An intelligent system for lung CT image denoising using a hybrid WT-NLM filter

Abstract

Image denoising is an extensively researched problem in computer vision that is commonly used as a benchmark for many imaging tasks. Noise distorts an image throughout the acquisition and transmission cycle. The elimination of noise from the original image is a significant challenge for scientists and this work considers Gaussian, Salt and pepper noises, as medical images are prone to it. Hence, this work presents ways for mitigating noise, while preserving the relevant image information. In this study, a Hybrid Wavelet Transform with Non-Local Mean (Hybrid WT-NLM) filter is proposed for reducing noise in lung CT images. The final denoised images are formed by the summation of NLM-filtered images and wavelet coefficients. The proposed study offers a straightforward method for removing noise to attain better visual quality in a reasonable period. The efficacy of the proposed denoising approach is proven by comparing it with traditional denoising approaches such as Morphological filtering, Mean Filter, Median filter, Adaptive median filter and Non-Local Means (NLM) upon two public datasets such as Public LIDC database and in-house clinical ICCN database. The average PSNR of the proposed work is 25.47 dB at a time consumption of 1.03 s.