Premium
Echocardiogram analysis in a pattern recognition framework
Author(s) -
Chu W. K.,
Raeside D. E.,
Chandraratna P. A. N.,
Brown R. E.,
Poehlmann H.
Publication year - 1979
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.594579
Subject(s) - stenosis , medicine , waveform , cardiology , warrant , mitral valve , pattern recognition (psychology) , artificial intelligence , radiology , computer science , telecommunications , radar , economics , financial economics
Echocardiogram analysis is treated in a pattern recognition framework. Anterior mitral leaflet waveforms are classified for the four‐class problem consisting of the classes “normal,” “mitral stenosis,” “mitral valve prolapse,” and “idiopathic hypertrophic subaortic stenosis.” In addition, aortic root waveforms and left ventricular wall waveforms are classified for the two‐class problem consisting of the classes “normal” and “idiopathic hypertrophic subaortic stenosis.” One common method of analysis (Fourier analysis) underlies each classification scheme. Classification accuracy is sufficiently good to warrant the inference that successful automated decision‐making based on the algorithms investigated is feasible.