RobustDespeckling: Robust speckle noise reduction method using multi-scale and kernel fisher discriminant analysis

Abstract

In medical ultrasound imaging, speckle noise is an important property since it usually involves worsening the image resolution along with contrast, thus reducing the diagnostic significance of the imaging modality. The "RobustDespeckling" method, which has been proposed in this study to reduce speckle noise, involves extracting the noise-only signal from the image signal through applying the bidimesional empirical mode decomposition (BEMD) method and wavelet transform (WT) in the encapsulated way. Then, wavelet coefficients are thresholded to filter the noisy coefficients by an optimal threshold parameter that is estimated from kernel fisher discriminant analysis (KFDA). Finally, BEMD and WT processes are employed to obtain a de-noised image. The investigation is conducted by way of upsampling and downsampling operations of ultrasound images to analyze the efficiency of different de-noising techniques including the proposed “RobustDespeckling” method. The visual observation and statistical analysis signify that the “RobustDespeckling” method is robust in minimizing the speckle noise of ultrasound images over existing de-noising techniques. Consequently, the method is more competent to preserve the clarity of the edge without losing the significant image detail.