L,Ding Y,Hui P.Texture analysis based on vascular ultrasound to identify the vulnerable carotid plaques.Front Neurosci2022;16:885209 PMCID:PMC9204477

[62] Akkus Z,Van Den Oord SCH.Carotid intraplaque neovascularization quantification software (CINQS).IEEE J Biomed Heal2014;19:332-8

[63] Guang Y,Ning B.Deep learning-based carotid plaque vulnerability classification with multicentre contrast-enhanced ultrasound video: a comparative diagnostic study.BMJ Open2021;11:e047528 PMCID:PMC8404444

[64] Saba L,Gupta SK.A multicenter study on carotid ultrasound plaque tissue characterization and classification using six deep artificial intelligence models: a stroke application.IEEE Trans Instrum Meas2021;70:1-12

[65] Cilla S,Lenkowicz J.CT angiography-based radiomics as a tool for carotid plaque characterization: a pilot study.Radiol Med2022;127:743-53

[66] Buckler AJ,Rajeev A.Atherosclerosis risk classification with computed tomography angiography: A radiologic-pathologic validation study.Atherosclerosis2023;366:42-8

[67] Kigka VI,Mantzaris MD.A machine learning model for the identification of high risk carotid atherosclerotic plaques.Annu Int Conf IEEE Eng Med Biol Soc2021;2021:2266-9

[68] Zhang R,Ji A.Identification of high-risk carotid plaque with MRI-based radiomics and machine learning.Eur Radiol2021;31:3116-26

[69] Li H,Dong Z.Identification of high-risk intracranial plaques with 3D high-resolution magnetic resonance imaging-based radiomics and machine learning.J Neurol2022;269:6494-503