Abstract
At present, the spectrum correction method based on medical image restoration has the problems of low reconstruction accuracy and long calculation time. However, the method based on compressed sensing can use the sparse characteristics of medical images to improve the reconstruction performance of images. In this paper, a signal reconstruction algorithm based on composite cosine conjugate gradient smoothing L0 (CCGSL0) is proposed. Firstly, we construct a new smooth function family called composite cosine function family (FCCF), which can approximate the mathematical representation of L0 norm. Secondly, the conjugate gradient method (CGM) is used to form the FCCF-CGM optimization strategy to improve the signal reconstruction rate and image restoration accuracy. Finally, the block mechanism is used for parallel processing of the original signal to reduce the processing time of the signal, thereby greatly improving the speed of image restoration. In addition, the computed tomography images and magnetic resonance imaging images in Gaussian and Poisson noise environment were simulated. Experimental results show that CCGSL0 can improve image reconstruction accuracy by 0.4–1.6 dB and reduce reconstruction time by 30–70%. CCGSL0 has better robustness and can save more image signal details.
Similar content being viewed by others
References
Xie, Z., Liu, L., Wang, X., Yang, C.: An iterative method with enhanced Laplacian scaled thresholding for noise-robust compressive sensing magnetic resonance image reconstruction. IEEE Access 8, 177021–177040 (2020)
Song, P., Weizman, L., Mota, J., et al.: Coupled dictionary learning for multi-contrast MRI reconstruction. IEEE Trans. Med. Imaging 39(3), 621–633 (2020)
Zeng, C., Zhu, W., Jia, X., et al.: Sparse aperture ISAR imaging method based on joint constraints of sparsity and low rank. IEEE Trans. Geosci. Remote Sens. 59(1), 168–181 (2021)
Lu, X., Gu, H., Su, W.: Noise Radar Doppler imaging via 2D generalized smoothed-L0. Electron. Lett. 57, 448–450 (2021)
Wen, B., Li, Y., Bresler, Y.: Image recovery via transform learning and low-rank modeling: the power of complementary regularizers. IEEE Trans. Image Process. 29, 5310–5323 (2020)
Candes, E., Wakin, M.: An introduction to compressive sampling. IEEE Signal Process. Mag. 25(2), 21–30 (2008)
Jian, W., Seokbeop, K., Byonghyo, S.: Generalized orthogonal matching pursuit. IEEE Transl. Signal Process. 12, 6202–6216 (2012)
Tropp, J., Gilbert, A.: Signal recovery from random measurements via orthogonal matching pursuit. IEEE Trans. Inf. Theory 53(12), 4655–4666 (2007)
Long, T., Jiao, W., He, G.: RPC estimation via \(\ell \)1-norm-regularized least squares (L1LS). IEEE Trans. Geosci. Remote Sens. 8, 4554–4567 (2015)
Pant, J., Lu, W., Antoniou, A.: New improved algorithms for compressive sensing based on Lp norm. IEEE Trans. Circuits Syst. II Express Briefs 61, 198–202 (2014)
Mohimani, H., Babaie-Zadeh, M., Jutten, C.: A fast approach for overcomplete sparse decomposition based on smoothed L0 norm. IEEE Trans. Signal Process. 57(1), 289–301 (2009)
Zhao, R., Lin, W., Li, H., et al.: Reconstruction algorithm for compressive sensing based on smoothed L0 norm and revised newton method. J. Comput. Aided Des. Comput. Graph. 24(4), 478–484 (2012)
Guo, Y., Zheng, M., Zhang, L.: Compressive sensing and its applications. In: Microelectronics & Computer (2015)
Wang, L., Ye, P., Xiang, J.: A modified algorithm based on smoothed L0 norm in compressive sensing signal reconstruction. In: 2018 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece (2018)
Nazari, M. Mehrpooya, A., Bastani, M., et al.: Sparse recovery using modified SL0 algorithm by weighted projection and application to ISAR imaging. In: 2020 28th Iranian Conference on Electrical Engineering (ICEE), Tabriz, Iran (2020)
Feng, J., Sun, Y., Ji, X.: High-resolution ISAR imaging based on improved sparse signal recovery algorithm. In: Wireless Communications and Mobile Computing (2021)
Fletcher, R., Reeves, C.: Function minimization by conjugate gradients. Comput. J. 7(2), 149–154 (1964)
Polyakb, T.: The conjugate gradient method in extreme problems. USSR Comput. Math. Math. Phys. 9, 94–112 (1969)
Dai, Y., Yuan, Y.: A nonlinear conjugate gradient method with a strong global convergence property. SIAM J. Optim. 10(1), 177–182 (1999)
Liu, X., Chen, S., Song, L., et al.: Self-attention negative feedback network for real-time image super-resolution. J. King Saud Univ. Comput. Inf. Sci. (2021)
Guo, L., Wozniak, M.: An image super-resolution reconstruction method with single frame character based on wavelet neural network in internet of things. Mob. Netw. Appl. 26(1), 390–403 (2021)
Acknowledgements
This paper is supported by National Key Laboratory of Communication Anti Jamming Technology.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wang, L., Zang, X., Xiang, J. et al. A Medical Image Reconstruction Algorithm Based on Composite Cosine Function Family. SIViP 16, 2103–2111 (2022). https://doi.org/10.1007/s11760-022-02172-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-022-02172-9