基于卷积盲降噪的混合式核磁共振成像
作者:
基金项目:

国家自然科学基金(61876124);教育部人文社科青年基金(20YJC630034)


Hybrid Magnetic Resonance Imaging Based on Convolutional Blind Denoising
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [25]
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    为了解决图像压缩感知重建研究领域中通过有效的图像先验信息重构与原图相似性高且保留细节消除伪影的高质量图像的问题, 针对不足采样的K空间数据, 在经典的CNN算法CBDNet算法的基础上, 通过融合深度学习先验信息及传统图像恢复各自优势的方法, 研究了基于深度神经网络去噪先验和BM3D块压缩感知算法的混合式重构算法. 该算法采用交互式方法训练多尺度残差网络抑制噪声水平, 借优化选择的方式将深度学习与传统块匹配多尺度结合以提取图像不同尺度的特征数据从而实现抑制伪影、快速重建高质量MRI. 实结果表明深度学习结合BM3D在MR图像重构领域能够有效降低伪影保留细节信息, 加强重构效果. 与此同时, 通过采用GPU的加速运算, 算法的计算复杂度较使用单一算法并未增加很多. 可见基于卷积盲降噪的混合式核磁共振成像效果更佳.

    Abstract:

    In the field of image compression perceptual reconstruction, high-quality images are reconstructed with high similarity to the original image, and details are retained to eliminate artifacts through effective image prior information reconstruction. Thus, aiming at the K-space data with insufficient sampling, based on the classic CNN algorithm CBDNet algorithm, this study adopts the method to combine the advantages of fusing deep learning prior information and traditional image restoration. Meanwhile, a hybrid reconstruction algorithm based on prior denoising of deep neural network and compressed sensing algorithm of BM3D block is studied. The algorithm employs an interactive method to train a multi-scale residual network to suppress noise levels and combines deep learning with the multi-scale matching of traditional blocks to extract image feature data at different scales through optimal selection, thus suppressing artifacts and quickly reconstructing high-quality MRI. The experimental results show that deep learning combined with BM3D can reduce artifacts and retain details in MR image reconstruction, enhancing the reconstruction effect. Additionally, the computational complexity of the algorithm is not much more than that of the single algorithm by the GPU accelerated operation. It can be seen that the hybrid MRI based on convolution blind denoising has a better effect.

    参考文献
    [1] Qiu JX, Liu J, Bi ZX, et al. An investigation of 2D spine magnetic resonance imaging (MRI) with compressed sensing (CS). Skeletal Radiology, 2022, 51(6): 1273–1283. [doi: 10.1007/s00256-021-03954-x
    [2] Yuan M, Yang BX, Ma YD, et al. Compressed sensing MRI reconstruction from highly undersampled K-space data using nonsubsampled shearlet transform sparsity prior. Mathematical Problems in Engineering, 2015, 2015: 615439
    [3] Huang JP, Zhu LK, Wang LH, et al. Compressed sensing MRI using sparsity averaging and FISTA. Applied Magnetic Resonance, 2017, 48(8): 749–760. [doi: 10.1007/s00723-017-0910-0
    [4] Kojima S, Shinohara H, Hashimoto T, et al. Undersampling patterns in K-space for compressed sensing MRI using two-dimensional Cartesian sampling. Radiological Physics and Technology, 2018, 11(3): 303–319. [doi: 10.1007/s12194-018-0469-y
    [5] Kazama R, Sekine K, Ito S. Compressed sensing in magnetic resonance imaging using non-randomly under-sampled signal in Cartesian coordinates. IEICE Transactions on Information and Systems, 2019, E102.D(9): 1851–1859. [doi: 10.1587/transinf.2019EDP7016
    [6] Yuan LJ, Li YY, Dai F, et al. Analysis L1/2 regularization: Iterative half thresholding algorithm for CS-MRI. IEEE Access, 2019, 7: 79366–79373. [doi: 10.1109/ACCESS.2019.2923171
    [7] Mathew RS, Paul JS. Automated regularization parameter selection using continuation based proximal method for compressed sensing MRI. IEEE Transactions on Computational Imaging, 2020, 6: 1309–1319. [doi: 10.1109/TCI.2020.3019111
    [8] He W, Zhao LM. MRI reconstruction with separate magnitude and phase priors based on dual-tree complex wavelet transform. International Journal of Biomedical Imaging, 2022, 2022: 7251674
    [9] Hashimoto F, Ote K, Oida T, et al. Compressed-sensing magnetic resonance image reconstruction using an iterative convolutional neural network approach. Applied Sciences, 2020, 10(6): 1902. [doi: 10.3390/app10061902
    [10] Ran MS, Xia WJ, Huang YQ, et al. MD-Recon-Net: A parallel dual-domain convolutional neural network for compressed sensing MRI. IEEE Transactions on Radiation and Plasma Medical Sciences, 2021, 5(1): 120–135. [doi: 10.1109/TRPMS.2020.2991877
    [11] Zhao D, Zhao F, Gan YJ. Reference-driven compressed sensing MR image reconstruction using deep convolutional neural networks without pre-training. Sensors, 2020, 20(1): 308. [doi: 10.3390/s20010308
    [12] Njeh I, Mzoughi H, Ben Slima M, et al. Deep convolutional encoder-decoder algorithm for MRI brain reconstruction. Medical & Biological Engineering & Computing, 2021, 59(1): 85–106
    [13] Mardani M, Gong EH, Cheng JY, et al. Deep generative adversarial neural networks for compressive sensing MRI. IEEE Transactions on Medical Imaging, 2019, 38(1): 167–179. [doi: 10.1109/TMI.2018.2858752
    [14] Liu YS, Zhan ZF, Cai JF, et al. Projected iterative soft-thresholding algorithm for tight frames in compressed sensing magnetic resonance imaging. IEEE Transactions on Medical Imaging, 2016, 35(9): 2130–2140. [doi: 10.1109/TMI.2016.2550080
    [15] Eksioglu EM, Tanc AK. Denoising AMP for MRI reconstruction: BM3D-AMP-MRI. SIAM Journal on Imaging Sciences, 2018, 11(3): 2090–2109. [doi: 10.1137/18M1169655
    [16] Eksioglu EM. Decoupled algorithm for MRI reconstruction using nonlocal block matching model: BM3D-MRI. Journal of Mathematical Imaging and Vision, 2016, 56(3): 430–440. [doi: 10.1007/s10851-016-0647-7
    [17] Huang JP, Wang LH, Zhu YM. Compressed sensing MRI reconstruction with multiple sparsity constraints on radial sampling. Mathematical Problems in Engineering, 2019, 2019: 3694604
    [18] Zhang K, Zuo WM, Zhang L. FFDNet: Toward a fast and flexible solution for CNN-based image denoising. IEEE Transactions on Image Processing, 2018, 27(9): 4608–4622. [doi: 10.1109/TIP.2018.2839891
    [19] Quan TM, Nguyen-Duc T, Jeong WK. Compressed sensing MRI reconstruction using a generative adversarial network with a cyclic loss. IEEE Transactions on Medical Imaging, 2018, 37(6): 1488–1497. [doi: 10.1109/TMI.2018.2820120
    [20] Yang G, Yu SM, Dong H, et al. DAGAN: Deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE Transactions on Medical Imaging, 2018, 37(6): 1310–1321. [doi: 10.1109/TMI.2017.2785879
    [21] Cha E, Oh G, Ye JC. Geometric approaches to increase the expressivity of deep neural networks for MR reconstruction. IEEE Journal of Selected Topics in Signal Processing, 2020, 14(6): 1292–1305. [doi: 10.1109/JSTSP.2020.2982777
    [22] Jin KH, Lee D, Ye JC. A general framework for compressed sensing and parallel MRI using annihilating filter based low-rank hankel matrix. IEEE Transactions on Computational Imaging, 2016, 2(4): 480–495. [doi: 10.1109/TCI.2016.2601296
    [23] Guo S, Yan ZF, Zuo WM, et al. Toward convolutional blind denoising of real photographs. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019. 1712–1722.
    [24] Dabov K, Foi A, Katkovnik V, et al. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Transactions on image processing, 2007, 16(8): 2080–2095. [doi: 10.1109/TIP.2007.901238
    [25] 宗春梅, 张月琴, 曹建芳, 等. 基于深度先验及非局部相似性的压缩感知核磁共振成像. 计算机应用, 2020, 40(10): 3054–3059. [doi: 10.11772/j.issn.1001-9081.2020030285
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

宗春梅,张月琴,郝耀军.基于卷积盲降噪的混合式核磁共振成像.计算机系统应用,2023,32(12):12-20

复制
分享
文章指标
  • 点击次数:601
  • 下载次数: 1436
  • HTML阅读次数: 933
  • 引用次数: 0
历史
  • 收稿日期:2023-05-28
  • 最后修改日期:2023-06-28
  • 在线发布日期: 2023-09-21
文章二维码
您是第11277971位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号