Comparison of Denoising Techniques Applied on Low-Field MR Brain Images

Low-field magnetic resonance imaging (MRI) is vital for sensitive surgery to allow real-time imaging in the operation theatre. In this paper, we demonstrate implementations of denoising algorithms on low-field MR brain 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. This paper gives some useful insight on the application of pre-processing techniques towards segmenting and labeling the brain images. Promising results are reported for anisotropic diffusion filtering.