PIE-ARNet: Prior Image Enhanced Artifact Removal Network for Limited-Angle DECT

Dual-energy computed tomography (DECT) is of great clinical significance because it can simultaneously visualize the internal structure of the scanned object and provide material-specific information. DECT obtains two attenuation measurements of the same object at two different X-ray spectra, resulting in obvious redundant information. In this context, this article suggests acquiring dual-energy projection data using two complementary incomplete scans and utilizes a pretrained Prior-Net to generate the artifact-free prior image. Then the prior image is fed into the proposed prior image enhanced artifact removal network (PIE-ARNet) together with the degraded DECT images to improve the artifact removal performance. The generator of PIE-ARNet has two encoders and two decoders, with each component being responsible for a specific task. Two encoders extract and fuse prior information and image features, while two decoders perform differential learning for data in different energy channels. The discriminator of PIE-ARNet is dedicated to transferring the real statistical properties to the generated images, producing results with enhanced visual perception. Please note that Prior-Net could be trained using the freely available conventional single-energy CT data, which will not bring extra demand for DECT data. Experiments based on the simulated data and real rat data have demonstrated the promising performance of the proposed PIE-ARNet in removing artifacts, recovering image details, and preserving reconstruction accuracy.

[1]  Jun Zhang,et al.  A Deep Convolutional Gated Recurrent Unit for CT Image Reconstruction , 2022, IEEE Transactions on Neural Networks and Learning Systems.

[2]  S. Ohira,et al.  Pseudo low-energy monochromatic imaging of head and neck cancers: Deep learning image reconstruction with dual-energy CT , 2022, International Journal of Computer Assisted Radiology and Surgery.

[3]  Quanzheng Li,et al.  End-to-end deep learning for interior tomography with low-dose x-ray CT , 2022, Physics in medicine and biology.

[4]  D. Liang,et al.  Quantitative dual-energy CBCT imaging with deep triple-material decomposition , 2022, Medical Imaging.

[5]  Dianlin Hu,et al.  DIOR: Deep Iterative Optimization-Based Residual-Learning for Limited-Angle CT Reconstruction , 2022, IEEE Transactions on Medical Imaging.

[6]  Y. Noda,et al.  Deep-learning image-reconstruction algorithm for dual-energy CT angiography with reduced iodine dose: preliminary results. , 2021, Clinical radiology.

[7]  Selin S. Aslan,et al.  Limited-angle computed tomography with deep image and physics priors , 2021, Scientific Reports.

[8]  Guang-Hong Chen,et al.  Accurate and robust sparse-view angle CT image reconstruction using deep learning and prior image constrained compressed sensing (DL-PICCS). , 2021, Medical physics.

[9]  J. Pauly,et al.  NeRP: Implicit Neural Representation Learning With Prior Embedding for Sparsely Sampled Image Reconstruction , 2021, IEEE Transactions on Neural Networks and Learning Systems.

[10]  Hongming Shan,et al.  DU-GAN: Generative Adversarial Networks With Dual-Domain U-Net-Based Discriminators for Low-Dose CT Denoising , 2021, IEEE Transactions on Instrumentation and Measurement.

[11]  E. Sidky,et al.  Dual-energy CT imaging with limited-angular-range data , 2021, Physics in medicine and biology.

[12]  Lei Zhu,et al.  Fast and Effective Single-Scan Dual-Energy Cone-Beam CT Reconstruction and Decomposition Denoising Based on Dual-Energy Vectorization. , 2021, Medical physics.

[13]  Hengyong Yu,et al.  CLEAR: Comprehensive Learning Enabled Adversarial Reconstruction for Subtle Structure Enhanced Low-Dose CT Imaging , 2021, IEEE Transactions on Medical Imaging.

[14]  Quanzheng Li,et al.  Iterative material decomposition for spectral CT using self-supervised Noise2Noise prior , 2021, Physics in medicine and biology.

[15]  Guangming Lu,et al.  DS-TransUNet: Dual Swin Transformer U-Net for Medical Image Segmentation , 2021, IEEE Transactions on Instrumentation and Measurement.

[16]  Bin Yan,et al.  Image-domain material decomposition for single-energy CT images using cascaded network , 2021, 2021 International Conference on Artificial Intelligence and Electromechanical Automation (AIEA).

[17]  S. Oda,et al.  Conditional generative adversarial networks to generate pseudo low monoenergetic CT image from a single-tube voltage CT scanner. , 2021, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics.

[18]  Kanggeun Lee,et al.  ISCL: Interdependent Self-Cooperative Learning for Unpaired Image Denoising , 2021, IEEE Transactions on Medical Imaging.

[19]  T. Kimura,et al.  Image synthesis of monoenergetic CT image in dual‐energy CT using kilovoltage CT with deep convolutional generative adversarial networks , 2021, Journal of applied clinical medical physics.

[20]  Lei Xing,et al.  Estimating dual-energy CT imaging from single-energy CT data with material decomposition convolutional neural network , 2021, Medical Image Anal..

[21]  Hsuan-Ming Huang,et al.  Generation of Brain Dual-Energy CT from Single-Energy CT Using Deep Learning , 2021, Journal of Digital Imaging.

[22]  Zhanli Hu,et al.  The synthesis of high-energy CT images from low-energy CT images using an improved cycle generative adversarial network. , 2021, Quantitative imaging in medicine and surgery.

[23]  Ailong Cai,et al.  One half-scan dual-energy CT imaging using the Dual-domain Dual-way Estimated Network (DoDa-Net) model. , 2021, Quantitative imaging in medicine and surgery.

[24]  Il Yong Chun,et al.  An Improved Iterative Neural Network for High-Quality Image-Domain Material Decomposition in Dual-Energy CT , 2020, Medical physics.

[25]  Jong Chul Ye,et al.  Deep learning for tomographic image reconstruction , 2020, Nature Machine Intelligence.

[26]  Daisuke Kawahara,et al.  Image synthesis with deep convolutional generative adversarial networks for material decomposition in dual-energy CT from a kilovoltage CT , 2020, Comput. Biol. Medicine.

[27]  Shuai Leng,et al.  Low Dose CT Image and Projection Dataset. , 2020, Medical physics.

[28]  Bruno De Man,et al.  Virtual Monoenergetic CT Imaging via Deep Learning , 2020, Patterns.

[29]  Ailong Cai,et al.  An effective sinogram inpainting for complementary limited-angle dual-energy computed tomography imaging using generative adversarial networks. , 2020, Journal of X-ray science and technology.

[30]  Yang Chen,et al.  Iterative Reconstruction for Low-Dose CT Using Deep Gradient Priors of Generative Model , 2020, IEEE Transactions on Radiation and Plasma Medical Sciences.

[31]  Yikun Zhang,et al.  DIRECT-Net: a unified mutual-domain material decomposition network for quantitative dual-energy CT imaging. , 2020, Medical physics.

[32]  Zhongqi Wang,et al.  A material decomposition method for dual-energy CT via dual interactive Wasserstein generative adversarial networks. , 2020, Medical physics.

[33]  Yanning Zhang,et al.  Deep Blind Hyperspectral Image Super-Resolution , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[34]  Xiaofeng Yang,et al.  Learning-based synthetic dual energy CT imaging from single energy CT for stopping power ratio calculation in proton radiation therapy. , 2020, The British journal of radiology.

[35]  Yang Chen,et al.  A deep learning approach for virtual monochromatic spectral CT imaging with a standard single energy CT scanner , 2020, 2005.09859.

[36]  Jianxing Feng,et al.  End-to-End Unpaired Image Denoising with Conditional Adversarial Networks , 2020, AAAI.

[37]  Hairong Zheng,et al.  Dual-energy CT reconstruction using deep mutual-domain knowledge for basis decomposition and denoising , 2020 .

[38]  Lei Li,et al.  Reconstruction method for DECT with one half-scan plus a second limited-angle scan using prior knowledge of complementary support set (Pri-CSS) , 2019, Physics in medicine and biology.

[39]  Wei Zhao,et al.  Patient-specific reconstruction of volumetric computed tomography images from a single projection view via deep learning , 2019, Nature Biomedical Engineering.

[40]  Jiebo Luo,et al.  ADN: Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction , 2019, IEEE Transactions on Medical Imaging.

[41]  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..

[42]  Z. Weng,et al.  X2CT-GAN: Reconstructing CT From Biplanar X-Rays With Generative Adversarial Networks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[43]  D. Sahani,et al.  Dual-Source Dual-Energy CT in Detection and Characterization of Urinary Stones in Patients With Large Body Habitus: Observations in a Large Cohort. , 2019, AJR. American journal of roentgenology.

[44]  Paul Babyn,et al.  Generative Adversarial Network in Medical Imaging: A Review , 2018, Medical Image Anal..

[45]  Bin Yan,et al.  Image Decomposition Algorithm for Dual-Energy Computed Tomography via Fully Convolutional Network , 2018, Comput. Math. Methods Medicine.

[46]  Jeffrey A. Fessler,et al.  Image Reconstruction is a New Frontier of Machine Learning , 2018, IEEE Transactions on Medical Imaging.

[47]  Bin Yan,et al.  Image domain dual material decomposition for dual-energy CT using butterfly network. , 2018, Medical physics.

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

[49]  Lei Zhu,et al.  Single-Scan Dual-Energy CT Using Primary Modulation , 2018, IEEE Transactions on Medical Imaging.

[50]  Changhwan Kim,et al.  A Feasibility Study of Low-Dose Single-Scan Dual-Energy Cone-Beam CT in Many-View Under-Sampling Framework , 2017, IEEE Transactions on Medical Imaging.

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

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

[53]  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.

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

[55]  Jianhua Ma,et al.  Iterative reconstruction for dual energy CT with an average image-induced nonlocal means regularization , 2017, Physics in medicine and biology.

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

[57]  Bruce R. Rosen,et al.  Image reconstruction by domain-transform manifold learning , 2017, Nature.

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

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

[60]  M. Kachelriess,et al.  Performance of today's dual energy CT and future multi energy CT in virtual non-contrast imaging and in iodine quantification: A simulation study. , 2015, Medical physics.

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

[62]  Shuai Leng,et al.  Maximizing Iodine Contrast-to-Noise Ratios in Abdominal CT Imaging through Use of Energy Domain Noise Reduction and Virtual Monoenergetic Dual-Energy CT. , 2015, Radiology.

[63]  Thomas Henzler,et al.  Optimization of kiloelectron volt settings in cerebral and cervical dual-energy CT angiography determined with virtual monoenergetic imaging. , 2014, Academic radiology.

[64]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[65]  Guang-Hong Chen,et al.  Dual energy CT using slow kVp switching acquisition and prior image constrained compressed sensing , 2010, Physics in medicine and biology.

[66]  Li Zhang,et al.  An improved TV minimization algorithm for incomplete data problem in computer tomography , 2010, IEEE Nuclear Science Symposuim & Medical Imaging Conference.

[67]  C D Claussen,et al.  Automatic bone and plaque removal using dual energy CT for head and neck angiography: feasibility and initial performance evaluation. , 2010, European journal of radiology.

[68]  Borut Marincek,et al.  Characterization of Urinary Stones With Dual-Energy CT: Improved Differentiation Using a Tin Filter , 2010, Investigative radiology.

[69]  Maximilian F Reiser,et al.  Cervical and Cranial Computed Tomographic Angiography With Automated Bone Removal: Dual Energy Computed Tomography Versus Standard Computed Tomography , 2009, Investigative radiology.

[70]  Jie Tang,et al.  Prior image constrained compressed sensing (PICCS): a method to accurately reconstruct dynamic CT images from highly undersampled projection data sets. , 2008, Medical physics.

[71]  L. Feldkamp,et al.  Practical cone-beam algorithm , 1984 .

[72]  Dexin Ma,et al.  Deep Siamese Semantic Segmentation Network for PCB Welding Defect Detection , 2022, IEEE Transactions on Instrumentation and Measurement.

[73]  Lei Yang,et al.  An Automatic Deep Segmentation Network for Pixel-Level Welding Defect Detection , 2022, IEEE Transactions on Instrumentation and Measurement.

[74]  Qiegen Liu,et al.  SPECIAL: Single-Shot Projection Error Correction Integrated Adversarial Learning for Limited-Angle CT , 2021, IEEE Transactions on Computational Imaging.

[75]  Weiwen Wu,et al.  Spectral-Image Decomposition With Energy-Fusion Sensing for Spectral CT Reconstruction , 2021, IEEE Transactions on Instrumentation and Measurement.

[76]  Hossein Rabbani,et al.  A Lightweight Mimic Convolutional Auto-Encoder for Denoising Retinal Optical Coherence Tomography Images , 2021, IEEE Transactions on Instrumentation and Measurement.

[77]  Weiwen Wu,et al.  A High-Quality Photon-Counting CT Technique Based on Weight Adaptive Total-Variation and Image-Spectral Tensor Factorization for Small Animals Imaging , 2021, IEEE Transactions on Instrumentation and Measurement.

[78]  Qiegen Liu,et al.  CD-Net: Comprehensive Domain Network With Spectral Complementary for DECT Sparse-View Reconstruction , 2021, IEEE Transactions on Computational Imaging.

[79]  Dong Liang,et al.  CaGAN: A Cycle-Consistent Generative Adversarial Network With Attention for Low-Dose CT Imaging , 2020, IEEE Transactions on Computational Imaging.

[80]  Zhaoying Bian,et al.  Iterative reconstruction for low dose dual energy CT using information-divergence constrained spectral redundancy information. , 2018, Journal of X-ray science and technology.

[81]  中澤 哲郎.  Lung perfused blood volume images with dual-energy computed tomography for chronic thromboembolic pulmonary hypertension : correlation to scintigraphy with single-photon emission computed tomography , 2012 .