1
|
Stratification of risk of atherosclerotic plaque using Hu’s moment invariants of segmented ultrasonic images. BIOMED ENG-BIOMED TE 2022; 67:391-402. [DOI: 10.1515/bmt-2021-0044] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/24/2021] [Accepted: 06/21/2022] [Indexed: 11/15/2022]
Abstract
Abstract
Myocardial infarction is one of the major life-threatening diseases. The cause is atherosclerosis i.e. the occlusion of the coronary artery by deposition of plaque on its walls. The severity of plaque deposition in the artery depends on the characteristics of the plaque. Hence, the classification of the type of plaque is crucial for assessing the risk of atherosclerosis and predicting the chances of myocardial infarction. This paper proposes prediction of atherosclerotic risk by non-invasive ultrasound image segmentation and textural feature extraction. The intima-media complex is segmented using a snakes-based segmentation algorithm on the arterial wall in the ultrasound images. Then, the plaque is extracted from the segmented intima-media complex. The features of the plaque are obtained by computing Hu’s moment invariants. Visual pattern recognition independent of position, size, orientation and parallel projection could be done using these moment invariants. For the classification of the features of the plaque, an SVM classifier is used. The performance shows improvement in accuracy using lesser number of features than previous works. The reduction in feature size is achieved by incorporating segmentation in the pre-processing stage. Tenfold cross-validation protocol is used for training and testing the classifier. An accuracy of 97.9% is obtained with only two features. This proposed technique could work as an adjunct tool in quick decision-making for cardiologists and radiologists. The segmentation step introduced in the preprocessing stage improved the feature extraction technique. An improvement in performance is achieved with much less number of features.
Collapse
|
2
|
Yang Q, Guo H, Shi X, Xu X, Zha M, Cai H, Yang D, Huang F, Zhang X, Lv Q, Liu R, Liu X. Identification of Symptomatic Carotid Artery Plaque: A Three-Item Scale Combined Angiography With Optical Coherence Tomography. Front Neurosci 2021; 15:792437. [PMID: 34955737 PMCID: PMC8702715 DOI: 10.3389/fnins.2021.792437] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2021] [Accepted: 11/12/2021] [Indexed: 01/08/2023] Open
Abstract
Introduction: Symptomatic carotid disease conveys a high risk of recurrent stroke. Plaque morphology and specific plaque characteristics are associated with the risk of stroke. This study aimed to evaluate the detailed plaque features by optical coherence tomography (OCT) and develop a simple scale combining clinical indicators, digital subtraction angiography (DSA), and OCT imaging markers to identify symptomatic carotid plaque. Methods: Carotid plaques from consecutive patients who underwent carotid OCT imaging between June 2017 and June 2021 were evaluated. Clinical characteristics, DSA, and OCT data were compared between the symptomatic and asymptomatic groups. Logistic regression was performed to identify the factors associated with symptomatic carotid plaque and to develop a scale. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of the scale. Results: A total of 90 carotid plaques from 90 patients were included (symptomatic 35.6%, asymptomatic 64.4%). Three main factors were found to be associated with symptomatic carotid plaque: high-density lipoprotein cholesterol (HDL-C) <0.925 mmol/L (OR, 4.708; 95% CI, 1.640 to 13.517; P = 0.004), irregular plaque (OR, 4.017; 95% CI, 1.250 to 12.910; P = 0.020), and white thrombus (OR, 4.594; 95% CI, 1.141 to 18.487; P = 0.032). The corresponding score of three items produced a scale with good discrimination (AUC, 0.768; 95% CI, 0.665 to 0.871). The optimal cutoff value of the scale was 1.5 points with 59.4% sensitivity and 84.5% specificity. Conclusion: The three-item scale comprising HDL-C <0.925 mmol/L, angiographical irregular plaque, and white thrombus detected by OCT may provide information to identify symptomatic carotid plaque. Further large-scale studies are required to validate whether the symptomatic carotid plaque scale is clinically valuable in recognizing carotid atherosclerosis in the early stages.
Collapse
Affiliation(s)
- Qingwen Yang
- Department of Neurology, Jinling Hospital, Medical School of Southeast University, Nanjing, China
| | - Hongquan Guo
- Department of Neurology, Jinling Hospital, The First School of Clinical Medicine, Southern Medical University, Nanjing, China
| | - Xuan Shi
- Department of Neurology, Affiliated Jinling Hospital, Medical School of Nanjing University, Nanjing, China
| | - Xiaohui Xu
- Department of Neurology, Affiliated Jinling Hospital, Medical School of Nanjing University, Nanjing, China
| | - Mingming Zha
- Department of Neurology, Jinling Hospital, Medical School of Southeast University, Nanjing, China
| | - Haodi Cai
- Department of Neurology, Jinling Hospital, Medical School of Southeast University, Nanjing, China
| | - Dahong Yang
- Department of Neurology, Jinling Hospital, The First School of Clinical Medicine, Southern Medical University, Nanjing, China
| | - Feihong Huang
- Department of Neurology, Jinling Hospital, The First School of Clinical Medicine, Southern Medical University, Nanjing, China
| | - Xiaohao Zhang
- Department of Neurology, Affiliated Jinling Hospital, Medical School of Nanjing University, Nanjing, China
| | - Qiushi Lv
- Department of Neurology, Jinling Hospital, Medical School of Southeast University, Nanjing, China.,Department of Neurology, Jinling Hospital, The First School of Clinical Medicine, Southern Medical University, Nanjing, China.,Department of Neurology, Affiliated Jinling Hospital, Medical School of Nanjing University, Nanjing, China
| | - Rui Liu
- Department of Neurology, Jinling Hospital, Medical School of Southeast University, Nanjing, China.,Department of Neurology, Jinling Hospital, The First School of Clinical Medicine, Southern Medical University, Nanjing, China.,Department of Neurology, Affiliated Jinling Hospital, Medical School of Nanjing University, Nanjing, China
| | - Xinfeng Liu
- Department of Neurology, Jinling Hospital, Medical School of Southeast University, Nanjing, China.,Department of Neurology, Jinling Hospital, The First School of Clinical Medicine, Southern Medical University, Nanjing, China.,Department of Neurology, Affiliated Jinling Hospital, Medical School of Nanjing University, Nanjing, China
| |
Collapse
|
3
|
Saba L, Sanagala SS, Gupta SK, Koppula VK, Johri AM, Khanna NN, Mavrogeni S, Laird JR, Pareek G, Miner M, Sfikakis PP, Protogerou A, Misra DP, Agarwal V, Sharma AM, Viswanathan V, Rathore VS, Turk M, Kolluri R, Viskovic K, Cuadrado-Godia E, Kitas GD, Sharma N, Nicolaides A, Suri JS. Multimodality carotid plaque tissue characterization and classification in the artificial intelligence paradigm: a narrative review for stroke application. ANNALS OF TRANSLATIONAL MEDICINE 2021; 9:1206. [PMID: 34430647 PMCID: PMC8350643 DOI: 10.21037/atm-20-7676] [Citation(s) in RCA: 36] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/26/2020] [Accepted: 02/25/2021] [Indexed: 12/12/2022]
Abstract
Cardiovascular disease (CVD) is one of the leading causes of morbidity and mortality in the United States of America and globally. Carotid arterial plaque, a cause and also a marker of such CVD, can be detected by various non-invasive imaging modalities such as magnetic resonance imaging (MRI), computer tomography (CT), and ultrasound (US). Characterization and classification of carotid plaque-type in these imaging modalities, especially into symptomatic and asymptomatic plaque, helps in the planning of carotid endarterectomy or stenting. It can be challenging to characterize plaque components due to (I) partial volume effect in magnetic resonance imaging (MRI) or (II) varying Hausdorff values in plaque regions in CT, and (III) attenuation of echoes reflected by the plaque during US causing acoustic shadowing. Artificial intelligence (AI) methods have become an indispensable part of healthcare and their applications to the non-invasive imaging technologies such as MRI, CT, and the US. In this narrative review, three main types of AI models (machine learning, deep learning, and transfer learning) are analyzed when applied to MRI, CT, and the US. A link between carotid plaque characteristics and the risk of coronary artery disease is presented. With regard to characterization, we review tools and techniques that use AI models to distinguish carotid plaque types based on signal processing and feature strengths. We conclude that AI-based solutions offer an accurate and robust path for tissue characterization and classification for carotid artery plaque imaging in all three imaging modalities. Due to cost, user-friendliness, and clinical effectiveness, AI in the US has dominated the most.
Collapse
Affiliation(s)
- Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria (AOU), Cagliari, Italy
| | - Skandha S Sanagala
- CSE Department, CMR College of Engineering & Technology, Hyderabad, India.,CSE Department, Bennett University, Greater Noida, UP, India
| | - Suneet K Gupta
- CSE Department, Bennett University, Greater Noida, UP, India
| | - Vijaya K Koppula
- CSE Department, CMR College of Engineering & Technology, Hyderabad, India
| | - Amer M Johri
- Department of Medicine, Division of Cardiology, Queen's University, Kingston, Ontario, Canada
| | - Narendra N Khanna
- Department of Cardiology, Indraprastha APOLLO Hospitals, New Delhi, India
| | - Sophie Mavrogeni
- Cardiology Clinic, Onassis Cardiac Surgery Center, Athens, Greece
| | - John R Laird
- Heart and Vascular Institute, Adventist Health St. Helena, St Helena, CA, USA
| | - Gyan Pareek
- Minimally Invasive Urology Institute, Brown University, Providence, Rhode Island, USA
| | - Martin Miner
- Men's Health Center, Miriam Hospital Providence, Rhode Island, USA
| | - Petros P Sfikakis
- Rheumatology Unit, National Kapodistrian University of Athens, Greece
| | - Athanasios Protogerou
- Department of Cardiovascular Prevention, National and Kapodistrian University of Athens, Athens, Greece
| | - Durga P Misra
- Department of Clinical Immunology and Rheumatology, SGPGIMS, Lucknow, India
| | - Vikas Agarwal
- Department of Clinical Immunology and Rheumatology, SGPGIMS, Lucknow, India
| | - Aditya M Sharma
- Division of Cardiovascular Medicine, University of Virginia, VA, USA
| | - Vijay Viswanathan
- MV Hospital for Diabetes & Professor M Viswanathan Diabetes Research Centre, Chennai, India
| | - Vijay S Rathore
- Nephrology Department, Kaiser Permanente, Sacramento, CA, USA
| | - Monika Turk
- The Hanse-Wissenschaftskolleg Institute for Advanced Study, Delmenhorst, Germany
| | | | | | | | - George D Kitas
- R & D Academic Affairs, Dudley Group NHS Foundation Trust, Dudley, UK
| | - Neeraj Sharma
- Department of Biomedical Engineering, IIT-BHU, Banaras, UP, India
| | - Andrew Nicolaides
- Vascular Screening and Diagnostic Centre, University of Nicosia, Nicosia, Cyprus
| | - Jasjit S Suri
- Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA, USA
| |
Collapse
|
4
|
Fernandes E Fernandes J, Mendes Pedro L, Gonçalves I. The conundrum of asymptomatic carotid stenosis-determinants of decision and evidence. ANNALS OF TRANSLATIONAL MEDICINE 2020; 8:1279. [PMID: 33178811 PMCID: PMC7607137 DOI: 10.21037/atm-2020-cass-12] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 01/27/2023]
Abstract
Management of asymptomatic carotid disease continues to challenge medical practice and present evidence is often conflicting. Stroke is a significant burden in Public Health and 11% to 15% appear as first neurologic event associated with asymptomatic carotid stenosis. Randomized trials provided support for Guidelines and Recommendations to intervene on asymptomatic stenosis, but at a known cost of a high number of unnecessary operations. Conflicting evidence from natural history studies and the widespread use of proper medical management including risk factors control, lowering-lipid drugs and strict control of arterial hypertension have reduced the incidence of strokes associated to asymptomatic carotid disease challenging established practice. Need to identify vulnerable lesions prone to develop thromboembolic brain events and also vulnerable patients at a higher risk of stroke is necessary and essential to further improve effectiveness of our interventions. After review of published literature on natural history of asymptomatic carotid stenosis, diagnostic methods to identify plaque vulnerability and present-day results of both endarterectomy and stenting, a strategy for management of asymptomatic carotid stenosis is suggested aiming to reduce unnecessary interventions and effectively contribute to stroke prevention.
Collapse
Affiliation(s)
- José Fernandes E Fernandes
- Department of Surgery and Vascular Surgery, Faculty of Medicine University of Lisbon, Lisbon, Portugal.,Santa Maria University Hospital, Lisbon Academic Medical Center, Lisbon, Portugal.,Senior Consultant Vascular Surgeon, Cardiovascular Institute/Hospital da Luz Torres de Lisboa, Lisbon, Portugal
| | - Luis Mendes Pedro
- Senior Consultant Vascular Surgeon, Cardiovascular Institute/Hospital da Luz Torres de Lisboa, Lisbon, Portugal.,Department of Vascular Surgery, Faculty of Medicine University of Lisbon, Lisbon, Portugal.,Vascular Surgery Department, Santa Maria University Hospital, Lisbon Academic Medical Center, Lisbon, Portugal
| | - Isabel Gonçalves
- Cardiology Department, Skåne University Hospital and Clinical Sciences Malmö, Lund University, Sweden
| |
Collapse
|
5
|
SMITHA B, JOSEPH KPAUL. A NEW APPROACH FOR CLASSIFICATION OF ATHEROSCLEROSIS OF COMMON CAROTID ARTERY FROM ULTRASOUND IMAGES. J MECH MED BIOL 2019. [DOI: 10.1142/s0219519419400013] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Background and objectives: The diagnosis of carotid atherosclerosis is of vital importance, as this cardiovascular disease may cause myocardial infarction. One-third of deaths in the world occur due to myocardial infarction, commonly known as heart attack. Atherosclerosis is deposition of plaque in artery wall. It could be detected from the features of intima-media complex of the artery wall. This study proposes a new classification approach to distinguish between symptomatic and asymptomatic plaques using non-invasive carotid B-mode ultrasound images. These two types of plaques have diverse impacts on human life. In the first condition, slowly plaque formation reaches life-threatening condition and the second condition is acute in nature. Hence treatment protocol is to be decided based on the type of plaque. Methods: To locate the intima-media-complex region, the images are segmented using snake-based segmentation algorithm. Several features are extracted using fixed size blocks selected from the segmented region using gray-level co-occurrence matrix. Finally classification is performed using support vector machine. Results: The performance shows improvement in accuracy using lesser number of features than previous works. The reduction in feature size is achieved by incorporating segmentation in the pre-processing stage. In the classifier, 10-fold cross-validation protocol is used for training and testing and an accuracy of 100% is obtained. Conclusion: This proposed technique could work as an adjunct tool in quick decision-making for cardiologists and radiologists.
Collapse
Affiliation(s)
- B. SMITHA
- Department of Electrical Engineering, National Institute of Technology, Calicut 673601, Kerala, India
| | - K. PAUL JOSEPH
- Department of Electrical Engineering, National Institute of Technology, Calicut 673601, Kerala, India
| |
Collapse
|
6
|
Molinari F, Raghavendra U, Gudigar A, Meiburger KM, Rajendra Acharya U. An efficient data mining framework for the characterization of symptomatic and asymptomatic carotid plaque using bidimensional empirical mode decomposition technique. Med Biol Eng Comput 2018; 56:1579-1593. [DOI: 10.1007/s11517-018-1792-5] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2017] [Accepted: 01/13/2018] [Indexed: 10/18/2022]
|
7
|
Perez-Gonzalez J, Arámbula-Cosío F, Guzmán M, Camargo L, Gutierrez B, Mateus D, Navab N, Medina-Bañuelos V. Spatial Compounding of 3-D Fetal Brain Ultrasound Using Probabilistic Maps. ULTRASOUND IN MEDICINE & BIOLOGY 2018; 44:278-291. [PMID: 29107355 DOI: 10.1016/j.ultrasmedbio.2017.09.001] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/11/2017] [Revised: 08/12/2017] [Accepted: 09/01/2017] [Indexed: 06/07/2023]
Abstract
A new method to address the problem of shadowing in fetal brain ultrasound volumes is presented. The proposed approach is based on the spatial composition of multiple 3-D fetal head projections using the weighted Euclidean norm as an operator. A support vector machine, which is trained with optimal textural features, was used to assign weighting according to the posterior probabilities of brain tissue and shadows. Both phantom and real fetal head ultrasound volumes were compounded using previously reported operators and compared with the proposed composition method to validate it. The quantitative evaluations revealed increases in signal-to-noise ratio ≤35% and in contrast-to-noise ratio ≤135% using real data. Qualitative comparisons made by obstetricians indicated that this novel method adequately recovers brain tissue and improves the visibility of the main cerebral structures. This may prove useful both for fetal monitoring and in the diagnosis of brain defects. Overall this new approach outperforms spatial composition methods previously reported.
Collapse
Affiliation(s)
- Jorge Perez-Gonzalez
- Neuroimaging Laboratory, Electrical Engineering Department, Universidad Autónoma Metropolitana, Iztapalapa, Mexico
| | - Fernando Arámbula-Cosío
- Biomedical Imaging Laboratory, Centro de Ciencias Aplicadas y Desarrollo Tecnológico, Universidad Nacional Autónoma de México, Mexico City, Mexico
| | - Mario Guzmán
- Department of Fetal Medicine, Instituto Nacional de Perinatología, Mexico City, Mexico
| | - Lisbeth Camargo
- Department of Fetal Medicine, Instituto Nacional de Perinatología, Mexico City, Mexico
| | - Benjamin Gutierrez
- Department of Child and Adolescent Psychiatry, Psychosomatic and Psychotherapy, Ludwig-Maximilians-Universität, Munich, Germany; Chair for Computer Aided Medical Procedures, Technische Universität München, Munich, Germany
| | - Diana Mateus
- Chair for Computer Aided Medical Procedures, Technische Universität München, Munich, Germany
| | - Nassir Navab
- Chair for Computer Aided Medical Procedures, Technische Universität München, Munich, Germany
| | - Verónica Medina-Bañuelos
- Neuroimaging Laboratory, Electrical Engineering Department, Universidad Autónoma Metropolitana, Iztapalapa, Mexico.
| |
Collapse
|
8
|
Abstract
PURPOSE OF REVIEW The purpose of this review is to update the reader on current concepts of workup and secondary prevention in patients with stroke of undetermined cause. RECENT FINDINGS Clinical research in patients with cryptogenic stroke has been hampered by the lack of standardized, widely accepted diagnostic criteria. The new definition of 'Embolic stroke of undetermined etiology' postulates an embolic mechanism of ischemic stroke. It is based on the exclusion of lacunar infarction by brain imaging, arterial stenosis more than 50% or dissection of the respective brain-supplying artery by computed tomography/magnetic resonance-angiography or ultrasound, atrial fibrillation by at least 24 h EKG monitoring, as well as some rare etiologies such as vasculitis, drug abuse, or coagulopathies. However, it still comprises many patients with atherosclerotic etiologies (but <50% stenosis) as well as covert paroxysmal atrial fibrillation which can be detected by repeated Holter EKG or an implantable device. A patent foramen ovale can be found in up to 58% of cryptogenic stroke patients, but causality in an individual patient remains uncertain and can only be statistically inferred. SUMMARY The new concept of embolic stroke of undetermined etiology enabled three ongoing randomized controlled trials which investigate oral anticoagulation versus aspirin for secondary stroke prevention.
Collapse
|
9
|
Imam YZ, D'Souza A, Malik RA, Shuaib A. Secondary Stroke Prevention: Improving Diagnosis and Management with Newer Technologies. Transl Stroke Res 2016; 7:458-477. [PMID: 27586681 DOI: 10.1007/s12975-016-0494-2] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/19/2016] [Revised: 08/08/2016] [Accepted: 08/15/2016] [Indexed: 12/22/2022]
Abstract
Treatment of hypertension, diabetes, high cholesterol, smoking cessation, and healthy lifestyle have all contributed to the decline in the incidence of vascular disease over the last several decades. Patients who suffer an acute stroke are at a high risk for recurrence. Introduction of newer technologies and their wider use allows for better identification of patients in whom the risk of recurrence following an acute stroke may be very high. Traditionally, the major focus for diagnosis and management has focused on patient history, examination, imaging for carotid stenosis/occlusion, and detection of AF and paroxysmal AF (PAF) with 24-48 h cardiac monitoring. This review focuses on the usefulness of three newer investigative tools that are becoming widely available and lead to better prevention. Continuous ambulatory blood pressure measurements for 24 h or longer and 3D Doppler measures of the carotid arteries provide key useful information on the state of vascular health and enhance our ability to monitor the response to preventive therapies. Furthermore, the detection of PAF can be significantly improved with prolonged cardiac monitoring for 3 weeks or longer, enabling the initiation of appropriate prevention therapy. This review will focus on the potential impact and importance of these emerging technologies on the prevention of recurrent stroke in high-risk patients.
Collapse
Affiliation(s)
- Yahia Z Imam
- Neuroscience Institute, Hamad Medical Corporation, Doha, Qatar.,Weill Cornell Medicine in Qatar, Doha, Qatar
| | | | - Rayaz A Malik
- University of Manchester, Manchester, UK.,Weill Cornell Medicine in Qatar, Doha, Qatar
| | - Ashfaq Shuaib
- Neuroscience Institute, Hamad Medical Corporation, Doha, Qatar. .,Division of Neurology, Department of Medicine, University of Alberta, Edmonton, Canada.
| |
Collapse
|