dnoiseNET - A Deep CNN for MRI Image Denoising
Improving performance without compromising quantitative metrics.
This project proposes a deep convolutional neural network (CNN) for MRI denoising that integrates residual learning and skip connections to achieve improved noise suppression without compromising clinically-relevant quantitative MRI metrics.
Conference talk
- HP Do, et al. "dnoiseNET: Deep Convolutional Neural Network for Image Denoising." The ISMRM & SCMR Co-Provided Workshop on the Emerging Role of Machine Learning in Cardiovascular Magnetic Resonance Imaging, Seattle, Feb 2019. SLIDES-PDF
Get future posts delivered to your inbox.
