Deep Encoder-Decoder Adversarial Reconstruction (DEAR) Network for 3D CT from Few-View Data

X-ray computed tomography (CT) is widely used in clinical practice. The involved ionizing X-ray radiation, however, could increase cancer risk. Hence, the reduction of the radiation dose has been an important topic in recent years. Few-view CT image reconstruction is one of the main ways to minimize radiation dose and potentially allow a stationary CT architecture. In this paper, we propose a deep encoder-decoder adversarial reconstruction (DEAR) network for 3D CT image reconstruction from few-view data. Since the artifacts caused by few-view reconstruction appear in 3D instead of 2D geometry, a 3D deep network has a great potential for improving the image quality in a data driven fashion. More specifically, our proposed DEAR-3D network aims at reconstructing 3D volume directly from clinical 3D spiral cone-beam image data. DEAR is validated on a publicly available abdominal CT dataset prepared and authorized by Mayo Clinic. Compared with other 2D deep learning methods, the proposed DEAR-3D network can utilize 3D information to produce promising reconstruction results.

[1]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[2]  Hengyong Yu,et al.  Approximate and exact cone-beam reconstruction with standard and non-standard spiral scanning , 2006, SPIE Optics + Photonics.

[3]  Hongming Shan,et al.  3-D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning From a 2-D Trained Network , 2018, IEEE Transactions on Medical Imaging.

[4]  Steven J. Kenyon,et al.  Stationary Computed Tomography for Space and other Resource-constrained Environments , 2018, Scientific Reports.

[5]  Hu Chen,et al.  LEARN: Learned Experts’ Assessment-Based Reconstruction Network for Sparse-Data CT , 2017, IEEE Transactions on Medical Imaging.

[6]  A. J. Jerri.  Correction to "The Shannon sampling theorem—Its various extensions and applications: A tutorial review" , 1979 .

[7]  Hongming Shan,et al.  Deep-learning-based Breast CT for Radiation Dose Reduction , 2019, Developments in X-Ray Tomography XII.

[8]  Max A. Viergever,et al.  Generative Adversarial Networks for Noise Reduction in Low-Dose CT , 2017, IEEE Transactions on Medical Imaging.

[9]  Anthony P. H. Butler,et al.  Guest Editorial Special Issue on Spectral CT , 2015, IEEE Trans. Medical Imaging.

[10]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[11]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Jari Korhonen,et al.  Peak signal-to-noise ratio revisited: Is simple beautiful? , 2012, 2012 Fourth International Workshop on Quality of Multimedia Experience.

[13]  P. Grangeat.  Mathematical framework of cone beam 3D reconstruction via the first derivative of the radon transform , 1991 .

[14]  Jongha Lee,et al.  Deep-Neural-Network-Based Sinogram Synthesis for Sparse-View CT Image Reconstruction , 2018, IEEE Transactions on Radiation and Plasma Medical Sciences.

[15]  M. Glas,et al.  Principles of Computerized Tomographic Imaging , 2000 .

[16]  Michael Unser,et al.  Convolutional Neural Networks for Inverse Problems in Imaging: A Review , 2017, IEEE Signal Processing Magazine.

[17]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[18]  Pascal Sire,et al.  Evaluation of the 3-D radon transform algorithm for cone beam reconstruction , 1991, Medical Imaging.

[19]  Uwe Kruger,et al.  Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction , 2019, Nat. Mach. Intell..

[20]  Alan C. Bovik,et al.  Mean squared error: Love it or leave it? A new look at Signal Fidelity Measures , 2009, IEEE Signal Processing Magazine.

[21]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[22]  David L Donoho,et al.  Compressed sensing , 2006, IEEE Transactions on Information Theory.

[23]  Feng Lin,et al.  Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network , 2017, IEEE Transactions on Medical Imaging.

[24]  G. Herman,et al.  Algebraic reconstruction techniques (ART) for three-dimensional electron microscopy and x-ray photography. , 1970, Journal of theoretical biology.

[25]  A. J. Jerri.  The Shannon sampling theorem—Its various extensions and applications: A tutorial review , 1977, Proceedings of the IEEE.

[26]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[27]  Ian T. Foster,et al.  TomoGAN: low-dose synchrotron x-ray tomography with generative adversarial networks: discussion. , 2019, Journal of the Optical Society of America. A, Optics, image science, and vision.

[28]  Ke Li,et al.  Learning to Reconstruct Computed Tomography Images Directly From Sinogram Data Under A Variety of Data Acquisition Conditions , 2019, IEEE Transactions on Medical Imaging.

[29]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[31]  Hu Chen,et al.  Low-dose CT via convolutional neural network. , 2017, Biomedical optics express.

[32]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[33]  C. Willmott,et al.  Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance , 2005 .

[34]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[35]  Yoshua Bengio,et al.  Generative Adversarial Networks , 2014, ArXiv.

[36]  Jan Kautz,et al.  Loss Functions for Image Restoration With Neural Networks , 2017, IEEE Transactions on Computational Imaging.

[37]  Hongming Shan,et al.  Dual Network Architecture for Few-view CT - Trained on ImageNet Data and Transferred for Medical Imaging , 2019, Developments in X-Ray Tomography XII.

[38]  Stephen J Glick,et al.  Breast CT. , 2007, Annual review of biomedical engineering.

[39]  Alexander Katsevich,et al.  An improved exact filtered backprojection algorithm for spiral computed tomography , 2004, Adv. Appl. Math..

[40]  A. Kak,et al.  Simultaneous Algebraic Reconstruction Technique (SART): A Superior Implementation of the Art Algorithm , 1984, Ultrasonic imaging.

[41]  Ge Wang,et al.  A Perspective on Deep Imaging , 2016, IEEE Access.

[42]  Peter Steffen,et al.  An efficient Fourier method for 3-D radon inversion in exact cone-beam CT reconstruction , 1998, IEEE Transactions on Medical Imaging.

[43]  Gilles Soulez,et al.  Three-dimensional C-arm cone-beam CT: applications in the interventional suite. , 2008, Journal of vascular and interventional radiology : JVIR.

[44]  Michael Unser,et al.  Deep Convolutional Neural Network for Inverse Problems in Imaging , 2016, IEEE Transactions on Image Processing.

[45]  L. Tanoue.  Computed Tomography — An Increasing Source of Radiation Exposure , 2009 .

[46]  Ronald M. Summers,et al.  Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique , 2016 .