首页 > 论文 > 光学学报 > 38卷 > 1期(pp:111003--1)


Improved Stochastic CT Reconstruction Based on Particle Swarm Optimization for Limited-Angle Sparse Projection Data

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文


当计算机断层成像(CT)中X射线的采样范围和数量受限时, 得到的稀疏投影数据完备性很低, 重建算法的搜索空间巨大。基于凸优化思路的迭代求解算法及其改进采用固定搜索路径, 难以在有限时间内收敛至全局最优解; 粒子群优化具有全局搜索能力, 但计算成本和存储代价过高。为解决这类不完备投影数据的重建问题, 提出基于粒子群优化的随机稀疏重建算法。首先, 通过随机策略生成具有多样性的初始种群, 以保证算法的搜索能力; 其次, 随机选择梯度下降或基于个体历史最优解和全局历史最优解的随机方向进行迭代, 以兼顾算法效率和搜索方向的多样性; 最后, 基于适应度评价, 有针对性地重新生成随机初始种群, 强制跳离局部最优。针对角度受限下无噪声和含噪声的稀疏投影数据, 分别进行重建实验。结果显示, 与常见的凸优化迭代和粒子群优化算法相比, 本文算法既能保证算法效率, 又在重建质量和算法稳健性上具有明显优势。


Because of the sampling scope and quantity limitation in the computed tomography (CT), the completeness of sparse projection data is very low, which leads to a huge search space for the reconstruction algorithm. The iterative algorithm based on convex optimization can not converge to the global minima in finite time due to the fixed search path. Particle swarm optimization has global search capability, but costs tremendous computation and memory. To improve the quality of reconstruction from incomplete projection data, a new stochastic sparse reconstruction algorithm based on particle swarm optimization is proposed. Firstly, the initial solutions with diversity are generated by the stochastic strategy to ensure the search capability. Secondly, the proposed algorithm stochastically chooses either gradient descent direction or random direction based on the local best known solution and the global best known solution in the iteration, to ensure the efficiency of this algorithm and the diversity of search directions. Finally, to avoid trapping in local optimum, the random initial populations are generated based on the fitness evaluation, which represents the current situation. The contrast reconstruction experiments are conducted on both noise-free and noisy limited-angle sparse projection data. The experimental results demonstrate that the proposed algorithm is efficient and evidently superior in reconstruction quality and robustness compared to common iterative algorithms based on convex optimization or particle swarm optimization.









作者单位    点击查看

高红霞:华南理工大学自动化科学与工程学院, 广东 广州 510640
罗澜:华南理工大学自动化科学与工程学院, 广东 广州 510640
骆英浩:华南理工大学自动化科学与工程学院, 广东 广州 510640
陈展鸿:华南理工大学自动化科学与工程学院, 广东 广州 510640
马鸽:广州大学机械与电气工程学院, 广东 广州 510006


备注:高红霞(1975-), 女, 博士, 教授, 主要从事机器视觉和图像处理方面的研究。E-mail: hxgao@scut.edu.cn

【1】庄天戈. CT原理与算法[M]. 上海: 上海交通大学出版社, 1992: 77-97.

【2】Heang K T. An inversion formula for cone-beam reconstruction[J]. Siam Journal on Applied Mathematics, 1983, 43(3): 546-552.

【3】Bruce D S. Image reconstruction from cone-beam projections: necessary and sufficient conditions and reconstruction methods[J]. IEEE Transactions on Medical Imaging, 1985, 4(1): 14-25.

【4】Hunink M G, Gazelle G S. CT screening: a trade-off of risks, benefits, and costs[J]. Journal of Clinical Investigation, 2003, 111(11): 1612-1619.

【5】张朝宗. 工业CT技术和原理[M]. 北京: 科学出版社, 2009: 46.

【6】Wang L Y, Liu H K, Li L, et al. Review of sparse optimization-based computed tomography image reconstruction from few-view projections[J]. Acta Physica Sinica, 2014, 63(20): 208702.
王林元, 刘宏奎, 李磊, 等. 基于稀疏优化的计算机断层成像图像不完全角度重建综述[J]. 物理学报, 2014, 63(20): 208702.

【7】Guo H B, He X W, Hou Y Q, et al. Fluorescence molecular tomography based on nonconvex sparse regularization[J]. Acta Optica Sinica, 2015, 35(7): 0717001.
郭红波, 贺小伟, 侯榆青, 等. 基于非凸稀疏正则的荧光分子断层成像[J]. 光学学报, 2015, 35(7): 0717001.

【8】Sidky E Y, Kao C M, Pan X. Accurate image reconstruction from few-views and limited-angle data in divergent-beam CT[J]. Journal of X-Ray Science and Technology, 2006, 14(2): 119-139.

【9】Emil Y S, Pan X. Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization[J]. Physics in Medicine & Biology, 2008, 53(17): 4777-4807.

【10】Liu Y, Ma J H, Fan Y, et al. Adaptive-weighted total variation minimization for sparse data toward low-dose X-ray computed tomography image reconstruction[J]. Physics in Medicine & Biology, 2012, 57(23): 7923-7956.

【11】Li Y. The study of limited angle three-dimensional CT image reconstruction algorithm[D]. Taiyuan: North University of China, 2011.
李毅. 有限角度三维CT图像重建算法研究[D]. 太原: 中北大学, 2011.

【12】Dhawan A P, Rangayyan R M, Gordon R. Image restoration by Wiener deconvolution in limited-view computed tomography[J]. Applied Optics, 1985, 24(23): 4013-4020.

【13】Park J C, Song B, Jin S K, et al. Fast compressed sensing-based CBCT reconstruction using Barzilai-Borwein formulation for application to on-line IGRT[J]. Medical Physics, 2012, 39(3): 1207-1217.

【14】Zou J, Sun Y Q, Zhang P. A fast iterative image reconstruction algorithm from few-views projection data[J]. Acta Optica Sinica, 2009, 29(5): 1198-1204.
邹晶, 孙艳勤, 张朋. 由少量投影数据快速重建图像的迭代算法[J]. 光学学报, 2009, 29(5): 1198-1204.

【15】Yu H Y, Wang G. A soft-threshold filtering approach for reconstruction from a limited number of projections[J]. Physics in Medicine & Biology, 2010, 55(13): 3905-3916.

【16】Karp R M. An introduction to randomized algorithms[J]. Discrete Applied Mathematics, 1991, 34(1/2/3): 165-201.

【17】Andersson T, Lathen G, Lenz R, et al. Modified gradient search for level set based image segmentation[J]. IEEE Transactions on Image Processing, 2013, 22(2): 621-630.

【18】Bianchini S. On the Euler-Lagrange equation for a variational problem[M]. [S.l.]: Birkhuser Basel, 2007: 61-77.

【19】Frey J. Introduction to stochastic search and optimization: estimation, simulation, and control[M]. Hoboken: John Wiley & Sons, 2003: 368-369.

【20】Solis F J, Wets R J B. Minimization by random search techniques[J]. Mathematics of Operations Research, 1981, 6(1): 19-30.

【21】陈昊, 颜秀铭, 曹福凯, 等. 粒子群优化算法在CT图像复原中的应用研究[C]. 全国光谱仪器与分析学术研讨会, 2007.

【22】Yu Z. Research on cerebral CT image registration by adaptive particle swarm optimization[D]. Dalian: Dalian Maritime University, 2010.
于泽. 脑CT图像配准中自适应粒子群算法的应用研究[D]. 大连: 大连海事大学, 2010.

【23】Zhao J J, Ji G H, Xia Y, et al. Cavitary nodule segmentation in computed tomography images based on self-generating neural networks and particle swarm optimization[J]. International Journal of Bio-Inspired Computation, 2015, 7(1): 567-580.

【24】Idier J. Bayesian approach to inverse problems[M]. Hoboken: John Wiley & Sons, 2008.

【25】Lu X Q, Sun Q. Limited angle computed tomography reconstruction algorithm based on multiplicative regularization method[J]. Acta Optica Sinica, 2010, 30(5): 1285-1290.
卢孝强, 孙恰. 基于乘性正则化的有限角度CT重建算法[J]. 光学学报, 2010, 30(5): 1285-1290.

【26】Kennedy J. Particle swarm optimization[M]∥ Encyclopedia of Machine Learning. New York: Springer, 2011: 760-766.

【27】Shi X H, Liang Y C, Lee H P, et al. An improved GA and a novel PSO-GA-based hybrid algorithm[J]. Information Processing Letters, 2005, 93(5): 255-261.

【28】Gao X. Research on particle swarm optimization and its application in image retrieval[D]. Xi′an: Xidian University, 2013.
高璇. 粒子群算法优化及其在图像检索中的应用研究[D]. 西安: 西安电子科技大学, 2013.

【29】方峻. 粒子群算法及其应用研究[D]. 成都: 电子科技大学, 2006.

【30】Nojima Y, Chen Y W, Han X H. Image and video restoration with TV/L2-norm constraint[C]. International Conference on Computer Information Systems and Industrial Applications, 2015: 642-644.

【31】Liu X W. Efficient algorithms for hybrid regularizers based image denoising and deblurring[J]. Computers & Mathematics with Applications, 2015, 69(7): 675-687.

【32】Liu Y, Liang Z R, Ma J H, et al. Total variation-Stokes strategy for sparse-view X-ray CT image reconstruction[J]. IEEE Transactions on Medical Imaging, 2014, 33(3): 749-763.

【33】Roux N L, Schmidt M, Bach F. A stochastic gradient method with an exponential convergence rate for finite training sets[J]. Advances in Neural Information Processing Systems, 2013, 4: 2663-2671.

【34】Schmidt M, Roux N L, Bach F. Minimizing finite sums with the stochastic average gradient[M]. New York: Springer-Verlag, 2017.

【35】Rini D P, Shamsuddin S M, Yuhaniz S S. Particle swarm optimization: technique, system and challenges[J]. International Journal of Computer Applications, 2011, 14(1): 19-26.


Gao Hongxia,Luo Lan,Luo Yinghao,Chen Zhanhong,Ma Ge. Improved Stochastic CT Reconstruction Based on Particle Swarm Optimization for Limited-Angle Sparse Projection Data[J]. Acta Optica Sinica, 2018, 38(1): 0111003

高红霞,罗澜,骆英浩,陈展鸿,马鸽. 角度受限下稀疏投影数据的改进粒子群优化随机CT重建[J]. 光学学报, 2018, 38(1): 0111003


【1】秦小云,苏丹,贾新月,周玮,郭汉明. 自适应激光共焦高速扫描显微成像错位校正算法. 光学学报, 2019, 39(1): 118001--1

【2】王少宇,伍伟文,龚长城,刘丰林. 相对平行直线扫描计算机分层成像研究. 光学学报, 2018, 38(12): 1211002--1

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF