Abstract
Visual or manual characterization and classification of atherosclerotic plaque lesions are tedious, error-prone, and time-consuming. The purpose of this study is to develop and design an automated carotid plaque characterization and classification system into binary classes, namely symptomatic and asymptomatic types via the deep learning (DL) framework implemented on a supercomputer. We hypothesize that on ultrasound images, symptomatic carotid plaques have (a) a low grayscale median because of a histologically large lipid core and relatively little collagen and calcium, and (b) a higher chaotic (heterogeneous) grayscale distribution due to the composition. The methodology consisted of building a DL model of Artificial Intelligence (called Atheromatic 2.0, AtheroPoint, CA, USA) that used a classic convolution neural network consisting of 13 layers and implemented on a supercomputer. The DL model used a cross-validation protocol for estimating the classification accuracy (ACC) and area-under-the-curve (AUC). A sample of 346 carotid ultrasound-based delineated plaques were used (196 symptomatic and 150 asymptomatic, mean age 69.9 ± 7.8 years, with 39% females). This was augmented using geometric transformation yielding 2312 plaques (1191 symptomatic and 1120 asymptomatic plaques). K10 (90% training and 10% testing) cross-validation DL protocol was implemented and showed an (i) accuracy and (ii) AUC without and with augmentation of 86.17%, 0.86 (p-value < 0.0001), and 89.7%, 0.91 (p-value < 0.0001), respectively. The DL characterization system consisted of validation of the two hypotheses: (a) mean feature strength (MFS) and (b) Mandelbrot's fractal dimension (FD) for measuring chaotic behavior. We demonstrated that both MFS and FD were higher in symptomatic plaques compared to asymptomatic plaques by 64.15 ± 0.73% (p-value < 0.0001) and 6 ± 0.13% (p-value < 0.0001), respectively. The benchmarking results show that DL with augmentation (ACC: 89.7%, AUC: 0.91 (p-value < 0.0001)) is superior to previously published machine learning (ACC: 83.7%) by 6.0%. The Atheromatic runs the test patient in < 2 s. Deep learning can be a useful tool for carotid ultrasound-based characterization and classification of symptomatic and asymptomatic plaques.
Similar content being viewed by others
References
Benjamin EJ et al (2019) Heart disease and stroke Statistics-2019 update a report from the American Heart Association. Circulation. https://doi.org/10.1161/CIR.0000000000000659
Fryar, C.D., T.-C. Chen, and X. Li, Prevalence of uncontrolled risk factors for cardiovascular disease: United States, 1999–2010. 2012: US Department of Health and Human Services, Centers for Disease Control and ….
Heron, M.P., Deaths: leading causes for 2015. 2017.
Suri JS, Kathuria C, Molinari F (2010) Atherosclerosis disease management. Springer Science & Business Media, USA
Sirimarco G et al (2013) Carotid atherosclerosis and risk of subsequent coronary event in outpatients with atherothrombosis. Stroke 44(2):373–379
El-Baz A, Suri JS (2011) Lung imaging and computer aided diagnosis. CRC Press, USA
Radeva, P. and J.S. Suri, Vascular and Intravascular Imaging Trends, Analysis, and Challenges, Volume 2; Plaque characterization, by Radeva, Petia; and Suri, Jasjit S.. ISBN: 978–0–7503–1999–7. IOP ebooks. Bristol, UK: IOP Publishing, 2019, 2019.
Liu Y et al (2019) Size of carotid artery intraplaque hemorrhage and acute ischemic stroke: a cardiovascular magnetic resonance Chinese atherosclerosis risk evaluation study. J Cardiovasc Magn Reson 21(1):36
Chien JD et al (2013) Demographics of carotid atherosclerotic plaque features imaged by computed tomography. Journal of Neuroradiology 40(1):1–10
Laine A, Sanches JM, Suri JS (2012) Ultrasound Imaging: Advances and Applications. Springer, USA
Liu, K. and J.S. Suri, Automatic vessel indentification for angiographic screening. 2005, Google Patents.
Aichner F et al (2009) High cardiovascular event rates in patients with asymptomatic carotid stenosis: the REACH Registry. Eur J Neurol 16(8):902–908
Viswanathan V et al (2020) Low-cost preventive screening using carotid ultrasound in patients with diabetes. Front Biosci (Landmark Ed) 25:1132–1171
Saba L et al (2014) Multi-modality atherosclerosis imaging and diagnosis. Springer, USA
Kotsis V et al (2018) Echolucency-based phenotype in carotid atherosclerosis disease for risk stratification of diabetes patients. Diabetes Res Clin Pract 143:322–331
Nicolaides AN et al (2005) Effect of image normalization on carotid plaque classification and the risk of ipsilateral hemispheric ischemic events: results from the asymptomatic carotid stenosis and risk of stroke study. Vascular 13(4):211–221
Nicolaides AN et al (2002) Ultrasound plaque characterisation, genetic markers and risks. Pathophysiol Haemost Thromb 32(5–6):371
Hussain MA et al (2018) Association between statin use and cardiovascular events after carotid artery revascularization. Journal of the American Heart Association 7(16):e009745
Nicolaides AN et al (2010) Asymptomatic internal carotid artery stenosis and cerebrovascular risk stratification. J Vasc Surg 52(6):1486-1496.e5
Kakkos SK et al (2013) The size of juxtaluminal hypoechoic area in ultrasound images of asymptomatic carotid plaques predicts the occurrence of stroke. J Vasc Surg 57(3):609–618
Paraskevas KI, Nicolaides AN, Kakkos SK (2020) Asymptomatic Carotid Stenosis and Risk of Stroke (ACSRS) study: what have we learned from it? Annals of Translational Medicine. https://doi.org/10.21037/atm.2020.02.156
Sharma AM et al (2015) A review on carotid ultrasound atherosclerotic tissue characterization and stroke risk stratification in machine learning framework. Current atherosclerosis reports 17(9):55
Acharya UR et al (2012) Atherosclerotic risk stratification strategy for carotid arteries using texture-based features. Ultrasound Med Biol 38(6):899–915
Acharya, U.R., et al. Carotid far wall characterization using LBP, Laws' Texture Energy and wall variability: A novel class of Atheromatic systems. in 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2012. IEEE.
Acharya, U.R., et al. Carotid ultrasound symptomatology using atherosclerotic plaque characterization: a class of Atheromatic systems. in 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2012. IEEE.
Acharya U et al (2013) Computed tomography carotid wall plaque characterization using a combination of discrete wavelet transform and texture features: A pilot study. Proc Inst Mech Eng [H] 227(6):643–654
Acharya UR et al (2013) Understanding symptomatology of atherosclerotic plaque by image-based tissue characterization. Comput Methods Programs Biomed 110(1):66–75
Araki T et al (2017) Stroke risk stratification and its validation using ultrasonic Echolucent Carotid Wall plaque morphology: a machine learning paradigm. Comput Biol Med 80:77–96
Araki T et al (2016) PCA-based polling strategy in machine learning framework for coronary artery disease risk assessment in intravascular ultrasound: A link between carotid and coronary grayscale plaque morphology. Comput Methods Programs Biomed 128:137–158
Saba L et al (2017) Plaque Tissue Morphology-Based Stroke Risk Stratification Using Carotid Ultrasound: A Polling-Based PCA Learning Paradigm. J Med Syst 41(6):98
Saba L et al (2019) The present and future of deep learning in radiology. Eur J Radiol 114:14–24
Khanna NN et al (2019) Rheumatoid arthritis: atherosclerosis imaging and cardiovascular risk assessment using machine and deep learning–based tissue characterization. Current atherosclerosis reports 21(2):7
Biswas M et al (2019) State-of-the-art review on deep learning in medical imaging. Frontiers in bioscience (Landmark edition) 24:392–426
Huang X et al (2017) Evaluation of carotid plaque echogenicity based on the integral of the cumulative probability distribution using gray-scale ultrasound images. PLoS ONE 12(10):e0185261
Lekadir K et al (2017) A Convolutional Neural Network for Automatic Characterization of Plaque Composition in Carotid Ultrasound. IEEE journal of biomedical and health informatics 21(1):48–55
Liu, B., et al. Feature generation by convolutional neural network for click-through rate prediction. in The World Wide Web Conference. 2019.
Yasar F, Akgunlu F (2005) Fractal dimension and lacunarity analysis of dental radiographs. Dentomaxillofacial radiology 34(5):261–267
Acharya UR et al (2012) An accurate and generalized approach to plaque characterization in 346 carotid ultrasound scans. IEEE Trans Instrum Meas 61(4):1045–1053
Martis RJ et al (2013) Application of higher order statistics for atrial arrhythmia classification. Biomed Signal Process Control 8(6):888–900
Biswas M et al (2017) Symtosis: A Liver Ultrasound Tissue Characterization and Risk Stratification in Optimized Deep Learning Paradigm. Comput Methods Programs Biomed 155:165–177
Kuppili V et al (2017) Extreme Learning Machine Framework for Risk Stratification of Fatty Liver Disease Using Ultrasound Tissue Characterization. J Med Syst 41(10):152
Saba L et al (2016) Automated stratification of liver disease in ultrasound: An online accurate feature classification paradigm. Comput Methods Programs Biomed 130:118–134
Acharya UR et al (2012) Data mining framework for fatty liver disease classification in ultrasound: a hybrid feature extraction paradigm. Med Phys 39:4255–4264
Singh BK et al (2017) Risk stratification of 2D ultrasound-based breast lesions using hybrid feature selection in machine learning paradigm. Measurement 105:146–157
Acharya U et al (2013) Diagnosis of Hashimoto’s thyroiditis in ultrasound using tissue characterization and pixel classification. Proc Inst Mech Eng [H] 227(7):788–798
Acharya UR et al (2012) Non-invasive automated 3D thyroid lesion classification in ultrasound: a class of ThyroScanTM systems. Ultrasonics 52(4):508–520
Acharya UR et al (2011) Cost-effective and non-invasive automated benign & malignant thyroid lesion classification in 3D contrast-enhanced ultrasound using combination of wavelets and textures: a class of ThyroScanTM algorithms. Technology in cancer research & treatment 10(4):371–380
Acharya UR et al (2014) A review on ultrasound-based thyroid cancer tissue characterization and automated classification. Technology in cancer research & treatment 13(4):289–301
Molinari F et al (2010) Characterization of single thyroid nodules by contrast-enhanced 3-D ultrasound. Ultrasound Med Biol 36(10):1616–1625
Banchhor SK et al (2017) Wall-based measurement features provides an improved IVUS coronary artery risk assessment when fused with plaque texture-based features during machine learning paradigm. Comput Biol Med 91:198–212
Pareek G et al (2013) Prostate tissue characterization/classification in 144 patient population using wavelet and higher order spectra features from transrectal ultrasound images. Technology in cancer research & treatment 12(6):545–557
McClure P et al (2014) In-vitro and in-vivo diagnostic techniques for prostate cancer: a review. J Biomed Nanotechnol 10(10):2747–2777
Acharya UR et al (2015) Ovarian tissue characterization in ultrasound: a review. Technology in cancer research & treatment 14(3):251–261
Acharya UR et al (2013) Ovarian tumor characterization and classification using ultrasound: A new online paradigm. Ovarian neoplasm imaging. Springer, New York p, pp 413–423
Maniruzzaman M et al (2017) Comparative approaches for classification of diabetes mellitus data: Machine learning paradigm. Comput Methods Programs Biomed 152:23–34
Shrivastava VK et al (2016) Computer-aided diagnosis of psoriasis skin images with HOS, texture and color features: a first comparative study of its kind. Comput Methods Programs Biomed 126:98–109
Acharya UR et al (2013) Automated classification of patients with coronary artery disease using grayscale features from left ventricle echocardiographic images. Comput Methods Programs Biomed 112(3):624–632
Cuadrado-Godia E et al (2018) Cerebral small vessel disease: A review focusing on pathophysiology, biomarkers, and machine learning strategies. Journal of stroke 20(3):302
Suri, J.S., Imaging based symptomatic classification and cardiovascular stroke risk score estimation. 2011, Google Patents.
Acharya UR et al (2013) Atherosclerotic plaque tissue characterization in 2D ultrasound longitudinal carotid scans for automated classification: a paradigm for stroke risk assessment. Med Biol Eng Compu 51(5):513–523
Monkam P et al (2018) CNN models discriminating between pulmonary micro-nodules and non-nodules from CT images. Biomedical engineering online 17(1):96
Acharya, U.R., et al. Atheromatic™: Symptomatic vs. asymptomatic classification of carotid ultrasound plaque using a combination of HOS, DWT & texture. in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2011. IEEE.
Than JC et al (2017) Lung disease stratification using amalgamation of Riesz and Gabor transforms in machine learning framework. Comput Biol Med 89:197–211
Li A et al (2019) Evaluating modern GPU interconnect: Pcie, nvlink, nv-sli, nvswitch and gpudirect. IEEE Trans Parallel Distrib Syst 31(1):94–110
Sanagala, S.S., et al. A Fast and Light Weight Deep Convolution Neural Network Model for Cancer Disease Identification in Human Lung (s). in 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA). 2019. IEEE.
Ho SSY (2016) Current status of carotid ultrasound in atherosclerosis. Quantitative imaging in medicine and surgery 6(3):285
Kurosaki Y et al (2017) Asymptomatic carotid T1-high-intense plaque as a risk factor for a subsequent cerebrovascular ischemic event. Cerebrovascular Diseases 43(5–6):250–256
Rujirakul K, So-In C (2014) and B. A parallel expectation-maximization PCA face recognition architecture. The Scientific World Journal, Arnonkijpanich, PEM-PCA, p 2014
Golle, P. Machine learning attacks against the Asirra CAPTCHA. in Proceedings of the 15th ACM conference on Computer and communications security. 2008.
Christodoulou CI et al (2003) Texture-based classification of atherosclerotic carotid plaques. IEEE Trans Med Imaging 22(7):902–912
Acharya UR et al (2011) An accurate and generalized approach to plaque characterization in 346 carotid ultrasound scans. IEEE Trans Instrum Meas 61(4):1045–1053
Gastounioti A et al (2014) A novel computerized tool to stratify risk in carotid atherosclerosis using kinematic features of the arterial wall. IEEE journal of biomedical and health informatics 19(3):1137–1145
Skandha S et al (2020) 3-D optimized classification and characterization artificial intelligence paradigm for cardiovascular/stroke risk stratification using carotid ultrasound-based delineated plaque: Atheromatic™ 2.0. Computers Biol Med 125:103958
Acharya R, Ng YE, Suri JS (eds) (2008) Image modeling of the human eye. Artech House, MA USA
Narayanan, R., et al. MRI-ultrasound registration for targeted prostate biopsy. in 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. 2009. IEEE.
El-Baz A, Suri JS (2019) Big Data in Multimodal Medical Imaging. CRC Press, USA
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Dr. Deepak L. Bhatt discloses the following relationships - Advisory Board: Cardax, CellProthera, Cereno Scientific, Elsevier Practice Update Cardiology, Level Ex, Medscape Cardiology, MyoKardia, PhaseBio, PLx Pharma, Regado Biosciences; Board of Directors: Boston VA Research Institute, Society of Cardiovascular Patient Care, TobeSoft; Chair: American Heart Association Quality Oversight Committee; Data Monitoring Committees: Baim Institute for Clinical Research (formerly Harvard Clinical Research Institute, for the PORTICO trial, funded by St. Jude Medical, now Abbott), Cleveland Clinic (including for the ExCEED trial, funded by Edwards), Contego Medical (Chair, PERFORMANCE 2), Duke Clinical Research Institute, Mayo Clinic, Mount Sinai School of Medicine (for the ENVISAGE trial, funded by Daiichi Sankyo), Population Health Research Institute; Honoraria: American College of Cardiology (Senior Associate Editor, Clinical Trials and News, ACC.org; Vice-Chair, ACC Accreditation Committee), Baim Institute for Clinical Research (formerly Harvard Clinical Research Institute; RE-DUAL PCI clinical trial steering committee funded by Boehringer Ingelheim; AEGIS-II executive committee funded by CSL Behring), Belvoir Publications (Editor in Chief, Harvard Heart Letter), Canadian Medical and Surgical Knowledge Translation Research Group (clinical trial steering committees), Duke Clinical Research Institute (clinical trial steering committees, including for the PRONOUNCE trial, funded by Ferring Pharmaceuticals), HMP Global (Editor in Chief, Journal of Invasive Cardiology), Journal of the American College of Cardiology (Guest Editor; Associate Editor), K2P (Co-Chair, interdisciplinary curriculum), Level Ex, Medtelligence/ReachMD (CME steering committees), MJH Life Sciences, Population Health Research Institute (for the COMPASS operations committee, publications committee, steering committee, and USA national co-leader, funded by Bayer), Slack Publications (Chief Medical Editor, Cardiology Today’s Intervention), Society of Cardiovascular Patient Care (Secretary/Treasurer), WebMD (CME steering committees); Other: Clinical Cardiology (Deputy Editor), NCDR-ACTION Registry Steering Committee (Chair), VA CART Research and Publications Committee (Chair); Research Funding: Abbott, Afimmune, Amarin, Amgen, AstraZeneca, Bayer, Boehringer Ingelheim, Bristol-Myers Squibb, Cardax, Chiesi, CSL Behring, Eisai, Ethicon, Ferring Pharmaceuticals, Forest Laboratories, Fractyl, Idorsia, Ironwood, Ischemix, Lexicon, Lilly, Medtronic, MyoKardia, Pfizer, PhaseBio, PLx Pharma, Regeneron, Roche, Sanofi, Synaptic, The Medicines Company; Royalties: Elsevier (Editor, Cardiovascular Intervention: A Companion to Braunwald’s Heart Disease); Site Co-Investigator: Biotronik, Boston Scientific, CSI, St. Jude Medical (now Abbott), Svelte; Trustee: American College of Cardiology; Unfunded Research: FlowCo, Merck, Novo Nordisk, Takeda. Dr. Jasjit S. Suri is with AtheroPoint™, focused in the area of stroke/cardiovascular imaging.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Saba, L., Sanagala, S.S., Gupta, S.K. et al. Ultrasound-based internal carotid artery plaque characterization using deep learning paradigm on a supercomputer: a cardiovascular disease/stroke risk assessment system. Int J Cardiovasc Imaging 37, 1511–1528 (2021). https://doi.org/10.1007/s10554-020-02124-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10554-020-02124-9