Deep Learning Based Beam Hardening Artifact Reduction in Industrial X-ray CT
ZHOU Li-ping
SUN Yi
CHENG Kai
YU Jian-qiao
Abstract：In the nondestructive detection with industrial CT,due to the fact that the actual X-raysource has a wide spectrum,slices reconstructed by most existing reconstruction algorithms will sufferfrom beam hardening artifacts.It will degrade image quality greatly,affecting important CT imagetask such as CT diagnosis and so on.In this study,we propose a method to suppress beam hardeningartifacts based on deep learning.We train a eonvolutional neural network using a large number ofimages with beam hardening artifacts as input and the corresponding artifact-free images reconstructedat a fixed energy as output to establish the mapping between image with beam hardening artifacts andartifact-free image for suppressing beam hardening artifacts.Experimental results show theeffectiveness of the proposed method in the beam hardening artifact reduction of CT images.
Keywords：beam hardeningCTdeep learningconvolutional neural network
Publication Date：2018-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：14( 227-240 )