PET Image Reconstruction Using a Cascading Back-Projection Neural Network

Positron emission tomography (PET) imaging is a noninvasive technique that makes it possible to probe biological metabolic processes in vivo. However, PET image reconstruction is challenging due to the ill-posedness of the inverse problem. Many image reconstruction methods have been proposed over the past few years to improve diagnostic performance. However, most of these methods can compromise the reconstruction of important high-frequency structural details after aggressive denoising. To address this problem, in this work, we propose a novel deep learning method that reconstructs PET images using a cascading back-projection neural network (bpNet). This network consists of a domain translation operation, which acts as prior knowledge, cascaded with a modified encoder-decoder network. The image reconstruction pipeline ranges from the sinogram to the back-projection image and then to the PET image. Quantitative results from simulation data and Derenzo phantom experiments with the small animal PET prototype system developed in our laboratory clearly demonstrate that our proposed method provides favorable reconstructed image quality, especially for low-count PET image reconstruction.

[1]  E. Sidky,et al.  Convex optimization problem prototyping for image reconstruction in computed tomography with the Chambolle–Pock algorithm , 2011, Physics in medicine and biology.

[2]  Guobao Wang,et al.  Penalized Likelihood PET Image Reconstruction Using Patch-Based Edge-Preserving Regularization , 2012, IEEE Transactions on Medical Imaging.

[3]  Ashrani Aizzuddin Abd. Rahni,et al.  Modelling the GE discovery 690 PET/CT scanner , 2015, 2015 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).

[4]  Quanzheng Li,et al.  Iterative PET Image Reconstruction Using Convolutional Neural Network Representation , 2017, IEEE Transactions on Medical Imaging.

[5]  Michel Defrise,et al.  Exact and approximate rebinning algorithms for 3-D PET data , 1997, IEEE Transactions on Medical Imaging.

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

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

[8]  Jong Hoon Kim,et al.  Penalized PET Reconstruction Using Deep Learning Prior and Local Linear Fitting , 2018, IEEE Transactions on Medical Imaging.

[9]  Dong Liang,et al.  Super-resolution of PET image based on dictionary learning and random forests , 2019, Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment.

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

[11]  Jeffrey A. Fessler,et al.  Globally convergent image reconstruction for emission tomography using relaxed ordered subsets algorithms , 2003, IEEE Transactions on Medical Imaging.

[12]  Ke Li,et al.  Learning to Reconstruct Computed Tomography Images Directly From Sinogram Data Under A Variety of Data Acquisition Conditions , 2019, IEEE Transactions on Medical Imaging.

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

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

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

[16]  Pawel Markiewicz,et al.  PET Reconstruction With an Anatomical MRI Prior Using Parallel Level Sets , 2016, IEEE Transactions on Medical Imaging.

[17]  Hakan Erdogan,et al.  Ordered subsets algorithms for transmission tomography. , 1999, Physics in medicine and biology.

[18]  Gengsheng Lawrence Zeng,et al.  Medical Image Reconstruction: A Conceptual Tutorial , 2010 .

[19]  Ce Liu,et al.  Deep Convolutional Neural Network for Image Deconvolution , 2014, NIPS.

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

[21]  L. Shepp,et al.  Maximum Likelihood Reconstruction for Emission Tomography , 1983, IEEE Transactions on Medical Imaging.

[22]  Jianwei Chen,et al.  Deconvolution-Based Backproject-Filter (BPF) Computed Tomography Image Reconstruction Method Using Deep Learning Technique , 2018 .

[23]  Dong Liang,et al.  Image reconstruction for positron emission tomography based on patch‐based regularization and dictionary learning , 2019, Medical physics.

[24]  Guobao Wang,et al.  Direct Patlak Reconstruction From Dynamic PET Data Using the Kernel Method With MRI Information Based on Structural Similarity , 2018, IEEE Transactions on Medical Imaging.

[25]  Guobao Wang,et al.  Anatomically-aided PET reconstruction using the kernel method , 2016, Physics in medicine and biology.

[26]  O. Mawlawi,et al.  Performance characteristics of a newly developed PET/CT scanner using NEMA standards in 2D and 3D modes. , 2004, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[27]  Vladimir Panin,et al.  Image Reconstruction Using TOF Back Projection and a Deblurring Neural Network , 2019, 2019 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC).

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

[29]  John L. Humm,et al.  Relaxed ordered subset preconditioned alternating projection algorithm for PET reconstruction with automated penalty weight selection , 2017, Medical physics.

[30]  Andrew J Reader,et al.  Patch-based image reconstruction for PET using prior-image derived dictionaries , 2016, Physics in medicine and biology.

[31]  Hengyong Yu,et al.  Convolutional Neural Network Based Metal Artifact Reduction in X-Ray Computed Tomography , 2017, IEEE Transactions on Medical Imaging.

[32]  Dong Liang,et al.  Low-count PET image restoration using sparse representation , 2018 .

[33]  Thomas J. Fuchs,et al.  DeepPET: A deep encoder–decoder network for directly solving the PET image reconstruction inverse problem , 2018, Medical Image Anal..

[34]  G. Muehllehner,et al.  Positron emission tomography , 2006, Physics in medicine and biology.

[35]  Alan C. Evans,et al.  BrainWeb: Online Interface to a 3D MRI Simulated Brain Database , 1997 .

[36]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[37]  Dong Liang,et al.  Artifact correction in low‐dose dental CT imaging using Wasserstein generative adversarial networks , 2019, Medical physics.

[38]  Zoubin Ghahramani,et al.  Probabilistic machine learning and artificial intelligence , 2015, Nature.

[39]  Chen Guo,et al.  ADMM-EM Method for L 1-Norm Regularized Weighted Least Squares PET Reconstruction , 2016, Comput. Math. Methods Medicine.

[40]  A. McMillan,et al.  Deep learning Mr imaging–based attenuation correction for PeT/Mr imaging 1 , 2017 .

[41]  Shuhang Chen,et al.  Sparse representation and dictionary learning penalized image reconstruction for positron emission tomography , 2015, Physics in medicine and biology.