Name
Title | ||
|---|---|---|
Multiscale energy and eigenspace approach to Detection and Localization of Myocardial Infarction |
Abstract | ||
|---|---|---|
In this paper, a novel technique on multiscale energy and eigenspace (MEES) approach is proposed for detection and localization of myocardial infarction from multilead electrocardiogram (ECG). Wavelet decomposition of multilead ECG signals grossly segments the clinical components at different subbands. In myocardial infarction, pathological characteristics such as hypercute T-wave, inversion of T-wave, changes in ST elevation or pathological Q-wave are seen in ECG signals. These pathological information alter the covariance structures of multiscale multivariate matrices at different scales and the corresponding eigenvalues. The clinically relevant components can be captured by eigenvalues. In this work, multiscale wavelet energies and eigenvalues of multiscale covariance matrices are used as diagnostic features. Support vector machine (SVM) with both linear and radial basis function (RBF) kernel and K-nearest neighbor (KNN) are used as classifier. Data sets, which include healthy control (HC), various types of myocardial infarction: anterior, anterio-lateral, anterio-septal, inferior, inferio-lateral and inferio-posterio-lateral, from PTB diagnostic ECG database are used for evaluation. The results show that the proposed technique can successfully detect the MI pathologies. The MEES approach also helps localize different types of myocardial infarctions. For MI detection, the accuracy, the sensitivity and the specificity values are as 96%, 93% and 99% respectively. The localization accuracy is 99.58%, using multiclass SVM classifier with RBF kernel. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/TBME.2015.2405134 | Biomedical Engineering, IEEE Transactions |
Keywords | Field | DocType |
covariance,ecg,knn,multilead ecg,multiscale eigenvalues,multiscale wavelet energy,myocardial infarction,rbf,support vector machine,sensitivity,pathology,muscle,k nearest neighbor,matrix decomposition,eigenvalues,radial basis function,wavelet transforms,support vector machines | Kernel (linear algebra),Radial basis function,Pattern recognition,Radial basis function kernel,Computer science,Support vector machine,Matrix decomposition,Artificial intelligence,Wavelet transform,Covariance,Wavelet | Journal |
Volume | Issue | ISSN |
PP | 99 | 0018-9294 |
Citations | PageRank | References |
30 | 1.17 | 9 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| L. N. Sharma | 1 | 118 | 10.04 |
| Tripathy, R.K. | 2 | 59 | 5.09 |
| S. Dandapat | 3 | 261 | 28.51 |