Open AccessShading correction for volumetric CT using deep convolutional neural network and adaptive filter
Author(s) -
Xiaokun Liang,
Na Li,
Zhicheng Zhang,
Shaode Yu,
Wenjian Qin,
Yafen Li,
Shupeng Chen,
Huailing Zhang,
Yaoqin Xie
Publication year - 2019
Publication title -
quantitative imaging in medicine and surgery
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.766
H-Index - 21
eISSN - 2223-4292
pISSN - 2223-4306
DOI - 10.21037/qims.2019.05.19
Subject(s) - artifact (error) , artificial intelligence , computer science , computer vision , shading , convolutional neural network , segmentation , filter (signal processing) , contrast (vision) , image (mathematics) , region of interest , pattern recognition (psychology) , computer graphics (images)
Shading artifact may lead to CT number inaccuracy, image contrast loss and spatial non-uniformity (SNU), which is considered as one of the fundamental limitations for volumetric CT (VCT) application. To correct the shading artifact, a novel approach is proposed using deep learning and an adaptive filter (AF).