Automated segmentation of optical coherence tomography images
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Automated segmentation of optical coherence tomography images
  • 作者:C.Kharmyssov ; 高偉倫 ; J.R.Kim
  • 英文作者:C.Kharmyssov;M.W.L.Ko;J.R.Kim;School of Engineering, Nazarbayev University;The University of Hong Kong;
  • 中文刊名:GXKB
  • 英文刊名:中国光学快报(英文版)
  • 机构:School of Engineering, Nazarbayev University;The University of Hong Kong;
  • 出版日期:2019-01-25
  • 出版单位:Chinese Optics Letters
  • 年:2019
  • 期:v.17
  • 基金:supported by the NU ORAU research grant(No.SOE2017004),Nazarbayev University
  • 语种:英文;
  • 页:GXKB201901014
  • 页数:6
  • CN:01
  • ISSN:31-1890/O4
  • 分类号:66-71
摘要
We propose a fast and accurate automated algorithm to segment retinal pigment epithelium and internal limiting membrane layers from spectral domain optical coherence tomography(SDOCT) B-scan images. A hybrid algorithm, which combines intensity thresholding and graph-based algorithms, was used to process and analyze SDOCT radial scans(120 B scans) images obtained from twenty patients. The relative difference in position of the layers segmented by the proposed hybrid algorithm and by the clinical expert was 1.49% ± 0.01%. The processing time of the hybrid algorithm was 9.3 s for six B scans. Dice's coefficient of the hybrid algorithm was 96.7% ± 1.6%. The proposed hybrid algorithm for the segmentation of SDOCT images had good agreement with manual segmentation and reduced processing time.
        We propose a fast and accurate automated algorithm to segment retinal pigment epithelium and internal limiting membrane layers from spectral domain optical coherence tomography(SDOCT) B-scan images. A hybrid algorithm, which combines intensity thresholding and graph-based algorithms, was used to process and analyze SDOCT radial scans(120 B scans) images obtained from twenty patients. The relative difference in position of the layers segmented by the proposed hybrid algorithm and by the clinical expert was 1.49% ± 0.01%. The processing time of the hybrid algorithm was 9.3 s for six B scans. Dice's coefficient of the hybrid algorithm was 96.7% ± 1.6%. The proposed hybrid algorithm for the segmentation of SDOCT images had good agreement with manual segmentation and reduced processing time.
引文
1.Z.Wu,G.Xu,R.N.Weinreb,M.Yu,and C.K.Leung,Ophthalmology 122,1317(2015).
    2.D.C.De Buc,Image Segmentation(INTECH Open Access,2011),p.15.
    3.D.Xiang,G.Chen,F.Shi,W.Zhu,Q.Liu,S.Yuan,and X.Chen,IEEE J.Biomed.Health Info.27,5880(2018).
    4.D.Koozekanani,K.Boyer,and C.Roberts,IEEE Trans.Med.Imaging 20,900(2001).
    5.A.Chan,J.S.Duker,H.Ishikawa,T.H.Ko,J.S.Schuman,and J.G.Fujimoto,Retina 26,655(2006).
    6.D.C.Fernández,H.M.Salinas,and C.A.Puliafito,Opt.Express 13,10200(2005).
    7.M.Shahidi,Z.Wang,and R.Zelkha,Am.J.Ophthalmol.139,1056(2005).
    8.M.Baroni,P.Fortunato,and A.La Torre,Med.Eng.Phys.29,432(2007).
    9.D.C.Fernandez,IEEE Trans.Med.Imaging 24,929(2005).
    10.A.M.Bagci,M.Shahidi,R.Ansari,M.Blair,N.P.Blair,and R.Zelkha,Am.J.Ophthalmol.146,679(2008).
    11.A.Yazdanpanah,G.Hamarneh,B.Smith,and M.Sarunic,in International Conference on Medical Image Computing and Computer-Assisted Intervention(Springer,2009),p.649.
    12.M.Haeker,M.Abràmoff,R.Kardon,and M.Sonka,in International Conference on Medical Image Computing and Computer-Assisted Intervention(Springer,2006),p.800.
    13.M.K.Garvin,M.D.Abràmoff,R.Kardon,S.R.Russell,X.Wu,and M.Sonka,IEEE Trans.Med.Imaging 27,1495(2008).
    14.S.J.Chiu,X.T.Li,P.Nicholas,C.A.Toth,J.A.Izatt,and S.Farsiu,Opt.Express 18,19413(2010).
    15.J.Qiu,X.Qian,Q.Cui,C.Mu,K.Zhang,B.Na,H.Song,H.Quan,and Z.Liu,Jpn.J.Appl.Phys.51,067001(2012).
    16.M.J.Girard,M.R.Beotra,K.S.Chin,A.Sandhu,M.Clemo,E.Nikita,D.S.Kamal,M.Papadopoulos,J.M.Mari,and T.Aung,Ophthalmology 123,1190(2016).
    17.M.Ko,C.Leung,and T.Yuen,in Global Medical Engineering Physics Exchanges/Pan American Health Care Exchanges(GMEPE/PAHCE)(IEEE,2016),p.1.
    18.P.-Y.Teng,Zenodo 10.528(2013).
    19.T.C.Chen,B.Cense,M.C.Pierce,N.Nassif,B.H.Park,S.H.Yun,B.R.White,B.E.Bouma,G.J.Tearney,and J.F.de Boer,Arch.Ophthalmol.123,1715(2005).
    20.T.Fabritius,S.Makita,M.Miura,R.Myllyl?,and Y.Yasuno,Opt.Express 17,15659(2009).
    21.N.Otsu,IEEE Trans.Syst.Man Cybernet.9,62(1979).
    22.E.W.Dijkstra,Numerische Mathematik 1,269(1959).
    23.J.Shi and J.Malik,IEEE Trans.Pattern Anal.Mach.Intell.22,888(2000).
    24.S.Lu,C.Y.-L.Cheung,J.Liu,J.H.Lim,C.K.-S.Leung,and T.Y.Wong,IEEE Trans.Biomed.Eng.57,2605(2010).
    25.H.Kobatake and Y.Masutani,Computational Anatomy Based on Whole Body Imaging(Springer,2017).
    26.J.M.Bland and D.G.Altman,Lancet 327,307(1986).
    27.M.K.Garvin,M.D.Abramoff,X.Wu,S.R.Russell,T.L.Burns,and M.Sonka,IEEE Trans.Med.Imaging 28,1436(2009).
    28.M.S.Miri,M.D.Abràmoff,K.Lee,M.Niemeijer,J.-K.Wang,Y.H.Kwon,and M.K.Garvin,IEEE Trans.Med.Imaging 34,1854(2015).
    29.B.J.Antony,M.D.Abràmoff,M.M.Harper,W.Jeong,E.H.Sohn,Y.H.Kwon,R.Kardon,and M.K.Garvin,Biomed.Opt.Express 4,2712(2013).

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700