For incomplete medical CT scan data, traditional algorithms cannot ensure that the reconstructed images meet the diagnostic requirements. In order to solve this situation, a CT reconstruction algorithm based on the combination of weighted guided filtering and gradient domain convolutional sparse coding was proposed. Firstly, the penalty least squares method is used to iteratively reconstruct the initial CT image. Secondly, the weighted guided filtering is used to obtain the low-frequency components of the image, and the convolutional sparse coding with gradient constraints is used to process the high-frequency components of the image. Finally, the two components are combined to obtain a new image as input, and the least-squares approximation is continued, and the iterative reconstruction is repeated until a clearer image is obtained. Experimental results show that compared with other convolutional sparse algorithms and group sparse algorithms, the proposed algorithm can effectively suppress noise and artifacts, recover more image structure and edge detail information, and obtain better reconstructed images.
ZHOUShaofei, CHAIRui, QINPinle, et al. A three-stage kidney and tumor segmentation method based on the combination of mask RCNN and U-net[J]. Journal of North University of China (Natural Science Edition), 2022, 43(3): 236-243. (in Chinese)
[3]
DONOHOD L. Compressed sensing[J]. IEEE Transactions on Information Theory, 2006, 52(4): 1289-1306.
[4]
SIDKYE Y, KAOC M, PANX. Accurate image reconstruction from few-views and limited-angle \t\t\t data in divergent-beam CT[J]. Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics, 2006, 14(2): 119-139.
[5]
QUZ, ZHAOX, PANJ, et al. Sparse-view CT reconstruction based on gradient directional total variation[J]. Measurement Science and Technology, 2019, 30(5): 055404.
[6]
PANZ, LIUZ, LUOK, et al. Compressive sensing total-variation primal-dual algorithms for image reconstruction[J]. IEEE Signal Processing Letters, 2024, 31: 1965-1969.
[7]
XIY, ZHOUP, YUH, et al. Adaptive-weighted high order TV algorithm for sparse-view CT reconstruction[J]. Medical Physics, 2023, 50(9): 5568-5584.
[8]
BAOP, ZHOUJ, ZHANGY. Group sparsity based sparse-sampling CT reconstruction[C]//2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2018: 5097-5100.
[9]
BRISTOWH, ERIKSSONA, LUCEYS. Fast convolutional sparse coding[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013: 391-398.
[10]
BAOP, XIAW, YANGK, et al. Sparse-view ct reconstruction via convolutional sparse coding[C]//2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), 2019: 1446-1449.
[11]
LIZ, ZHENGJ, ZHUZ, et al. Weighted guided image filtering[J]. IEEE Transactions on Image Processing, 2014, 24(1): 120-129.
LIYu, SHINa, KONGHuihua, et al. Sparse angle CT reconstruction algorithm based on total variation and convolutional sparse coding in gradient domain[J]. Laser & Optoelectronics Progress, 2021, 58(12): 339-348. (in Chinese)
[14]
GUY, LIUY, LIUW, et al. Sparse angle CT reconstruction based on group sparse representation[J]. Journal of X-Ray Science and Technology, 2022, 30(6): 1085-1097.
[15]
BOYDS, PARIKHN, CHUE, et al. Distributed optimization and statistical learning via the alternating direction method of multipliers[J]. Foundations and Trends® in Machine Learning, 2011, 3(1): 1-122.
[16]
BIOUCAS-DIASJ M, FIGUEIREDOM A T. A new twIst: two-step iterative shrinkage/thresholding algorithms for image restoration[J]. IEEE Transactions on Image Processing, 2007, 16(12): 2992-3004.
[17]
ROGGEMANNM C, TYLERD W. Model-based image reconstruction by means of a constrained least-squares solution[J]. Applied Optics, 1997, 36(11): 2360.