Plaque Tissue Morphology-Based Stroke Risk Stratification Using Carotid Ultrasound: A Polling-Based PCA Learning Paradigm

Abstract

Severe atherosclerosis disease in carotid arteries causes stenosis which in turn leads to stroke. Machine learning systems have been previously developed for plaque wall risk assessment using morphology-based characterization. The fundamental assumption in such systems is the extraction of the grayscale features of the plaque region. Even though these systems have the ability to perform risk stratification, they lack the ability to achieve higher performance due their inability to select and retain dominant features. This paper introduces a polling-based principal component analysis (PCA) strategy embedded in the machine learning framework to select and retain dominant features, resulting in superior performance. This leads to more stability and reliability. The automated system uses offline image data along with the ground truth labels to generate the parameters, which are then used to transform the online grayscale features to predict the risk of stroke. A set of sixteen grayscale plaque features is computed. Utilizing the cross-validation protocol (K = 10), and the PCA cutoff of 0.995, the machine learning system is able to achieve an accuracy of 98.55 and 98.83%corresponding to the carotidfar wall and near wall plaques, respectively. The corresponding reliability of the system was 94.56 and 95.63%, respectively. The automated system was validated against the manual risk assessment system and the precision of merit for same cross-validation settings and PCA cutoffs are 98.28 and 93.92%for the far and the near wall, respectively.PCA-embedded morphology-based plaque characterization shows a powerful strategy for risk assessment and can be adapted in clinical settings.

Morphological Carotid Plaque Area Is Associated With Glomerular Filtration Rate: A Study of South Asian Indian Patients With Diabetes and Chronic Kidney Disease

“…78,102 Grayscale morphological plaque features or tissue characterization has shown powerful results for risk stratification. 103 –107 Machine learning and extreme learning machines has recently shown that CVD risk stratification by the amalgamation of this morphological grayscale feature with phenotype measurements leads to higher accuracy for risk stratification. 65,108 Total plaque area is one of the key features which can be amalgamated with grayscale plaque features for the online risk stratification using the machine learning paradigm.…”

Cerebral Small Vessel Disease: A Review Focusing on Pathophysiology, Biomarkers, and Machine Learning Strategies

“…More recently, machine learning paradigm has been used for stroke risk stratification using ultrasonic echolucent carotid wall plaque morphology [ 98 ]. In another similar study, stroke risk stratification based on plaque tissue morphology using carotid ultrasound was improved in their performance by embedding pollingbased principal component analysis strategy into the machine learning framework to select and retain dominant features, resulting in superior performance [ 99 ]. Machine learning analyses compute and distinguish one feature from other by trained dataset.…”

Geometric Total Plaque Area Is an Equally Powerful Phenotype Compared With Carotid Intima-Media Thickness for Stroke Risk Assessment: A Deep Learning Approach

“…Our TPA 8,[42][43] by default is only relevant to the longitudinal plane taken from clavicle bone to jaw in the neck region. Even though the carotid artery 28,30 has 3 segments (ICA, Bulb, CCAdistal, CCA-mid, CCA-proximal), our model assumes CCA region for gTPA measurement, along the lines as reported by Spence et al, 14,15 Rundek et al, 16 Mathiesen et al, 17 Herder et al, 18 Kamycheva et al, 19 Romanens et al, 20 and Adams et al 21 Further due to simplicity of projection rates for cIMT, we only consider image-based projection rates for computing the 10-year risk, unlike adding the CCVR factors.…”

“…5,6 The stenosis in the arterial walls can be imaged using several imaging modalities such as magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound (US), of which US offers several advantages such as low cost, user friendliness, and diagnosis. [7][8][9] With advancement in image reconstruction technology such as US beam formation, one can obtain a high resolution US image depicting the arterial lesions. The quantification of these lesions can act as a risk biomarker for carotid artery disease.…”