Noise cancellation in Doppler ultrasound signals with adaptive neuro-fuzzy inference system

Abstract

Adaptive noise cancellation using adaptive neuro-fuzzy inference system (ANFIS) is proposed for denoising Doppler ultrasound signals. Doppler ultrasound technology has been widely used in the clinic to diagnose vascular diseases for its noninvasive advantage. Therefore, the improvement in the flow velocity estimation performed by Doppler ultrasound blood measurement systems is important in vascular diseases diagnosis. The Doppler ultrasound signals were modeled as the summation of the true velocity signal, a wall motion signal, a clutter signal, and a random noise component. The ophthalmic arterial (OA) Doppler signals recorded from the healthy subjects and subjects suffering from the OA stenosis were used as the test sources. The signal-to-noise ratio (SNR) improvements were studied for the OA Doppler signals. Based on the results (SNR improvements and root mean square - RMS error) of the experiments, it was concluded that the performance of the proposed method is higher than that of the existing methods in the literature for denoising the Doppler ultrasound signals. (C) 2009 Elsevier Inc. All rights reserved.