Engineering Commons^™

Denoising Medical Imagery Using A Novel Framework, Samuel Peter Kozaitis, Jeetkumar M. Mehta, S. Ponkia

Electrical Engineering and Computer Science Faculty Publications

We proposed a novel framework that allows a method optimized for white noise to be used for denoising CT imagery. We considered low-dose x-ray CT imagery where lowering the dose of x-rays results in an increase in quantum noise. We first denoised an image independently several times using different parameters. Then, we selected pixels from those denoised images to form a final composite image. We produced results using blockmatching denoising, but in principle other methods could work within this framework, as well. The proposed method was able to better reproduce regions of low-contrast than the conventional BM3D approach.