No abstract

No abstract

In this paper, we present a new method for detection of septal defects from cardiac sound signals using tunable-Q wavelet transform (TQWT). To begin with, the cardiac sound signals have been segmented into heart beat cycles using constrained TQWT based approach. In order to extract the timefrequency domain based features, TQWT based decomposition of heart beat cycles has been performed up to sixth stage. The murmurs have more fluctuations than heart sounds. Therefore, to characterize murmurs in cardiac sound signals, proposed feature set was formed with fluctuation indices that have been computed from reconstruction of decomposed sub-bands. Then, this feature set containing twenty one features has been used to classify cardiac sound signals for detection of septal defects. In order to validate the usefulness of the proposed method for diagnosis of septal defects, besides cardiac sound signals for septal defects and normal, this study also considers signals to be detected for valvular defects and other defects like ventricular hypertrophy, constrictive pericarditis etc. The classification has been performed using least squares support vector machine (LS-SVM) with radial basis (RBF) kernel function. In order to tune the quality-factor (Q) of the TQWT to provide highest classification accuracy, the experiment has been conducted with varying value of Q. The experimental results show that the proposed method has provided significant classification performance at Q = 2 for various clinical cases as comprised in the publicly available datasets. The test results demonstrate classification accuracy of 91.75% with sensitivity of 88.23% and specificity of 96.48% at Q = 2.

This work presents a new method for detection of atrial fibrillation using predictors derived from Fourier-Bessel (FB) expansion and Teager energy operator (TEO) which are applied strategically on electrocardiogram (ECG) signals. The proposed method begins by extracting a set of direct and indirect predictors. The direct predictors are computed from pre-processed ECG signals themselves. A part of indirect predictors are computed from (a) RR-interval and heart rate (HR) signals, and (b) FB expansion along with its spectrum applied on RR and HR signals. The rationale of using FB expansion is that the clinical information is found to be more evident in the FB coefficients (FBC) and their spectrum than that of RR and HR signals themselves. In the same line of thought, TEO is applied on preprocessed ECG, RR-interval, HR signals, said FBC and their spectrum to obtain the other part of predictors. In all, 47 predictors are computed and subsequently they are fed to an ensemble system of bagged decision trees for classifying the ECG recordings. When evaluated with 2017 PhysioNet/CinC Challenge dataset (Phase II subset), the experimental outcomes demonstrate the F 1 scores of Normal, AF and other classes as: 90.89 %, 80.07%, 72.24% respectively with overall F 1 score of 81% for the hidden test data.

A 35-year-old menstruating woman presented with exertional angina, and was diagnosed with an unruptured left sinus of Valsalva and a noncoronary sinus of Valsalva aneurysm. Hypereosinophilia and coronary artery occlusion was also observed; this association is extremely rare.