Gradient regularized convolutional neural networks for low-dose CT image enhancement

The potential risks of x-ray to patients have transferred the public's attention from normal dose CT (NDCT) to low-dose CT (LDCT). However, simply lowering the radiation dose of the CT system will significantly degrade the quality of CT images such as noise and artifacts, which compromises the diagnostic performance. Hence, various methods have been proposed to solve this problem over the past decades. Although these methods have achieved impressive results, they also suffer from a drawback of smoothing image details after denoising, which makes it difficult for clinical diagnosis and treatment. To address this issue, this paper introduces a novel gradient regularization method for LDCT enhancement. Rather than common methods which only consider the pixel-wise gray value loss in the reconstruction procedure, we also take the image gradient loss into consideration to preserve image details. By combining the gradient regularization method and the convolutional neural network (CNN) framework, a gradient regularized convolutional neural network (GRCNN) is proposed to enhance LDCT images which has achieved promising performance in our experiments both visually and quantitatively.

[1]  Armando Manduca,et al.  Adaptive nonlocal means filtering based on local noise level for CT denoising. , 2013, Medical physics.

[2]  Paul Babyn,et al.  Sharpness-Aware Low-Dose CT Denoising Using Conditional Generative Adversarial Network , 2017, Journal of Digital Imaging.

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

[4]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  D. Brenner,et al.  Computed tomography--an increasing source of radiation exposure. , 2007, The New England journal of medicine.

[6]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[7]  Larry S. Davis,et al.  A survey of edge detection techniques , 1975 .

[8]  Tomaso A. Poggio,et al.  On Edge Detection , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  David Zhang,et al.  Gradient Histogram Estimation and Preservation for Texture Enhanced Image Denoising , 2014, IEEE Transactions on Image Processing.

[10]  Dennis F. Dunn,et al.  Optimal Gabor filters for texture segmentation , 1995, IEEE Trans. Image Process..

[11]  D R Dance,et al.  Influence of anode/filter material and tube potential on contrast, signal-to-noise ratio and average absorbed dose in mammography: a Monte Carlo study. , 2000, The British journal of radiology.

[12]  Piotr J. Slomka,et al.  Image denoising of low-radiation dose coronary CT angiography by an adaptive block-matching 3D algorithm , 2013, Medical Imaging.

[13]  David J Brenner,et al.  Cancer risks from CT scans: now we have data, what next? , 2012, Radiology.

[14]  Steve B. Jiang,et al.  Cine Cone Beam CT Reconstruction Using Low-Rank Matrix Factorization: Algorithm and a Proof-of-Principle Study , 2012, IEEE Transactions on Medical Imaging.

[15]  Xuanqin Mou,et al.  Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss , 2017, IEEE Transactions on Medical Imaging.

[16]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[17]  Xuanqin Mou,et al.  Tensor-Based Dictionary Learning for Spectral CT Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[18]  Enhong Chen,et al.  Image Denoising and Inpainting with Deep Neural Networks , 2012, NIPS.

[19]  Gang Sun,et al.  Squeeze-and-Excitation Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[20]  Cynthia M. McCollough,et al.  Projection space denoising with bilateral filtering and CT noise modeling for dose reduction in CT. , 2009, Medical physics.

[21]  M. Nikolova.  A Variational Approach to Remove Outliers and Impulse Noise , 2004 .

[22]  Rafael C. González,et al.  Digital image processing using MATLAB , 2006 .

[23]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[25]  Jiasong Wu,et al.  Improving Low-Dose CT Image Using Residual Convolutional Network , 2017, IEEE Access.

[26]  Steve B. Jiang,et al.  Low-dose CT reconstruction via edge-preserving total variation regularization , 2010, Physics in medicine and biology.

[27]  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).

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

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

[30]  Steve B. Jiang,et al.  Low-dose CT reconstruction via edge-preserving total variation regularization. , 2010, Physics in medicine and biology.

[31]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

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

[33]  Daniel Rueckert,et al.  Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Jong Chul Ye,et al.  A deep convolutional neural network using directional wavelets for low‐dose X‐ray CT reconstruction , 2016, Medical physics.

[35]  Shuiping Gou,et al.  Denoised and texture enhanced MVCT to improve soft tissue conspicuity. , 2014, Medical physics.

[36]  Jiliu Zhou,et al.  Few-view image reconstruction with fractional-order total variation. , 2014, Journal of the Optical Society of America. A, Optics, image science, and vision.

[37]  W. D. Evans,et al.  PARTIAL DIFFERENTIAL EQUATIONS , 1941 .

[38]  Shiliang Sun,et al.  Multitask Twin Support Vector Machines , 2012, ICONIP.

[39]  J. O’Sullivan,et al.  Properties of preprocessed sinogram data in x-ray computed tomography. , 2006, Medical physics.

[40]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Lixin Shen,et al.  Proximity algorithms for the L1/TV image denoising model , 2011, Advances in Computational Mathematics.

[42]  Junyan Rong,et al.  Adaptive non‐local means on local principle neighborhood for noise/artifacts reduction in low‐dose CT images , 2017, Medical physics.

[43]  Lei Zhang,et al.  Low-Dose X-ray CT Reconstruction via Dictionary Learning , 2012, IEEE Transactions on Medical Imaging.

[44]  Ke Sheng,et al.  Denoising of low dose CT image with context-based BM3D , 2016, 2016 IEEE Region 10 Conference (TENCON).

[45]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[46]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[47]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[48]  Randy E. Ellis,et al.  Validation of bone segmentation and improved 3-D registration using contour coherency in CT data , 2006, IEEE Transactions on Medical Imaging.

[49]  Zhengrong Liang,et al.  Robust Low-Dose CT Sinogram Preprocessing via Exploiting Noise-Generating Mechanism , 2017, IEEE Transactions on Medical Imaging.

[50]  Feng Zhou,et al.  Texture feature based on local Fourier transform , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[51]  Jing Wang,et al.  Penalized weighted least-squares approach to sinogram noise reduction and image reconstruction for low-dose X-ray computed tomography , 2006, IEEE Transactions on Medical Imaging.

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

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

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

[55]  Huazhong Shu,et al.  Artifact Suppressed Dictionary Learning for Low-Dose CT Image Processing , 2014, IEEE Transactions on Medical Imaging.

[56]  Baiyu Chen,et al.  Low‐dose CT for the detection and classification of metastatic liver lesions: Results of the 2016 Low Dose CT Grand Challenge , 2017, Medical physics.

[57]  R. Weissleder,et al.  Block matching 3D random noise filtering for absorption optical projection tomography , 2010, Physics in medicine and biology.

[58]  Chun Jiao,et al.  Multiscale noise reduction on low-dose CT sinogram by stationary wavelet transform , 2008, 2008 IEEE Nuclear Science Symposium Conference Record.

[59]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[60]  Mannudeep K. Kalra,et al.  Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN) , 2017, ArXiv.

[61]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[62]  Christine Toumoulin,et al.  Thoracic low-dose CT image processing using an artifact suppressed large-scale nonlocal means , 2012, Physics in medicine and biology.

[63]  Léon Bottou,et al.  Towards Principled Methods for Training Generative Adversarial Networks , 2017, ICLR.

[64]  H. Sebastian Seung,et al.  Natural Image Denoising with Convolutional Networks , 2008, NIPS.

[65]  Seong Jong Hong,et al.  A feasibility study of an integrated NIR/gamma/visible imaging system for endoscopic sentinel lymph node mapping , 2017, Medical physics.

[66]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

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

[68]  E. Sidky,et al.  Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization , 2008, Physics in medicine and biology.

[69]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[70]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[71]  Stefan Harmeling,et al.  Image denoising: Can plain neural networks compete with BM3D? , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

[73]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[74]  Tomas Pfister,et al.  Learning from Simulated and Unsupervised Images through Adversarial Training , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[75]  Léon Bottou,et al.  The Tradeoffs of Large Scale Learning , 2007, NIPS.

[76]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[77]  Sergio Goma,et al.  Novel bilateral filter approach: Image noise reduction with sharpening , 2006, Electronic Imaging.