Research And Realizition On Medical Ultrasonic Image Processing

This paper mainly focused on the medical ultrasonic image. Due to its unique real-time performance, non-destructive property, low cost, high sensitivity and other advantages, medical ultrasonic image is widely used in clinical diagnosis. When it is applied in clinic, it is usual to extract some information of the specific organs and areas, and an indispensable mean for this is image segmentation. We can extract the parts which we are interested in through image segmentation from an ultrasonic image, or find out the location of lesions and its shape. It decides the accuracy of the clinical pathologic analysis, diagnosis and treatment.However, Due to the random disturbance of electronic devices in ultrasonic imaging system, and the effect of the environment, in the process of acquiring image, there will be some noises and distortions which may influence image quality. If we segment the noisy image directly, it may not fit for the requirements of clinical application because of the inaccurate image information. Therefore, we need to take some measures to improve the image quality, for instance, abating each noise, representing target contour, which are called image enhancement technology. Segment an enhanced image can obtain a more exact result, which is the reliable guarantee for the following analysis.This paper briefly described the development of medical ultrasound and the imaging principle, and introduced some existing medical ultrasonic image enhancement algorithms according to ultrasonic image characteristics. These algorithms were put into experiment and a comparison was made among them. Directing toward the advantages and disadvantages of these algorithms, this paper presented a new enhancement method—Adaptive Template Filter Method (ATFM) based on immune genetic algorithm. Unlike conventional filters, where the template shapes and coefficients are fixed, in ATFM, multi-templates were defined and the right template for each pixel can be matched adaptively based on local image characteristics, and the adaptive search ability of immune genetic algorithm with the elitist selection and elitist crossover (IGAE) was used to optimize the parameter t of the transformation function, which guaranteed its rapidity and accuracy.After obtaining a high quality image by enhancement process, segmentation operation was executed on the enhanced image using some existing segmentation method. Based on the advanced segmentation technology—Fuzzy C-Mean Algorithm segmentation method, this paper presented Ant Colony Algorithm-based Fuzzy C-Mean Algorithm segmentation method and improved Fuzzy C-Mean Algorithm segmentation method, and some classic image segmentation evaluation measurement were adopted to evaluate these segmented image, which would provide some guidance for the selection from lots of medical ultrasonic image segmentation methods in the future.