Title:De-noising Medical Images Using Machine Learning, Deep Learning Approaches: A survey
VOLUME: 16
Author(s):Ali Arshaghi *, Mohsen Ashourian and Leila Ghabeli
Affiliation:Department of Electrical Engineering, Central Tehran Branch, Islamic Azad University, Tehran, Department of Electrical Engineering, Majlesi Branch, Islamic Azad University, Isfahan, Department of Electrical Engineering, Central Tehran Branch, Islamic Azad University, Tehran
Keywords:Medical de-noising, NLM, PSNR, image processing, CNN, Adaptive wiener filter
Abstract:Objective: Several de-noising methods for medical images have been applied such as Wavelet Transform,
CNN, linear and Non-linear method.
Methods: In this paper, a median filter algorithm will be modified and explain the image de-noising to wavelet transform
and Non-local means (NLM), deep convolutional neural network (DnCNN) and Gaussian noise and Salt and pepper noise
used in the medical skin image.
Results: PSNR values of CNN methods is higher and better than to others filters (Adaptive Wiener filter, Median filter
and Adaptive Median filter, Wiener filter).
Conclusion: De-noising methods performance with indices SSIM, PSNR and MSE are tested and survey the result of
simulation image de-noising.
