基于NSCT稀疏编码的医学图像超分辨率重建算法
Super-Resolution Reconstruction of Medical Images Based on Sparse Representation in the NSCT Domain
摘要: 为了满足临床对医学图像分辨率的进一步需求，提出了一种非下采样Contourlet变换和稀疏表示结合的单帧医学图像超分辨率重建算法。该方法在改进字典学习步骤中，首先通过非下采样Contourlet变换中的方向滤波器提取训练样本集图像的高频特征；其次，采用K-SVD奇异值分解法和OMP正交匹配追踪算法来求取高、低分辨率字典和稀疏表示系数，并重建出高分辨率图像。最后，将提出的方法与Yang、Zeyde提出的稀疏表示重建算法都应用于医学图像超分辨率重建上，通过实验对比分析，提出算法重建结果的PSNR值与SSIM值分别达到45.389和0.907，充分展现出了提出算法的优势。
Abstract: In order to meet the additional demands of image resolution in clinical medicine, a super-resolution reconstruction algorithm based on sparse representation in the nonsubsampled contourlet transform (NSCT) domain is proposed. In this method, in the improved dictionary learning step, firstly, the high-frequency features of the training sample set images are extracted by the direction filter in the non-downsampling Contourlet transform; secondly, the K-SVD singular value decomposition method and the OMP orthogonal matching tracking algorithm are used to find the high- and low-resolution dictionaries and sparse representation coefficients, and reconstruct the high-resolution images. Finally, the proposed method and the sparse representation reconstruction algorithm proposed by Yang and Zeyde are both applied to the super-resolution reconstruction of medical images. Through experimental comparison and analysis, the PSNR and SSIM values of the reconstruction results of the proposed algorithm reach 45.389 and 0.907 respectively, fully demonstrating the advantages of the proposed algorithm.
文章引用：聂小栋, 成云凤. 基于NSCT稀疏编码的医学图像超分辨率重建算法[J]. 软件工程与应用, 2023, 12(2): 276-292. https://doi.org/10.12677/SEA.2023.122028

参考文献

[1] Irani, M. and Peleg, S. (1990) Super Resolution from Image Sequences. Proceedings of 10th International Conference on Pattern Recognition, Vol. 2, 115-120. [Google Scholar] [CrossRef] 
[2] Stark, H. and Olsen, E.T. (1992) Projection-Based Image Restoration. Journal of the Optical Society of America A, 9, 1914-1919. [Google Scholar] [CrossRef] 
[3] Schultz, R.R., Stevenson, R.L., Stevenson, R.L. and Sezan, M.I. (1996) Motion-Compensated Scan Conversion of Interlaced Video Sequences. Proceedings of SPIE: The International Society for Optical Engineering, 2666, 107-118. [Google Scholar] [CrossRef] 
[4] Mahmoudzadeh, A.P. and Kashou, N.H. (2014) Interpolation-Based Super-Resolution Reconstruction: Effects of Slice Thickness. Journal of Medical Imaging, 1, Article ID: 034007. [Google Scholar] [CrossRef] 
[5] Yu, X. and Cen, X. (2013) An Image Reconstruction Approach in Discrete Cosine Transform Domain. International Congress on Image & Signal Processing, Chongqing, 16-18 October 2012, 587-591. [Google Scholar] [CrossRef] 
[6] Witwit, W., Zhao, Y., Jenkins, K., et al. (2018) Global Motion Based Video Super-Resolution Reconstruction Using Discrete Wavelet Transform. Multimedia Tools & Applications, 77, 1-20. [Google Scholar] [CrossRef] 
[7] 曹昆. 基于Contourlet变换的图像超分辨率重建算法研究[D]: [硕士学位论文]. 西安: 西安电子科技大学, 2010.
[8] 杨贞萍, 牛海军, 丁磊, 等. 一种新的NSCT超分辨率图像复原技术[J]. 西安电子科技大学学报, 2012, 39(1): 34-37.
[9] Pak, F., Kanan, H.R. and Alikhassi, A. (2015) Breast Cancer Detection and Classification in Digital Mammography Based on Non-Subsampled Contourlet Transform (NSCT) and Super Resolution. Computer Methods and Programs in Biomedicine, 122, 89-107. [Google Scholar] [CrossRef] [PubMed]
[10] Zheng, H., Zeng, K., Guo, D., et al. (2018) Multi-Contrast Brain MRI Image Super-Resolution with Gradient-Guided Edge Enhancement. IEEE Access, 6, 57856-57867. [Google Scholar] [CrossRef] 
[11] Xu, H., Miao, H., Yang, C., et al. (2015) Research on Super-Resolution Image Reconstruction Based on an Improved POCS Algorithm. International Conference on Optical and Photonic Engineering (icOPEN 2015), Vol. 9524, 95242V. [Google Scholar] [CrossRef] 
[12] Woo, J., Bai, Y., Roy, S., et al. (2012) Super-Resolution Reconstruction for Tongue MRimages. Proceedings of SPIE: The International Society for Optical Engineering, 8314, 11-24. [Google Scholar] [CrossRef] [PubMed]
[13] Stark, H. and Olsen, E.T. (1992) Projection-Based Image Restoration. Journal of the Optical Society of America A, 9, 1914-1919. [Google Scholar] [CrossRef] 
[14] Chang, H., Yeung, D.Y. and Xiong, Y. (2004) Super-Resolution through Neighbor Embedding. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington DC, 27 June-2 July 2004, 1.
[15] Li, H., Gao, Y., Dong, J., et al. (2018) Super-Resolution Based on Noise Resistance Deep Convolutional Network. Proceedings of the 2018 6th International Conference on Bioinformatics and Computational Biology, ACM, Chengdu, 12-14 March 2018, 88-94. [Google Scholar] [CrossRef] 
[16] Oktay, O., Ferrante, E., Kamnitsas, K., et al. (2018) Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation. IEEE Transactions on Medical Imaging, 37, 384-395. [Google Scholar] [CrossRef] 
[17] Yang, J., Wright, J., Huang, T., et al. (2008) Image Super-Resolution as Sparse Representation of Raw Image Patches.
[18] Engan, K., Aase, S.O. and Husoy, J.H. (2002) Method of Optimal Directions for Frame Design. 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings, Phoenix, 15-19 March 1999, 2443-2446. [Google Scholar] [CrossRef] 
[19] Aharon, M., Elad, M. and Brucksteina, M. (2006) The K-SVD: An Algorithm for Designing of over Complete Dictionaries for Sparse Representation. IEEE Transactions on Signal Processing, 54, 4311-4322. [Google Scholar] [CrossRef] 
[20] Mairal, J., Bach, F., Ponce, J., et al. (2010) Online Learning for Matrix Factorization and Sparse Coding. Journal of Machine Learning Research, 11, 19-60.
[21] Besl, P.J. and Mckay, N.D. (2002) A Method for Registration of 3-D Shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14, 239-256. [Google Scholar] [CrossRef] 
[22] Ota, J., Umehara, K., Ishimaru, N., et al. (2017) Evaluation of the Sparse Coding Super-Resolution Method for Improving Image Quality of Up-Sampled Images in Computed Tomography. Medical Imaging 2017: Image Processing, Vol. 10133, 101331S. [Google Scholar] [CrossRef] 
[23] Asif, M., Akram, M.U., Hassan, T., et al. (2017) High Resolution OCT Image Generation Using Super Resolution via Sparse Representation. 8th International Conference on Graphic and Image Processing (ICGIP 2016), Vol. 10225, Article ID: 1022512. [Google Scholar] [CrossRef] 
[24] Zeyde, R., Elad, M. and Protter, M. (2010) On Single Image Scale-Up Using Sparse-Representations. In: Boissonnat, J.-D., Chenin, P., Cohen, A., Gout, C., Lyche, T., Mazure, M.-L., Schumaker, L., et al., eds., Curves and Surfaces, Springer, Berlin, Heidelberg. [Google Scholar] [CrossRef] 
[25] 汪伟, 程斌. 基于稀疏表示分类的人工地物目标检测[J]. 控制工程, 2020, 27(12): 2158-2167.
[26] Zhu, Z., Zheng, M., Qi, G., et al. (2019) A Phase Congruency and Local Laplacian Energy Based Multi-Modality Medical Image Fusion Method in NSCT Domain. IEEE Access, 7, 20811-20824. [Google Scholar] [CrossRef] 
[27] Pati, Y.C., Rezaiifar, R. and Krishnaprasad, P.S. (1993) Orthogonal Matching Pursuit: Recursive Function Approximation with Applications to Wavelet Decomposition. Proceedings of 27th Asilomar Conference on Signals, Systems and Computers, Pacific Grove, 1-3 November 1993, 40-44.

为你推荐