Improved digital chest tomosynthesis image quality by use of a projection-based dual-energy virtual monochromatic convolutional neural network with super resolution

We developed a novel dual-energy (DE) virtual monochromatic (VM) very-deep super-resolution (VDSR) method with an unsharp masking reconstruction algorithm (DE–VM–VDSR) that uses projection data to improve the nodule contrast and reduce ripple artifacts during chest digital tomosynthesis (DT). For es...

Full description

Saved in:

Bibliographic Details
Published in:	PloS one Vol. 15; no. 12; p. e0244745
Main Authors:	Gomi, Tsutomu, Hara, Hidetake, Watanabe, Yusuke, Mizukami, Shinya
Format:	Journal Article
Language:	English
Published:	United States Public Library of Science 31.12.2020 Public Library of Science (PLoS)
Subjects:	Algorithms Aluminum Artificial neural networks Biology and Life Sciences Chest Computer simulation Decomposition Deep learning Digital imaging Engineering and Technology Health sciences Humans Image contrast Image processing Image Processing, Computer-Assisted - methods Image quality Image reconstruction Image resolution Lung cancer Lung Neoplasms - diagnostic imaging Medicine and Health Sciences Modulation transfer function Neural networks Neural Networks, Computer Nodules Noise Opacity Optical communication Phantoms, Imaging Physical Sciences Projection Radiography Radiography, Thoracic - methods Research and Analysis Methods Ripples Stochasticity Tomography, X-Ray Computed - methods Japan
ISSN:	1932-6203, 1932-6203
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!