Two-stage artificial intelligence model for jointly measurement of atherosclerotic wall thickness and plaque burden in carotid ultrasound: A screening tool for cardiovascular/stroke risk assessment

MOTIVATION The early screening of cardiovascular diseases (CVD) can lead to effective treatment. Thus, accurate and reliable atherosclerotic carotid wall detection and plaque measurements are crucial. Current measurement methods are time-consuming and do not utilize the power of knowledge-based paradigms such as artificial intelligence (AI). We present an AI-based methodology for the joint automated detection and measurement of wall thickness and carotid plaque (CP) in the form of carotid intima-media thickness (cIMT) and total plaque area (TPA), a class of AtheroEdge™ system (AtheroPoint™, CA, USA). METHOD The novel system consists of two stages, and each stage comprises an independent deep learning (DL) model. In Stage I, the first DL model segregates the common carotid artery (CCA) patches from ultrasound (US) images into the rectangular wall and non-wall patches. The characterized wall patches are integrated to form the region of interest (ROI), which is then fed into Stage II. In Stage II, the second DL model segments the far wall region. Lumen-intima (LI) and media-adventitial (MA) boundaries are then extracted from the wall region, which is then used for cIMT and PA measurement. RESULTS Using the database of 250 carotid scans, the cIMT error using the AI model is 0.0935±0.0637 mm, which is lower than those of all previous methods. The PA error is found to be 2.7939±2.3702 mm2. The system's correlation coefficient (CC) between AI and ground truth (GT) values for cIMT is 0.99 (p < 0.0001), which is higher compared with the CC of 0.96 (p < 0.0001) shown by the earlier DL method. The CC for PA between AI and GT values is 0.89 (p < 0.0001). CONCLUSION A novel AI-based strategy was applied to carotid US images for the joint detection of carotid wall thickness (cWT) and plaque area (PA), followed by cIMT and PA measurement. This AI-based strategy shows improved performance using the patch technique compared with previous methods using full carotid scans.

[1]  Tadashi Araki,et al.  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 , 2016, Comput. Methods Programs Biomed..

[2]  R. Ross,et al.  Atherosclerosis is an inflammatory disease. , 1998, American heart journal.

[3]  Jasjit S. Suri,et al.  Inter-Greedy Technique for Fusion of Different Segmentation Strategies Leading to High-Performance Carotid IMT Measurement in Ultrasound Images , 2011, Journal of Medical Systems.

[4]  A. Becker,et al.  Atherosclerotic lesions in humans. In situ immunophenotypic analysis suggesting an immune mediated response. , 1989, Laboratory investigation; a journal of technical methods and pathology.

[5]  J. Suri,et al.  CALSFOAM-completed automated local statistics based first order absolute moment" for carotid wall recognition, segmentation and IMT measurement: validation and benchmarking on a 300 patient database. , 2011, International angiology : a journal of the International Union of Angiology.

[6]  J. Suri,et al.  Link between automated coronary calcium volumes from intravascular ultrasound to automated carotid IMT from B-mode ultrasound in coronary artery disease population. , 2014, International angiology : a journal of the International Union of Angiology.

[7]  Robert M. Haralick,et al.  Greedy Algorithm for Error Correction in Automatically Produced Boundaries from Low Contrast Ventriculograms , 2000, Pattern Analysis & Applications.

[8]  Pierre Baldi,et al.  Autoencoders, Unsupervised Learning, and Deep Architectures , 2011, ICML Unsupervised and Transfer Learning.

[9]  Ajay Gupta,et al.  Accurate lumen diameter measurement in curved vessels in carotid ultrasound: an iterative scale-space and spatial transformation approach , 2017, Medical & Biological Engineering & Computing.

[10]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Geoffrey E. Hinton.  Deep belief networks , 2009, Scholarpedia.

[12]  Ajay Gupta,et al.  Web-based accurate measurements of carotid lumen diameter and stenosis severity: An ultrasound-based clinical tool for stroke risk assessment during multicenter clinical trials , 2017, Comput. Biol. Medicine.

[13]  Petia Radeva,et al.  Five multiresolution-based calcium volume measurement techniques from coronary IVUS videos: A comparative approach , 2016, Comput. Methods Programs Biomed..

[14]  U Rajendra Acharya,et al.  Automated carotid IMT measurement and its validation in low contrast ultrasound database of 885 patient Indian population epidemiological study: results of AtheroEdge™ Software. , 2012, International angiology : a journal of the International Union of Angiology.

[15]  Han Zhao,et al.  Extreme learning machine: algorithm, theory and applications , 2013, Artificial Intelligence Review.

[16]  Jasjit S. Suri,et al.  Atherosclerosis disease management , 2011 .

[17]  Jasjit S. Suri,et al.  White Matter/Gray Matter Boundary Segmentation Using Geometric Snakes: A Fuzzy Deformable Model , 2001, ICAPR.

[18]  Filippo Molinari,et al.  Carotid IMT Variability (IMTV) and Its Validation in Symptomatic versus Asymptomatic Italian Population: Can This Be a Useful Index for Studying Symptomaticity? , 2012, Echocardiography.

[19]  U. Rajendra Acharya,et al.  Hypothesis Validation of Far-Wall Brightness in Carotid-Artery Ultrasound for Feature-Based IMT Measurement Using a Combination of Level-Set Segmentation and Registration , 2012, IEEE Transactions on Instrumentation and Measurement.

[20]  R. Kronmal,et al.  Carotid-artery intima and media thickness as a risk factor for myocardial infarction and stroke in older adults. Cardiovascular Health Study Collaborative Research Group. , 1999, The New England journal of medicine.

[21]  U. Rajendra Acharya,et al.  Constrained snake vs. conventional snake for carotid ultrasound automated IMT measurements on multi-center data sets. , 2012, Ultrasonics.

[22]  Laura Igual,et al.  Semantic segmentation with DenseNets for carotid artery ultrasound plaque segmentation and CIMT estimation , 2020, Artif. Intell. Medicine.

[23]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[24]  Jasjit S. Suri,et al.  Automated Measurement of Carotid Artery Intima-Media Thickness , 2011 .

[25]  Luca Saba,et al.  Intima Media Thickness Variability (IMTV) and its association with cerebrovascular events: a novel marker of carotid therosclerosis? , 2011, Cardiovascular diagnosis and therapy.

[26]  Nilanjan Dey,et al.  Automated segmental-IMT measurement in thin/thick plaque with bulb presence in carotid ultrasound from multiple scanners: Stroke risk assessment , 2017, Comput. Methods Programs Biomed..

[27]  V. Fuster,et al.  Coronary plaque disruption. , 1995, Circulation.

[28]  J. Suri,et al.  Improved correlation between carotid and coronary atherosclerosis SYNTAX score using automated ultrasound carotid bulb plaque IMT measurement. , 2015, Ultrasound in medicine & biology.

[29]  José-Luis Sancho-Gómez,et al.  Fully automatic segmentation of ultrasound common carotid artery images based on machine learning , 2015, Neurocomputing.

[30]  M L Bots,et al.  Manual or semi‐automated edge detection of the maximal far wall common carotid intima–media thickness: a direct comparison , 2012, Journal of internal medicine.

[31]  Jasjit S. Suri,et al.  Ankle–Brachial Index and Its Link to Automated Carotid Ultrasound Measurement of Intima–Media Thickness Variability in 500 Japanese Coronary Artery Disease Patients , 2014, Current Atherosclerosis Reports.

[32]  Jasjit S. Suri,et al.  A new method for IVUS-based coronary artery disease risk stratification: A link between coronary & carotid ultrasound plaque burdens , 2016, Comput. Methods Programs Biomed..

[33]  Jasjit S. Suri,et al.  Deep learning strategy for accurate carotid intima-media thickness measurement: An ultrasound study on Japanese diabetic cohort , 2018, Comput. Biol. Medicine.

[34]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[35]  Nima Tajbakhsh,et al.  Automating Carotid Intima-Media Thickness Video Interpretation with Convolutional Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  A. Tedgui,et al.  Cytokines in atherosclerosis: pathogenic and regulatory pathways. , 2006, Physiological reviews.

[37]  J. David Spence,et al.  Carotid Plaque Area: A Tool for Targeting and Evaluating Vascular Preventive Therapy , 2002, Stroke.

[38]  Jasjit S. Suri,et al.  Deep learning fully convolution network for lumen characterization in diabetic patients using carotid ultrasound: a tool for stroke risk , 2018, Medical & Biological Engineering & Computing.

[39]  C. Rajasekaran,et al.  Convolutional Neural Network for Segmentation and Measurement of Intima Media Thickness , 2018, Journal of Medical Systems.

[40]  Ayman El-Baz,et al.  Big Data in Multimodal Medical Imaging , 2019 .

[41]  Jasjit S. Suri,et al.  Effect of carotid image-based phenotypes on cardiovascular risk calculator: AECRS1.0 , 2019, Medical & Biological Engineering & Computing.

[42]  U. Rajendra Acharya,et al.  Completely automated robust edge snapper for carotid ultrasound IMT measurement on a multi-institutional database of 300 images , 2011, Medical & Biological Engineering & Computing.

[43]  Kecheng Liu,et al.  White and black blood volumetric angiographic filtering: ellipsoidal scale-space approach , 2002, IEEE Transactions on Information Technology in Biomedicine.

[44]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[45]  Jasjit S. Suri,et al.  Multi-Modality Atherosclerosis Imaging and Diagnosis , 2013 .

[46]  Jasjit S. Suri,et al.  Morphologic TPA (mTPA) and composite risk score for moderate carotid atherosclerotic plaque is strongly associated with HbA1c in diabetes cohort , 2018, Comput. Biol. Medicine.

[47]  S. Laxminarayan,et al.  Angiography and Plaque Imaging: Advanced Segmentation Techniques , 2007 .

[48]  Guang Zeng,et al.  Carotid artery recognition system: a comparison of three automated paradigms for ultrasound images. , 2011, Medical physics.

[49]  Jasjit S. Suri,et al.  Characterization of a Completely User-Independent Algorithm for Carotid Artery Segmentation in 2-D Ultrasound Images , 2007, IEEE Transactions on Instrumentation and Measurement.

[50]  Jasjit S Suri,et al.  Ultrasound-based carotid stenosis measurement and risk stratification in diabetic cohort: a deep learning paradigm. , 2019, Cardiovascular diagnosis and therapy.

[51]  U. Rajendra Acharya,et al.  An Accurate and Generalized Approach to Plaque Characterization in 346 Carotid Ultrasound Scans , 2012, IEEE Transactions on Instrumentation and Measurement.

[52]  J. Suri,et al.  Introduction to cognitive science, informatics, and modeling , 2020 .

[53]  A. Folsom,et al.  Carotid wall thickness is predictive of incident clinical stroke: the Atherosclerosis Risk in Communities (ARIC) study. , 2000, American journal of epidemiology.

[54]  Filippo Molinari,et al.  Fully Automated Dual‐Snake Formulation for Carotid Intima‐Media Thickness Measurement , 2012, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[55]  Filippo Molinari,et al.  Automated carotid artery intima layer regional segmentation , 2011, Physics in medicine and biology.

[56]  Jasjit S. Suri,et al.  A state of the art review on intima-media thickness (IMT) measurement and wall segmentation techniques for carotid ultrasound , 2010, Comput. Methods Programs Biomed..

[57]  Jasjit S. Suri,et al.  Intra- and inter-operator reproducibility of automated cloud-based carotid lumen diameter ultrasound measurement , 2018, Indian heart journal.

[58]  Jasjit S Suri,et al.  Nonlinear model for the carotid artery disease 10‐year risk prediction by fusing conventional cardiovascular factors to carotid ultrasound image phenotypes: A Japanese diabetes cohort study , 2019, Echocardiography.

[59]  M. Fornage,et al.  Heart Disease and Stroke Statistics—2017 Update: A Report From the American Heart Association , 2017, Circulation.

[60]  Jasjit S. Suri,et al.  Performance evaluation of 10-year ultrasound image-based stroke/cardiovascular (CV) risk calculator by comparing against ten conventional CV risk calculators: A diabetic study , 2019, Comput. Biol. Medicine.

[61]  J. Suri,et al.  Morphological Carotid Plaque Area Is Associated With Glomerular Filtration Rate: A Study of South Asian Indian Patients With Diabetes and Chronic Kidney Disease , 2020, Angiology.

[62]  U. Rajendra Acharya,et al.  Ultrasound IMT measurement on a multi-ethnic and multi-institutional database: Our review and experience using four fully automated and one semi-automated methods , 2012, Comput. Methods Programs Biomed..

[63]  Filippo Molinari,et al.  Association of automated carotid IMT measurement and HbA1c in Japanese patients with coronary artery disease. , 2013, Diabetes research and clinical practice.

[64]  Jasjit S. Suri,et al.  Extreme Learning Machine Framework for Risk Stratification of Fatty Liver Disease Using Ultrasound Tissue Characterization , 2017, Journal of Medical Systems.

[65]  Jasjit S. Suri,et al.  Ranking of stroke and cardiovascular risk factors for an optimal risk calculator design: Logistic regression approach , 2019, Comput. Biol. Medicine.

[66]  Filippo Molinari,et al.  Comparison between manual and automated analysis for the quantification of carotid wall by using sonography. A validation study with CT. , 2012, European journal of radiology.

[67]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[68]  Ajay Gupta,et al.  Accurate cloud-based smart IMT measurement, its validation and stroke risk stratification in carotid ultrasound: A web-based point-of-care tool for multicenter clinical trial , 2016, Comput. Biol. Medicine.

[69]  Filippo Molinari,et al.  Intima-media thickness: setting a standard for a completely automated method of ultrasound measurement , 2010, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[70]  Jasjit S. Suri,et al.  CAUDLES-EF: Carotid Automated Ultrasound Double Line Extraction System Using Edge Flow , 2011, Journal of Digital Imaging.

[71]  Joao Sanches,et al.  Ultrasound Imaging: Advances and Applications , 2011 .

[72]  Nilanjan Dey,et al.  Automated stratification of liver disease in ultrasound: An online accurate feature classification paradigm , 2016, Comput. Methods Programs Biomed..

[73]  J. Suri,et al.  What is the correct distance measurement metric when measuring carotid ultrasound intima-media thickness automatically? , 2012, International angiology : a journal of the International Union of Angiology.

[74]  Filippo Molinari,et al.  An automated technique for carotid far wall classification using grayscale features and wall thickness variability , 2015, Journal of clinical ultrasound : JCU.

[75]  Jasjit S. Suri,et al.  Relationship between leukoaraiosis, carotid intima-media thickness and intima-media thickness variability: Preliminary results , 2016, European Radiology.

[76]  U. Rajendra Acharya,et al.  Completely Automated Multiresolution Edge Snapper—A New Technique for an Accurate Carotid Ultrasound IMT Measurement: Clinical Validation and Benchmarking on a Multi-Institutional Database , 2012, IEEE Transactions on Image Processing.

[77]  Jasjit S. Suri,et al.  Symtosis: A liver ultrasound tissue characterization and risk stratification in optimized deep learning paradigm , 2018, Comput. Methods Programs Biomed..

[78]  J. Polak,et al.  Edge-Detected Common Carotid Artery Intima–Media Thickness and Incident Coronary Heart Disease in the Multi-Ethnic Study of Atherosclerosis , 2015, Journal of the American Heart Association.

[79]  Ankush D. Jamthikar,et al.  Global perspective on carotid intima-media thickness and plaque: should the current measurement guidelines be revisited? , 2019, International angiology : a journal of the International Union of Angiology.

[80]  G. Bondjers,et al.  Regional Accumulations of T Cells, Macrophages, and Smooth Muscle Cells in the Human Atherosclerotic Plaque , 1986, Arteriosclerosis.