ENHANCEMENT AND SEGMENTATION OF ULTRASOUND IMAGES

Abstract

Diagnostic imaging is an important addition to clinical examination in the case of patients with many common illnesses and provides affective and noninvasive mapping of anatomy and physiology of human being. A large number of disease process influence human body tissue in such a manner as to produce abnormalities which are detectable from the image. The different imaging technologies provide exceptional views of an internal anatomy and functionality of organs, and the trained radiologists quantify and investigate the image. However, the manual analysis of image is a time consuming process and also susceptible to human error. The choice of the best imaging technique to help to solve any particular problem is based on resolution, contrast, speed, convenience, safety. For imaging soft tissues, ultrasound becomes the first choice as it scores high for all of these factors. Ultrasound B-scan imaging has become the most widely used method of imaging soft tissue such as the lungs, liver, rectum, prostate etc. However ultrasound image analysis in general -is complex due to interference patterns called speckle. Speckle can be modeled as random noise (irregular pattern), which degrades the detection of low-contrast lesions and also reduces the ability of a human observer to resolve fine detail. " So the quality of the image can be improved by using speckle reduction (filtering) techniques. The main drawbacks in adaptive techniques are "edge preserving" and "feature preserving". We have implemented the Ridgelet and Curvelet filter (recently proposed methods for image Denoising) to overcome the above drawbacks. Curvelet gave the superior results compared with Ridgelet filter. Image segmentation is a vital step in many advanced imaging technology. Accurate segmentation is required for medical diagnosis, image guided procedure and so on. Due to Relatively low quality of clinical ultrasound images a good ultrasound image segmentation method is very necessary. Because of attenuation, shadowing artifacts and speckle edge based detection is proved popular and successful recently in B-mode image segmentation.