Computer evaluation of Doppler spectral envelope area in patients having a valvular aortic stenosis

The reliability of three algorithms to estimate the maximal and minimal frequency contours of Doppler spectrograms was evaluated in a group of 48 patients. Two algorithms had previously been used in the literature. These are the Modified Threshold Crossing Method and the Hybrid method. The third algorithm is new and is the Maximal Background Noise Threshold Crossing Method. A new approach was also proposed in the present study to estimate the background noise level of Doppler spectrograms. This level was used as a threshold in the computation of the spectral envelopes. Two diagnostic spectral parameters (the spectral envelope area and the systolic velocity integral) extracted from Doppler spectrograms recorded in the left ventricular outflow tract were also evaluated and tested to discriminate between 23 patients having no aortic pressure gradient and 25 patients with a stenotic aortic valve. Results describe the influence of the threshold level used in the Modified Threshold Crossing Method and the Hybrid method on the variability of the spectral contours. It is clearly demonstrated that the variability of minimal frequency contours is higher than that of maximal frequency contours. All three algorithms provided similar diagnostic performances with the spectral envelope area (71% to 73% of correct classifications) while the Maximal Background Noise Threshold Crossing Method and the Hybrid method provided the best results for the systolic velocity integral (69% of correct classifications). Because the systolic velocity integral combined with the continuity equation is used in the literature to evaluate noninvasively the aortic valve area, these results suggest the use of the spectral envelope area instead of the systolic velocity integral.