An Optimized Preprocessing Decision for Multispectral MRI- Based Applications

Abstract

Medical imaging refers to technique and process used to create images of human body for clinical purpose .Image processing techniques in medical imaging are used to analyze the symptoms of the patients with ease. Medical images often consist of random noise and which are affected during acquisition and it spread over the image. In such situation it is very difficult to diagnosis the particular disease. The overall noise characteristic in an image depends on many factors, which include sensor type, pixel dimensions, temperature, exposure time, and ISO speed. Therefore it is necessary to remove the noise from the image. Real images are often degraded by noise and this noise can occur during image transmission and digitization. The key function of preprocessing is to improve the image in ways that increase the chances for success of the other processes. This paper evaluates different types of preprocessing filters and proposes a new type of preprocessing. Many of these methods use the information of a single image without taking into consideration the intrinsic multispectral nature of MR images, the proposed a new technique reduce random noise in multispectral MR images by spatially averaging similar pixels using information from all available image components to perform the preprocessing process. One of the main goals in the image pre-processing is to remove the redundant information as much as possible using simple and high-speed methods. Experimental results demonstrate that the performance of the proposed image preprocessing method is superior to that of other spatial-type filters.

 

Keywords: Medical Imaging, Preprocessing, Spatial filters, Multispectral MRI Image, Noise removal.