Classification of Internal Carotid Artery Doppler Signals Using Hidden Markov Model and Wavelet Transform with Entropy

Doppler ultrasound has been usually preferred for investigation of the artery conditions in the last two decade, since it is a non-invasive method which is not risky. In this study, a biomedical system based on Discrete Hidden Markov Model (DHMM) has been developed in order to classify the internal carotid artery Doppler signals recorded from 191 subjects (136 of them had suffered from internal carotid artery stenosis and rest of them had been healthy subjects). Developed system comprises of three stages. In the first stage, for feature extraction, obtained Doppler signals were separated to its sub-bands using Discrete Wavelet Transform (DWT). In the second stage, entropy of each sub-band was calculated using Shannon entropy algorithm to reduce the dimensionality of the feature vectors via DWT. In the third stage, the reduced features of carotid artery Doppler signals were used as input patterns of the DHMM classifier. Our proposed method reached 97.38% classification accuracy with 5 fold cross validation (CV) technique. The classification results showed that purposed method is effective for classification of internal carotid artery Doppler signals.