AUTHOR=Shan Dezhi , Wang Siyu , Wang Junjie , Lu Jun , Ren Junhong , Chen Juan , Wang Daming , Qi Peng 

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

JOURNAL=Frontiers in Neurology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2023.1151326

DOI=10.3389/fneur.2023.1151326

ISSN=1664-2295

ABSTRACT=Vulnerable carotid atherosclerotic plaque (CAP) is a significant contributor leading 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
radiomics features associated with neovascularization of CAP and construct a prediction model
for CAP vulnerability based on radiomics features. CTA and clinical data of patients with CAPs
who underwent CTA and CEUS between January 2018 and December 2021 in Beijing Hospital
were retrospectively collected. Data were split into training cohort and testing cohort by 7:3.
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 radiomics 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 curve (ROC), 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. 1316 radiomics features were extracted, and 10 radiomics 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. Radiomics features associated with 
neovascularization of CAP were obtained. The model_RF, utilizing radiomics features extracted 
from CTA, provides a non-invasive and efficient method for accurately predicting the vulnerability 
status of CAP. This model shows great potential in offering clinical guidance for early detection and
improving patient outcomes.