Deblurring Computed Tomography Medical Images Using a Novel Amended Landweber Algorithm

Abstract

In computed tomography (CT), blurring occurs due to different hardware or software errors and hides certain medical details that are present in an image. Image blur is difficult to avoid in many circumstances and can frequently ruin an image. For this, many methods have been developed to reduce the blurring artifact from CT images. The problems with these methods are the high implementation time, noise amplification and boundary artifacts. Hence, this article presents an amended version of the iterative Landweber algorithm to attain artifact-free boundaries and less noise amplification in a faster application time. In this study, both synthetic and real blurred CT images are used to validate the proposed method properly. Similarly, the quality of the processed synthetic images is measured using the feature similarity index, structural similarity and visual information fidelity in pixel domain metrics. Finally, the results obtained from intensive experiments and performance evaluations show the efficiency of the proposed algorithm, which has potential as a new approach in medical image processing.

Research on an image restoration method of cubic phase plate wave-front coding with mixed noise

“…Next, we removed AWGN using Shearlet [31]. For image deblurring, we finally selected the Amended Landweber (ALW) [59] algorithm.…”

“…Ref. [59] proposed a novel improved Landweber algorithm to eliminate blur from computed tomography (CT) medical images. The Landweber algorithm is a popular iterative algorithm for image deblurring, but it has the problems of slow convergence and noise sensitivity.…”

Deblurring decay-energy distribution from an invariant-mass measurement

“…The deblurring procedure uses the Richardson-Lucy (RL) algorithm initially developed to restore blurred images in optics [2,3]. Over time the algorithm found uses in other fields, such as astronomy [4] and medical image analysis [5], to list a few. Furthermore, in high-energy physics, an analogous procedure was developed [6], and more recently it has been demonstrated that the method can be utilized in nuclear physics [7,8,9].…”

Restauración de imágenes borrosas usando un modelo regularizado de programación lineal

“…Es muy común que estas imágenes no puedan ser tomadas de nuevo, lo que obliga a restaurarlas a su estado original para mejorar su nitidez antes de poder realizar otros pasos, como la detección, la segmentación, la clasificación [1]. En este sentido la restauración de imágenes juega un papel muy importante en áreas como: la tomografía computarizada [2], la tomografía de capacitancia y de impedancia eléctrica [3], el reconocimiento facial [4], la teledetección [5] y otras aplicaciones.…”