A Proposed Framework to Denoise the Medical Images Using Deep Learning Techniques

---

Abstract

Image Denoising has become a promising task nowadays in the domain of Image processing. Throughout this paper, a complete analysis of all the methods of Image Denoising has been studied. In this paper, medical image dataset which include Chest X-ray images of a patient has been taken into consideration. Numerous deep learning methods including Convolutional Neural Networks and Denoising Autoencoder have been discussed here. Chest X-ray images has been denoised first using a Denoising Autoencoder and then a Convolutional Neural network is implemented with a U-Net structure. A number of performance evaluation metrics have been employed to assess the quality of denoised images, such as SSIM (Structural Similarity Index) and PSNR (Peak Signal to Noise Ratio). A comparison of all the methods has been done in a tabular format. Later the conclusion and future scope of this paper has been discussed.

---

Keywords

Image Processing; Peak signal-tonoise ratio (PSNR); Structural similarity index measure (SSIM); Deep Learning; Convolutional neural networks (CNNs); U-Net;