Constructing a tissue-specific texture prior by machine learning from previous full-dose scan for Bayesian reconstruction of current ultralow-dose CT images

Abstract. Purpose: Bayesian theory provides a sound framework for ultralow-dose computed tomography (ULdCT) image reconstruction with two terms for modeling the data statistical property and incorporating a priori knowledge for the image that is to be reconstructed. We investigate the feasibility of using a machine learning (ML) strategy, particularly the convolutional neural network (CNN), to construct a tissue-specific texture prior from previous full-dose computed tomography. Approach: Our study constructs four tissue-specific texture priors, corresponding with lung, bone, fat, and muscle, and integrates the prior with the prelog shift Poisson (SP) data property for Bayesian reconstruction of ULdCT images. The Bayesian reconstruction was implemented by an algorithm called SP-CNN-T and compared with our previous Markov random field (MRF)-based tissue-specific texture prior algorithm called SP-MRF-T. Results: In addition to conventional quantitative measures, mean squared error and peak signal-to-noise ratio, structure similarity index, feature similarity, and texture Haralick features were used to measure the performance difference between SP-CNN-T and SP-MRF-T algorithms in terms of the structure and tissue texture preservation, demonstrating the feasibility and the potential of the investigated ML approach. Conclusions: Both training performance and image reconstruction results showed the feasibility of constructing CNN texture prior model and the potential of improving the structure preservation of the nodule comparing to our previous regional tissue-specific MRF texture prior model.

[1]  Hakan Erdogan,et al.  Monotonic algorithms for transmission tomography , 1999, IEEE Transactions on Medical Imaging.

[2]  Linda Kaufman,et al.  Maximum likelihood, least squares, and penalized least squares for PET , 1993, IEEE Trans. Medical Imaging.

[3]  Zhengrong Liang,et al.  Texture-preserved penalized weighted least-squares reconstruction of low-dose CT image via image segmentation and high-order MRF modeling , 2016, SPIE Medical Imaging.

[4]  Jeffrey A. Fessler.  Penalized weighted least-squares image reconstruction for positron emission tomography , 1994, IEEE Trans. Medical Imaging.

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

[6]  Zhengrong Liang,et al.  Different Lung Nodule Detection Tasks at Different Dose Levels by Different Computed Tomography Image Reconstruction Strategies , 2018, 2018 IEEE Nuclear Science Symposium and Medical Imaging Conference Proceedings (NSS/MIC).

[7]  Jing Wang,et al.  Deriving adaptive MRF coefficients from previous normal-dose CT scan for low-dose image reconstruction via penalized weighted least-squares minimization. , 2014, Medical physics.

[8]  Michael Elad,et al.  The Little Engine That Could: Regularization by Denoising (RED) , 2016, SIAM J. Imaging Sci..

[9]  Jeffrey A. Fessler,et al.  Grouped-coordinate ascent algorithms for penalized-likelihood transmission image reconstruction , 1997, IEEE Transactions on Medical Imaging.

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

[11]  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.

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

[13]  R. Gillies,et al.  Quantitative imaging in cancer evolution and ecology. , 2013, Radiology.

[14]  Wangmeng Zuo,et al.  Learning Deep CNN Denoiser Prior for Image Restoration , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  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).

[16]  Hao Zhang,et al.  A Feasibility Study of Extracting Tissue Textures From a Previous Full-Dose CT Database as Prior Knowledge for Bayesian Reconstruction of Current Low-Dose CT Images , 2019, IEEE Transactions on Medical Imaging.

[17]  Guobao Wang,et al.  Hybrid Pre-Log and Post-Log Image Reconstruction for Computed Tomography , 2017, IEEE Transactions on Medical Imaging.

[18]  Xun Jia,et al.  Quality-guided deep reinforcement learning for parameter tuning in iterative CT reconstruction , 2019 .

[19]  Steve B. Jiang,et al.  Z-Index Parameterization for Volumetric CT Image Reconstruction via 3-D Dictionary Learning , 2017, IEEE Transactions on Medical Imaging.

[20]  Patrick Dupont,et al.  An iterative maximum-likelihood polychromatic algorithm for CT , 2001, IEEE Transactions on Medical Imaging.

[21]  Wufan Chen,et al.  Variance analysis of x-ray CT sinograms in the presence of electronic noise background. , 2012, Medical physics.

[22]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Jeffrey A. Fessler,et al.  Statistical image reconstruction for polyenergetic X-ray computed tomography , 2002, IEEE Transactions on Medical Imaging.

[24]  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.

[25]  Zhaoying Bian,et al.  A Simple Low-Dose X-Ray CT Simulation From High-Dose Scan , 2015, IEEE Transactions on Nuclear Science.

[26]  Zhengrong Liang,et al.  Texture Feature Extraction and Analysis for Polyp Differentiation via Computed Tomography Colonography , 2016, IEEE Transactions on Medical Imaging.

[27]  Jeffrey A. Fessler,et al.  Efficient and accurate likelihood for iterative image reconstruction in x-ray computed tomography , 2003, SPIE Medical Imaging.

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

[29]  Zhaoying Bian,et al.  Optimizing a Parameterized Plug-and-Play ADMM for Iterative Low-Dose CT Reconstruction , 2019, IEEE Transactions on Medical Imaging.

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

[31]  David Zhang,et al.  FSIM: A Feature Similarity Index for Image Quality Assessment , 2011, IEEE Transactions on Image Processing.

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

[33]  Richard M. Leahy,et al.  Statistical Modeling and Reconstruction of Randoms Precorrected PET Data , 2006, IEEE Transactions on Medical Imaging.

[34]  Lin Fu,et al.  Comparison Between Pre-Log and Post-Log Statistical Models in Ultra-Low-Dose CT Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[35]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[36]  Yuxiang Xing,et al.  Characterizing CT Reconstruction of Pre-log Transmission Data toward Ultra-low Dose Imaging by Texture Measures , 2018, 2018 IEEE Nuclear Science Symposium and Medical Imaging Conference Proceedings (NSS/MIC).

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

[38]  Patrick Dupont,et al.  Reduction of metal streak artifacts in X-ray computed tomography using a transmission maximum a posteriori algorithm , 1999 .

[39]  Michael A. Speidel,et al.  Radiation Dose Reduction in CT Myocardial Perfusion Imaging Using SMART-RECON , 2017, IEEE Transactions on Medical Imaging.

[40]  Jianhua Ma,et al.  Extracting Information From Previous Full-Dose CT Scan for Knowledge-Based Bayesian Reconstruction of Current Low-Dose CT Images , 2016, IEEE Transactions on Medical Imaging.

[41]  V. Goh,et al.  Assessment of primary colorectal cancer heterogeneity by using whole-tumor texture analysis: contrast-enhanced CT texture as a biomarker of 5-year survival. , 2013, Radiology.

[42]  Zhengrong Liang,et al.  A machine learning approach to construct a tissue-specific texture prior from previous full-dose CT for Bayesian reconstruction of current ultralow-dose CT images , 2019, 15th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine.

[43]  Tomaso A. Poggio,et al.  Regularization Theory and Neural Networks Architectures , 1995, Neural Computation.