Delineation of T-wave in ECG by wavelet transform using multiscale differential operator. Chen, P., Lee, S., & Kuo, C. IEEE transactions on bio-medical engineering, 53(7):1429-33, 7, 2006.
Delineation of T-wave in ECG by wavelet transform using multiscale differential operator. [pdf]Paper  Delineation of T-wave in ECG by wavelet transform using multiscale differential operator. [link]Website  abstract   bibtex   
This paper proposes an improved wavelet-based method for the delineation of T wave in the electrocardiogram by using multiscale dif-operator (MDO). MDO was employed to automatically categorize the T wave into one of the three categories of T wave morphologies and to improve the precision of T wave delineation for each category. The new algorithm was evaluated on QT database (QTDB) and new annotations of 2160 beats from QTDB were performed by two cardiologists. To evaluate the performance of the wave delineation, the time differences between automatic detection versus cardiologists' annotations and intercardiologist differences were measured. The new algorithm can attain better results than the previous methods by achieving the smallest standard deviation of the differences and qualifying the strict error criterion for T-off measurement. This new algorithm also exhibited excellent T wave categorization agreement with the cardiologists, resulting in kappa values above 0.75.
@article{
 title = {Delineation of T-wave in ECG by wavelet transform using multiscale differential operator.},
 type = {article},
 year = {2006},
 identifiers = {[object Object]},
 keywords = {Algorithms,Arrhythmias, Cardiac,Arrhythmias, Cardiac: diagnosis,Arrhythmias, Cardiac: physiopathology,Diagnosis, Computer-Assisted,Diagnosis, Computer-Assisted: methods,Electrocardiography,Electrocardiography: methods,Humans,Reproducibility of Results,Sensitivity and Specificity,Signal Processing, Computer-Assisted},
 pages = {1429-33},
 volume = {53},
 websites = {http://www.ncbi.nlm.nih.gov/pubmed/16830948},
 month = {7},
 id = {673599e4-3592-37dd-8e34-ed6fab844552},
 created = {2014-03-14T12:18:45.000Z},
 file_attached = {true},
 profile_id = {5e73f9af-1f10-3a70-a285-d3fbb699efe2},
 group_id = {e134fb94-8118-3ebe-b82d-bfbf0a8ae633},
 last_modified = {2014-05-12T05:46:35.000Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 abstract = {This paper proposes an improved wavelet-based method for the delineation of T wave in the electrocardiogram by using multiscale dif-operator (MDO). MDO was employed to automatically categorize the T wave into one of the three categories of T wave morphologies and to improve the precision of T wave delineation for each category. The new algorithm was evaluated on QT database (QTDB) and new annotations of 2160 beats from QTDB were performed by two cardiologists. To evaluate the performance of the wave delineation, the time differences between automatic detection versus cardiologists' annotations and intercardiologist differences were measured. The new algorithm can attain better results than the previous methods by achieving the smallest standard deviation of the differences and qualifying the strict error criterion for T-off measurement. This new algorithm also exhibited excellent T wave categorization agreement with the cardiologists, resulting in kappa values above 0.75.},
 bibtype = {article},
 author = {Chen, Po-Ching and Lee, Steven and Kuo, Cheng-Deng},
 journal = {IEEE transactions on bio-medical engineering},
 number = {7}
}
Downloads: 0