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.