Image Enhancement Technique Applied to Low-field MR Brain Images

Abstract

Image processing techniques are used to extract meaningful information from medical images. A major concern in denoising low-field MR brain images is the poor quality images secondary to a worsening signal-to-noise ratio (SNR) compared with the high-field MRI scanners. Low-field Magnetic Resonance Imaging (MRI) is vital in sensitive surgeries to allow real-time imaging in the operation theatre. Since low-field MRI uses low strength electromagnetic fields, noisy low resolution images are produced. In contrast, highfield MRI machines (approximately 7T) are able to produce clear detailed images with almost no noise at all. Considering the above, it is required to enhance the low-field images, so that the same conventional and high-field MRI processing techniques and applications could be applied to pre-processed low-field MRI images. In this paper, pre-processing steps are applied to low-field MR brain images for improving quality of the image.

An Approach for Enhancement of MR Images of Brain Tumor

“…Rallabandi and Roy [18] proposed a stochastic resonator algorithm for denoising the images and gave an enhancement factor. Bandyopadhyay [19] presented histogram equalization with median filter, unsharp masking, thresholding, and mean filter for noise removing before segmentation by region growing. George and Karnan [20] proposed a center-weighted median filter for denoising and compared it with the median and weighted median filter.…”