基于稀疏处理的多能X射线分离成像

利用独立成分分析(Independent Component Analysis, ICA)并结合多能X射线图像的丰富信息可以将二维X射线图像中重叠目标分离成像, 但是海量的图像数量, 以及高像素数的要求均会使内存占有量和计算速度面临挑战, 因此本研究将压缩感知(Compressed Sensing, CS)与ICA相结合进行分离成像, 以提高计算速度和分离成像性能。研究过程中, 首先根据被拍摄物体的物质组成确定拍摄多能X射线图像数量, 并选取CS技术中K均值奇异值分解(K-means SingularValue Decomposition,K-SVD)稀疏基将多能X射线图像进行稀疏表示, 然后利用ICA将此稀疏表示进行盲源分离得到独立源, 最后采用正交匹配追踪算法(Orthogonal Matching Pursuit, OMP)将独立源进行重构实现分离成像。研究结果表明: 采用ICA&CS技术比仅采用ICA进行目标分离成像的运行时间减少了46.14 s(23.3%)、内存占有率降低了21%、重构图像峰值信噪比(Peak Signal to Noise Ratio, PSNR)提高了2.665 dB、边缘梯度提高了0.001、信息熵提高了0.09。

Abstract

Independent Component Analysis (ICA) combined with abundant information of multi-energy X-ray images can achieve the imaging separation of overlapping targets in 2D X-ray images, but the increasing number of images and higher pixel requirements may serve as an obstacle for memory occupancy and calculating speed. In this paper, Compressed Sensing (CS) was combined with ICA to achieve the imaging separation and to improve the calculating speed, as well as the imaging separation performance. First, the number of the multi-energy X-ray images was determined based on composition of the captured object, and then sparse representation of multi-energy X-ray images was carried out by selecting K-means Singular Value Decomposition (K-SVD) in the CS technology; then, Blind Source Separation(BSS) was conducted in such sparse representation to obtain the independent source by using ICA; finally, Orthogonal Matching Pursuit (OMP) was used to reconstruct the independent source, thus achieving the imaging separation. The results show that compared with the algorithm merely based on ICA, ICA&CS could reduce the algorithm running time by 46.14 s (23.3%) and memory occupancy by 21%, and improve the Peak Signal to Noise Ratio (PSNR) of the reconstructed image by 2.665 dB, edge gradient by 0.001 and information entropy by 0.09.

参考文献

[1] MCCOLLOUGH CH,LENG SA, YU L F,et al.. Dual- and multi-energy CT: principles, technical approaches, and clinical applications ［J］. Radiology, 2015, 276(3): 637-653.

[2] RICHARD K J, RICHARD A K. Application of high resolution X-ray computed tomography to mineral deposit origin, evaluation, and processing ［J］. Ore Geology Reviews, 2015, 65(SI): 821-839.

[3] STUTMAN D, TRITZ K, FINKENTHAL M. Multi-energy x-ray imaging and sensing for diagnostic and control of the burning plasma ［J］. Review of Scientific Instruments, 2012, 83(10): 10E535.

[4] SAIM A,TEBBOUNE A,BERKOK H, et al.. Linear and mass attenuation coefficient for CdTe compound of X-rays from 10 to 100 keV energy range in different phases ［J］. Journal of Alloys and Compounds, 2014, 602: 261-264.

[5] MIDGLEY SM. A model for multi-energy x-ray analysis ［J］. Physics in Medicine and Biology, 2011,56(10): 2943-2962.

[6] FIRSCHING M,NACHTRAB F,UHLMANN N,et al.. Multi-energy X-ray imaging as a quantitative method for materials characterization ［J］. Advanced Materials, 2011, 23(22-23): 2655-2656.

[7] 李艳, 喻春雨, 缪亚健, 等. 基于ICA的X射线医学图像目标提取［J］.光谱学与光谱分析,2015,35(3): 825-828.

LI Y, YU CH Y, MIAO Y J, et al.. Object separation from medical x-ray images based on ICA ［J］. Spectroscopy and Spectral Analysis, 2015, 35(3), 825-828. (in Chinese)

[8] HYVARINEN A. Independent component analysis: Recent advances ［J］. Philosophical Transactions of the Royal Society A, 2013,371(1984): 20110534.

[9] 陈媛媛, 王芳, 王志斌, 等. 独立成分分析在化学战剂混叠峰识别中的应用［J］. 红外与激光工程, 2016, 45(4): 0423001.

CHEN Y Y, WANG F, WANG ZH B, et al.. Application of independent component analysis in aliasing peak identification of chemical warfare agents ［J］. Infrared and Laser Engineering, 2016, 45(4): 0423001.(in Chinese)

[10] DONOHO D L. Compressed sensing ［J］. IEEE Transactions on Information Theory, 2006, 52(4): 1289-1306.

[11] 酉霞, 陈菲, 贾小林, 等.字典学习中字典尺度对 DICOM 图像压缩的影响［J］.液晶与显示, 2015, 30(6): 1045-1050.

YOU X, CHEN F, JIA X L, et al.. Effects of dictionary scale on dictionary learning for DICOM image compression ［J］.Chinese Journal of Liquid Crystals and Displays, 2015, 30(6): 1045-1050. (in Chinese)

[12] 周渝人,耿爱辉,张强.基于压缩感知的红外与可见光图像融合［J］.光学精密工程,2015,23(3): 855-863.

ZHOU Y R, GENG A H, ZHANG Q, et al.. Fusion of infrared and visible images based on compressive sensing［J］. Opt. Precision Eng., 2015,23(3): 855-863. (in Chinese)

[13] WU Z Y, ZHANG W, WANG J W, et al.. Feature extraction for gas photoacoustic spectroscopy and content inverse based on overcomplete ICA bases ［J］. Optics and Laser Technology, 2013, 48: 580-588.

[14] PENG H Y, ZHU S M. Handling of incomplete data sets using ICA and SOM in data mining ［J］. Neural Computing& Applications, 2007, 16(2): 167-172.

[15] EMMANUEL C J,ROMBERG J, TAO T. Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information ［J］. IEEE Transactions on Information Theory, 2006, 52(2): 489-509.

[16] RABAH H, AMIRA A, MOHANTY B K,et al.. FPGA implementation of orthogonal matching pursuit for compressive sensing reconstruction ［J］. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2015,23(10): 2209-2220.

[17] PTUCHA R,SAVAKIS A E. LGE-KSVD: Robust sparse representation classification ［J］. IEEE Transactions on Image Processing, 2014,23(4): 1737-1750.

费彬, 孙京阳, 张俊举, 喻春雨. 基于稀疏处理的多能X射线分离成像[J]. 光学精密工程, 2017, 25(4): 1106. FEI Bin, SUN Jing-yang, ZHANG Jun-ju, YU Chun-yu. Separation of multi-energy X-ray imaging based on sparse processing[J]. Optics and Precision Engineering, 2017, 25(4): 1106.

基于稀疏处理的多能X射线分离成像

关于本站 Cookie 的使用提示

全站搜索

基于稀疏处理的多能X射线分离成像

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索