Application of spectral analysis technques to Doppler signals and classification by artificial neural networks

Doppler ultrasonography is known as a reliable technique, which demonstrates the flow characteristics and resistance of arteries in various arterial disease. In this study, spectral analysis of ophthalmic arterial Doppler signals obtained from subjects having Behcet, uveitis disease and internal carotid arterial Doppler signals obtained from subjects having internal carotid artery stenosis, occlusion were performed by classical (fast Fourier transform based methods) and model based (autoregressive, moving average and autoregressive moving average) techniques. By using these spectral analysis techniques, power spectral densities and sonograms of ophthalmic and internal carotid arterial Doppler signals were obtained. These power spectral densities and sonograms were then used to compare the applied methods in terms of their frequency resolution and the effects in determination of flow characteristics in ophthalmic and internal carotid arteries. In this study, it has been determined that power spectral densities and sonograms obtained by autoregressive and autoregressive moving average methods give reliable information on hemodynamic alterations in ophthalmic and internal carotid arteries. Classification of ophthalmic arterial and internal carotid arterial Doppler signals were done by multilayer perceptron neural network trained with backpropagation algorithm. Ophthalmic artery stenosis, internal carotid artery stenosis and internal carotid artery occlusion were detected by the performed classification. TheIV classification results and the values of statistical parameters indicated that the classifications of ophthalmic arterial and internal carotid arterial Doppler signals were feasible by multilayer perceptron neural network trained with backpropagation algorithm. Science Code : 705 Key Words : Doppler signal, Spectral analysis, Power spectral density, Sonogram, Ophthalmic artery, Internal carotid artery, Behcet disease, Uveitis disease, Stenosis, Occlusion, Backpropagation artificial neural network