Noise dependent training for deep parallel ensemble denoising in magnetic resonance images

Open Webpage

Hazique Aetesam, Suman Kumar Maji

Published: 2021, Last Modified: 23 Oct 2025Biomed. Signal Process. Control. 2021EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•A deep learning technique for Magnetic Resonance Image (MRI) denoising.•Takes into account mixed Gaussian-impulse nature of noise.•Derives a loss function for training from the Bayesian likelihood of Gaussian-Laplace distribution.•Uses fully convolutional neural network with (CNN) based 3D residual learning strategy.