On-line classification of arterial stenosis severity using principal component analysis applied to Doppler ultrasound signals
- 1 August 1982
- journal article
- Published by IOP Publishing in Clinical Physics and Physiological Measurement
- Vol. 3 (3) , 191-200
- https://doi.org/10.1088/0143-0815/3/3/003
Abstract
Principal component analysis is a powerful method of feature extraction which can be applied to continuous-wave Doppler waveforms. A microprocessor system for the on-line calculation of the coefficients of principle components has been devised and tested in an experimental model. Doppler waveforms were obtained from positions distal to stenoses of known severity implanted in the iliac arteries of three dogs and classified into one of four groups. By reference to data from a previous series of experiments the microprocessor correctly classified 75% of stenoses. The remaining 25% were all classified as being one group more severe than they actually were.Keywords
This publication has 3 references indexed in Scilit:
- The effect of proximal stenosis on Doppler waveforms: a comparison of three methods of waveform analysis in an animal modelClinical Physics and Physiological Measurement, 1981
- Real-time calculation of ultrasonic pulsatility indexMedical & Biological Engineering & Computing, 1981
- Objective feature extraction applied to the diagnosis of carotid artery disease using a Doppler ultrasound techniqueClinical Physics and Physiological Measurement, 1980