Identification of Ultrasonic Echolucent Carotid Plaques Using Discrete Fréchet Distance Between Bimodal Gamma Distributions

An accurate and explainable ensemble learning method for carotid plaque prediction in an asymptomatic population

BACKGROUND AND OBJECTIVE

The identification of carotid plaque, one of the most crucial tasks in stroke screening, is of great significance in the assessment of subclinical atherosclerosis and preventing the onset of stroke. However, traditional ultrasound examination is not prevalent or cost-effective for asymptomatic people, particularly low-income individuals in rural areas. Thus, it is necessary to develop an accurate and explainable model for early identification of the risk of plaque prevalence that can help in the primary prevention of stroke.

METHODS

We developed an ensemble learning method to predict the occurrence of carotid plaques. A dataset comprising 1440 subjects (50% with plaques and 50% without plaques) and ten-fold cross-validation were utilized to evaluate the model performance. Four machine learning methods (extreme gradient boosting (XGBoost), gradient boosting decision tree, random forest, and support vector machine) were evaluated. Subsequently, the interpretability of the XGBoost model, which provided the best performance, was analyzed from three aspects: feature importance, feature effect on prediction model, and feature effect on prediction decision for a specific subject.

RESULTS

The XGBoost algorithm provided the best performance (sensitivity: 0.8678, specificity: 0.8592, accuracy: 0.8632, F1 score: 0.8621, area under the curve: 0.8635) in carotid plaque prediction and also had excellent performance under missing data circumstances. Further, interpretability analysis showed that the decisions of the XGBoost model were highly congruent with clinical knowledge.

CONCLUSION

The model results are superior to those of state-of-the-art methods. Thus, it is a promising carotid plaque prediction tool that could be used in the primary prevention of stroke.

Object-Specific Four-Path Network for Stroke Risk Stratification of Carotid Arteries in Ultrasound Images

Atherosclerotic carotid plaques have been shown to be closely associated with the risk of stroke. Since patients with symptomatic carotid plaques have a greater risk for stroke, stroke risk stratification based on the classification of carotid plaques into symptomatic or asymptomatic types is crucial in diagnosis, treatment planning, and medical treatment monitoring. A deep learning technique would be a good choice for implementing classification. Usually, to acquire a high-accuracy classification, a specific network architecture needs to be designed for a given classification task. In this study, we propose an object-specific four-path network (OSFP-Net) for stroke risk assessment by integrating ultrasound carotid plaques in both transverse and longitudinal sections of the bilateral carotid arteries. Each path of the OSFP-Net comprises of a feature extraction subnetwork (FE) and a feature downsampling subnetwork (FD). The FEs in the four paths use the same network structure to automatically extract features from ultrasound images of carotid plaques. The FDs use different object-specific pooling strategies for feature downsampling based on the observation that the sizes and shapes in the feature maps obtained from FEs should be different. The object-specific pooling strategies enable the network to accept arbitrarily sized carotid plaques as input and to capture a more informative context for improving the classification accuracy. Extensive experimental studies on a clinical dataset consisting of 333 subjects with 1332 carotid plaques show the superiority of our OSFP-Net against several state-of-the-art deep learning-based methods. The experimental results demonstrate better clinical agreement between the ground truth and the prediction, which indicates its great potential for use as a risk stratification and as a monitoring tool in the management of patients at risk for stroke.

Multilevel Strip Pooling-Based Convolutional Neural Network for the Classification of Carotid Plaque Echogenicity

Carotid plaque echogenicity in ultrasound images has been found to be closely correlated with the risk of stroke in atherosclerotic patients. The automatic and accurate classification of carotid plaque echogenicity is of great significance for clinically estimating the stability of carotid plaques and predicting cardiovascular events. Existing convolutional neural networks (CNNs) can provide an automatic carotid plaque echogenicity classification; however, they require a fixed-size input image, while the carotid plaques are of varying sizes. Although cropping and scaling the input carotid plaque images is promising, it will cause content loss or distortion and hence reduce the classification accuracy. In this study, we redesign the spatial pyramid pooling (SPP) and propose multilevel strip pooling (MSP) for the automatic and accurate classification of carotid plaque echogenicity in the longitudinal section. The proposed MSP module can accept arbitrarily sized carotid plaques as input and capture a long-range informative context to improve the accuracy of classification. In our experiments, we implement an MSP-based CNN by using the visual geometry group (VGG) network as the backbone. A total of 1463 carotid plaques (335 echo-rich plaques, 405 intermediate plaques, and 723 echolucent plaques) were collected from Zhongnan Hospital of Wuhan University. The 5-fold cross-validation results show that the proposed MSP-based VGGNet achieves a sensitivity of 92.1%, specificity of 95.6%, accuracy of 92.1%, and F1-score of 92.1%. These results demonstrate that our approach provides a way to enhance the applicability of CNN by enabling the acceptance of arbitrary input sizes and improving the classification accuracy of carotid plaque echogenicity, which has a great potential for an efficient and objective risk assessment of carotid plaques in the clinic.

Machine Learning Quantitation of Cardiovascular and Cerebrovascular Disease: A Systematic Review of Clinical Applications

Research into machine learning (ML) for clinical vascular analysis, such as those useful for stroke and coronary artery disease, varies greatly between imaging modalities and vascular regions. Limited accessibility to large diverse patient imaging datasets, as well as a lack of transparency in specific methods, are obstacles to further development. This paper reviews the current status of quantitative vascular ML, identifying advantages and disadvantages common to all imaging modalities. Literature from the past 8 years was systematically collected from MEDLINE^® and Scopus database searches in January 2021. Papers satisfying all search criteria, including a minimum of 50 patients, were further analysed and extracted of relevant data, for a total of 47 publications. Current ML image segmentation, disease risk prediction, and pathology quantitation methods have shown sensitivities and specificities over 70%, compared to expert manual analysis or invasive quantitation. Despite this, inconsistencies in methodology and the reporting of results have prevented inter-model comparison, impeding the identification of approaches with the greatest potential. The clinical potential of this technology has been well demonstrated in Computed Tomography of coronary artery disease, but remains practically limited in other modalities and body regions, particularly due to a lack of routine invasive reference measurements and patient datasets.

Carotid artery ultrasound image analysis: A review of the literature

Stroke is one of the prominent causes of death in the recent days. The existence of susceptible plaque in the carotid artery can be used in ascertaining the possibilities of cardiovascular diseases and long-term disabilities. The imaging modality used for early screening of the disease is B-mode ultrasound image of the person in the artery area. The objective of this article is to give a widespread review of the imaging modes and methods used for studying the carotid artery for identifying stroke, atherosclerosis and related cardiovascular diseases. We encompass the review in methods used for artery wall tracking, intima-media, and lumen segmentation which will help in finding the extent of the disease. Due to the characteristics of the imaging modality used, the images have speckle noise which worsens the image quality. Adaptive homomorphic filtering with wavelet and contourlet transforms, Levy Shrink, gamma distribution were used for image denoising. Learning-based neural network approaches for denoising give better edge preservation. Domain knowledge-based segmentation approaches have proved to provide more accurate intima-media thickness measurements. There is a requirement of useful fully automatic segmentation approaches, 3D, 4D systems, and plaque motion analysis. Taking into consideration the image priors like geometry, imaging physics, intensity and temporal data, image analysis has to be performed. Encouragingly more research has focused on content-specific segmentation and classification techniques. With the evaluation of machine learning algorithms, classifying the image as with or without a fat deposit has gained better accuracy and sensitivity. Machine learning-based approaches like self-organizing map, k-nearest neighborhood and support vector machine achieve promising accuracy and sensitivity in classification. The literature reveals that there is more scope in identifying a patient-specific model in a fully automatic manner.

Assessment of Carotid Artery Plaque Components With Machine Learning Classification Using Homodyned-K Parametric Maps and Elastograms

Quantitative ultrasound (QUS) imaging methods, including elastography, echogenicity analysis, and speckle statistical modeling, are available from a single ultrasound (US) radio-frequency data acquisition. Since these US imaging methods provide complementary quantitative tissue information, characterization of carotid artery plaques may gain from their combination. Sixty-six patients with symptomatic ( n = 26 ) and asymptomatic ( n = 40 ) carotid atherosclerotic plaques were included in the study. Of these, 31 underwent magnetic resonance imaging (MRI) to characterize plaque vulnerability and quantify plaque components. US radio-frequency data sequence acquisitions were performed on all patients and were used to compute noninvasive vascular US elastography and other QUS features. Additional QUS features were computed from three types of images: homodyned-K (HK) parametric maps, Nakagami parametric maps, and log-compressed B-mode images. The following six classification tasks were performed: detection of 1) a small area of lipid; 2) a large area of lipid; 3) a large area of calcification; 4) the presence of a ruptured fibrous cap; 5) differentiation of MRI-based classification of nonvulnerable carotid plaques from neovascularized or vulnerable ones; and 6) confirmation of symptomatic versus asymptomatic patients. Feature selection was first applied to reduce the number of QUS parameters to a maximum of three per classification task. A random forest machine learning algorithm was then used to perform classifications. Areas under receiver-operating curves (AUCs) were computed with a bootstrap method. For all tasks, statistically significant higher AUCs were achieved with features based on elastography, HK parametric maps, and B-mode gray levels, when compared to elastography alone or other QUS alone ( ). For detection of a large area of lipid, the combination yielding the highest AUC (0.90, 95% CI 0.80-0.92, ) was based on elastography, HK, and B-mode gray-level features. To detect a large area of calcification, the highest AUC (0.95, 95% CI 0.94-0.96, ) was based on HK and B-mode gray level features. For other tasks, AUCs varied between 0.79 and 0.97. None of the best combinations contained Nakagami features. This study shows the added value of combining different features computed from a single US acquisition with machine learning to characterize carotid artery plaques.