CT Super-Resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE)

In this paper, we present a semi-supervised deep learning approach to accurately recover high-resolution (HR) CT images from low-resolution (LR) counterparts. Specifically, with the generative adversarial network (GAN) as the building block, we enforce the cycle-consistency in terms of the Wasserste...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on medical imaging 2020-01, Vol.39 (1), p.188-203
Main Authors:	You, Chenyu, Cong, Wenxiang, Vannier, Michael W., Saha, Punam K., Hoffman, Eric A., Wang, Ge, Li, Guang, Zhang, Yi, Zhang, Xiaoliu, Shan, Hongming, Li, Mengzhou, Ju, Shenghong, Zhao, Zhen, Zhang, Zhuiyang
Format:	Article
Language:	eng
Subjects:	adversarial learning Computed tomography Computed tomography (CT) deep learning Gallium nitride Generative adversarial networks Image reconstruction Image resolution noise reduction residual learning super-resolution Training
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	In this paper, we present a semi-supervised deep learning approach to accurately recover high-resolution (HR) CT images from low-resolution (LR) counterparts. Specifically, with the generative adversarial network (GAN) as the building block, we enforce the cycle-consistency in terms of the Wasserstein distance to establish a nonlinear end-to-end mapping from noisy LR input images to denoised and deblurred HR outputs. We also include the joint constraints in the loss function to facilitate structural preservation. In this process, we incorporate deep convolutional neural network (CNN), residual learning, and network in network techniques for feature extraction and restoration. In contrast to the current trend of increasing network depth and complexity to boost the imaging performance, we apply a parallel 1 × 1 CNN to compress the output of the hidden layer and optimize the number of layers and the number of filters for each convolutional layer. The quantitative and qualitative evaluative results demonstrate that our proposed model is accurate, efficient and robust for super-resolution (SR) image restoration from noisy LR input images. In particular, we validate our composite SR networks on three large-scale CT datasets, and obtain promising results as compared to the other state-of-the-art methods.
ISSN:	0278-0062 1558-254X