X2CT-GAN: Reconstructing CT from Biplanar X-Rays with Generative Adversarial Networks
Authors:
- Xingde YingXYXingde Ying
- Heng GuoHGHeng Guo
- Kai MaKMKai Ma
- Jian WuJWJian Wu
- Zhengxin WengZWZhengxin Weng
- Yefeng ZhengYZYefeng Zheng
Preprint
Abstract
Computed tomography (CT) can provide a 3D view of the patient's internal organs, facilitating disease diagnosis, but it incurs more radiation dose to a patient and a CT scanner is much more cost prohibitive than an X-ray machine too. Traditional CT reconstruction methods require hundreds of X-ray projections through a full rotational scan of the body, which cannot be performed on a typical X-ray machine. In this work, we propose to reconstruct CT from two orthogonal X-rays using the generative adversarial network (GAN) framework. A specially designed generator network is exploited to increase data dimension from 2D (X-rays) to 3D (CT), which is not addressed in previous research of GAN. A novel feature fusion method is proposed to combine information from two X-rays.The mean squared error (MSE) loss and adversarial loss are combined to train the generator, resulting in a high-quality CT volume both visually and quantitatively. Extensive experiments on a publicly available chest CT dataset demonstrate the effectiveness of the proposed method. It could be a nice enhancement of a low-cost X-ray machine to provide physicians a CT-like 3D volume in several niche applications.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs2018
- Image reconstruction by domain-transform manifold learningNature, 2018
- 3D femur model reconstruction from biplane X-ray images: a novel method based on Laplacian surface deformationInternational Journal of Computer Assisted Radiology and Surgery, 2014
- 3D reconstruction of rib cage geometry from biplanar radiographs using a statistical parametric model approachComputer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2014
- Knowledge-Assisted Reconstruction of the Human Rib Cage and LungsIEEE Computer Graphics and Applications, 2009
- 3-D Reconstruction of the Human Ribcage Based on Chest X-Ray Images and Geometric Template ModelsIEEE MultiMedia, 2009
- 3D reconstruction of the human rib cage from 2D projection images using a statistical shape modelInternational Journal of Computer Assisted Radiology and Surgery, 2009
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Handbook of Medical Imaging. Processing and AnalysisMedical Physics, 2002
- CT imaging based digitally reconstructed radiographs and their application in brachytherapyPhysics in Medicine & Biology, 2000