主动形状模型分割方法对光学重建的影响
|
摘要
在非匀质成像中,器官形状是影响建模光在生物体内传播过程的重要因素,它能直接影响荧光分子断层成像(FMT)的重建过程。器官图像的手动分割过程较为复杂,且对图像质量要求较高,而边缘检测、区域生长、主动轮廓模型等自动分割方法在处理复杂医学图像时存在很大的局限性。因此,使用基于主动形状模型(ASM)的自动分割方法,对小鼠器官图像进行准确分割,并使用基于L1范数优化的重建算法实现光源重建。为分析基于ASM的器官图像分割精度与重建精度的关系,采集小鼠计算机断层扫描(CT)数据并进行真实实验,与流行的基于Snake模型的分割算法进行比较。实验结果表明,ASM算法可以替代手动分割,不影响光源的位置重建。
The organ shape is an important factor that affects the propagation of modeling light in vivo.It can directly affect the reconstruction process of fluorescence molecular tomography(FMT).Manual segmentation of organs is complex and requires high-quality images,while automatic segmentation methods such as edge detection,region growing and active contour models have great limitations in dealing with complex medical images.We propose an automatic segmentation method based on active shape models(ASM)to accurately segment the images of mouse organs.Moreover,the light source reconstruction is realized based on L1 norm optimization.We carry out an experiment with the computed tomography(CT)data of a real mouse to explore the relation between organ image segmentation accuracy based on ASM and reconstruction accuracy.The experimental results show that the ASM method can replace manual segmentation without affecting the position reconstruction of light source,when compared with the popular Snake model-based segmentation algorithm.
The organ shape is an important factor that affects the propagation of modeling light in vivo.It can directly affect the reconstruction process of fluorescence molecular tomography(FMT).Manual segmentation of organs is complex and requires high-quality images,while automatic segmentation methods such as edge detection,region growing and active contour models have great limitations in dealing with complex medical images.We propose an automatic segmentation method based on active shape models(ASM)to accurately segment the images of mouse organs.Moreover,the light source reconstruction is realized based on L1 norm optimization.We carry out an experiment with the computed tomography(CT)data of a real mouse to explore the relation between organ image segmentation accuracy based on ASM and reconstruction accuracy.The experimental results show that the ASM method can replace manual segmentation without affecting the position reconstruction of light source,when compared with the popular Snake model-based segmentation algorithm.
引文
[1]Ntziachristos V,Tung C,Bremer C,et al.Fluorescence molecular tomography resolves protease activity in vivo[J].Nature Medicine,2002,8(7):757-760.
[2]Milstein A B,Oh S,Webb K J,et al.Fluorescence optical diffusion tomography[J].Applied Optics,2003,42(16):3081-3094.
[3]Schulz R B,Ripoll J,Ntziachristos V.Experimental fluorescence tomography of tissues with noncontact measurements[J].IEEE Transactions on Medical Imaging,2004,23(4):492-500.
[4]Hou Y Q,Jin M Y,He X W,et al.Fluorescence molecular tomography using a stochastic variant of alternating direction method of multipliers[J].Acta Optica Sinica,2017,37(7):0717001.侯榆青,金明阳,贺小伟,等.基于随机变量交替方向乘子法的荧光分子断层成像[J].光学学报,2017,37(7):0717001.
[5]Dong F,Hou Y Q,Yu J J,et al.Fluorescence molecular tomography via greedy method combined with region-shrinking strategy[J].Laser&Optoelectronics Progress,2016,53(1):011701.董芳,侯榆青,余景景,等.结合区域收缩和贪婪策略的荧光分子断层成像[J].激光与光电子学进展,2016,53(1):011701.
[6]Zhang X,Yi H J,Hou Y Q,et al.Fast reconstruction in fluorescence molecular tomography based on locality preserving projections[J].Acta Optica Sinica,2016,36(7):0717001.张旭,易黄建,侯榆青,等.基于局部保留投影的荧光分子断层成像快速重建[J].光学学报,2016,36(7):0717001.
[7]Li Y,Cho S Y.A method for cell image segmentation using both local and global threshold techniques[C].Eighth International Symposium on Multispectral Image Processing and Pattern Recognition,2013:183-188.
[8]Zhu D H,Lin S M,Yang Y B.Threshold-based segmentation for 3D medical volumetric images[J].Computer Science,2013,40(1):269-272.朱代辉,林时苗,杨育彬.医学三维影像体数据阈值分割方法[J].计算机科学,2013,40(1):269-272.
[9]Mala C,Sridevi M.Multilevel threshold selection for image segmentation using soft computing techniques[J].Soft Computing,2015,20(5):1793-1810.
[10]Shrivakshan G T,Chandrasekar C.A comparison of various edge detection techniques used in image processing[J].International Journal of Computer Science Issues,2012,9(5):272-276.
[11]Meenakshisundari P,Kumar S B R.Comparison of various edge detection techniques in tree ring structure[J].International Journal of Computer Applications,2014,90(19):26-28.
[12]Zhu Z W,Liu G R,Liu Q H.Study of first-order edge detection algorithm[J].Modern Electronics Technique,2009,32(24):88-90.朱振伟,刘广瑞,刘巧红.一阶边缘检测算法的研究[J].现代电子技术,2009,32(24):88-90.
[13]Liu Y,Jiang T,Zang Y.Region growing method for the analysis of functional MRI data[J].Neuroimage,2003,20(1):455-465.
[14]Modi C K,Desai N P.A simple and novel algorithm for automatic selection of ROI for dental radiograph segmentation[C].2011 24th Canadian Conference on Electrical and Computer Engineering,2011:000504-000507.
[15]Verma O P,Hanmandlu M,Susan S,et al.A simple single seeded region growing algorithm for color image segmentation using adaptive thresholding[C].IEEE2011 International Conference on Communication Systems and Network Technologies,2011:500-503.
[16]Zhu S,Gao R.A novel generalized gradient vector flow snake model using minimal surface and componentnormalized method for medical image segmentation[J].Biomedical Signal Processing and Control,2016,26:1-10.
[17]Sun S,Ren H,Meng F.Abnormal lung regions segmentation method based on improved ASM[C].IEEE Control and Decision Conference,2016:5535-5539.
[18]Sharp G C,Sang W L,Wehe D K.ICP registration using invariant features[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(1):90-102.
[19]Yang J,Li H,Campbell D,et al.Go-ICP:aglobally optimal solution to 3DICP point-set registration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(11):2241-2254.
[20]Zhang L,Choi S I,Park S Y.Robust ICP registration using biunique correspondence[C].International Conference on 3D Imaging,Modeling,Processing,Visualization and Transmission,2011:80-85.
[21]Lee S W,Lee D J,Park H S.A new methodology for gray-scale character segmentation and recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,18(10):1045-1050.
[22]Cong A X,Wang G.A finite-element-based reconstruction method for 3Dfluorescence tomography[J].Optics Express,2005,13(24):9847-9857.
[23]Cong W,Kumar D,Liu Y,et al.A practical method to determine the light source distribution in bioluminescent imaging[C].SPIE,2004,5535:679-686.
[24]Alexandrakis G,Rannou F R,Chatziioannou A F.Tomographic bioluminescence imaging by use of a combined optical-PET(OPET)system:a computer simulation feasibility study[J].Physics in Medicine and Biology,2005,50(17):4225-4241.
[2]Milstein A B,Oh S,Webb K J,et al.Fluorescence optical diffusion tomography[J].Applied Optics,2003,42(16):3081-3094.
[3]Schulz R B,Ripoll J,Ntziachristos V.Experimental fluorescence tomography of tissues with noncontact measurements[J].IEEE Transactions on Medical Imaging,2004,23(4):492-500.
[4]Hou Y Q,Jin M Y,He X W,et al.Fluorescence molecular tomography using a stochastic variant of alternating direction method of multipliers[J].Acta Optica Sinica,2017,37(7):0717001.侯榆青,金明阳,贺小伟,等.基于随机变量交替方向乘子法的荧光分子断层成像[J].光学学报,2017,37(7):0717001.
[5]Dong F,Hou Y Q,Yu J J,et al.Fluorescence molecular tomography via greedy method combined with region-shrinking strategy[J].Laser&Optoelectronics Progress,2016,53(1):011701.董芳,侯榆青,余景景,等.结合区域收缩和贪婪策略的荧光分子断层成像[J].激光与光电子学进展,2016,53(1):011701.
[6]Zhang X,Yi H J,Hou Y Q,et al.Fast reconstruction in fluorescence molecular tomography based on locality preserving projections[J].Acta Optica Sinica,2016,36(7):0717001.张旭,易黄建,侯榆青,等.基于局部保留投影的荧光分子断层成像快速重建[J].光学学报,2016,36(7):0717001.
[7]Li Y,Cho S Y.A method for cell image segmentation using both local and global threshold techniques[C].Eighth International Symposium on Multispectral Image Processing and Pattern Recognition,2013:183-188.
[8]Zhu D H,Lin S M,Yang Y B.Threshold-based segmentation for 3D medical volumetric images[J].Computer Science,2013,40(1):269-272.朱代辉,林时苗,杨育彬.医学三维影像体数据阈值分割方法[J].计算机科学,2013,40(1):269-272.
[9]Mala C,Sridevi M.Multilevel threshold selection for image segmentation using soft computing techniques[J].Soft Computing,2015,20(5):1793-1810.
[10]Shrivakshan G T,Chandrasekar C.A comparison of various edge detection techniques used in image processing[J].International Journal of Computer Science Issues,2012,9(5):272-276.
[11]Meenakshisundari P,Kumar S B R.Comparison of various edge detection techniques in tree ring structure[J].International Journal of Computer Applications,2014,90(19):26-28.
[12]Zhu Z W,Liu G R,Liu Q H.Study of first-order edge detection algorithm[J].Modern Electronics Technique,2009,32(24):88-90.朱振伟,刘广瑞,刘巧红.一阶边缘检测算法的研究[J].现代电子技术,2009,32(24):88-90.
[13]Liu Y,Jiang T,Zang Y.Region growing method for the analysis of functional MRI data[J].Neuroimage,2003,20(1):455-465.
[14]Modi C K,Desai N P.A simple and novel algorithm for automatic selection of ROI for dental radiograph segmentation[C].2011 24th Canadian Conference on Electrical and Computer Engineering,2011:000504-000507.
[15]Verma O P,Hanmandlu M,Susan S,et al.A simple single seeded region growing algorithm for color image segmentation using adaptive thresholding[C].IEEE2011 International Conference on Communication Systems and Network Technologies,2011:500-503.
[16]Zhu S,Gao R.A novel generalized gradient vector flow snake model using minimal surface and componentnormalized method for medical image segmentation[J].Biomedical Signal Processing and Control,2016,26:1-10.
[17]Sun S,Ren H,Meng F.Abnormal lung regions segmentation method based on improved ASM[C].IEEE Control and Decision Conference,2016:5535-5539.
[18]Sharp G C,Sang W L,Wehe D K.ICP registration using invariant features[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(1):90-102.
[19]Yang J,Li H,Campbell D,et al.Go-ICP:aglobally optimal solution to 3DICP point-set registration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(11):2241-2254.
[20]Zhang L,Choi S I,Park S Y.Robust ICP registration using biunique correspondence[C].International Conference on 3D Imaging,Modeling,Processing,Visualization and Transmission,2011:80-85.
[21]Lee S W,Lee D J,Park H S.A new methodology for gray-scale character segmentation and recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,18(10):1045-1050.
[22]Cong A X,Wang G.A finite-element-based reconstruction method for 3Dfluorescence tomography[J].Optics Express,2005,13(24):9847-9857.
[23]Cong W,Kumar D,Liu Y,et al.A practical method to determine the light source distribution in bioluminescent imaging[C].SPIE,2004,5535:679-686.
[24]Alexandrakis G,Rannou F R,Chatziioannou A F.Tomographic bioluminescence imaging by use of a combined optical-PET(OPET)system:a computer simulation feasibility study[J].Physics in Medicine and Biology,2005,50(17):4225-4241.