A Robust Denoising for Medical Ultrasound Image Based on SVR Estimation in Wavelet Domain
Hui Cheng, Wei Tang · 2008
In this paper, we propose a robust method for the suppression of noise in medical ultrasound image by fusing the wavelet denoising technique with support vector regression (SVR). Based on the least squares support vector regression (LS- SVR), a new denoising operator and a new manipulation algorithm of wavelet coefficients are presented by incorporating neighboring coefficients. The proposed method adapts itself to various types of image noise as well as to the preference of the medical expert: a single parameter can be used to balance the preservation of relevant details against the degree of noise reduction. Simulated noise images and real medical ultrasound images are used to evaluate the denoising performance of our proposed algorithm along with another wavelet-based denoising algorithm. Experimental results show that the proposed denoising method outperforms standard wavelet denoising techniques in terms of the signal-to-noise ratio and the prevented details information in most cases.