Parameter Constrained Transfer Learning for Low Dose PET Image Denoising

Positron emission tomography (PET) is widely used in clinical practice. However, the potential risk of PET-associated radiation dose to patients needs to be minimized. With reduction of the radiation dose, the resultant images may suffer from noise and artifacts which compromises the diagnostic performance. In this paper, we propose a parameter-constrained generative adversarial network with Wasserstein distance and perceptual loss (PC-WGAN) for low-dose PET image denoising. This method makes two main contributions: 1) a PC-WGAN framework is designed to denoise low-dose PET images without compromising structural details; and 2) a transfer learning strategy is developed to train PC-WGAN with parameters being constrained, which has major merits; namely, making the training process of PC-WGAN efficient and improving the quality of denoised images. The experimental results on clinical data show that the proposed network can suppress image noise more effectively while preserving better image fidelity than three selected state-of-the-art methods.

[1]  Paul Kinahan,et al.  A combined PET/CT scanner for clinical oncology. , 2000, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[2]  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).

[3]  Josef Machac,et al.  Cardiac positron emission tomography imaging. , 2005, Seminars in nuclear medicine.

[4]  Karen O. Egiazarian,et al.  Image denoising with block-matching and 3D filtering , 2006, Electronic Imaging.

[5]  L. Tanoue.  Computed Tomography — An Increasing Source of Radiation Exposure , 2009 .

[6]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

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

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

[9]  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.

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

[11]  Mark Slifstein,et al.  Quantitative imaging of protein targets in the human brain with PET , 2015, Physics in medicine and biology.

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

[13]  Jürgen Schmidhuber,et al.  Training Very Deep Networks , 2015, NIPS.

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

[15]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[16]  Thomas Brox,et al.  Generating Images with Perceptual Similarity Metrics based on Deep Networks , 2016, NIPS.

[17]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[18]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[19]  Junshen Xu,et al.  200x Low-dose PET Reconstruction using Deep Learning , 2017, ArXiv.

[20]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[21]  Ravi Kiran Sarvadevabhatla,et al.  An Introduction to Deep Convolutional Neural Nets for Computer Vision , 2017, Deep Learning for Medical Image Analysis.

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

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

[24]  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.

[25]  Hongming Shan,et al.  3-D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning From a 2-D Trained Network , 2018, IEEE Transactions on Medical Imaging.

[26]  Lijun Zhao,et al.  Automatic Nasopharyngeal Carcinoma Segmentation Using Fully Convolutional Networks with Auxiliary Paths on Dual-Modality PET-CT Images , 2019, Journal of Digital Imaging.

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

[28]  Quanzheng Li,et al.  Attenuation Correction of PET/MR Using Cycle-Consistent Adversarial Network , 2019 .

[29]  Quanzheng Li,et al.  MAPEM-Net: an unrolled neural network for Fully 3D PET image reconstruction , 2019 .

[30]  Tianwei Ni,et al.  Elastic Boundary Projection for 3D Medical Image Segmentation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Pawel Markiewicz,et al.  Faster PET reconstruction with non-smooth priors by randomization and preconditioning , 2018, Physics in medicine and biology.

[32]  Kuang Gong,et al.  Generative adversarial network based regularized image reconstruction for PET , 2019, Physics in medicine and biology.