No abstract

No abstract

No abstract

No abstract

No abstract

Myocardial perfusion imaging (MPI) is a widely used and non-invasive diagnostic method for the detection of patients with suspected or known ischemic heart disease. MPI test is commonly realized by single photon emission computed tomography (SPECT). This test provides several images illustrating the function of the heart muscle. Appropriate segmentation of those images play a crucial role for the diagnosis of heart disease. Consequently, this paper proposes a segmentation method for 2D myocardial perfusion SPECT images acquired in both stress and rest cases. In this way, an expert can make visual assessment of the changes in the stress and rest images easily. Hence, possible heart diseases would be identified based on those changes without a need of using polar maps or reference databases.

Cardiac arrhythmia refers to abnormal activity of the heart. Correct classification of cardiac arrhythmia is, therefore, crucial for the appropriate treatment of heart diseases. In this paper, a novel approach is proposed for cardiac arrhythmia classification. Initially, the feature vectors extracted from raw electrocardiogram (ECG) signals are projected into a particular subspace obtained via the Common Vector Approach, which is an effective subspace method. The projected vectors are then fed into two distinct decision-tree-based classifiers-namely, C4.5 and random forest. The results obtained from the proposed approach are compared with those obtained with the original feature vectors using the same classifiers. For this purpose, the well-known MIT-BIH arrhythmia database was utilized. Six different sets of features based on QRS, time-domain, wavelet transform, and power spectral density are derived from ECG signals in this database. The feature sets are then used in the classification of five main beat types including non-ectopic, ventricular ectopic, supraventricular ectopic, fusion, and unknown. The experimental results reveal that the recognition performances achieved by most of the projected features are explicitly higher than those obtained with the original ones. In addition, the classification accuracy of the proposed approach climbs to 100% for the test set.