N. Dahdah

Deep feature learning for automatic tissue classification of coronary artery using optical coherence tomography

Kawasaki disease (KD) is an acute childhood disease complicated by coronary artery aneurysms, intima thickening, thrombi, stenosis, lamellar calcifications, and disappearance of the media border. Automatic classification of the coronary artery layers (intima, media, and scar features) is important for analyzing optical coherence tomography (OCT) images recorded in pediatric patients. OCT has been known as an intracoronary imaging modality using near-infrared light which has recently been used to image the inner coronary artery tissues of pediatric patients, providing high spatial resolution (ranging from 10 to 20 μm). This study aims to develop a robust and fully automated tissue classification method by using the convolutional neural networks (CNNs) as feature extractor and comparing the predictions of three state-of-the-art classifiers, CNN, random forest (RF), and support vector machine (SVM). The results show the robustness of CNN as the feature extractor and random forest as the classifier with classification rate up to 96%, especially to characterize the second layer of coronary arteries (media), which is a very thin layer and it is challenging to be recognized and specified from other tissues.

Aspirin Dose and Prevention of Coronary Abnormalities in Kawasaki Disease

This study suggests that low-dose ASA in KD is not inferior to higher doses in reducing the risk of CA abnormalities. BACKGROUND: Acetylsalicylic acid (ASA) is part of the recommended treatment of Kawasaki disease (KD). Controversies remain regarding the optimal dose of ASA to be used. We aimed to evaluate the noninferiority of ASA at an antiplatelet dose in acute KD in preventing coronary artery (CA) abnormalities. METHODS: This is a multicenter, retrospective, nonrandomized cohort study including children 0 to 10 years of age with acute KD between 2004 and 2015 from 5 institutions, of which 2 routinely use low-dose ASA (3–5 mg/kg per day) and 3 use high-dose ASA (80 mg/kg per day). Outcomes were CA abnormalities defined as a CA diameter with a z score ≥2.5. We assessed the risk difference of CA abnormalities according to ASA dose. All subjects received ASA and intravenous immunoglobulin within 10 days of fever onset. RESULTS: There were 1213 subjects included, 848 in the high-dose and 365 in the low-dose ASA group. There was no difference in the risk of CA abnormalities in the low-dose compared with the high-dose ASA group (22.2% vs 20.5%). The risk difference adjusted for potential confounders was 0.3% (95% confidence interval [CI]: −4.5% to 5.0%). The adjusted risk difference for CA abnormalities persisting at the 6-week follow-up was −1.9% (95% CI: −5.3% to 1.5%). The 95% CI of the risk difference of CA abnormalities adjusted for confounders was within the prespecified 5% margin considered to be noninferior. CONCLUSIONS: In conjunction with intravenous immunoglobulin, low-dose ASA in acute KD is not inferior to high-dose ASA for reducing the risk of CA abnormalities.

Natriuretic Peptides in Kawasaki Disease: the Myocardial Perspective

Making a diagnosis of Kawasaki disease with certainty may be challenging, especially since the recognition of cases with incomplete diagnostic criteria and its consequences. In order to build the diagnostic case in daily practice, clinicians rely on clinical criteria established over four decades ago, aided by non specific laboratory tests, and above all inspired by experience. We have recently studied the diagnostic value of N-terminal pro B-type natriuretic peptide to improve the diagnostic certainty of cases with complete or incomplete clinical criteria. Our working hypothesis was based on the fact that myocarditis is present in nearly all Kawasaki disease patients supported by histology data. In this paper, we review these facts and the myocardial perspective from the diagnostic and the mechanistic standpoints.

Carotid wall elastography to assess midterm vascular dysfunction secondary to intrauterine growth restriction: feasibility and comparison with standardized intima-media thickness.

Several studies have suggested that intrauterine growth restriction (IUGR) increases the risk of cardiovascular disease and early atherosclerosis. Early detection of arteriopathy is essential to early intervention. Although arterial intima-media thickness (IMT) is considered an index of subclinical atherosclerosis in the adult, its validity in pediatric patients may be limited. We have recently introduced a novel imaging-based biomarker (ImBioMark) to assess intrinsic mechanical features of the arterial wall from B-mode ultrasound data. The aim of the work described here was to evaluate the potential of ImBioMark in investigation of cardiovascular health status at the level of the common carotid artery (CCA) in adolescents born after IUGR. We also compared ImBioMark results with automated IMT measurements, a well-established biomarker used in clinical practice and research. The potential sequelae of IUGR on the CCA were examined in a group of adolescents in comparison with healthy controls. Patients with IUGR (n = 7) were 13.85 ± 0.46 y old; the healthy controls (n = 7) were 14.58 ± 0.80 y old (p = 0.058). Cine loops of the CCA B-mode data were digitally recorded, and the arterial elastic modulus was estimated a posteriori with ImBioMark. IMT of the CCA was automatically calculated using QLAB software (Philips, Andover, MA, USA). All patients had been evaluated in utero in our fetal echocardiographic laboratory. ImBioMark detected a significant increase in CCA stiffness in patients with IUGR as compared with healthy controls: elastic modulus = 90.74 ± 11.86 versus 61.30 ± 15.94 kPa, respectively (p = 0.002). There was, however, no significant difference between patients with IUGR and controls in IMT (0.483 ± 0.067 versus 0.476 ± 0.051 mm, respectively, p = 0.831). The impact of IUGR on CCA wall dynamics was confirmed by ImBioMark. The apparent limitation of IMT measurement in this cohort may be the result of geometric arterial changes, that is, the expected thickening, below the level of detection at this age. As early detection of vascular modulation is essential to early intervention in a population at risk, we now intend to extend ImBioMark to investigate larger pathologic cohorts with various degrees of arteriopathy.

Classification of coronary artery tissues using optical coherence tomography imaging in Kawasaki disease

Intravascular imaging modalities, such as Optical Coherence Tomography (OCT) allow nowadays improving diagnosis, treatment, follow-up, and even prevention of coronary artery disease in the adult. OCT has been recently used in children following Kawasaki disease (KD), the most prevalent acquired coronary artery disease during childhood with devastating complications. The assessment of coronary artery layers with OCT and early detection of coronary sequelae secondary to KD is a promising tool for preventing myocardial infarction in this population. More importantly, OCT is promising for tissue quantification of the inner vessel wall, including neo intima luminal myofibroblast proliferation, calcification, and fibrous scar deposits. The goal of this study is to classify the coronary artery layers of OCT imaging obtained from a series of KD patients. Our approach is focused on developing a robust Random Forest classifier built on the idea of randomly selecting a subset of features at each node and based on second- and higher-order statistical texture analysis which estimates the gray-level spatial distribution of images by specifying the local features of each pixel and extracting the statistics from their distribution. The average classification accuracy for intima and media are 76.36% and 73.72% respectively. Random forest classifier with texture analysis promises for classification of coronary artery tissue.

044 Cardiovascular Response to Exercise Late After Kawasaki Disease

diologist role in counselling about activity options and participation in competitive sport were equivocal (50% recommended, 50% not recommended). CONCLUSION: Guidelines regarding childhood physical activity after Fontan are numerous. Recommendations are often contradictory and important information about specific activity attributes is often absent. Contradictory published recommendations may prevent cardiologists from providing families with clear and consistent recommendations about physical activity for their child.