Prospective Prediction of Thin-Cap Fibroatheromas from Baseline Virtual Histology Intravascular Ultrasound Data
Thin-cap fibroatheroma (TCFA) is particularly prone to rupture, which may result in myocardial infarction and death. Virtual histology intravascular ultrasound (VH-IVUS) provides quantitative information about plaque composition and enables TCFA identific
- PDF / 1,133,981 Bytes
- 8 Pages / 439.363 x 666.131 pts Page_size
- 95 Downloads / 148 Views
3
Iowa Institute for Biomedical Imaging and Department of Electrical and Computer Engineering, University of Iowa, Iowa City IA, USA 2 Department of Medicine, Cardiology, Loyola University, Maywood, IL, USA 2nd Department of Internal Medicine of General University Hospital in Prague and Charles University, Prague, Czech Republic [email protected]
Abstract. Thin-cap fibroatheroma (TCFA) is particularly prone to rupture, which may result in myocardial infarction and death. Virtual histology intravascular ultrasound (VH-IVUS) provides quantitative information about plaque composition and enables TCFA identification. However, prospective prediction of future development of TCFA has not been previously possible. The aim of our study was to determine whether subsequent development of TCFA can be predicted from baseline VH-IVUS data. Corresponding VH-IVUS images of baseline and follow-up examinations were identified by a highly automated approach to register IVUS pullback pairs from 24 patients (2,331 image pairs). Next, 20 location-specific VH-based and IVUS-based features including plaque phenotype and morphology, and 15 systemic patient-specific features were extracted and ranked using a support vector machine recursive feature elimination (SVM RFE) technique. SVM was applied to assess the prediction power of different feature sets, by adding the first n-ranked features to the classification procedure (leave-one-patient-out cross validation) iteratively until all features were considered. The experimental results showed that the prospective prediction of TCFA achieves a sensitivity of 72.6% and a specificity of 73.3%, when an optimal set of the five best selected features is used. The results indicate the feasibility of prospective prediction of TCFA formation based on baseline VH-IVUS data.
1 Motivation Thrombotic coronary occlusion after rupture of a thin fibrous cap covering a lipidrich necrotic core (NC) [thin-cap fibroatheroma (TCFA)] is the most common cause of myocardial infarction and death [11]. Virtual histology intravascular ultrasound (VHIVUS) provides quantitative information about plaque composition and enables TCFA identification. The VH-IVUS-derived TCFA is strongly and independently predictive of major adverse cardiac events [3]. However, it is still a daunting challenge to predict whether, and if so, where any TCFA will occur in the future. Pioneer studies have found significant correlations between IVUS-derived morphological features and TCFA treatment outcome (healed or remaining) [7], and between plaque phenotype and increasing c Springer International Publishing Switzerland 2015 N. Navab et al. (Eds.): MICCAI 2015, Part II, LNCS 9350, pp. 603–610, 2015. DOI: 10.1007/978-3-319-24571-3_72
604
L. Zhang et al.
necrotic core (NC) area [4], respectively. However, these correlations do not necessarily imply the ability to successfully predict subsequent development of TCFA. In order to learn how to prospectively predict TCFA, frame-to-frame registration of baseline and follow-up VH-IVUS pullb
Data Loading...
