A Radiomics Approach to Assess High Risk Carotid Plaques: A Non-invasive Imaging Biomarker, Retrospective Study

A deep learning model for carotid plaques detection based on CTA images: a two stepwise early-stage clinical validation study

Objective

To develop a deep learning (DL) model for carotid plaque detection based on CTA images and evaluate the clinical application feasibility and value of the model.

Methods

We retrospectively collected data from patients with carotid atherosclerotic plaques who underwent continuous CTA examinations of the head and neck at a tertiary hospital from October 2020 to October 2022. The model combined ResUNet with the Pyramid Scene Parsing Network (PSPNet) to enhance plaque segmentation. Patient plaques were divided into training, validation, and testing sets in a ratio of 7:1.5:1.5. We analyzed recall (lesion-level sensitivity), sensitivity (patient-level), and precision to evaluate the model's diagnostic performance for carotid plaques. The two stepwise early-stage clinical validation study (Comparison study and Model-human study) was used to simulate real clinical plaque diagnostic scenarios.

Results

In total, 647 patients were included in the dataset, including 475 for training, 86 for validation, and 86 for testing. The DL model based on CTA images showed good precision in plaque diagnosis (validation set: precision = 80.49%, sensitivity = 90.70%, recall = 84.62%; test set: precision = 78.37%, sensitivity = 91.86%, recall = 84.58%). In addition, subgroup analysis of the plaque was carried out in the test set. The model had high accuracy in identifying plaques at different locations (Recall: 83.72, 76.32, 89.25, and 83.02%) and with different morphologies (Recall: 86.03, 79.17%). This model also analyzed the results of different types of plaques and showed good to moderate plaque diagnostic accuracy for different plaque types (Recall: 70.00, 86.87, 84.29%). Especially, in the clinical application scenario analysis, the model's diagnostic results for plaques were found to be higher than those of 4 out of 6 radiologists (p < 0.001). Furthermore, in Model-human Real Clinical Scenarios study, we found that the model improved the radiologists' sensitivity in diagnosing plaques. Additionally, the model's diagnostic time for plaques (6 s) was found to be significantly shorter than that all of radiologists (p < 0.001).

Conclusion

This AI model demonstrated strong clinical potential for carotid plaque detection with improved clinician diagnostic performance, shortening time, and practical implementation in real-world clinical cases.

Radiomics Studies on Ischemic Stroke and Carotid Atherosclerotic Disease: A Reporting Quality Assessment

Objective: To assess the reporting quality of radiomics studies on ischemic stroke, intracranial and carotid atherosclerotic disease using the Image Biomarker Standardization Initiative (IBSI) reporting guidelines with the aim of finding avenues of improvement for future publications. Method: PubMed database was searched to identify relevant radiomics studies. Of 560 articles, 41 original research articles were included in this analysis. Based on IBSI radiomics reporting guidelines, checklists for CT-based and MRI-based studies were created to allow a structured and comprehensive evaluation of each study's adherence to these guidelines. Results: The main topics covered included radiomics studies were ischemic stroke, intracranial artery disease, and carotid atherosclerotic disease. The reporting checklist median score was 17/40 for the 20 CT-based radiomics studies and 22.5/50 for the 20 MRI-based studies. Basic items like imaging modality, region of interest, and image biomarker set utilized were included in all studies. However, details regarding image acquisition and reconstruction, post-acquisition image processing, and image biomarkers computation were inconsistently detailed across studies. Conclusion: The overall reporting quality of the included radiomics studies was suboptimal. These findings underscore a pressing need for improved reporting practices in radiomics research, to ensure validation and reproducibility of results. Our study provides insights into current reporting standards and highlights specific areas where adherence to IBSI guidelines could be significantly improved.

Quality assessment of radiomics models in carotid plaque: a systematic review

Background

Although imaging techniques provide information about the morphology and stability of carotid plaque, they are operator dependent and may miss certain subtleties. A variety of radiomics models for carotid plaque have recently been proposed for identifying vulnerable plaques and predicting cardiovascular and cerebrovascular diseases. The purpose of this review was to assess the risk of bias, reporting, and methodological quality of radiomics models for carotid atherosclerosis plaques.

Methods

A systematic search was carried out to identify available literature published in PubMed, Web of Science, and the Cochrane Library up to March 2023. Studies that developed and/or validated machine learning models based on radiomics data to identify and/or predict unfavorable cerebral and cardiovascular events in carotid plaque were included. The basic information of each piece of included literature was identified, and the reporting quality, risk of bias, and radiomics methodology quality were assessed according the TRIPOD (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis) checklist, the Prediction Model Risk of Bias Assessment Tool (PROBAST), and the radiomics quality score (RQS), respectively.

Results

A total of 2,738 patients from 19 studies were included. The mean overall TRIPOD adherence rate was 66.1% (standard deviation 12.8%), with a range of 45-87%. All studies had a high overall risk of bias, with the analysis domain being the most common source of bias. The mean RQS was 9.89 (standard deviation 5.70), accounting for 27.4% of the possible maximum value of 36. The mean area under the curve for diagnostic or predictive properties of these included radiomics models was 0.876±0.09, with a range of 0.741-0.989.

Conclusions

Radiomics models may have value in the assessment of carotid plaque, the overall scientific validity and reporting quality of current carotid plaque radiomics reports are still lacking, and many barriers must be overcome before these models can be applied in clinical practice.

Computed tomography angiography-based radiomics model to identify high-risk carotid plaques

Background

Extracranial atherosclerosis is one of the major causes of stroke. Carotid computed tomography angiography (CTA) is a widely used imaging modality that allows detailed assessments of plaque characteristics. This study aimed to develop and test radiomics models of carotid plaques and perivascular adipose tissue (PVAT) to distinguish symptomatic from asymptomatic plaques and compare the diagnostic value between radiomics models and traditional CTA model.

Methods

A total of 144 patients with carotid plaques were divided into symptomatic and asymptomatic groups. The traditional CTA model was built by the traditional radiological features of carotid plaques measured on CTA images which were screened by univariate analysis and multivariable logistic regression. We extracted and screened radiomics features from carotid plaques and PVAT. Then, a support vector machine was used for building plaque and PVAT radiomics models, as well as a combined model using traditional CTA features and radiomics features. The diagnostic value between radiomics models and traditional CTA model was compared in identifying symptomatic carotid plaques by Delong method.

Results

The area under curve (AUC) values of traditional CTA model were 0.624 and 0.624 for the training and validation groups, respectively. The plaque radiomics model and PVAT radiomics model achieved AUC values of 0.766, 0.740 and 0.759, 0.618 in the two groups, respectively. Meanwhile, the combined model of plaque and PVAT radiomics features and traditional CTA features had AUC values of 0.883 and 0.840 for the training and validation groups, respectively, and the receiver operating characteristic curves of combined model were significantly better than those of traditional CTA model in the training group (P<0.001) and validation group (P=0.029).

Conclusions

The combined model of the radiomics features of carotid plaques and PVAT and the traditional CTA features significantly contributes to identifying high-risk carotid plaques compared with traditional CTA model.

Radiomics and artificial neural networks modelling for identification of high-risk carotid plaques

Objective

In this study, we aimed to investigate the classification of symptomatic plaques by evaluating the models generated via two different approaches, a radiomics-based machine learning (ML) approach, and an end-to-end learning approach which utilized deep learning (DL) techniques with several representative model frameworks.

Methods

We collected high-resolution magnetic resonance imaging (HRMRI) data from 104 patients with carotid artery stenosis, who were diagnosed with either symptomatic plaques (SPs) or asymptomatic plaques (ASPs), in two medical centers. 74 patients were diagnosed with SPs and 30 patients were ASPs. Sampling Perfection with Application-optimized Contrasts (SPACE) by using different flip angle Evolutions was used for MRI imaging. Repeated stratified five-fold cross-validation was used to evaluate the accuracy and receiver operating characteristic (ROC) of the trained classifier. The two proposed approaches were investigated to train the models separately. The difference in the model performance of the two proposed methods was quantitatively evaluated to find a better model to differentiate between SPs and ASPs.

Results

3D-SE-Densenet-121 model showed the best performance among all prediction models (AUC, accuracy, precision, sensitivity, and F1-score of 0.9300, 0.9308, 0.9008, 0.8588, and 0.8614, respectively), which were 0.0689, 0.1119, 0.1043, 0.0805, and 0.1089 higher than the best radiomics-based ML model (MLP). Decision curve analysis showed that the 3D-SE-Densenet-121 model delivered more net benefit than the best radiomics-based ML model (MLP) with a wider threshold probability.

Conclusion

The DL models were able to accurately differentiate between symptomatic and asymptomatic carotid plaques with limited data, which outperformed radiomics-based ML models in identifying symptomatic plaques.

Computed tomography angiography-based radiomics model for predicting carotid atherosclerotic plaque vulnerability

Vulnerable carotid atherosclerotic plaque (CAP) significantly contributes to ischemic stroke. Neovascularization within plaques is an emerging biomarker linked to plaque vulnerability that can be detected using contrast-enhanced ultrasound (CEUS). Computed tomography angiography (CTA) is a common method used in clinical cerebrovascular assessments that can be employed to evaluate the vulnerability of CAPs. Radiomics is a technique that automatically extracts radiomic features from images. This study aimed to identify radiomic features associated with the neovascularization of CAP and construct a prediction model for CAP vulnerability based on radiomic features. CTA data and clinical data of patients with CAPs who underwent CTA and CEUS between January 2018 and December 2021 in Beijing Hospital were retrospectively collected. The data were divided into a training cohort and a testing cohort using a 7:3 split. According to the examination of CEUS, CAPs were dichotomized into vulnerable and stable groups. 3D Slicer software was used to delineate the region of interest in CTA images, and the Pyradiomics package was used to extract radiomic features in Python. Machine learning algorithms containing logistic regression (LR), support vector machine (SVM), random forest (RF), light gradient boosting machine (LGBM), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and multi-layer perception (MLP) were used to construct the models. The confusion matrix, receiver operating characteristic (ROC) curve, accuracy, precision, recall, and f-1 score were used to evaluate the performance of the models. A total of 74 patients with 110 CAPs were included. In all, 1,316 radiomic features were extracted, and 10 radiomic features were selected for machine-learning model construction. After evaluating several models on the testing cohorts, it was discovered that model_RF outperformed the others, achieving an AUC value of 0.93 (95% CI: 0.88-0.99). The accuracy, precision, recall, and f-1 score of model_RF in the testing cohort were 0.85, 0.87, 0.85, and 0.85, respectively. Radiomic features associated with the neovascularization of CAP were obtained. Our study highlights the potential of radiomics-based models for improving the accuracy and efficiency of diagnosing vulnerable CAP. In particular, the model_RF, utilizing radiomic features extracted from CTA, provides a noninvasive and efficient method for accurately predicting the vulnerability status of CAP. This model shows great potential for offering clinical guidance for early detection and improving patient outcomes.

Prediction of new cerebral ischemic lesion after carotid artery stenting: a high-resolution vessel wall MRI-based radiomics analysis

OBJECTIVES

Carotid artery stenting (CAS) is an established treatment for local stenosis. The most common complication is new ipsilateral ischemic lesions (NIILs). This study aimed to develop models considering lesion morphological and compositional features, and radiomics to predict NIILs.

MATERIALS AND METHODS

One hundred and forty-six patients who underwent brain MRI and high-resolution vessel wall MR imaging (hrVWI) before and after CAS were retrospectively recruited. Lumen and outer wall boundaries were segmented on hrVWI as well as atherosclerotic components. A traditional model was constructed with patient clinical information, and lesion morphological and compositional features. Least absolute shrinkage and selection operator algorithm was performed to determine key radiomics features for reconstructing a radiomics model. The model in predicting NIILs was trained and its performance was tested.

RESULTS

Sixty-one patients were NIIL-positive and eighty-five negative. Volume percentage of intraplaque hemorrhage (IPH) and patients' clinical presentation (symptomatic/asymptomatic) were risk factors of NIILs. The traditional model considering these two features achieved an area under the curve (AUC) of 0.778 and 0.777 in the training and test cohorts, respectively. Twenty-two key radiomics features were identified and the model based on these features achieved an AUC of 0.885 and 0.801 in the two cohorts. The AUCs of the combined model considering IPH volume percentage, clinical presentation, and radiomics features were 0.893 and 0.842 in the training and test cohort respectively.

CONCLUSIONS

Compared with traditional features (clinical and compositional features), the combination of traditional and radiomics features improved the power in predicting NIILs after CAS.

KEY POINTS

• Volume percentage of IPH and symptomatic events were independent risk factors of new ipsilateral ischemic lesions (NIILs). • Radiomics features derived from carotid artery high-resolution vessel wall imaging had great potential in predicting NIILs after CAS. • The combination model with radiomics and traditional features further improved the diagnostic performance than traditional features alone.