Quantum Noise Removal in X-Ray Images with Adaptive Total Variation Regularization

Article type: Research Article

Authors: Prasath, V.B. Surya

Affiliations: Computational Imaging and VisAnalysis (CIVA) Lab, Department of Computer Science, University of Missouri-Columbia, MO 65211, USA, E-mail: prasaths@missouri.edu

Abstract: Medical X-ray images are prevalent and are the least expensive diagnostic imaging method available widely. The handling of film processing and digitization introduces noise in X-ray images and suppressing such noise is an important step in medical image analysis. In this work, we use an adaptive total variation regularization method for removing quantum noise from X-ray images. By utilizing an edge indicator measure along with the well-known edge preserving total variation regularization, we obtain noise removal without losing salient features. Experimental results on different X-ray images indicate the promise of our approach. Synthetic examples are given to compare the performance of our scheme with traditional total variation and anisotropic diffusion methods from the literature. Overall, our proposed approach obtains better results in terms of visual appearance as well as with respect to different error metrics and structural similarity.

Keywords: total variation, adaptive, regularization, quantum noise, X-ray images, denoising

Journal: Informatica, vol. 28, no. 3, pp. 505-515, 2017