基于多尺度残差网络与正则化约束的MR图像超分辨算法
MR Image Super-Resolution Using Multi-Scale Residual Networks with Regularization Norm
摘要: 核磁共振高分辨率的图像可以提供更加丰富的病理信息，起到辅助诊断的作用，超分辨重建是利用低分辨率图像通过算法重建出高分辨率图像的技术。本文研究了针对核磁共振图像的超分辨图像重建算法，该算法在超分辨卷积神经网络的基础上，在损失函数中添加全变分正则化项来降低生成图像的噪声，网络结构中增加多尺度残差模块，在后续网络层结构中补充更多图像的高频特征。通过在临床核磁共振数据集上实验，该算法相对于先前的网络在峰值信噪比和结构相似性两个指标上有显著提升。
Abstract: High-resolution images of MRI can provide richer pathological information to assist in diagnosis. Super-resolution reconstruction is a technique of using low-resolution images to reconstruct high-resolution images by algorithm. In this paper, the super-resolution image reconstruction al-gorithm for MRI images is studied, which is based on the super-resolution convolutional neural network and adds the total variation regularization to the loss function for smoothing processing. The multi-scale residual module is added to the network structure to supplement more high fre-quency characteristics of images in the subsequent network layer structure. By experimenting with clinical MR data sets, the algorithm improved significantly in peak signal-to-noise ratio and structural similarity compared to previous networks.
文章引用：蔡言. 基于多尺度残差网络与正则化约束的MR图像超分辨算法[J]. 理论数学, 2021, 11(5): 909-921. https://doi.org/10.12677/PM.2021.115104

参考文献

[1] Reeth, E.V., Tham, I.W.K., Tan, C.H. and Poh, C.L. (2012) Super-Resolution in Magnetic Resonance Imaging: A Re-view. Concepts in Magnetic Resonance Part A, 40, 306-325. [Google Scholar] [CrossRef] 
[2] Ji, C.T. (2014) An Edge-Oriented Interpolation Algorithm Based on Regularization. Journal of Electronic Information, 36, 293-297.
[3] Papyan, V. and Elad, M. (2016) Multi-Scale Patch-Based Image Restoration. IEEE Transactions on Image Processing, 25, 249-261. [Google Scholar] [CrossRef] 
[4] Lu, X.Q., Huang, Z.H. and Yuan, Y. (2015) MR Image Super-Resolution via Manifold Regularized Sparse Learning. Neurocomputing, 162, 96-104.
https://www.sciencedirect.com/science/article/pii/S0925231215003896
[5] Dong, C., Chen, C.L., He, K. and Tang, X. (2014) Learning a Deep Convolutional Network for Image Super-Resolution. 2014 European Conference on Computer Vision (ECCV), Zurich, 6-12 September 2014, 184-199. [Google Scholar] [CrossRef] 
[6] Dong, C., Loy, C.C. and Tang, X. (2016) Accelerating the Super-Resolution Convolutional Neural Network. 2016 European Conference on Computer Vision (ECCV), Amsterdam, 8-16 October, 391-407. [Google Scholar] [CrossRef] 
[7] He, K., Zhang, X., Ren, S. and Sun, J. (2016) Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 770-778. [Google Scholar] [CrossRef] 
[8] Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., et al. (2017) Photorealistic Single Image Super-Resolution Using a Generative Adversarial Network. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 105-114. [Google Scholar] [CrossRef] 
[9] Kim, J., Lee, J.K. and Lee, K.M. (2016) Accurate Image Su-per-Resolution Using Very Deep Convolutional Networks. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 1646-1654. [Google Scholar] [CrossRef] 
[10] Kim, J., Lee, J.K. and Lee, K.M. (2016) Deeply-Recursive Convo-lutional Network for Image Super-Resolution. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 1637-1645. [Google Scholar] [CrossRef] 
[11] Tai, Y., Jian, Y. and Liu, X. (2017) Image Super-Resolution via Deep Recursive Residual Network. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 2790-2798. [Google Scholar] [CrossRef] 
[12] Huang, G., Liu, Z., Maaten, L.V.D. and Weinberger, K.Q. (2017) Densely Connected Convolutional Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 2261-2269. [Google Scholar] [CrossRef] 
[13] Tong, T., Li, G., Liu, X. and Gao, Q. (2017) Image Su-per-Resolution Using Dense Skip Connections. 2017 IEEE International Conference on Computer Vision, Venice, 22-29 October 2017, 4809-4817. [Google Scholar] [CrossRef] 
[14] Zhang, Y., Tian, Y., Kong, Y., Zhong, B. and Fu, Y. (2018) Residual Dense Network for Image Super-Resolution. 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 2472-2481. [Google Scholar] [CrossRef] 
[15] Zhang, Y., Li, K., Wang, L., Zhong, B. and Fu, Y. (2018) Image Super-Resolution Using Very Deep Residual Channel Attention Networks. 2018 European Conference on Computer Vision, Munich, 8-14 September, 294-310. [Google Scholar] [CrossRef] 
[16] Zeiler, M.D. and Fergus, R. (2014) Visualizing and Under-standing Convolutional Networks. 2014 European Conference on Computer Vision, Zurich, 6-12 September 2014, 818-833. [Google Scholar] [CrossRef] 
[17] Kempton, M.J., Underwood, T.S.A., Brunton, S., Stylios, F., Schmechtig, A., Ettinger, U., et al. (2011) A Comprehensive Testing Protocol for MRI Neuroanatomical Segmentation Techniques Evaluation of a Novel Lateral Ventricle Segmentation method. NeuroImage, 58, 1051-1059. [Google Scholar] [CrossRef] [PubMed]
[18] Menze, B.H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., Farahani, K., Kirby, J., et al. (2015) The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS). IEEE Transactions on Medical Imaging, 34, 1993-2024. [Google Scholar] [CrossRef] 
[19] 佟雨兵, 张其善, 祁云平. 基于PSNR与SSIM联合的图像质量评价模型[J]. 中国图象图形学报, 2006, 11(12): 1758-1763.
[20] Wang, Z., Bovik, A.C., Sheikh, H.R. and Simoncelli, E.P. (2004) Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing, 13, 600-612. [Google Scholar] [CrossRef] 
[21] Keys, R. (1981) Cubic Con-volution Interpolation for Digital Image Processing. IEEE Transactions on Acoustics, Speech, and Signal Processing, 29, 1153-1160. [Google Scholar] [CrossRef] 

为你推荐