Introducing Swish and Parallelized Blind Removal Improves the Performance of a Convolutional Neural Network in Denoising MR Images.

Journal: Magnetic resonance in medical sciences : MRMS : an official journal of Japan Society of Magnetic Resonance in Medicine

Published Date: Feb 11, 2021

Abstract

PURPOSE: To improve the performance of a denoising convolutional neural network (DnCNN) and to make it applicable to images with inhomogeneous noise, a refinement involving an activation function (AF) and an application of the refined method for inhomogeneous-noise images was examined in combination with parallelized image denoising.

Authors

Taro Sugai

Department of Innovation Systems Engineering, Graduate School of Engineering, Utsunomiya University.
Kohei Takano

Information and Control Systems Science, Graduate School of Engineering, Utsunomiya University.
Shohei Ouchi

Intelligence and Information Science Course, Graduate School of Engineering Doctoral Degree Program, Utsunomiya University.
Satoshi Ito

Keywords

Image Processing, Computer-Assisted Neural Networks, Computer Noise Signal-To-Noise Ratio

External Resources

View on PubMed Access via DOI PubMed (33583867)

Introducing Swish and Parallelized Blind Removal Improves the Performance of a Convolutional Neural Network in Denoising MR Images.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals