Coronary Artery Disease (CAD), caused by the buildup of plaque on the inside of the coronary arteries, has a high mortality rate. To efficiently detect this condition from echocardiography images, with lesser inter-observer variability and visual interpretation errors, computer based data mining techniques may be exploited. We have developed and presented one such technique in this paper for the classification of normal and CAD affected cases. A multitude of grayscale features (fractal dimension, entropies based on the higher order spectra, features based on image texture and local binary patterns, and wavelet based features) were extracted from echocardiography images belonging to a huge database of 400 normal cases and 400 CAD patients. Only the features that had good discriminating capability were selected using t-test. Several combinations of the resultant significant features were used to evaluate many supervised classifiers to find the combination that presents a good accuracy. We observed that the Gaussian Mixture Model (GMM) classifier trained with a feature subset made up of nine significant features presented the highest accuracy, sensitivity, specificity, and positive predictive value of 100%. We have also developed a novel, highly discriminative HeartIndex, which is a single number that is calculated from the combination of the features, in order to objectively classify the images from either of the two classes. Such an index allows for an easier implementation of the technique for automated CAD detection in the computers in hospitals and clinics.
Left ventricular motion estimation is very important for diagnosing cardiac abnormality. One of the popular techniques, optical flow technique, promises useful results for motion quantification. However, optical flow technique often failed to provide smooth vector field due to the complexity of cardiac motion and the presence of speckle noise. This chapter proposed a new filtering technique, called quasi-Gaussian discrete cosine transform (QGDCT)-based filter, to enhance the optical flow field for myocardial motion estimation. Even though Gaussian filter and DCT concept have been implemented in other previous researches, this filter introduces a different approach of Gaussian filter model based on high frequency properties of cosine function. The QGDCT is a customized quasi discrete Gaussian filter in which its coefficients are derived from a selected two-dimensional DCT. This filter was implemented before and after the computation of optical flow to reduce the speckle noise and to improve the flow field smoothness, respectively. The algorithm was first validated on synthetic echocardiography image that simulates a contracting myocardium motion. Subsequently, this method was also implemented on clinical echocardiography images. To evaluate the performance of the technique, several quantitative measurements such as magnitude error, angular error, and standard error of measurement are computed and analyzed. The final motion estimation results were in good agreement with the physician manual interpretation.
Objectives: Our objective was to determine the feasibility and early to medium-term outcome of stenting the patent ductus arteriosus at the time of radiofrequency valvotomy in the subgroup of patients with pulmonary atresia with intact ventricular septum and intermediate right ventricle.
Background: Stenting of the patent ductus arteriosus and radiofrequency valvotomy have been proposed as the initial intervention for patients with intermediate right ventricle inasmuch as the sustainability for biventricular circulation or 1½-ventricle repair is unclear in the early period.
Methods: Between January 2001 and April 2009, of 143 patients with pulmonary atresia and intact ventricular septum, 37 who had bipartite right ventricle underwent radiofrequency valvotomy and stenting of the patent ductus arteriosus as the initial procedure. The mean tricuspid valve z-score was -3.8 ± 2.2 and the mean tricuspid valve/mitral valve ratio was 0.62 ± 0.16.
Results: Median age was 10 days (3-65 days) and median weight 3.1 kg (2.4-4.9 kg). There was no procedural mortality. Acute stent thrombosis developed in 1 patient and necessitated emergency systemic-pulmonary shunt. There were 2 early in-hospital deaths owing to low cardiac output syndrome. One late death occurred owing to right ventricular failure after the operation. Survival after the initial procedure was 94% at 6 months and 91% at 5 years. At a median follow-up of 4 years (6 months to 8 years), 17 (48%) attained biventricular circulation with or without other interventions and 9 (26%) achieved 1½-ventricle repair. The freedom from reintervention was 80%, 68%, 58%, and 40% at 1, 2, 3, and 4 years, respectively.
Conclusions: Concomitant stenting of the patent ductus arteriosus at the time of radiofrequency valvotomy in patients with pulmonary atresia with intact ventricular septum and intermediate right ventricle is feasible and safe with encouraging medium-term outcome.