Conditional Generative Adversarial Networks for Metal Artifact Reduction in CT Images of the Ear

• Published in: Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Vol. 11070; p. 3
• Main Authors: Wang, Jianing, Zhao, Yiyuan, Noble, Jack H, Dawant, Benoit M
• Format: Journal Article
• Language: English
• Published: Germany 01.01.2018
• Subjects: Algorithms; Cochlea - diagnostic imaging; Humans; Metals; Radiographic Image Enhancement; Radiographic Image Interpretation, Computer-Assisted; Reproducibility of Results; Sensitivity and Specificity; Tomography, X-Ray Computed; Metal Artifact Reduction; Conditional Generative Adversarial Networks; Cochlear Implants
• DOI: 10.1007/978-3-030-00928-1_1

We propose an approach based on a conditional generative adversarial network (cGAN) for the reduction of metal artifacts (RMA) in computed tomography (CT) ear images of cochlear implants (CIs) recipients. Our training set contains paired pre-implantation and post-implantation CTs of 90 ears. At the training phase, the cGAN learns a mapping from the artifact-affected CTs to the artifact-free CTs. At the inference phase, given new metal-artifact-affected CTs, the cGAN produces CTs in which the artifacts are removed. As a pre-processing step, we also propose a band-wise normalization method, which splits a CT image into three channels according to the intensity value of each voxel and we show that this method improves the performance of the cGAN. We test our cGAN on post-implantation CTs of 74 ears and the quality of the artifact-corrected images is evaluated quantitatively by comparing the segmentations of intra-cochlear anatomical structures, which are obtained with a previously published method, in the real pre-implantation and the artifact-corrected CTs. We show that the proposed method leads to an average surface error of 0.18 mm which is about half of what could be achieved with a previously proposed technique.