Related Experiment Videos
Computer analysis and pattern recognition of Doppler blood flow spectra for disease classification in the lower limb
L Allard1, Y E Langlois, L G Durand
1Biomedical Engineering Laboratory, Clinical Research Institute of Montreal, Québec, Canada.
Insights
A new computer method objectively classifies lower limb artery disease using Doppler ultrasound signals. This pattern recognition system achieved 83% accuracy, outperforming human interpretation for detecting arterial stenosis.
Area of Science:
- Medical Imaging
- Biomedical Engineering
- Cardiovascular Diagnostics
Background:
- Noninvasive ultrasonic duplex scanning is crucial for evaluating lower limb artery disease.
- Objective classification of arterial stenosis severity remains a challenge.
- Visual interpretation of Doppler spectrograms can be subjective and less accurate.
Purpose of the Study:
- To develop and validate a computer processing method for objective classification of lower limb arterial disease.
- To compare the performance of the automated system against human interpretation and conventional arteriography.
- To assess the system's ability to accurately categorize stenosis severity.
Main Methods:
- Analysis of Doppler blood flow signals and extraction of diagnostic features from Doppler spectrograms.
- Utilized frequency features, spectral broadening indices, and power spectrogram amplitudes.
- Employed a pattern recognition method based on the Bayes model for classification into 0-19%, 20-49%, and 50-99% diameter reduction categories.
Main Results:
- Two classification schemes achieved overall accuracies of 83% (Kappa = 0.42) and 81% (Kappa = 0.35).
- The automated system demonstrated superior performance compared to technologist visual interpretation (accuracy = 76%, Kappa = 0.33), particularly for mild lesions (0-19%).
- High specificity (99% and 98%) was achieved for detecting hemodynamically significant stenoses (50-99% lesions).
Conclusions:
- A computer processing method using pattern recognition can objectively and accurately classify lower limb arterial stenosis.
- This automated approach offers improved diagnostic performance over subjective visual interpretation of Doppler spectrograms.
- The developed system represents a significant advancement in the noninvasive assessment of peripheral arterial disease.
Abstract:
In the present study, a computer processing method was developed to objectively classify disease in the lower limb arteries evaluated by noninvasive ultrasonic duplex scanning. This method analyzes Doppler blood flow signals, extracts diagnostic features from Doppler spectrograms and classifies the severity of the disease into three categories of diameter reduction (0-19%, 20-49% and 50-99%). The features investigated were based on frequency features obtained at peak systole, spectral broadening indices and normalized amplitudes of the power spectrogram computed in various positive and negative frequency bands. A total of 379 arterial segments studied from the aorta to the popliteal artery were classified using a pattern recognition method based on the Bayes model. Two classification schemes using a two-node decision rule were tested. Both schemes gave similar results, the first one provided an overall accuracy of 83% (Kappa = 0.42) and the second an overall accuracy of 81% (Kappa = 0.35) when compared with conventional biplane contrast arteriography. These performances, especially for the 0 to 19% lesion category, are better than the one obtained by the technologist (accuracy = 76% and Kappa = 0.33), based on visual interpretation of the Doppler spectrograms. To recognize hemodynamically significant stenoses (50-99% lesions), the pattern recognition system has a sensitivity and a specificity of 50% and 99%, respectively, using classification scheme I. With classification scheme II, the sensitivity and the specificity are 50% and 98%, respectively. Visual interpretation of the Doppler spectrograms leads to a sensitivity and a specificity of 50% and 98%, respectively. These results are the first to be obtained by a pattern recognition system in classifying lower limb arterial stenoses.