ABSTRACT
Image denoising is one of the important issues for X-ray angiography of C-arm systems. Most existing methods in this field focus only on 2D image denoising from frame-by-frame independently, losing the temporal information of image sequence to some extents. In order to handle both spatial and temporal noises simultaneously to angiography imaging, we propose a novel deep architecture of hybrid 3D/2D CNN (convolutional neural network) for spatio-temporal noise reduction. The developed model takes multiple frames to input channels, and the final result is obtained through combining information of all channels. We evaluate the model applied to angiography images with normal and low doses of X-ray exposures. Results of both cases outperform those of state-of-the-art methods.
- A. Buades, B. Coll, and J.-M. Morel. 2005. A non-local algorithm for image denoising. In IEEE Conference on Computer Vision and Pattern Recognition. 2 (2005), 60--65.Google ScholarDigital Library
- L. I. Rudin, S. Osher, and E. Fatemi. 1992. Nonlinear total variation based noise removal algorithms. Physica D: Nonlinear Phenomena. 60, 1 (1992), 259--268.Google ScholarDigital Library
- M. Elad and M. Aharon. 2006. Image denoising via sparse and redundant representations over learned dictionaries. IEEE Transactions on Image Processing. 15, 12 (2006), 3736--3745.Google ScholarDigital Library
- X. Lan, S. Roth, D. Huttenlocher, and M. J. Black. 2006. Efficient belief propagation with learned higher-order Markov random fields. European Conference on Computer Vision(2006), 269--282.Google Scholar
- K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian. 2007. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Transactions on Image Processing. 16, 5 (2007), 2080--2095.Google ScholarDigital Library
- J. Mairal, F. Bach, J. Ponce, G. Sapiro, and A. Zisserman. 2009. Non-local sparse models for image restoration. IEEE International Conference on Computer Vision(2009), 2272--2279.Google Scholar
- W. Dong, L. Zhang, G. Shi, and X. Li. 2013. Nonlocally centralized sparse representation for image restoration. IEEE Transactions on Image Processing. 22, 4 (2013), 1620--1630.Google ScholarDigital Library
- S. Gu, L. Zhang, W. Zuo, and X. Feng. 2014. Weighted nuclear norm minimization with application to image denoising. IEEE Conference on Computer Vision and Pattern Recognition(2014), 2862--2869.Google Scholar
- Dippel, S., Stahl, M., Wiemker, R., and Blaffert, T. 2002. Multiscale Contrast Enhancement for Radiographies: Laplacian Pyramid Versus Fast Wavelet Transform. IEEE Trans. Medical Imaging. 21 (2002), 343--353Google ScholarCross Ref
- Burt, P.J., and Adelson, E.H. 1983. The Laplacian Pyramid as a Compact Image Code. IEEE Trans. Communications COM. 31 (1983), 532--540Google ScholarCross Ref
- Lagendijk, R.L., Roosmalen, P.M.B. van, Biemond, J., Rareş, A., and Reinders, M.J.T. 2005. Video Enhancement and Restoration. In Bovik, A.C., ed.: Handbook of Image and Video Processing. 2nd edn. Elsevier Academic Press (2005), 275--295.Google Scholar
- Aufrichtig, R., and Wilson, D.L. 1995. X-Ray Fluoroscopy Spatio-Temporal Filtering with Object Detection. IEEE Trans. Medical Imaging. 14 (1995), 733--746Google ScholarCross Ref
- Jain, V. and Seung, S. 2009. Natural image denoising with convolutional networks. Advances in Neural Information Processing Systems (2009), 769--776.Google Scholar
- Burger, H. C., Schuler, C. J., and Harmeling, S. 2012. Image denoising: Can plain neural networks compete with BM3D?. IEEE Conference on Computer Vision and Pattern Recognition (2012), 2392--2399.Google Scholar
- Xiao-Jiao Mao, Chunhua Shen, and Yu-Bin Yang. 2016. Image denoising using very deep fully convolutional encoder-decoder networks with symmetric skip connections. Advances in Neural Information Processing Systems. 29, 12 (Feb. 2016), 2802--2810.Google Scholar
- Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang. 2017. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Transactions on Image Processing. 26, 07 (Feb. 2017), 3142--3155.Google ScholarDigital Library
- Jaakko Lehtinen, Jacob Munkberg, Jon Hasselgren, Samuli Laine, Tero Karras, Miika Aittala, and Timo Aila. 2018. Noise2noise: Learning image restoration without clean data. Proceedings of the 35th International Conference on Machine Learning (Feb. 2018).Google Scholar
- Praneeth Sadda, Taha Qarni. 2018. Real-Time Medical Video Denoising with Deep Learning: Application to Angiography. International Journal of Applied Information Systems. 12, 13 (Mar. 2018).Google Scholar
- Hensel M, Pralow T, Grigat RR. 2006. Real-time denoising of medical x-ray image sequence: three entirely different approaches. LNCS. 4142 (2006), 479--490.Google Scholar
- Xiaokang Yang Xinyuan Chen, Li Song. 2016. Deep rnns for video denoising. In Proc. SPIE. 9971, 09 (Feb. 2016)Google Scholar
Index Terms
Hybrid 3D/2D-Based Deep Convolutional Neural Network for Spatio-Temporal Denoising of Angiography
Recommendations
Edge-preserving image denoising using a deep convolutional neural network
Highlights- This paper makes use of a deep CNN for image denoising.
- The network is trained ...
AbstractThis paper introduces a novel denoising approach making use of a deep convolutional neural network to preserve image edges. The network is trained by using the edge map obtained from the well-known Canny algorithm and aims at ...
Sparsity-constrained three-dimensional image reconstruction for C-arm angiography
X-ray C-arm is an important imaging tool in interventional radiology, road-mapping and radiation therapy because it provides accurate descriptions of vascular anatomy and therapeutic end point. In common interventional radiology, the C-arm scanner ...
A deep convolutional neural network model to classify heartbeats
The electrocardiogram (ECG) is a standard test used to monitor the activity of the heart. Many cardiac abnormalities will be manifested in the ECG including arrhythmia which is a general term that refers to an abnormal heart rhythm. The basis of ...
Comments