Logo image
Predicting Locations of High-Risk Plaques in Coronary Arteries in Patients Receiving Statin Therapy
Journal article   Open access   Peer reviewed

Predicting Locations of High-Risk Plaques in Coronary Arteries in Patients Receiving Statin Therapy

Ling Zhang, Andreas Wahle, Zhi Chen, John J Lopez, Tomas Kovarnik and Milan Sonka
IEEE transactions on medical imaging, Vol.37(1), pp.151-161
01/2018
DOI: 10.1109/TMI.2017.2725443
PMCID: PMC5765985
PMID: 28708548
url
https://www.ncbi.nlm.nih.gov/pmc/articles/5765985View
Open Access

Abstract

Features of high-risk coronary artery plaques prone to major adverse cardiac events (MACE) were identified by intravascular ultrasound (IVUS) virtual histology (VH). These plaque features are: thin-cap fibroatheroma (TCFA), plaque burden PB ≥ 70%, or minimal luminal area MLA ≤ 4 mm 2 . Identification of arterial locations likely to later develop such high-risk plaques may help prevent MACE. We report a machine learning method for prediction of future high-risk coronary plaque locations and types in patients under statin therapy. Sixty-one patients with stable angina on statin therapy underwent baseline and one-year follow-up VH-IVUS non-culprit vessel examinations followed by quantitative image analysis. For each segmented and registered VH-IVUS frame pair ({n} =6341 ), location-specific (\approx 0.5 mm) vascular features and demographic information at baseline were identified. Seven independent support vector machine classifiers with seven different feature subsets were trained to predict high-risk plaque types one year later. A leave-one-patient-out cross-validation was used to evaluate the prediction power of different feature subsets. The experimental results showed that our machine learning method predicted future TCFA with correctness of 85.9%, 81.7%, and 77.0% (G-mean) for baseline plaque phenotypes of TCFA, thick-cap fibroatheroma, and non-fibroatheroma, respectively. For predicting PB ≥ 70%, correctness was 80.8% for baseline PB ≥ 70% and 85.6% for 50% ≤ PB <; 70%. Accuracy of predicted MLA ≤ 4 mm 2 was 81.6% for baseline MLA ≤ 4 mm 2 and 80.2% for 4 mm 2 <; MLA ≤ 6 mm 2 . Location-specific prediction of future high-risk coronary artery plaques is feasible through machine learning using focal vascular features and demographic variables. Our approach outperforms previously reported results and shows the importance of local factors on high-risk coronary artery plaque development.
Arteries Atherosclerosis coronary artery disease Imaging intravascular ultrasound machine learning Medical treatment natural history Predictive models prognosis Support vector machines Training Volcanoes

Details

Metrics

Logo image