Sparse-View Cone Beam CT Reconstruction Using Data-Consistent Supervised and Adversarial Learning From Scarce Training Data

Reconstruction of CT images from a limited set of projections through an object is important in several applications ranging from medical imaging to industrial settings. As the number of available projections decreases, traditional reconstruction techniques such as the FDK algorithm and modelbased iterative reconstruction methods perform poorly. Recently, data-driven methods such as deep learning-based reconstruction have garnered a lot of attention in applications because they yield better performance when enough training data is available. However, even these methods have their limitations when there is a scarcity of available training data. This work focuses on image reconstruction in such settings, i.e., when both the number of available CT projections and the training data is extremely limited. We adopt a sequential reconstruction approach over several stages using an adversarially trained shallow network for ‘destreaking’ followed by a data-consistency update in each stage. To deal with the challenge of limited data, we use image subvolumes to train our method, and patch aggregation during testing. To deal with the computational challenge of learning on 3D datasets for 3D reconstruction, we use a hybrid 3D-to2D mapping network for the ‘destreaking’ part. Comparisons to other methods over several test examples indicate that the proposed method has much potential, when both the number of projections and available training data are highly limited.

[1]  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.

[2]  Yoram Bresler,et al.  MR Image Reconstruction From Highly Undersampled k-Space Data by Dictionary Learning , 2011, IEEE Transactions on Medical Imaging.

[3]  Yoram Bresler,et al.  Model-based iterative tomographic reconstruction with adaptive sparsifying transforms , 2014, Electronic Imaging.

[4]  Xiao Jin,et al.  Quantitative comparison of OSEM and penalized likelihood image reconstruction using relative difference penalties for clinical PET , 2015, Physics in medicine and biology.

[5]  Per-Erik Danielsson,et al.  Handling of long objects in iterative improvement of nonexact reconstruction in helical cone-beam CT , 2006, IEEE Transactions on Medical Imaging.

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

[7]  Steven Guan,et al.  Limited-View and Sparse Photoacoustic Tomography for Neuroimaging with Deep Learning , 2020, Scientific Reports.

[8]  Jong Chul Ye,et al.  Deep Learning Reconstruction for 9-View Dual Energy CT Baggage Scanner , 2018, ArXiv.

[9]  G T Herman,et al.  Image reconstruction from a small number of projections , 2008, Inverse problems.

[10]  C. Bouman,et al.  A recursive filter for noise reduction in statistical iterative tomographic imaging , 2006, Electronic Imaging.

[11]  Bo Yang,et al.  Sparse-view CBCT reconstruction via weighted Schatten p-norm minimization. , 2020, Optics express.

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

[13]  Songzhe Lian,et al.  Image reconstruction in sparse-view CT using improved nonlocal total variation regularization , 2019 .

[14]  Ken D. Sauer,et al.  A local update strategy for iterative reconstruction from projections , 1993, IEEE Trans. Signal Process..

[15]  Ge Wang,et al.  A Perspective on Deep Imaging , 2016, IEEE Access.

[16]  Wei Yu,et al.  Image Reconstruction for Few-view Computed Tomography Based on 0 Sparse Regularization , 2017 .

[17]  J. Fessler Statistical Image Reconstruction Methods for Transmission Tomography , 2000 .

[18]  Jun Zhao,et al.  Adaptive Prior Patch Size Based Sparse-View CT Reconstruction Algorithm , 2020, 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI).

[19]  Jeffrey A. Fessler,et al.  3D Forward and Back-Projection for X-Ray CT Using Separable Footprints , 2010, IEEE Transactions on Medical Imaging.

[20]  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.

[21]  Jeffrey A. Fessler,et al.  Improved low-count quantitative PET reconstruction with a variational neural network , 2019, ArXiv.

[22]  E. Sidky,et al.  Accurate image reconstruction from few-views and limited-angle data in divergent-beam CT , 2009, 0904.4495.

[23]  Ken D. Sauer,et al.  2.5D Deep Learning For CT Image Reconstruction Using A Multi-GPU Implementation , 2018, 2018 52nd Asilomar Conference on Signals, Systems, and Computers.

[24]  Eric Todd Quinto,et al.  Exterior and limited-angle tomography in non-destructive evaluation , 1998 .

[25]  Alexandros G. Dimakis,et al.  Deep Learning Techniques for Inverse Problems in Imaging , 2020, IEEE Journal on Selected Areas in Information Theory.

[26]  A. R. De Pierro,et al.  On the relation between the ISRA and the EM algorithm for positron emission tomography , 1993, IEEE Trans. Medical Imaging.

[27]  Jeffrey A. Fessler,et al.  Fast and convergent iterative image recovery using trained convolutional neural networks , 2018, 2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[28]  J. Schnabel,et al.  Memory-Efficient Training for Fully Unrolled Deep Learned PET Image Reconstruction with Iteration-Dependent Targets , 2021, IEEE Transactions on Radiation and Plasma Medical Sciences.

[29]  Hyojin Kim,et al.  Extreme Few-view CT Reconstruction using Deep Inference , 2019, ArXiv.

[30]  Jeffrey A. Fessler,et al.  A Splitting-Based Iterative Algorithm for Accelerated Statistical X-Ray CT Reconstruction , 2012, IEEE Transactions on Medical Imaging.

[31]  Jean-Baptiste Thibault,et al.  A three-dimensional statistical approach to improved image quality for multislice helical CT. , 2007, Medical physics.

[32]  Jeffrey A. Fessler,et al.  Blind Primed Supervised (BLIPS) Learning for MR Image Reconstruction , 2021, IEEE Transactions on Medical Imaging.

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

[34]  Ming Li,et al.  Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares , 2016, BioMedical Engineering OnLine.

[35]  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.

[36]  Michael T. McCann,et al.  Unified Supervised-Unsupervised (SUPER) Learning for X-Ray CT Image Reconstruction , 2020, IEEE Transactions on Medical Imaging.

[37]  Kees Joost Batenburg,et al.  A cone-beam X-ray computed tomography data collection designed for machine learning , 2019, Scientific Data.

[38]  Jeffrey A. Fessler,et al.  Image Reconstruction: From Sparsity to Data-Adaptive Methods and Machine Learning , 2019, Proceedings of the IEEE.

[39]  Hyojin Kim,et al.  Lose the Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[40]  Jingyan Xu,et al.  Interior and Sparse-View Image Reconstruction Using a Mixed Region and Voxel-Based ML-EM Algorithm , 2012, IEEE Transactions on Nuclear Science.

[41]  Xiaochuan Pan,et al.  Evaluation of sparse-view reconstruction from flat-panel-detector cone-beam CT , 2010, Physics in medicine and biology.

[42]  Hengyong Yu,et al.  Compressed sensing based interior tomography , 2009, Physics in medicine and biology.

[43]  Deep Learning-based Reconstruction of Volumetric CT Images of Vertebrae from a Single View X-Ray Image , 2021 .

[44]  Yonina C. Eldar,et al.  Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing , 2021, IEEE Signal Processing Magazine.

[45]  Charles A. Bouman,et al.  High-Precision Inversion of Dynamic Radiography Using Hydrodynamic Features , 2021, Optics express.

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

[47]  Jeffrey A. Fessler,et al.  Regularization Designs for Uniform Spatial Resolution and Noise Properties in Statistical Image Reconstruction for 3-D X-ray CT , 2015, IEEE Transactions on Medical Imaging.