Medical image denoising using adaptive spatial domain schemes with additive noise

Abstract EN

Image denoising is one of the most significant tasks in medical image processing due to the significant information obtained by these images related to the human body or the tissues of the body’s organs.

So, many methods have been proposed for removing the noise that affects the medical images.

In this research a new algorithm has been proposed for denoisning medical images work in spatial domain.

A new algorithm depends on the idea that combine between characteristic of different filters which work in spatial domain with adaptive sizes of windows for reaching to the acceptance results in remove noise from medical images.

This algorithm called Adaptive Window Wiener Filter (AWWF).

Two types of medical images and noise that corrupt these medical image used in this research.

The first type is Poisson noise which corrupts X-ray medical images and the second type is Rician noise which corrupts MRI medical images.

The algorithm begins with using a median filter on a noisy image to get the blurred version of the image.

Then using an edge detection algorithm, the edges detection of the resulted blurred image is found by using the Prewitt operator.

Then Wiener filter of variable size windows is applied throughout the noisy image to suppress the noise.

The window size is made bigger in homogenous and smooth regions and is made smaller in edge and complex regions.