DocumentCode
335921
Title
Self-organizing maps in arrhythmia localization from body surface potential mapping
Author
Simelius, K. ; Reinhardt, L. ; Nenonen, J. ; Tierala, I. ; Toivonen, L. ; Katila, T.
Author_Institution
Lab. of Biomed. Eng., Helsinki Univ. of Technol., Espoo, Finland
Volume
1
fYear
1997
fDate
30 Oct-2 Nov 1997
Firstpage
62
Abstract
The authors have developed a novel method for ventricular tachycardia (VT) source localization using body surface potential mapping (BSPM). Kohonen self-organizing maps (SOM) are utilized for the classification of different types of VTs. The method is a two-step process. First, a large number of potential patterns from VT QRS complexes are presented to the SOM. Second, QRS time traces on this SOM are created to find the representative patterns for different types of VT. The localization can be performed using these time traces as a reference. The presented method utilizes both spatial and temporal aspects of the recorded VT to create a representative pattern of the tachycardia. The data was obtained from 27 patients with ventricular tachycardia; 21 were used for the teaching set and 6 for the test set. Results comparable to the well-documented integral map method were obtained in this study
Keywords
electrocardiography; medical signal processing; self-organising feature maps; Kohonen self-organizing maps; VT QRS complexes; arrhythmia localization; body surface potential mapping; electrodiagnostics; potential patterns; teaching set; test set; ventricular tachycardia; Biomedical engineering; Cardiology; Education; Electrocardiography; Electrodes; Hospitals; Laboratories; Self organizing feature maps; Signal mapping; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Engineering in Medicine and Biology Society, 1997. Proceedings of the 19th Annual International Conference of the IEEE
Conference_Location
Chicago, IL
ISSN
1094-687X
Print_ISBN
0-7803-4262-3
Type
conf
DOI
10.1109/IEMBS.1997.754463
Filename
754463
Link To Document