邢琳 张旭 叶雨静 秦磊 沙雨纯 朱伟芳 石霏
摘要:脉络膜血管自动检测在临床上具有重要意义,可通过观察分析脉络膜血管的形态、厚度等信息对多种眼底疾病进行诊断。为辅助临床诊断,提出了一种新的基于SD-OCT图像的脉络膜血管自动检测方法。首先检测出色素上皮层下边界,确定感兴趣区域(Volume of Interest,VOI),然后对图像进行基于灰度线性变换的增强以及三维块匹配滤波等预处理,随后采用Hessian矩阵对血管进行初步提取,提取结果作为目标区域的种子点,进一步用三维区域生长方法检测完整的血管区域,并通过形状信息排除误检以及形态学滤波对检测结果进行后处理。测试结果表明,该方法是一种有效的脉络膜血管自动检测方法。
关键词:脉络膜血管;Hessian矩阵;区域生长;三维块匹配滤波
DOIDOI:10.11907/rjdk.161164
中图分类号:TP319文献标识码:A文章编号:1672-7800(2016)006-0132-05
参考文献:
[1]L WU N,ALPIZAR ALVAREZ.Choroidal imaging by spectral domainoptical coherence tomography[J].Taiwan Journal of Ophthalmology,2013,3(1):3-13.
[2]M HOPE-ROSS,L A YANNUZZI,E S GRAGOUDAS,et al.Puliafito,adverse reactions due to indocyanine green[J].Ophthalmology,1994(101):529-533.
[3]MOTAGHIANNEZAM SM,KOOS D,FRASER SE.Differential phasecontrast,swept-source optical coherence tomography at 1060 nm for in vivo human retinal and choroidal vasculature visualization[J].J Biomed Opt,2012(17):026011.
[4]N R MAHAJAN,R C R DONAPATI,S S CHANNAPPAYYA,et al.An automated algorithm for blood vessel count and area measurement in 2-D choroidal scan images[J].Engineering in Medicine and Biology Conference (EMBC),Osaka,Japan,2013(23): 3355-3358.
[5]V KAJIC ,E MARIEH,G CARL,et al .Automated threedimensional choroidal vessel segmentation of 3D 1060 nm OCT retinal data[J].Biomedical optics express,2013,4(1):134-150.
[6]Z HU,X WU,Y OUYANG,et al.Semiautomated segmentation of the choroid in spectral-domain optical coherence tomography volume scans[J].Investigative ophthalmology & visual science,2013,54(3):1722-1729.
[7]SRINATH N ,PATIL A ,KUMAR V K,et al.Automated detection of choroid boundary and vessels in optical coherence tomography images[C].2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC),2014.
[8]PAL N R,MACHINE INTELL,UNIT INDIAN STAT,et al.A review on image segmentation techniques[J].Pattern Recognition,1993,26(9):94-1277.
[9]K DABOV,A FOI,V KATKOVNIK,et al.Image denoising by sparse 3-D transform-domain collaborative filtering[J].IEEE Transactions on Image Processing,2007,16(8):2080-2095.
[10]SATO Y,WESTIN CF,BHALERAO A.Tissue classification based on 3D local intensity structures for volume rendering[J].IEEE Trans Vis Computer Graphics,2000(6):160-179.
[11]SATO Y,NAKAJIMA S,SHIRAGA N,et al.Three-dimensional multiscale line filter for segmentation and visualization of curvilinear structures in medical images[M].Med Image Anal,1998.
[12]FRANGI AF,NIESSEN WJ,VINCKEN KL,et al.Multiscale vessel enhancement filtering[M].New York,NY: Springer- Verlag,1998:130-137.
[13]LEVINE M D,NAZIF A M.Dynamic measurement of computer generated image segmentations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1985,7(2):64-155.
[14]S C ZHU,A YUILLE.Region competition:unifying snakes,region growing,and bayes/mdl for multiband image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,18(9):884-900.
[15]ZHU S C,YUILLE A.Region competition:unifying snakes,region growing,and bayes/mdl for multi-band image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1996:884-900.
[16]章毓晋.图像工程(上册) 图像处理[M].第3版.北京:清华大学出版社,2012.