Unsupervised/Semi-supervised Deep Learning for Low-dose CT Enhancement

Recently, deep learning(DL) methods have been proposed for the low-dose computed tomography(LdCT) enhancement, and obtain good trade-off between computational efficiency and image quality. Most of them need large number of pre-collected ground-truth/high-dose sinograms with less noise, and train the network in a supervised end-to-end manner. This may bring major limitations on these methods because the number of such low-dose/high-dose training sinogram pairs would affect the network's capability and sometimes the ground-truth sinograms are hard to be obtained in large scale. Since large number of low-dose ones are relatively easy to obtain, it should be critical to make these sources play roles in network training in an unsupervised learning manner. To address this issue, we propose an unsupervised DL method for LdCT enhancement that incorporates unlabeled LdCT sinograms directly into the network training. The proposed method effectively considers the structure characteristics and noise distribution in the measured LdCT sinogram, and then learns the proper gradient of the LdCT sinogram in a pure unsupervised manner. Similar to the labeled ground-truth, the gradient information in an unlabeled LdCT sinogram can be used for sufficient network training. The experiments on the patient data show effectiveness of the proposed method.

[1]  David Zhang,et al.  FSIM: A Feature Similarity Index for Image Quality Assessment , 2011, IEEE Transactions on Image Processing.

[2]  Zhaoying Bian,et al.  A Simple Low-Dose X-Ray CT Simulation From High-Dose Scan , 2015, IEEE Transactions on Nuclear Science.

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

[4]  Patrick J. La Rivière,et al.  Reduction of noise-induced streak artifacts in X-ray computed tomography through spline-based penalized-likelihood sinogram smoothing , 2005, IEEE Transactions on Medical Imaging.

[5]  D Brenner MO-FG-207A-02: What Do We Really Know About Cancer Risks at Doses Pertinent to CT Scans. , 2016, Medical physics.

[6]  Zhichao Yin,et al.  GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  P. J. La Riviere Reduction of noise-induced streak artifacts in X-ray computed tomography through penalized-likelihood sinogram smoothing , 2003 .

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

[9]  Stephen J. Wright,et al.  Duality-based algorithms for total-variation-regularized image restoration , 2010, Comput. Optim. Appl..

[10]  Pingkun Yan,et al.  CT Image Denoising with Perceptive Deep Neural Networks , 2017, ArXiv.

[11]  Lei Zhang,et al.  Low-Dose X-ray CT Reconstruction via Dictionary Learning , 2012, IEEE Transactions on Medical Imaging.

[12]  Kenji Suzuki,et al.  Neural Network Convolution (NNC) for Converting Ultra-Low-Dose to "Virtual" High-Dose CT Images , 2017, MLMI@MICCAI.

[13]  Patrick J. La Rivière,et al.  Penalized-likelihood sinogram restoration for computed tomography , 2006, IEEE Transactions on Medical Imaging.

[14]  Yi Zhang,et al.  Low-Dose CT via Deep Neural Network , 2016 .

[15]  J. Hsieh Adaptive streak artifact reduction in computed tomography resulting from excessive x-ray photon noise. , 1998, Medical physics.

[16]  Zhengrong Liang,et al.  Robust Low-Dose CT Sinogram Preprocessing via Exploiting Noise-Generating Mechanism , 2017, IEEE Transactions on Medical Imaging.

[17]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[18]  Zhengrong Liang,et al.  Iterative image reconstruction for cerebral perfusion CT using a pre-contrast scan induced edge-preserving prior , 2012, Physics in medicine and biology.

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

[20]  Jingyan Xu,et al.  Electronic Noise Modeling in Statistical Iterative Reconstruction , 2009, IEEE Transactions on Image Processing.

[21]  Paul Babyn,et al.  Sharpness-Aware Low-Dose CT Denoising Using Conditional Generative Adversarial Network , 2017, Journal of Digital Imaging.

[22]  L. Xing,et al.  Iterative image reconstruction for CBCT using edge-preserving prior. , 2008, Medical physics.

[23]  Zhengrong Liang,et al.  Noise properties of low-dose CT projections and noise treatment by scale transformations , 2001, 2001 IEEE Nuclear Science Symposium Conference Record (Cat. No.01CH37310).

[24]  Jaakko Lehtinen,et al.  Noise2Noise: Learning Image Restoration without Clean Data , 2018, ICML.

[25]  Luo Ouyang,et al.  Effects of the penalty on the penalized weighted least-squares image reconstruction for low-dose CBCT. , 2011, Physics in medicine and biology.

[26]  Steve B. Jiang,et al.  Low-dose CT reconstruction via edge-preserving total variation regularization. , 2010, Physics in medicine and biology.

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

[28]  Ken D. Sauer,et al.  A generalized Gaussian image model for edge-preserving MAP estimation , 1993, IEEE Trans. Image Process..

[29]  Cong Nie,et al.  Bayesian statistical reconstruction for low-dose X-ray computed tomography using an adaptive-weighting nonlocal prior , 2009, Comput. Medical Imaging Graph..

[30]  Gabriel Kreiman,et al.  Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning , 2016, ICLR.