Heart and Vascular Center, Semmelweis University, Budapest, Hungary
Several morphologic and metabolic adverse plaque characteristics have been linked to rupture prone high-risk plaques (HRP) using intravascular ultrasound (IVUS), optical coherence tomography (OCT) and NaF18-Positron Emission Tomography (NaF18-PET). Previous studies have shown that morphologic vulnerability identified using IVUS and OCT do not necessarily correspond to metabolic vulnerability demonstrated using NaF18-PET. It would be desirable to identify HRP showing morphologic and/or metabolic vulnerability with a widely available, single non-invasive imaging modality.
Therefore our objective was to assess the diagnostic accuracy of coronary computed tomography angiography (CTA) derived radiomic features to recognize morphologic and metabolic plaque vulnerability, as compared to conventional qualitative and quantitative CT metrics.
We analyzed 44 plaques in 25 patients using IVUS, OCT, NaF18-PET and coronary CTA. Next to conventional qualitative and quantitative metrics, 935 radiomic parameters were calculated. Morphologic vulnerability was defined as a plaque with positive remodeling and posterior attenuation on IVUS and thin-cap fibroatheroma or microvessels or macrophage infiltration on OCT. Metabolic vulnerability was defined as >25% NaF18 uptake as compared to a reference lesion. We calculated receiver operating characteristics area under the curve (AUC) values using a 5-fold cross validation with 1000 repeats to estimate the diagnostic accuracy of each parameter.
The best conventional CT metric resulted in an AUC value close to random (AUC=0.52), while the best radiomic feature had a good diagnostic accuracy (AUC=0.74) to identify morphologic vulnerability. Radiomic features also outperformed conventional CT metrics to identify metabolic vulnerability (AUC: 0.87 vs. 0.65; respectively).
Radiomics is capable of identifying both morphologic and metabolic HRP using coronary CTA images. Novel image analytic techniques could pose as a bridge between different modalities, allowing the non-invasive identification of imaging biomarkers of other invasive and non-invasive modalities.
Doctoral School: Basic and Translational Medicine
Program: Cardiovascular Disorders: Physiology and Medicine of Ischaemic Circulatory Diseases
Supervisor: Pál Maurovich-Horvat
E-mail address: email@example.com