Performance Analysis of Speckle Reduction Filtering algorithms in B-Mode Ultrasound Images

Medical field is enriched with various imaging modalities that help experts for analyzing and diagnosis of the diseases. Among them, Computer Tomography(CT), X-rays, Magnetic Resonance Imaging(MRI), Ultrasound(US) are popular practices that have great impact on the lives. Almost all the medical images are contaminated by noise while capturing the image and they pose huge difficulty for the interpretation of the details in the images. Automating various medical image tasks including prediction, classification, segmentation of certain region of interests require preprocessing of these images. Major task in preprocessing steps are noise removal and image enhancement. Ultrasonography is a non-invasive and inexpensive technique for obtaining cross sectional views of the different organs, visualizing blood vessels, tissues and detecting abnormal masses. Speckle noise intrinsically present in ultrasound images, are multiplicative unlike additive Gaussian noise. Images corrupted with noise degrades the image quality and reduces the accuracy in their interpretation. This paper is a comparative study on various denoising techniques that reduce the speckle noise present in B-mode US images. Different image quality metrics like Speckle suppression index(SSI), Peak signal to noise ratio(PSNR), and Structural similarity index measure(SSIM) are used to effectively measure the performance of the methods discussed.