CT-image Super Resolution Using 3D Convolutional Neural Network

Computed Tomography (CT) imaging technique is widely used in geological exploration, medical diagnosis and other fields. In practice, however, the resolution of CT image is usually limited by scanning devices and great expense. Super resolution (SR) methods based on deep learning have achieved surprising performance in two-dimensional (2D) images. Unfortunately, there are few effective SR algorithms for three-dimensional (3D) images. In this paper, we proposed a novel network named as three-dimensional super resolution convolutional neural network (3DSRCNN) to realize voxel super resolution for CT images. To solve the practical problems in training process such as slow convergence of network training, insufficient memory, etc., we utilized adjustable learning rate, residual-learning, gradient clipping, momentum stochastic gradient descent (SGD) strategies to optimize training procedure. In addition, we have explored the empirical guidelines to set appropriate number of layers of network and how to use residual learning strategy. Additionally, previous learning-based algorithms need to separately train for different scale factors for reconstruction, yet our single model can complete the multi-scale SR. At last, our method has better performance in terms of PSNR, SSIM and efficiency compared with conventional methods.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Chih-Yuan Yang,et al.  Single-Image Super-Resolution: A Benchmark , 2014, ECCV.

[4]  Yen-Wei Chen,et al.  Super-resolution of MR volumetric images using sparse representation and self-similarity , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[5]  Xiaoou Tang,et al.  Learning a Deep Convolutional Network for Image Super-Resolution , 2014, ECCV.

[6]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Christoph H. Arns,et al.  Super resolution reconstruction of μ-CT image of rock sample using neighbour embedding algorithm , 2018 .

[8]  Xiaohai He,et al.  Sparse representation-based volumetric super-resolution algorithm for 3D CT images of reservoir rocks , 2017 .

[9]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[10]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Xiaogang Wang,et al.  DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection , 2014, ArXiv.

[12]  Yi Zhang,et al.  Low-Dose CT via Deep CNN with Skip Connection and Network in Network , 2018, Developments in X-Ray Tomography XII.

[13]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[14]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[15]  Veerle Cnudde,et al.  High-resolution X-ray computed tomography in geosciences: A review of the current technology and applications , 2013 .

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

[17]  Hayit Greenspan,et al.  MRI inter-slice reconstruction using super-resolution , 2002 .

[18]  Christoph H. Arns,et al.  Porous Structure Reconstruction Using Convolutional Neural Networks , 2018, Mathematical Geosciences.

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

[20]  Geoffrey E. Hinton.  Deep belief networks , 2009, Scholarpedia.

[21]  J. T. Fredrich,et al.  3D imaging of porous media using laser scanning confocal microscopy with application to microscale transport processes , 1999 .

[22]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[23]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[24]  Kyoung Mu Lee,et al.  Accurate Image Super-Resolution Using Very Deep Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[26]  Zhi Xu,et al.  Stable-phase method for hierarchical annealing in the reconstruction of porous media images. , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

[27]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[28]  D. Louis Collins,et al.  Non-local MRI upsampling , 2010, Medical Image Anal..

[29]  Randy D. Hazlett,et al.  Simulation of capillary-dominated displacements in microtomographic images of reservoir rocks , 1995 .

[30]  Geoffrey E. Hinton,et al.  On the importance of initialization and momentum in deep learning , 2013, ICML.

[31]  Thomas S. Huang,et al.  Image super-resolution as sparse representation of raw image patches , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  Thomas S. Huang,et al.  Image Super-Resolution Via Sparse Representation , 2010, IEEE Transactions on Image Processing.

[33]  Xiaohai He,et al.  Reconstruction of multiphase microstructure based on statistical descriptors , 2014 .

[34]  Christoph H. Arns,et al.  Three-dimensional porous structure reconstruction based on structural local similarity via sparse representation on micro-computed-tomography images , 2018, Physical Review E.

[35]  이상헌,et al.  Deep Belief Networks , 2010, Encyclopedia of Machine Learning.

[36]  Ge Wang,et al.  Super-resolution MRI through Deep Learning , 2018, 1810.06776.

[37]  Guang Li,et al.  CT Super-Resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE) , 2018, IEEE Transactions on Medical Imaging.

[38]  Ge Wang,et al.  Structurally-Sensitive Multi-Scale Deep Neural Network for Low-Dose CT Denoising , 2018, IEEE Access.

[39]  M. Starnoni,et al.  Computation of fluid flow and pore-space properties estimation on micro-CT images of rock samples , 2017, Comput. Geosci..