Sinogram denoising via attention residual dense convolutional neural network for low-dose computed tomography

The widespread use of computed tomography (CT) in clinical practice has made the public focus on the cumulative radiation dose delivered to patients. Low-dose CT (LDCT) reduces the X-ray radiation dose, yet compromises quality and decreases diagnostic performance. Researchers have made great efforts to develop various algorithms for LDCT and introduced deep-learning techniques, which have achieved impressive results. However, most of these methods are directly performed on reconstructed LDCT images, in which some subtle structures and details are readily lost during the reconstruction procedure, and convolutional neural network (CNN)-based methods for raw LDCT projection data are rarely reported. To address this problem, we adopted an attention residual dense CNN, referred to as AttRDN, for LDCT sinogram denoising. First, it was aided by the attention mechanism, in which the advantages of both feature fusion and global residual learning were used to extract noise from the contaminated LDCT sinograms. Then, the denoised sinogram was restored by subtracting the noise obtained from the input noisy sinogram. Finally, the CT image was reconstructed using filtered back-projection. The experimental results qualitatively and quantitatively demonstrate that the proposed AttRDN can achieve a better performance than state-of-the-art methods. Importantly, it can prevent the loss of detailed information and has the potential for clinical application.

[1]  Jong Chul Ye,et al.  Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis , 2016, ArXiv.

[2]  J. Coatrieux,et al.  Improving abdomen tumor low-dose CT images using a fast dictionary learning based processing , 2013, Physics in medicine and biology.

[3]  Steve B. Jiang,et al.  Cine Cone Beam CT Reconstruction Using Low-Rank Matrix Factorization: Algorithm and a Proof-of-Principle Study , 2012, IEEE Transactions on Medical Imaging.

[4]  Jan Kautz,et al.  Loss Functions for Image Restoration With Neural Networks , 2017, IEEE Transactions on Computational Imaging.

[5]  Armando Manduca,et al.  Adaptive nonlocal means filtering based on local noise level for CT denoising. , 2013, Medical physics.

[6]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[7]  Bruno De Man,et al.  An outlook on x-ray CT research and development. , 2008, Medical physics.

[8]  Yonina C. Eldar,et al.  Structured Compressed Sensing: From Theory to Applications , 2011, IEEE Transactions on Signal Processing.

[9]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[10]  Piotr J. Slomka,et al.  Image denoising of low-radiation dose coronary CT angiography by an adaptive block-matching 3D algorithm , 2013, Medical Imaging.

[11]  Shanghai Jiang,et al.  Hybrid reconstruction algorithm for computed tomography based on diagonal total variation , 2018, Nuclear Science and Techniques.

[12]  Uwe Kruger,et al.  Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction , 2019, Nat. Mach. Intell..

[13]  Jing Wang,et al.  Penalized weighted least-squares approach to sinogram noise reduction and image reconstruction for low-dose X-ray computed tomography , 2006, IEEE Transactions on Medical Imaging.

[14]  Ge Wang,et al.  Low-Dose CT Image Denoising Using a Generative Adversarial Network With a Hybrid Loss Function for Noise Learning , 2020, IEEE Access.

[15]  Jin Keun Seo,et al.  CT sinogram‐consistency learning for metal‐induced beam hardening correction , 2017, Medical physics.

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

[17]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[18]  T. Mohammed,et al.  Patient size matters: Effect of tube current modulation on size‐specific dose estimates (SSDE) and image quality in low‐dose lung cancer screening CT , 2020, Journal of applied clinical medical physics.

[19]  Yuxiang Xing,et al.  Slice-wise reconstruction for low-dose cone-beam CT using a deep residual convolutional neural network , 2019, Nuclear Science and Techniques.

[20]  Yun Fu,et al.  Residual Dense Network for Image Restoration , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Ge Wang,et al.  Spectral CT Reconstruction With Image Sparsity and Spectral Mean , 2016, IEEE Transactions on Computational Imaging.

[22]  Cynthia M. McCollough,et al.  Projection space denoising with bilateral filtering and CT noise modeling for dose reduction in CT. , 2009, Medical physics.

[23]  Joachim Hornegger,et al.  Ray Contribution Masks for Structure Adaptive Sinogram Filtering , 2012, IEEE Transactions on Medical Imaging.

[24]  C. McCollough TU-FG-207A-04: Overview of the Low Dose CT Grand Challenge. , 2016, Medical physics.

[25]  Q. Gao,et al.  Physical studies of minor actinide transmutation in the accelerator-driven subcritical system , 2019, Nuclear Science and Techniques.

[26]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[28]  Ge Wang,et al.  Analytic Comparison Between X-Ray Fluorescence CT and K-Edge CT , 2014, IEEE Transactions on Biomedical Engineering.

[29]  Huazhong Shu,et al.  Artifact Suppressed Dictionary Learning for Low-Dose CT Image Processing , 2014, IEEE Transactions on Medical Imaging.

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

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

[32]  Srinivasan Vedantham,et al.  Cone-beam breast computed tomography using ultra-fast image reconstruction with constrained, total-variation minimization for suppression of artifacts. , 2020, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics.

[33]  Hongbing Lu,et al.  Nonlinear sinogram smoothing for low-dose X-ray CT , 2004 .

[34]  Peng He,et al.  Low-dose CT with a deep convolutional neural network blocks model using mean squared error loss and structural similar loss , 2019, Other Conferences.

[35]  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.

[36]  Mannudeep K. Kalra,et al.  Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN) , 2017, ArXiv.

[37]  Yun Fu,et al.  Residual Dense Network for Image Super-Resolution , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[38]  Jin Keun Seo,et al.  Sinogram-consistency learning in CT for metal artifact reduction , 2017, ArXiv.