Inpainting of Ring Artifacts on Microtomographic Images by 3D CNN

Ring artifacts are inevitable in microtomographic images. In a Digital Rock workflow, such defects might affect the subsequent segmentation and flow simulation. We propose a correction of ring artifacts in reconstructed microtomographic images by inpainting. Our blind inpainting method uses a 3D convolutional network U-net. For the creation of training and validation datasets, we suggest an algorithm for transferring real ring artifacts to an arbitrary place in the undistorted slices of 8 big images of sandstones and sand. The parameters of the deep neural network and loss functions are analyzed. A loss function based on the multi-scale structural similarity index (MS-SSIM) allows to achieve the best performance. The developed solution corrects ring artifacts perfectly from a point of view of visual assessment and outperforms existing inpainting methods according to quality metrics based on MS-SSIM and mean absolute error (MAE).

[1]  B. Münch,et al.  Stripe and ring artifact removal with combined wavelet--Fourier filtering. , 2009, Optics express.

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

[3]  Zhou Wang,et al.  A Comprehensive Performance Evaluation of Image Quality Assessment Algorithms , 2019, IEEE Access.

[4]  Stina Svensson,et al.  Reduction of Ring Artifacts in High Resolution X-Ray Microtomography Images , 2006, DAGM-Symposium.

[5]  Ivan Yakimchuk,et al.  Algorithms for 3D Particles Characterization Using X-Ray Microtomography in Proppant Crush Test , 2018, J. Imaging.

[6]  Jae G. Kim,et al.  Comparison of ring artifact removal methods using flat panel detector based CT images , 2011, Biomedical engineering online.

[7]  Julia F. Barrett,et al.  Artifacts in CT: recognition and avoidance. , 2004, Radiographics : a review publication of the Radiological Society of North America, Inc.

[8]  Enhong Chen,et al.  Image Denoising and Inpainting with Deep Neural Networks , 2012, NIPS.

[9]  Alexandru Telea,et al.  An Image Inpainting Technique Based on the Fast Marching Method , 2004, J. Graphics, GPU, & Game Tools.

[10]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[11]  C. Berg,et al.  Industrial applications of digital rock technology , 2017, 2005.02815.

[12]  Shiguang Shan,et al.  Shift-Net: Image Inpainting via Deep Feature Rearrangement , 2018, ECCV.

[13]  Ting-Chun Wang,et al.  Image Inpainting for Irregular Holes Using Partial Convolutions , 2018, ECCV.

[14]  Thomas S. Huang,et al.  Generative Image Inpainting with Contextual Attention , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[15]  Jayanthi Sivaswamy,et al.  FPD-M-net: Fingerprint Image Denoising and Inpainting Using M-Net Based Convolutional Neural Networks , 2018, Inpainting and Denoising Challenges.

[16]  Hiroshi Ishikawa,et al.  Globally and locally consistent image completion , 2017, ACM Trans. Graph..

[17]  Raghav Mehta,et al.  M-net: A Convolutional Neural Network for deep brain structure segmentation , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[18]  Hao Li,et al.  High-Resolution Image Inpainting Using Multi-scale Neural Patch Synthesis , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  T. Pan.  Computed Tomography: from Photon Statistics to Modern Cone-Beam CT , 2009, Journal of Nuclear Medicine.

[20]  Baiyu Chen,et al.  Low‐dose CT for the detection and classification of metastatic liver lesions: Results of the 2016 Low Dose CT Grand Challenge , 2017, Medical physics.

[21]  Jan Sijbers,et al.  Reduction of ring artefacts in high resolution micro-CT reconstructions. , 2004, Physics in medicine and biology.

[22]  Igor Varfolomeev,et al.  An Application of Deep Neural Networks for Segmentation of Microtomographic Images of Rock Samples , 2019, Comput..

[23]  Ivan Yakimchuk,et al.  Blind Quality Assessment for Slice of Microtomographic Image , 2019, 2019 24th Conference of Open Innovations Association (FRUCT).

[24]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[25]  Xuanqin Mou,et al.  A hybrid ring artifact reduction algorithm based on CNN in CT images , 2019 .

[26]  Paul Tafforeau,et al.  Correction of Ring Artifacts in X-ray Tomographic Images , 2011 .

[27]  W. Kalender,et al.  Comparison of ring artifact correction methods for flat-detector CT , 2009, Physics in medicine and biology.

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

[29]  Zhou Wang,et al.  Multiscale structural similarity for image quality assessment , 2003, The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003.

[30]  Christine Guillemot,et al.  Image Inpainting : Overview and Recent Advances , 2014, IEEE Signal Processing Magazine.

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

[32]  Toshihiko Yamasaki,et al.  Lunar surface image restoration using U-net based deep neural networks , 2019, ArXiv.

[33]  Mathias Unberath,et al.  Deep Learning-based Inpainting for Virtual DSA , 2017 .

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

[35]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.