Citation: | Wang Fan, Chen Minghui, Gao Naijun, et al. OCT image speckle sparse noise reduction based on dictionary algorithm[J]. Opto-Electronic Engineering, 2019, 46(6): 180572. doi: 10.12086/oee.2019.180572 |
[1] | Huang D, Swanson E A, Lin C P, et al. Optical coherence tomography[J]. Science, 1991, 254(5035): 1178-1181. doi: 10.1126/science.1957169 |
[2] | 孙延奎.光学相干层析医学图像处理及其应用[J].光学精密工程, 2014, 22(4): 1086-1104. Sun Y K. Medical image processing techniques based on optical coherence tomography and their applications[J]. Optics and Precision Engineering, 2014, 22(4): 1086-1104. |
[3] | Xiang S H, Zhou L, Schmitt J M. Speckle noise reduction for optical coherence tomography[J]. Proceedings of SPIE, 1998, 3196: 79-88. doi: 10.1117/12.297921 |
[4] | Jung C R, Schacanski J. Adaptive image denoising in scale-space using the wavelet transform[C]//Proceedings of the 14th Brazilian Symposium on Computer Graphics and Image Processing, Florianopolis, Brazil, 2001: 172-178. |
[5] | Schmitt J M. Array detection for speckle reduction in optical coherence microscopy[J]. Physics in Medicine & Biology, 1997, 42(7): 1427-1439. doi: 10.1088/0031-9155/42/7/015 |
[6] | Pircher M, Gotzinger E, Leitgeb R, et al. Speckle reduction in optical coherence tomography by frequency compounding[J]. Journal of Biomedical Optics, 2003, 8(3): 565-569. doi: 10.1117/1.1578087 |
[7] | Romano Y, Elad M. Improving K-SVD denoising by post-processing its method-noise[C]//Proceedings of 2013 IEEE International Conference on Image Processing, Melbourne, VIC, Australia, 2013: 435-439. |
[8] | Tang X O, Wang X G. Face sketch synthesis and recognition[C]//Proceedings of the 9th IEEE International Conference on Computer Vision, Nice, France, 2003: 687-694. |
[9] | Elad M, Aharon M. Image denoising via sparse and redundant representations over learned dictionaries[J]. IEEE Transactions on Image Processing, 2006, 15(12): 3736-3745. doi: 10.1109/TIP.2006.881969 |
[10] | Elad M. Sparse and Redundant Representations: From Theory to Applications in Signal and Image Processing[M]. New York: Springer, 2010: 1094-1097. |
[11] | Bruckstein A M, Donoho D L, Elad M. From sparse solutions of systems of equations to sparse modeling of signals and images[J]. SIAM Review, 2009, 51(1): 34-81. doi: 10.1137/060657704 |
[12] | Zhang Y S, Ji K F, Deng Z P, et al. Clustering-based SAR image denoising by sparse representation with KSVD[C]//Proceedings of 2016 IEEE International Geoscience and Remote Sensing Symposium, Beijing, 2016: 5003-5006. |
[13] | Song X R, Wu L D, Hao H X. Hyperspectral image denoising base on adaptive sparse representation[C]//Proceedings of 2018 IEEE Third International Conference on Data Science in Cyberspace, Guangzhou, 2018: 735-739. |
[14] | Nguyen T T, Trinh D H, Linh-Trung N. An efficient example-based method for CT image denoising based on frequency decomposition and sparse representation[C]//Proceedings of 2016 International Conference on Advanced Technologies for Communications, Hanoi, Vietnam, 2016: 293-296. |
[15] | 杨培, 高雷阜, 王江, 等.基于稀疏表示与字典学习的彩色图像去噪算法[J].计算机工程与科学, 2018, 40(5): 842-848. doi: 10.3969/j.issn.1007-130X.2018.05.012 Yang P, Gao L F, Wang J, et al. A color image denoising algorithm based on sparse representation and dictionary learning[J]. Computer Engineering & Science, 2018, 40(5): 842-848. doi: 10.3969/j.issn.1007-130X.2018.05.012 |
[16] | Pyatykh S, Hesser J, Zheng L. Image noise level estimation by principal component analysis[J]. IEEE Transactions on Image Processing, 2013, 22(2): 687-699. doi: 10.1109/TIP.2012.2221728 |
[17] | 何锦涛, 陈明惠, 贾文宇, 等.眼底OCT图像中糖尿病性黄斑水肿的分割[J].光电工程, 2018, 45(7): 170605. doi: 10.12086/oee.2018.170605 He J T, Chen M H, Jia W Y, et al. Segmentation of diabetic macular edema in OCT retinal images[J]. Opto-Electronic Engineering, 2018, 45(7): 170605. doi: 10.12086/oee.2018.170605 |
[18] | Huynh-Thu Q, Ghanbari M. Scope of validity of PSNR in image/video quality assessment[J]. Electronics Letters, 2008, 44(13): 800-801. doi: 10.1049/el:20080522 |
[19] | Wang Z, Bovik A C, Sheikh H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612. doi: 10.1109/TIP.2003.819861 |
[20] | 邓菊香, 梁艳梅.光学相干层析图像的小波去噪方法研究[J].光学学报, 2009, 29(8): 2138-2141. Deng J X, Liang Y M. Noise reduction with wavelet transform in optical coherence tomographic images[J]. Acta Optica Sinica, 2009, 29(8): 2138-2141. |
[21] | Donoho D L, Johnstone I M. Ideal spatial adaptation by wavelet shrinkage[J]. Biometrika, 1994, 81(3): 425-455. doi: 10.1093/biomet/81.3.425 |
Overview: As a new non-invasive high-resolution scanning method, optical coherence tomography (OCT) has been widely used in clinical practice. Since the OCT imaging system uses an interference technique, the use of tissue scattering properties of light will inevitably introduce speckle noise. These speckle noises reduce the signal-to-noise ratio and contrast of the image, and also destroy the edge features of the image. As a result, it seriously affects people's accurate acquisition of image information. Therefore, the processing of OCT image speckle noise is very important before making a clinical diagnosis. The dictionary algorithm was originally proposed for Gaussian additive noise. This paper improves two original dictionary noise reduction algorithms for multiplicative speckle noise in OCT. The improved algorithm is divided into four steps. The first step is to establish and solve the speckle noise model of the OCT image. Firstly, the sparse domain model of small-sized image blocks is established and its noise reduction problem is solved. Then, the ideas in the Markov random field are used to generalize to large-size images. In the second step, logarithmically transforming the OCT image and performing noise estimation; In the third step, overlapping blocks the noisy image, the size of the image block is 8 pixels×8 pixels, the dictionary algorithm requires sparse coding and noise reduction for each block. The orthogonal matching pursuit algorithm (OMP) is used to perform sparse coding of two dictionary algorithms. In the fixed dictionary algorithm, the dictionary selects the discrete cosine transform (DCT) dictionary. In the adaptive dictionary algorithm, the initial dictionary selects the DCT dictionary and the dictionary training is performed by itself, and the dictionary update is completed by the K singular value decomposition learning algorithm; In the fourth step, the overlapping image blocks in the sparse coding stage are weighted averaged and returned to the spatial domain by exponential transformation. Selecting a randomly OCT slice and reduce noise for it, compared with the two original dictionary noise reduction algorithms and the traditional filtering algorithms, the improved two dictionary algorithms preserve most of the image information and edge detail information while suppressing speckle noise. Furthermore, three random OCT slice images are selected to simulate the improved two dictionary denoising algorithms. The improved adaptive dictionary algorithm has better noise reduction performance through subjective visual effects and four objective evaluation indicators. The two improved dictionary noise reduction algorithms proposed in this paper can be flexibly applied to various OCT noisy images and serve for subsequent image processing.
The noise reduction flowchart of improved dictionary algorithm
Trained dictionary.(a) Fixed dictionary; (b) Adaptive dictionary
Speckle reduction results of seven algorithms.(a) Original OCT image; (b) Original fixed dictionary algorithm; (c) Original adaptive dictionary algorithm; (d) Median filtering; (e) Lee filtering; (f) Wiener filtering; (g) Improved fixed dictionary algorithm; (h) Improved adaptive dictionary algorithm
Speckle reduction results of two improved dictionary algorithms.(ac) Randomly selected three OCT slices; (df) Noise reduction results by improved fixed dictionary algorithms; (gi) Noise reduction results by improved adaptive dictionary algorithms