Residual U-Net Convolutional Neural Network Architecture for Low-Dose CT Denoising release_wopz2vgafrhjro5r5huok6pezi

by Mattias P. Heinrich, Maik Stille, Thorsten M. Buzug

Published in Current Directions in Biomedical Engineering by Walter de Gruyter GmbH.

2018   p297-300

Abstract

<jats:title>Abstract</jats:title> Low-dose CT has received increasing attention in the recent years and is considered a promising method to reduce the risk of cancer in patients. However, the reduction of the dosage leads to quantum noise in the raw data, which is carried on in the reconstructed images. Two different multilayer convolutional neural network (CNN) architectures for the denoising of CT images are investigated. ResFCN is based on a fully-convolutional network that consists of three blocks of 5<jats:italic>×</jats:italic>5 convolutions filters and a ResUNet that is trained with 10 convolutional blocks that are arranged in a multi-scale fashion. Both architectures feature a residual connection of the input image to ease learning. Training images are based on realistic simulations by using the XCAT phantom. The ResUNet approach shows the most promising results with a peak signal to noise ratio of 44.00 compared to ResFCN with 41.79.
In application/xml+jats format

Archived Files and Locations

application/pdf  1.9 MB
file_7fwlnnby2jfwfb4ugot7h7p7ue
www.degruyter.com (publisher)
web.archive.org (webarchive)
application/pdf  1.9 MB
file_u7j4bqumqncq5krcpmh56lqnu4
www.degruyter.com (publisher)
web.archive.org (webarchive)
application/pdf  1.9 MB
file_wjd23ecmnnetpeo6vldndi35ou
www.degruyter.com (publisher)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2018-09-01
Container Metadata
Open Access Publication
In DOAJ
In Keepers Registry
ISSN-L:  2364-5504
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: e72dd84b-30c0-4d74-9f2c-ace4939d62c5
API URL: JSON