Unsupervised PET Reconstruction from a Bayesian Perspective

Positron emission tomography (PET) reconstruction becomes an ill-posed inverse problem due to the low-count projection data (sinogram). In this paper, we leverage DeepRED from a Bayesian perspective to reconstruct PET image from a single corrupted sinogram without any supervised or auxiliary in-formation. DeepRED is a typical representation learning that combines deep image prior (DIP) and regularization by de-noising (RED) to mitigate the overfitting of network training. Instead of the conventional denoisers usually used in RED, DnCNN-like denoiser, which can constrain the DIP adaptively and facilitate the derivation, is employed. Moreover, stochastic gradient Langevin dynamics (SGLD) is utilized to approximate the Markov chain Monte Carlo (MCMC) sampler. Specifically, Gaussian noise is injected into the gradient updates to further relieve the overfitting. Experimental studies on whole-body dataset demonstrate that our proposed method can achieve better performance compared to several classic and state-of-the-art methods in both qualitative and quantitative aspects.

[1]  A. Mehranian,et al.  Image enhancement of whole-body oncology [18F]-FDG PET scans using deep neural networks to reduce noise , 2021, European Journal of Nuclear Medicine and Molecular Imaging.

[2]  Jiliu Zhou,et al.  CT Reconstruction With PDF: Parameter-Dependent Framework for Data From Multiple Geometries and Dose Levels , 2021, IEEE Transactions on Medical Imaging.

[3]  Yu-Jung Tsai,et al.  MDPET: A Unified Motion Correction and Denoising Adversarial Network for Low-Dose Gated PET , 2021, IEEE Transactions on Medical Imaging.

[4]  Thomas Carlier,et al.  Low-count PET image reconstruction with Bayesian inference over a Deep Prior , 2021, Medical Imaging.

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

[6]  Long Zhou,et al.  Supervised learning with cyclegan for low-dose FDG PET image denoising , 2020, Medical Image Anal..

[7]  A. Mehranian,et al.  Model-Based Deep Learning PET Image Reconstruction Using Forward–Backward Splitting Expectation–Maximization , 2020, IEEE Transactions on Radiation and Plasma Medical Sciences.

[8]  Hairong Zheng,et al.  DPIR-Net: Direct PET Image Reconstruction Based on the Wasserstein Generative Adversarial Network , 2020, IEEE Transactions on Radiation and Plasma Medical Sciences.

[9]  Yan Liu,et al.  MD-Recon-Net: A Parallel Dual-Domain Convolutional Neural Network for Compressed Sensing MRI , 2020, IEEE Transactions on Radiation and Plasma Medical Sciences.

[10]  Positron , 2020, Definitions.

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

[12]  Hidekata Hontani,et al.  Dynamic PET Image Reconstruction Using Nonnegative Matrix Factorization Incorporated With Deep Image Prior , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[13]  Andrew J. Reader,et al.  Model-Based Deep Learning PET Image Reconstruction Using Forward-Backward Splitting Expectation Maximisation , 2019, 2019 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC).

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

[15]  Jiahe Tian,et al.  PET image denoising using unsupervised deep learning , 2019, European Journal of Nuclear Medicine and Molecular Imaging.

[16]  Ciprian Catana,et al.  PET Image Reconstruction Using Deep Image Prior , 2019, IEEE Transactions on Medical Imaging.

[17]  Jeffrey A. Fessler,et al.  Improved Low-Count Quantitative PET Reconstruction With an Iterative Neural Network , 2019, IEEE Transactions on Medical Imaging.

[18]  Chih-Chieh Liu,et al.  Higher SNR PET image prediction using a deep learning model and MRI image , 2019, Physics in medicine and biology.

[19]  Subhransu Maji,et al.  A Bayesian Perspective on the Deep Image Prior , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Michael Elad,et al.  DeepRED: Deep Image Prior Powered by RED , 2019, ICCV 2019.

[21]  Chih-Chieh Liu,et al.  PET Image Denoising Using a Deep Neural Network Through Fine Tuning , 2019, IEEE Transactions on Radiation and Plasma Medical Sciences.

[22]  Eric Moulines,et al.  The promises and pitfalls of Stochastic Gradient Langevin Dynamics , 2018, NeurIPS.

[23]  Nicolas Dobigeon,et al.  Factor Analysis of Dynamic PET Images: Beyond Gaussian Noise , 2018, IEEE Transactions on Medical Imaging.

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

[25]  Jeffrey A. Fessler,et al.  Deep BCD-Net Using Identical Encoding-Decoding CNN Structures for Iterative Image Recovery , 2018, 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP).

[26]  Andrea Vedaldi,et al.  Deep Image Prior , 2017, International Journal of Computer Vision.

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

[28]  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.

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

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

[31]  Huafeng Liu,et al.  Low Dose PET Image Reconstruction with Total Variation Using Alternating Direction Method , 2016, PloS one.

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

[33]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[34]  Lawrence Carin,et al.  Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks , 2015, AAAI.

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

[36]  Emil Y. Sidky,et al.  Investigation of optimization-based reconstruction with an image-total-variation constraint in PET , 2015, 2015 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC).

[37]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[39]  Michael Elad,et al.  Boosting of Image Denoising Algorithms , 2015, SIAM J. Imaging Sci..

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

[41]  Peyman Milanfar,et al.  A General Framework for Regularized, Similarity-Based Image Restoration , 2014, IEEE Transactions on Image Processing.

[42]  Chung Chan,et al.  Postreconstruction Nonlocal Means Filtering of Whole-Body PET With an Anatomical Prior , 2014, IEEE Transactions on Medical Imaging.

[43]  Tianqi Chen,et al.  Stochastic Gradient Hamiltonian Monte Carlo , 2014, ICML.

[44]  Stephen M. Moore,et al.  The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository , 2013, Journal of Digital Imaging.

[45]  J. Qi,et al.  PET image reconstruction using kernel method , 2013, 2013 IEEE 10th International Symposium on Biomedical Imaging.

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

[47]  Max Welling,et al.  Bayesian Posterior Sampling via Stochastic Gradient Fisher Scoring , 2012, ICML.

[48]  Jungah Son,et al.  Gap compensation during PET image reconstruction by constrained, total variation minimization. , 2012, Medical physics.

[49]  J. Qi,et al.  PET image reconstruction with anatomical edge guided level set prior , 2011, Physics in medicine and biology.

[50]  Uygar Tuna,et al.  PET sinogram denoising by block-matching and 3D filtering , 2011, 2011 IEEE Nuclear Science Symposium Conference Record.

[51]  Yee Whye Teh,et al.  Bayesian Learning via Stochastic Gradient Langevin Dynamics , 2011, ICML.

[52]  Simon R. Arridge,et al.  PET Image Reconstruction Using Information Theoretic Anatomical Priors , 2011, IEEE Transactions on Medical Imaging.

[53]  S. Meikle,et al.  Regularized image reconstruction with an anatomically adaptive prior for positron emission tomography , 2009, Physics in medicine and biology.

[54]  M. Burger,et al.  Accurate EM-TV algorithm in PET with low SNR , 2008, 2008 IEEE Nuclear Science Symposium Conference Record.

[55]  Richard M. Leahy,et al.  Analysis of Resolution and Noise Properties of Nonquadratically Regularized Image Reconstruction Methods for PET , 2008, IEEE Transactions on Medical Imaging.

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

[57]  Jean-Michel Morel,et al.  A non-local algorithm for image denoising , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[58]  Andrew F. Laine,et al.  Improving PET-based physiological quantification through methods of wavelet denoising , 2001, IEEE Transactions on Biomedical Engineering.

[59]  Zhengrong Liang,et al.  A fast ray-tracing technique for TCT and ECT studies , 1999, 1999 IEEE Nuclear Science Symposium. Conference Record. 1999 Nuclear Science Symposium and Medical Imaging Conference (Cat. No.99CH37019).

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

[61]  Shuangliang Cao,et al.  Dynamic PET Image Denoising Using Deep Image Prior Combined With Regularization by Denoising , 2021, IEEE Access.

[62]  Huafeng Liu,et al.  Low dose PET reconstruction with total variation regularization , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[63]  Yair Censor.  The Mathematics of Computerized Tomography (Classics in Applied Mathematics, Vol. 32) , 2002 .

[64]  Sk. Mohammadul Haque,et al.  Ieee Transactions on Image Processing 1 Symmetric Smoothing Filters from Global Consistency Constraints , 2022 .