The Open Bioinformatics Journal

Article Title:

Abstract:

Background: The main emphasis of this study is the medical Computed Tomography (CT) imaging denoising technique, which is particularly useful in interpreting patient illness information for medical diagnosis. CT imaging is indispensable for diagnosing this illness. However, image clarity is affected by noise and other artefacts. The primary goal is to improve the accuracy of denoising algorithms ,which allows for early disease prediction and increase the accuracy of a patient’s diagnostic outcome. Objective: The major objective was to examine and assess the effectiveness of applying a method noise-based Low-dose CT (LDCT) image denoising using Convolutional-neural-network (CNN) in diagnostic imaging. This method aims to suppress noise, improve image quality, and effectively minimize radiation. This, in turn, improving the accuracy of denoising algorithm, enabling it to accurately predict the disease diagnosis. Method noise, or residual noise, plays a major role in denoising CT images accurately while preserving noise and other artefacts generated during the denoising process. Method noise encompasses the omitted structural and other minute artefacts during the denoising process as well as the preservation of fine details. Applying the denoising technique to the method noise through CNN enhances the final image quality and clarity, thereby enhancing the diagnostic accuracy. Methods: The study includes a systematic, method noise-based approach to determine the performance of denoising algorithm in diagnosing various diseases from medical CT images often encountered with Gaussian noise. It entails selecting a pervasive data set, applying a method noise approach using CNN, and comparing it with quantitative measures such as PSNR, SNR and SSIM to assess diagnostic interpretation, thereby improving accuracy in identifying the efficacy of the method noise approach in CT medical imaging.