Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstruction

We propose a provably convergent method, called Efficient Learned Descent Algorithm (ELDA), for low-dose CT (LDCT) reconstruction. ELDA is a highly interpretable neural network architecture with learned parameters and meanwhile retains convergence guarantee as classical optimization algorithms. To improve reconstruction quality, the proposed ELDA also employs a new non-local feature mapping and an associated regularizer. We compare ELDA with several state-of-the-art deep image methods, such as RED-CNN and Learned Primal-Dual, on a set of LDCT reconstruction problems. Numerical experiments demonstrate improvement of reconstruction quality using ELDA with merely 19 layers, suggesting promising performance of ELDA in solution accuracy and parameter efficiency.

[1]  Claude Nahmias,et al.  Radiation Risk to Children From Computed Tomography , 2008, Pediatrics.

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

[3]  Thomas Frauenfelder,et al.  Organ Dose and Attributable Cancer Risk in Lung Cancer Screening with Low-Dose Computed Tomography , 2016, PloS one.

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

[5]  Francesco Visin,et al.  A guide to convolution arithmetic for deep learning , 2016, ArXiv.

[6]  Thomas Koehler,et al.  Ultra Low Dose CT Pulmonary Angiography with Iterative Reconstruction , 2016, PloS one.

[7]  Tim Leiner,et al.  Radiation dose reduction in pediatric great vessel stent computed tomography using iterative reconstruction: A phantom study , 2017, PloS one.

[8]  Jian Sun,et al.  Deep ADMM-Net for Compressive Sensing MRI , 2016, NIPS.

[9]  Jyh-Cheng Chen,et al.  Performance of sparse-view CT reconstruction with multi-directional gradient operators , 2019, PloS one.

[10]  B. De Man,et al.  Distance-driven projection and backprojection in three dimensions. , 2004, Physics in medicine and biology.

[11]  J. Collins,et al.  Reinforcing the Importance and Feasibility of Implementing a Low-dose Protocol for CT-guided Biopsies. , 2018, Academic radiology.

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

[13]  Jeffrey A. Fessler,et al.  Momentum-Net: Fast and Convergent Iterative Neural Network for Inverse Problems , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

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

[16]  B. De Man,et al.  Distance-driven projection and backprojection , 2002, 2002 IEEE Nuclear Science Symposium Conference Record.

[17]  Jonas Adler,et al.  Learned Primal-Dual Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[18]  Quanzheng Li,et al.  Iterative Low-Dose CT Reconstruction With Priors Trained by Artificial Neural Network , 2017, IEEE Transactions on Medical Imaging.

[19]  A. Cormack.  Representation of a Function by Its Line Integrals, with Some Radiological Applications , 1963 .

[20]  Zhengrong Liang,et al.  Sinogram noise reduction for low-dose CT by statistics-based nonlinear filters , 2005, SPIE Medical Imaging.

[21]  Gaohang Yu,et al.  Sparse-view x-ray CT reconstruction via total generalized variation regularization , 2014, Physics in medicine and biology.

[22]  D. Brenner,et al.  Estimated risks of radiation-induced fatal cancer from pediatric CT. , 2001, AJR. American journal of roentgenology.

[23]  Jeffrey A. Fessler,et al.  PWLS-ULTRA: An Efficient Clustering and Learning-Based Approach for Low-Dose 3D CT Image Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[24]  Juan Feng,et al.  Hybrid-Domain Neural Network Processing for Sparse-View CT Reconstruction , 2021, IEEE Transactions on Radiation and Plasma Medical Sciences.

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

[26]  Jeffrey A. Fessler,et al.  Convolutional Analysis Operator Learning: Acceleration and Convergence , 2018, IEEE Transactions on Image Processing.

[27]  Yan Liu,et al.  MAGIC: Manifold and Graph Integrative Convolutional Network for Low-Dose CT Reconstruction , 2020, IEEE Transactions on Medical Imaging.

[28]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.

[29]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[30]  Yaoqin Xie,et al.  A Sparse-View CT Reconstruction Method Based on Combination of DenseNet and Deconvolution , 2018, IEEE Transactions on Medical Imaging.

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

[32]  C. McCollough.  TU-FG-207A-04: Overview of the Low Dose CT Grand Challenge. , 2016, Medical physics.

[33]  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.

[34]  Thomas Flohr,et al.  Iterative reconstruction in image space (IRIS) and lesion detection in abdominal CT , 2010, Medical Imaging.

[35]  Jaejun Yoo,et al.  Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network , 2017, IEEE Transactions on Medical Imaging.

[36]  Ali Borji,et al.  What are the Receptive, Effective Receptive, and Projective Fields of Neurons in Convolutional Neural Networks? , 2017, ArXiv.

[37]  Jong Chul Ye,et al.  Framing U-Net via Deep Convolutional Framelets: Application to Sparse-View CT , 2017, IEEE Transactions on Medical Imaging.

[38]  Jeffrey A. Fessler,et al.  Convolutional Dictionary Learning: Acceleration and Convergence , 2017, IEEE Transactions on Image Processing.

[39]  Yurii Nesterov,et al.  Smooth minimization of non-smooth functions , 2005, Math. Program..

[40]  Yuxiang Xing,et al.  Improve angular resolution for sparse-view CT with residual convolutional neural network , 2018, Medical Imaging.

[41]  Jeffrey A. Fessler,et al.  SPULTRA: Low-Dose CT Image Reconstruction With Joint Statistical and Learned Image Models , 2018, IEEE Transactions on Medical Imaging.

[42]  Jeffrey A. Fessler,et al.  BCD-Net for Low-dose CT Reconstruction: Acceleration, Convergence, and Generalization , 2019, MICCAI.

[43]  G. Hounsfield.  Computerized transverse axial scanning (tomography). 1. Description of system. , 1973, The British journal of radiology.

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

[45]  Il Yong Chun,et al.  Momentum-Net for Low-Dose CT Image Reconstruction , 2020, ArXiv.

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

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

[48]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[49]  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.

[50]  Shipeng Xie,et al.  Artifact Removal in Sparse-Angle CT Based on Feature Fusion Residual Network , 2021, IEEE Transactions on Radiation and Plasma Medical Sciences.

[51]  Arnold M. R. Schilham,et al.  Iterative reconstruction techniques for computed tomography part 2: initial results in dose reduction and image quality , 2013, European Radiology.

[52]  J. Leipsic,et al.  State of the Art: Iterative CT Reconstruction Techniques. , 2015, Radiology.

[53]  Jongha Lee,et al.  View-interpolation of sparsely sampled sinogram using convolutional neural network , 2017, Medical Imaging.

[54]  Xiaojing Ye,et al.  Learnable Descent Algorithm for Nonsmooth Nonconvex Image Reconstruction , 2021, SIAM J. Imaging Sci..

[55]  F. Clarke.  Optimization And Nonsmooth Analysis , 1983 .

[56]  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..