Abstract

Modern optical coherence tomography (OCT) devices used in ophthalmology acquire steadily increasing amounts of imaging data. Thus, reliable automated quantitative analysis of OCT images is considered to be of utmost importance. Current automated retinal OCT layer segmentation methods work reliably on healthy or mildly diseased retinas, but struggle with the complex interaction of the layers with fluid accumulations in macular edema. In this work, we present a fully automated 3D method which is able to segment all the retinal layers and fluid-filled regions simultaneously, exploiting their mutual interaction to improve the overall segmentation results. The machine learning based method combines unsupervised feature representation and heterogeneous spatial context with a graph-theoretic surface segmentation. The method was extensively evaluated on manual annotations of 20,000 OCT B-scans from 100 scans of patients and on a publicly available data set consisting of 110 annotated B-scans from 10 patients, all with severe macular edema, yielding an overall mean Dice coefficient of 0.76 and 0.78, respectively.

© 2017 Optical Society of America

Full Article  |  PDF Article
OSA Recommended Articles
ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks

Abhijit Guha Roy, Sailesh Conjeti, Sri Phani Krishna Karri, Debdoot Sheet, Amin Katouzian, Christian Wachinger, and Nassir Navab
Biomed. Opt. Express 8(8) 3627-3642 (2017)

Automated segmentation of subretinal layers for the detection of macular edema

Taimur Hassan, M. Usman Akram, Bilal Hassan, Adeel M. Syed, and Shafaat Ahmed Bazaz
Appl. Opt. 55(3) 454-461 (2016)

Deep learning approach for the detection and quantification of intraretinal cystoid fluid in multivendor optical coherence tomography

Freerk G. Venhuizen, Bram van Ginneken, Bart Liefers, Freekje van Asten, Vivian Schreur, Sascha Fauser, Carel Hoyng, Thomas Theelen, and Clara I. Sánchez
Biomed. Opt. Express 9(4) 1545-1569 (2018)

References

  • View by:
  • |
  • |
  • |

  1. R. D. Jager, W. F. Mieler, and J. W. Miller, “Age-related macular degeneration,” New Engl. J. Med. 358, 2606–2617 (2008).
    [Crossref] [PubMed]
  2. J. A. Davidson, T. A. Ciulla, J. B. McGill, K. A. Kles, and P. W. Anderson, “How the diabetic eye loses vision,” Endocrine 32, 107–116 (2007).
    [Crossref] [PubMed]
  3. P. A. Campochiaro, L. P. Aiello, and P. J. Rosenfeld, “Anti-vascular endothelial growth factor agents in the treatment of retinal disease: From bench to bedside,” Ophthalmology 123, S78–S88 (2016).
    [Crossref] [PubMed]
  4. K. A. Rezaei and T. W. Stone, “2016 Global Trends in Retina Survey,” American Society of Retina Specialists, Chicago, IL. (2016).
  5. U. Schmidt-Erfurth, S. M. Waldstein, G.-G. Deak, M. Kundi, and C. Simader, “Pigment epithelial detachment followed by retinal cystoid degeneration leads to vision loss in treatment of neovascular age-related macular degeneration,” Ophthalmology 122, 822–832 (2015).
    [Crossref] [PubMed]
  6. S. M. Waldstein, J. Wright, J. Warburton, P. Margaron, C. Simader, and U. Schmidt-Erfurth, “Predictive value of retinal morphology for visual acuity outcomes of different ranibizumab treatment regimens for neovascular AMD,” Ophthalmology 123, 60–69 (2016).
    [Crossref]
  7. C. K. Hitzenberger, P. Trost, P.-W. Lo, and Q. Zhou, “Three-dimensional imaging of the human retina by high-speed optical coherence tomography,” Opt. Express 11, 2753–2761 (2003).
    [Crossref] [PubMed]
  8. A. Salinas-Alamán, A. García-Layana, M. J. Maldonado, C. Sainz-Gómez, and A. Alvárez-Vidal, “Using optical coherence tomography to monitor photodynamic therapy in age related macular degeneration,” Am. J. Ophthalmol. 140, 23e1 (2005).
    [Crossref]
  9. S. M. Waldstein, A.-M. Philip, R. Leitner, C. Simader, G. Langs, B. S. Gerendas, and U. Schmidt-Erfurth, “Correlation of 3-dimensionally quantified intraretinal and subretinal fluid with visual acuity in neovascular age-related macular degeneration,” JAMA Ophthalmol. 134, 182–190 (2016).
    [Crossref]
  10. S. J. Chiu, X. T. Li, P. Nicholas, C. A. Toth, J. A. Izatt, and S. Farsiu, “Automatic segmentation of seven retinal layers in SDOCT images congruent with expert manual segmentation,” Opt. Express 18, 19413–19428 (2010).
    [Crossref] [PubMed]
  11. A. A. Taha and A. Hanbury, “Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool”, BMC Med Imaging 15, 29 (2015).
    [Crossref] [PubMed]
  12. S. J. Chiu, M. J. Allingham, P. S. Mettu, S. W. Cousins, J. A. Izatt, and S. Farsiu, “Kernel regression based segmentation of optical coherence tomography images with diabetic macular edema,” Biomed. Opt. Express 6, 1172–1194 (2015).
    [Crossref] [PubMed]
  13. X. Chen, M. Niemeijer, L. Zhang, K. Lee, M. D. Abramoff, and M. Sonka, “Three-dimensional segmentation of fluid-associated abnormalities in retinal OCT: Probability constrained graph-search-graph-cut,” IEEE Trans. Med. Imaging 31, 1521–1531 (2012).
    [Crossref] [PubMed]
  14. M. K. Garvin, M. D. Abramoff, X. Wu, S. R. Russell, T. L. Burns, and M. Sonka, “Automated 3-D intraretinal layer segmentation of macular spectral-domain optical coherence tomography images,” IEEE Trans. Med. Imaging 28, 1436–1447 (2009).
    [Crossref] [PubMed]
  15. T. Schlegl, S. M. Waldstein, W.-D. Vogl, U. Schmidt-Erfurth, and G. Langs, “Predicting semantic descriptions from medical images with convolutional neural networks,” Inf. Process. Med. Imaging 24, 437–448 (2015).
    [PubMed]
  16. Q. Chen, T. Leng, L. Zheng, L. Kutzscher, J. Ma, L. de Sisternes, and D. L. Rubin, “Automated drusen segmentation and quantification in SD-OCT images,” Med. Image Anal. 17, 1058–1072 (2013).
    [Crossref] [PubMed]
  17. I. Oguz, L. Zhang, M. D. Abrámoff, and M. Sonka, “Optimal retinal cyst segmentation from OCT images,” in “Medical Imaging 2016: Image Processing,” M. A. Styner and Elsa D. Angelini, eds., Proc. SPIE9784, 97841E (2016)
    [Crossref]
  18. J. Wang, M. Zhang, A. D. Pechauer, L. Liu, T. S. Hwang, D. J. Wilson, D. Li, and Y. Jia, “Automated volumetric segmentation of retinal fluid on optical coherence tomography,” Biomed. Opt. Express 7, 1577–1589 (2016).
    [Crossref] [PubMed]
  19. S. P. K. Karri, D. Chakraborthi, and J. Chatterjee, “Learning layer-specific edges for segmenting retinal layers with large deformations,” Biomed. Opt. Express 7, 2888–28901 (2016).
    [Crossref] [PubMed]
  20. M. Zhang, J. Wang, A. D. Pechauer, T. S. Hwang, S. S. Gao, L. Liu, Li Liu, S. T. Bailey, D. J. Wilson, D. Huang, and Y. Jia, “Advanced image processing for optical coherence tomographic angiography of macular diseases,” Biomed. Opt. Express 6, 4661–4675 (2015).
    [Crossref] [PubMed]
  21. Z. Tu and X. Bai, “Auto-context and its application to high-level vision tasks and 3D brain image segmentation,” IEEE Trans. Pattern Anal. Mach. Intell. 32, 1744–1757 (2010).
    [Crossref] [PubMed]
  22. L. Breiman, “Random forests,” Mach. Learn. 45, 5–32 (2001).
    [Crossref]
  23. A. Montuoro, C. Simader, G. Langs, and U. Schmidt-Erfurth, “Rotation invariant eigenvessels and auto-context for retinal vessel detection,” in “Medical Imaging 2015: Image Processing,” S. Ourselin and M. A. Styner, eds., Proc. SPIE941394131F (2015)
    [Crossref]
  24. D. A. Ross, J. Lim, R.-S. Lin, and M.-H. Yang, “Incremental learning for robust visual tracking,” Int. J. Comput. Vision 77, 125–141 (2008).
    [Crossref]

2016 (5)

P. A. Campochiaro, L. P. Aiello, and P. J. Rosenfeld, “Anti-vascular endothelial growth factor agents in the treatment of retinal disease: From bench to bedside,” Ophthalmology 123, S78–S88 (2016).
[Crossref] [PubMed]

S. M. Waldstein, J. Wright, J. Warburton, P. Margaron, C. Simader, and U. Schmidt-Erfurth, “Predictive value of retinal morphology for visual acuity outcomes of different ranibizumab treatment regimens for neovascular AMD,” Ophthalmology 123, 60–69 (2016).
[Crossref]

S. M. Waldstein, A.-M. Philip, R. Leitner, C. Simader, G. Langs, B. S. Gerendas, and U. Schmidt-Erfurth, “Correlation of 3-dimensionally quantified intraretinal and subretinal fluid with visual acuity in neovascular age-related macular degeneration,” JAMA Ophthalmol. 134, 182–190 (2016).
[Crossref]

J. Wang, M. Zhang, A. D. Pechauer, L. Liu, T. S. Hwang, D. J. Wilson, D. Li, and Y. Jia, “Automated volumetric segmentation of retinal fluid on optical coherence tomography,” Biomed. Opt. Express 7, 1577–1589 (2016).
[Crossref] [PubMed]

S. P. K. Karri, D. Chakraborthi, and J. Chatterjee, “Learning layer-specific edges for segmenting retinal layers with large deformations,” Biomed. Opt. Express 7, 2888–28901 (2016).
[Crossref] [PubMed]

2015 (5)

M. Zhang, J. Wang, A. D. Pechauer, T. S. Hwang, S. S. Gao, L. Liu, Li Liu, S. T. Bailey, D. J. Wilson, D. Huang, and Y. Jia, “Advanced image processing for optical coherence tomographic angiography of macular diseases,” Biomed. Opt. Express 6, 4661–4675 (2015).
[Crossref] [PubMed]

A. A. Taha and A. Hanbury, “Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool”, BMC Med Imaging 15, 29 (2015).
[Crossref] [PubMed]

S. J. Chiu, M. J. Allingham, P. S. Mettu, S. W. Cousins, J. A. Izatt, and S. Farsiu, “Kernel regression based segmentation of optical coherence tomography images with diabetic macular edema,” Biomed. Opt. Express 6, 1172–1194 (2015).
[Crossref] [PubMed]

U. Schmidt-Erfurth, S. M. Waldstein, G.-G. Deak, M. Kundi, and C. Simader, “Pigment epithelial detachment followed by retinal cystoid degeneration leads to vision loss in treatment of neovascular age-related macular degeneration,” Ophthalmology 122, 822–832 (2015).
[Crossref] [PubMed]

T. Schlegl, S. M. Waldstein, W.-D. Vogl, U. Schmidt-Erfurth, and G. Langs, “Predicting semantic descriptions from medical images with convolutional neural networks,” Inf. Process. Med. Imaging 24, 437–448 (2015).
[PubMed]

2013 (1)

Q. Chen, T. Leng, L. Zheng, L. Kutzscher, J. Ma, L. de Sisternes, and D. L. Rubin, “Automated drusen segmentation and quantification in SD-OCT images,” Med. Image Anal. 17, 1058–1072 (2013).
[Crossref] [PubMed]

2012 (1)

X. Chen, M. Niemeijer, L. Zhang, K. Lee, M. D. Abramoff, and M. Sonka, “Three-dimensional segmentation of fluid-associated abnormalities in retinal OCT: Probability constrained graph-search-graph-cut,” IEEE Trans. Med. Imaging 31, 1521–1531 (2012).
[Crossref] [PubMed]

2010 (2)

Z. Tu and X. Bai, “Auto-context and its application to high-level vision tasks and 3D brain image segmentation,” IEEE Trans. Pattern Anal. Mach. Intell. 32, 1744–1757 (2010).
[Crossref] [PubMed]

S. J. Chiu, X. T. Li, P. Nicholas, C. A. Toth, J. A. Izatt, and S. Farsiu, “Automatic segmentation of seven retinal layers in SDOCT images congruent with expert manual segmentation,” Opt. Express 18, 19413–19428 (2010).
[Crossref] [PubMed]

2009 (1)

M. K. Garvin, M. D. Abramoff, X. Wu, S. R. Russell, T. L. Burns, and M. Sonka, “Automated 3-D intraretinal layer segmentation of macular spectral-domain optical coherence tomography images,” IEEE Trans. Med. Imaging 28, 1436–1447 (2009).
[Crossref] [PubMed]

2008 (2)

R. D. Jager, W. F. Mieler, and J. W. Miller, “Age-related macular degeneration,” New Engl. J. Med. 358, 2606–2617 (2008).
[Crossref] [PubMed]

D. A. Ross, J. Lim, R.-S. Lin, and M.-H. Yang, “Incremental learning for robust visual tracking,” Int. J. Comput. Vision 77, 125–141 (2008).
[Crossref]

2007 (1)

J. A. Davidson, T. A. Ciulla, J. B. McGill, K. A. Kles, and P. W. Anderson, “How the diabetic eye loses vision,” Endocrine 32, 107–116 (2007).
[Crossref] [PubMed]

2005 (1)

A. Salinas-Alamán, A. García-Layana, M. J. Maldonado, C. Sainz-Gómez, and A. Alvárez-Vidal, “Using optical coherence tomography to monitor photodynamic therapy in age related macular degeneration,” Am. J. Ophthalmol. 140, 23e1 (2005).
[Crossref]

2003 (1)

2001 (1)

L. Breiman, “Random forests,” Mach. Learn. 45, 5–32 (2001).
[Crossref]

Abramoff, M. D.

X. Chen, M. Niemeijer, L. Zhang, K. Lee, M. D. Abramoff, and M. Sonka, “Three-dimensional segmentation of fluid-associated abnormalities in retinal OCT: Probability constrained graph-search-graph-cut,” IEEE Trans. Med. Imaging 31, 1521–1531 (2012).
[Crossref] [PubMed]

M. K. Garvin, M. D. Abramoff, X. Wu, S. R. Russell, T. L. Burns, and M. Sonka, “Automated 3-D intraretinal layer segmentation of macular spectral-domain optical coherence tomography images,” IEEE Trans. Med. Imaging 28, 1436–1447 (2009).
[Crossref] [PubMed]

Abrámoff, M. D.

I. Oguz, L. Zhang, M. D. Abrámoff, and M. Sonka, “Optimal retinal cyst segmentation from OCT images,” in “Medical Imaging 2016: Image Processing,” M. A. Styner and Elsa D. Angelini, eds., Proc. SPIE9784, 97841E (2016)
[Crossref]

Aiello, L. P.

P. A. Campochiaro, L. P. Aiello, and P. J. Rosenfeld, “Anti-vascular endothelial growth factor agents in the treatment of retinal disease: From bench to bedside,” Ophthalmology 123, S78–S88 (2016).
[Crossref] [PubMed]

Allingham, M. J.

Alvárez-Vidal, A.

A. Salinas-Alamán, A. García-Layana, M. J. Maldonado, C. Sainz-Gómez, and A. Alvárez-Vidal, “Using optical coherence tomography to monitor photodynamic therapy in age related macular degeneration,” Am. J. Ophthalmol. 140, 23e1 (2005).
[Crossref]

Anderson, P. W.

J. A. Davidson, T. A. Ciulla, J. B. McGill, K. A. Kles, and P. W. Anderson, “How the diabetic eye loses vision,” Endocrine 32, 107–116 (2007).
[Crossref] [PubMed]

Bai, X.

Z. Tu and X. Bai, “Auto-context and its application to high-level vision tasks and 3D brain image segmentation,” IEEE Trans. Pattern Anal. Mach. Intell. 32, 1744–1757 (2010).
[Crossref] [PubMed]

Bailey, S. T.

Breiman, L.

L. Breiman, “Random forests,” Mach. Learn. 45, 5–32 (2001).
[Crossref]

Burns, T. L.

M. K. Garvin, M. D. Abramoff, X. Wu, S. R. Russell, T. L. Burns, and M. Sonka, “Automated 3-D intraretinal layer segmentation of macular spectral-domain optical coherence tomography images,” IEEE Trans. Med. Imaging 28, 1436–1447 (2009).
[Crossref] [PubMed]

Campochiaro, P. A.

P. A. Campochiaro, L. P. Aiello, and P. J. Rosenfeld, “Anti-vascular endothelial growth factor agents in the treatment of retinal disease: From bench to bedside,” Ophthalmology 123, S78–S88 (2016).
[Crossref] [PubMed]

Chakraborthi, D.

Chatterjee, J.

Chen, Q.

Q. Chen, T. Leng, L. Zheng, L. Kutzscher, J. Ma, L. de Sisternes, and D. L. Rubin, “Automated drusen segmentation and quantification in SD-OCT images,” Med. Image Anal. 17, 1058–1072 (2013).
[Crossref] [PubMed]

Chen, X.

X. Chen, M. Niemeijer, L. Zhang, K. Lee, M. D. Abramoff, and M. Sonka, “Three-dimensional segmentation of fluid-associated abnormalities in retinal OCT: Probability constrained graph-search-graph-cut,” IEEE Trans. Med. Imaging 31, 1521–1531 (2012).
[Crossref] [PubMed]

Chiu, S. J.

Ciulla, T. A.

J. A. Davidson, T. A. Ciulla, J. B. McGill, K. A. Kles, and P. W. Anderson, “How the diabetic eye loses vision,” Endocrine 32, 107–116 (2007).
[Crossref] [PubMed]

Cousins, S. W.

Davidson, J. A.

J. A. Davidson, T. A. Ciulla, J. B. McGill, K. A. Kles, and P. W. Anderson, “How the diabetic eye loses vision,” Endocrine 32, 107–116 (2007).
[Crossref] [PubMed]

de Sisternes, L.

Q. Chen, T. Leng, L. Zheng, L. Kutzscher, J. Ma, L. de Sisternes, and D. L. Rubin, “Automated drusen segmentation and quantification in SD-OCT images,” Med. Image Anal. 17, 1058–1072 (2013).
[Crossref] [PubMed]

Deak, G.-G.

U. Schmidt-Erfurth, S. M. Waldstein, G.-G. Deak, M. Kundi, and C. Simader, “Pigment epithelial detachment followed by retinal cystoid degeneration leads to vision loss in treatment of neovascular age-related macular degeneration,” Ophthalmology 122, 822–832 (2015).
[Crossref] [PubMed]

Farsiu, S.

Gao, S. S.

García-Layana, A.

A. Salinas-Alamán, A. García-Layana, M. J. Maldonado, C. Sainz-Gómez, and A. Alvárez-Vidal, “Using optical coherence tomography to monitor photodynamic therapy in age related macular degeneration,” Am. J. Ophthalmol. 140, 23e1 (2005).
[Crossref]

Garvin, M. K.

M. K. Garvin, M. D. Abramoff, X. Wu, S. R. Russell, T. L. Burns, and M. Sonka, “Automated 3-D intraretinal layer segmentation of macular spectral-domain optical coherence tomography images,” IEEE Trans. Med. Imaging 28, 1436–1447 (2009).
[Crossref] [PubMed]

Gerendas, B. S.

S. M. Waldstein, A.-M. Philip, R. Leitner, C. Simader, G. Langs, B. S. Gerendas, and U. Schmidt-Erfurth, “Correlation of 3-dimensionally quantified intraretinal and subretinal fluid with visual acuity in neovascular age-related macular degeneration,” JAMA Ophthalmol. 134, 182–190 (2016).
[Crossref]

Hanbury, A.

A. A. Taha and A. Hanbury, “Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool”, BMC Med Imaging 15, 29 (2015).
[Crossref] [PubMed]

Hitzenberger, C. K.

Huang, D.

Hwang, T. S.

Izatt, J. A.

Jager, R. D.

R. D. Jager, W. F. Mieler, and J. W. Miller, “Age-related macular degeneration,” New Engl. J. Med. 358, 2606–2617 (2008).
[Crossref] [PubMed]

Jia, Y.

Karri, S. P. K.

Kles, K. A.

J. A. Davidson, T. A. Ciulla, J. B. McGill, K. A. Kles, and P. W. Anderson, “How the diabetic eye loses vision,” Endocrine 32, 107–116 (2007).
[Crossref] [PubMed]

Kundi, M.

U. Schmidt-Erfurth, S. M. Waldstein, G.-G. Deak, M. Kundi, and C. Simader, “Pigment epithelial detachment followed by retinal cystoid degeneration leads to vision loss in treatment of neovascular age-related macular degeneration,” Ophthalmology 122, 822–832 (2015).
[Crossref] [PubMed]

Kutzscher, L.

Q. Chen, T. Leng, L. Zheng, L. Kutzscher, J. Ma, L. de Sisternes, and D. L. Rubin, “Automated drusen segmentation and quantification in SD-OCT images,” Med. Image Anal. 17, 1058–1072 (2013).
[Crossref] [PubMed]

Langs, G.

S. M. Waldstein, A.-M. Philip, R. Leitner, C. Simader, G. Langs, B. S. Gerendas, and U. Schmidt-Erfurth, “Correlation of 3-dimensionally quantified intraretinal and subretinal fluid with visual acuity in neovascular age-related macular degeneration,” JAMA Ophthalmol. 134, 182–190 (2016).
[Crossref]

T. Schlegl, S. M. Waldstein, W.-D. Vogl, U. Schmidt-Erfurth, and G. Langs, “Predicting semantic descriptions from medical images with convolutional neural networks,” Inf. Process. Med. Imaging 24, 437–448 (2015).
[PubMed]

A. Montuoro, C. Simader, G. Langs, and U. Schmidt-Erfurth, “Rotation invariant eigenvessels and auto-context for retinal vessel detection,” in “Medical Imaging 2015: Image Processing,” S. Ourselin and M. A. Styner, eds., Proc. SPIE941394131F (2015)
[Crossref]

Lee, K.

X. Chen, M. Niemeijer, L. Zhang, K. Lee, M. D. Abramoff, and M. Sonka, “Three-dimensional segmentation of fluid-associated abnormalities in retinal OCT: Probability constrained graph-search-graph-cut,” IEEE Trans. Med. Imaging 31, 1521–1531 (2012).
[Crossref] [PubMed]

Leitner, R.

S. M. Waldstein, A.-M. Philip, R. Leitner, C. Simader, G. Langs, B. S. Gerendas, and U. Schmidt-Erfurth, “Correlation of 3-dimensionally quantified intraretinal and subretinal fluid with visual acuity in neovascular age-related macular degeneration,” JAMA Ophthalmol. 134, 182–190 (2016).
[Crossref]

Leng, T.

Q. Chen, T. Leng, L. Zheng, L. Kutzscher, J. Ma, L. de Sisternes, and D. L. Rubin, “Automated drusen segmentation and quantification in SD-OCT images,” Med. Image Anal. 17, 1058–1072 (2013).
[Crossref] [PubMed]

Li, D.

Li, X. T.

Lim, J.

D. A. Ross, J. Lim, R.-S. Lin, and M.-H. Yang, “Incremental learning for robust visual tracking,” Int. J. Comput. Vision 77, 125–141 (2008).
[Crossref]

Lin, R.-S.

D. A. Ross, J. Lim, R.-S. Lin, and M.-H. Yang, “Incremental learning for robust visual tracking,” Int. J. Comput. Vision 77, 125–141 (2008).
[Crossref]

Liu, L.

Liu, Li

Lo, P.-W.

Ma, J.

Q. Chen, T. Leng, L. Zheng, L. Kutzscher, J. Ma, L. de Sisternes, and D. L. Rubin, “Automated drusen segmentation and quantification in SD-OCT images,” Med. Image Anal. 17, 1058–1072 (2013).
[Crossref] [PubMed]

Maldonado, M. J.

A. Salinas-Alamán, A. García-Layana, M. J. Maldonado, C. Sainz-Gómez, and A. Alvárez-Vidal, “Using optical coherence tomography to monitor photodynamic therapy in age related macular degeneration,” Am. J. Ophthalmol. 140, 23e1 (2005).
[Crossref]

Margaron, P.

S. M. Waldstein, J. Wright, J. Warburton, P. Margaron, C. Simader, and U. Schmidt-Erfurth, “Predictive value of retinal morphology for visual acuity outcomes of different ranibizumab treatment regimens for neovascular AMD,” Ophthalmology 123, 60–69 (2016).
[Crossref]

McGill, J. B.

J. A. Davidson, T. A. Ciulla, J. B. McGill, K. A. Kles, and P. W. Anderson, “How the diabetic eye loses vision,” Endocrine 32, 107–116 (2007).
[Crossref] [PubMed]

Mettu, P. S.

Mieler, W. F.

R. D. Jager, W. F. Mieler, and J. W. Miller, “Age-related macular degeneration,” New Engl. J. Med. 358, 2606–2617 (2008).
[Crossref] [PubMed]

Miller, J. W.

R. D. Jager, W. F. Mieler, and J. W. Miller, “Age-related macular degeneration,” New Engl. J. Med. 358, 2606–2617 (2008).
[Crossref] [PubMed]

Montuoro, A.

A. Montuoro, C. Simader, G. Langs, and U. Schmidt-Erfurth, “Rotation invariant eigenvessels and auto-context for retinal vessel detection,” in “Medical Imaging 2015: Image Processing,” S. Ourselin and M. A. Styner, eds., Proc. SPIE941394131F (2015)
[Crossref]

Nicholas, P.

Niemeijer, M.

X. Chen, M. Niemeijer, L. Zhang, K. Lee, M. D. Abramoff, and M. Sonka, “Three-dimensional segmentation of fluid-associated abnormalities in retinal OCT: Probability constrained graph-search-graph-cut,” IEEE Trans. Med. Imaging 31, 1521–1531 (2012).
[Crossref] [PubMed]

Oguz, I.

I. Oguz, L. Zhang, M. D. Abrámoff, and M. Sonka, “Optimal retinal cyst segmentation from OCT images,” in “Medical Imaging 2016: Image Processing,” M. A. Styner and Elsa D. Angelini, eds., Proc. SPIE9784, 97841E (2016)
[Crossref]

Pechauer, A. D.

Philip, A.-M.

S. M. Waldstein, A.-M. Philip, R. Leitner, C. Simader, G. Langs, B. S. Gerendas, and U. Schmidt-Erfurth, “Correlation of 3-dimensionally quantified intraretinal and subretinal fluid with visual acuity in neovascular age-related macular degeneration,” JAMA Ophthalmol. 134, 182–190 (2016).
[Crossref]

Rezaei, K. A.

K. A. Rezaei and T. W. Stone, “2016 Global Trends in Retina Survey,” American Society of Retina Specialists, Chicago, IL. (2016).

Rosenfeld, P. J.

P. A. Campochiaro, L. P. Aiello, and P. J. Rosenfeld, “Anti-vascular endothelial growth factor agents in the treatment of retinal disease: From bench to bedside,” Ophthalmology 123, S78–S88 (2016).
[Crossref] [PubMed]

Ross, D. A.

D. A. Ross, J. Lim, R.-S. Lin, and M.-H. Yang, “Incremental learning for robust visual tracking,” Int. J. Comput. Vision 77, 125–141 (2008).
[Crossref]

Rubin, D. L.

Q. Chen, T. Leng, L. Zheng, L. Kutzscher, J. Ma, L. de Sisternes, and D. L. Rubin, “Automated drusen segmentation and quantification in SD-OCT images,” Med. Image Anal. 17, 1058–1072 (2013).
[Crossref] [PubMed]

Russell, S. R.

M. K. Garvin, M. D. Abramoff, X. Wu, S. R. Russell, T. L. Burns, and M. Sonka, “Automated 3-D intraretinal layer segmentation of macular spectral-domain optical coherence tomography images,” IEEE Trans. Med. Imaging 28, 1436–1447 (2009).
[Crossref] [PubMed]

Sainz-Gómez, C.

A. Salinas-Alamán, A. García-Layana, M. J. Maldonado, C. Sainz-Gómez, and A. Alvárez-Vidal, “Using optical coherence tomography to monitor photodynamic therapy in age related macular degeneration,” Am. J. Ophthalmol. 140, 23e1 (2005).
[Crossref]

Salinas-Alamán, A.

A. Salinas-Alamán, A. García-Layana, M. J. Maldonado, C. Sainz-Gómez, and A. Alvárez-Vidal, “Using optical coherence tomography to monitor photodynamic therapy in age related macular degeneration,” Am. J. Ophthalmol. 140, 23e1 (2005).
[Crossref]

Schlegl, T.

T. Schlegl, S. M. Waldstein, W.-D. Vogl, U. Schmidt-Erfurth, and G. Langs, “Predicting semantic descriptions from medical images with convolutional neural networks,” Inf. Process. Med. Imaging 24, 437–448 (2015).
[PubMed]

Schmidt-Erfurth, U.

S. M. Waldstein, A.-M. Philip, R. Leitner, C. Simader, G. Langs, B. S. Gerendas, and U. Schmidt-Erfurth, “Correlation of 3-dimensionally quantified intraretinal and subretinal fluid with visual acuity in neovascular age-related macular degeneration,” JAMA Ophthalmol. 134, 182–190 (2016).
[Crossref]

S. M. Waldstein, J. Wright, J. Warburton, P. Margaron, C. Simader, and U. Schmidt-Erfurth, “Predictive value of retinal morphology for visual acuity outcomes of different ranibizumab treatment regimens for neovascular AMD,” Ophthalmology 123, 60–69 (2016).
[Crossref]

U. Schmidt-Erfurth, S. M. Waldstein, G.-G. Deak, M. Kundi, and C. Simader, “Pigment epithelial detachment followed by retinal cystoid degeneration leads to vision loss in treatment of neovascular age-related macular degeneration,” Ophthalmology 122, 822–832 (2015).
[Crossref] [PubMed]

T. Schlegl, S. M. Waldstein, W.-D. Vogl, U. Schmidt-Erfurth, and G. Langs, “Predicting semantic descriptions from medical images with convolutional neural networks,” Inf. Process. Med. Imaging 24, 437–448 (2015).
[PubMed]

A. Montuoro, C. Simader, G. Langs, and U. Schmidt-Erfurth, “Rotation invariant eigenvessels and auto-context for retinal vessel detection,” in “Medical Imaging 2015: Image Processing,” S. Ourselin and M. A. Styner, eds., Proc. SPIE941394131F (2015)
[Crossref]

Simader, C.

S. M. Waldstein, J. Wright, J. Warburton, P. Margaron, C. Simader, and U. Schmidt-Erfurth, “Predictive value of retinal morphology for visual acuity outcomes of different ranibizumab treatment regimens for neovascular AMD,” Ophthalmology 123, 60–69 (2016).
[Crossref]

S. M. Waldstein, A.-M. Philip, R. Leitner, C. Simader, G. Langs, B. S. Gerendas, and U. Schmidt-Erfurth, “Correlation of 3-dimensionally quantified intraretinal and subretinal fluid with visual acuity in neovascular age-related macular degeneration,” JAMA Ophthalmol. 134, 182–190 (2016).
[Crossref]

U. Schmidt-Erfurth, S. M. Waldstein, G.-G. Deak, M. Kundi, and C. Simader, “Pigment epithelial detachment followed by retinal cystoid degeneration leads to vision loss in treatment of neovascular age-related macular degeneration,” Ophthalmology 122, 822–832 (2015).
[Crossref] [PubMed]

A. Montuoro, C. Simader, G. Langs, and U. Schmidt-Erfurth, “Rotation invariant eigenvessels and auto-context for retinal vessel detection,” in “Medical Imaging 2015: Image Processing,” S. Ourselin and M. A. Styner, eds., Proc. SPIE941394131F (2015)
[Crossref]

Sonka, M.

X. Chen, M. Niemeijer, L. Zhang, K. Lee, M. D. Abramoff, and M. Sonka, “Three-dimensional segmentation of fluid-associated abnormalities in retinal OCT: Probability constrained graph-search-graph-cut,” IEEE Trans. Med. Imaging 31, 1521–1531 (2012).
[Crossref] [PubMed]

M. K. Garvin, M. D. Abramoff, X. Wu, S. R. Russell, T. L. Burns, and M. Sonka, “Automated 3-D intraretinal layer segmentation of macular spectral-domain optical coherence tomography images,” IEEE Trans. Med. Imaging 28, 1436–1447 (2009).
[Crossref] [PubMed]

I. Oguz, L. Zhang, M. D. Abrámoff, and M. Sonka, “Optimal retinal cyst segmentation from OCT images,” in “Medical Imaging 2016: Image Processing,” M. A. Styner and Elsa D. Angelini, eds., Proc. SPIE9784, 97841E (2016)
[Crossref]

Stone, T. W.

K. A. Rezaei and T. W. Stone, “2016 Global Trends in Retina Survey,” American Society of Retina Specialists, Chicago, IL. (2016).

Taha, A. A.

A. A. Taha and A. Hanbury, “Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool”, BMC Med Imaging 15, 29 (2015).
[Crossref] [PubMed]

Toth, C. A.

Trost, P.

Tu, Z.

Z. Tu and X. Bai, “Auto-context and its application to high-level vision tasks and 3D brain image segmentation,” IEEE Trans. Pattern Anal. Mach. Intell. 32, 1744–1757 (2010).
[Crossref] [PubMed]

Vogl, W.-D.

T. Schlegl, S. M. Waldstein, W.-D. Vogl, U. Schmidt-Erfurth, and G. Langs, “Predicting semantic descriptions from medical images with convolutional neural networks,” Inf. Process. Med. Imaging 24, 437–448 (2015).
[PubMed]

Waldstein, S. M.

S. M. Waldstein, J. Wright, J. Warburton, P. Margaron, C. Simader, and U. Schmidt-Erfurth, “Predictive value of retinal morphology for visual acuity outcomes of different ranibizumab treatment regimens for neovascular AMD,” Ophthalmology 123, 60–69 (2016).
[Crossref]

S. M. Waldstein, A.-M. Philip, R. Leitner, C. Simader, G. Langs, B. S. Gerendas, and U. Schmidt-Erfurth, “Correlation of 3-dimensionally quantified intraretinal and subretinal fluid with visual acuity in neovascular age-related macular degeneration,” JAMA Ophthalmol. 134, 182–190 (2016).
[Crossref]

U. Schmidt-Erfurth, S. M. Waldstein, G.-G. Deak, M. Kundi, and C. Simader, “Pigment epithelial detachment followed by retinal cystoid degeneration leads to vision loss in treatment of neovascular age-related macular degeneration,” Ophthalmology 122, 822–832 (2015).
[Crossref] [PubMed]

T. Schlegl, S. M. Waldstein, W.-D. Vogl, U. Schmidt-Erfurth, and G. Langs, “Predicting semantic descriptions from medical images with convolutional neural networks,” Inf. Process. Med. Imaging 24, 437–448 (2015).
[PubMed]

Wang, J.

Warburton, J.

S. M. Waldstein, J. Wright, J. Warburton, P. Margaron, C. Simader, and U. Schmidt-Erfurth, “Predictive value of retinal morphology for visual acuity outcomes of different ranibizumab treatment regimens for neovascular AMD,” Ophthalmology 123, 60–69 (2016).
[Crossref]

Wilson, D. J.

Wright, J.

S. M. Waldstein, J. Wright, J. Warburton, P. Margaron, C. Simader, and U. Schmidt-Erfurth, “Predictive value of retinal morphology for visual acuity outcomes of different ranibizumab treatment regimens for neovascular AMD,” Ophthalmology 123, 60–69 (2016).
[Crossref]

Wu, X.

M. K. Garvin, M. D. Abramoff, X. Wu, S. R. Russell, T. L. Burns, and M. Sonka, “Automated 3-D intraretinal layer segmentation of macular spectral-domain optical coherence tomography images,” IEEE Trans. Med. Imaging 28, 1436–1447 (2009).
[Crossref] [PubMed]

Yang, M.-H.

D. A. Ross, J. Lim, R.-S. Lin, and M.-H. Yang, “Incremental learning for robust visual tracking,” Int. J. Comput. Vision 77, 125–141 (2008).
[Crossref]

Zhang, L.

X. Chen, M. Niemeijer, L. Zhang, K. Lee, M. D. Abramoff, and M. Sonka, “Three-dimensional segmentation of fluid-associated abnormalities in retinal OCT: Probability constrained graph-search-graph-cut,” IEEE Trans. Med. Imaging 31, 1521–1531 (2012).
[Crossref] [PubMed]

I. Oguz, L. Zhang, M. D. Abrámoff, and M. Sonka, “Optimal retinal cyst segmentation from OCT images,” in “Medical Imaging 2016: Image Processing,” M. A. Styner and Elsa D. Angelini, eds., Proc. SPIE9784, 97841E (2016)
[Crossref]

Zhang, M.

Zheng, L.

Q. Chen, T. Leng, L. Zheng, L. Kutzscher, J. Ma, L. de Sisternes, and D. L. Rubin, “Automated drusen segmentation and quantification in SD-OCT images,” Med. Image Anal. 17, 1058–1072 (2013).
[Crossref] [PubMed]

Zhou, Q.

Am. J. Ophthalmol. (1)

A. Salinas-Alamán, A. García-Layana, M. J. Maldonado, C. Sainz-Gómez, and A. Alvárez-Vidal, “Using optical coherence tomography to monitor photodynamic therapy in age related macular degeneration,” Am. J. Ophthalmol. 140, 23e1 (2005).
[Crossref]

Biomed. Opt. Express (4)

BMC Med Imaging (1)

A. A. Taha and A. Hanbury, “Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool”, BMC Med Imaging 15, 29 (2015).
[Crossref] [PubMed]

Endocrine (1)

J. A. Davidson, T. A. Ciulla, J. B. McGill, K. A. Kles, and P. W. Anderson, “How the diabetic eye loses vision,” Endocrine 32, 107–116 (2007).
[Crossref] [PubMed]

IEEE Trans. Med. Imaging (2)

X. Chen, M. Niemeijer, L. Zhang, K. Lee, M. D. Abramoff, and M. Sonka, “Three-dimensional segmentation of fluid-associated abnormalities in retinal OCT: Probability constrained graph-search-graph-cut,” IEEE Trans. Med. Imaging 31, 1521–1531 (2012).
[Crossref] [PubMed]

M. K. Garvin, M. D. Abramoff, X. Wu, S. R. Russell, T. L. Burns, and M. Sonka, “Automated 3-D intraretinal layer segmentation of macular spectral-domain optical coherence tomography images,” IEEE Trans. Med. Imaging 28, 1436–1447 (2009).
[Crossref] [PubMed]

IEEE Trans. Pattern Anal. Mach. Intell. (1)

Z. Tu and X. Bai, “Auto-context and its application to high-level vision tasks and 3D brain image segmentation,” IEEE Trans. Pattern Anal. Mach. Intell. 32, 1744–1757 (2010).
[Crossref] [PubMed]

Inf. Process. Med. Imaging (1)

T. Schlegl, S. M. Waldstein, W.-D. Vogl, U. Schmidt-Erfurth, and G. Langs, “Predicting semantic descriptions from medical images with convolutional neural networks,” Inf. Process. Med. Imaging 24, 437–448 (2015).
[PubMed]

Int. J. Comput. Vision (1)

D. A. Ross, J. Lim, R.-S. Lin, and M.-H. Yang, “Incremental learning for robust visual tracking,” Int. J. Comput. Vision 77, 125–141 (2008).
[Crossref]

JAMA Ophthalmol. (1)

S. M. Waldstein, A.-M. Philip, R. Leitner, C. Simader, G. Langs, B. S. Gerendas, and U. Schmidt-Erfurth, “Correlation of 3-dimensionally quantified intraretinal and subretinal fluid with visual acuity in neovascular age-related macular degeneration,” JAMA Ophthalmol. 134, 182–190 (2016).
[Crossref]

Mach. Learn. (1)

L. Breiman, “Random forests,” Mach. Learn. 45, 5–32 (2001).
[Crossref]

Med. Image Anal. (1)

Q. Chen, T. Leng, L. Zheng, L. Kutzscher, J. Ma, L. de Sisternes, and D. L. Rubin, “Automated drusen segmentation and quantification in SD-OCT images,” Med. Image Anal. 17, 1058–1072 (2013).
[Crossref] [PubMed]

New Engl. J. Med. (1)

R. D. Jager, W. F. Mieler, and J. W. Miller, “Age-related macular degeneration,” New Engl. J. Med. 358, 2606–2617 (2008).
[Crossref] [PubMed]

Ophthalmology (3)

P. A. Campochiaro, L. P. Aiello, and P. J. Rosenfeld, “Anti-vascular endothelial growth factor agents in the treatment of retinal disease: From bench to bedside,” Ophthalmology 123, S78–S88 (2016).
[Crossref] [PubMed]

U. Schmidt-Erfurth, S. M. Waldstein, G.-G. Deak, M. Kundi, and C. Simader, “Pigment epithelial detachment followed by retinal cystoid degeneration leads to vision loss in treatment of neovascular age-related macular degeneration,” Ophthalmology 122, 822–832 (2015).
[Crossref] [PubMed]

S. M. Waldstein, J. Wright, J. Warburton, P. Margaron, C. Simader, and U. Schmidt-Erfurth, “Predictive value of retinal morphology for visual acuity outcomes of different ranibizumab treatment regimens for neovascular AMD,” Ophthalmology 123, 60–69 (2016).
[Crossref]

Opt. Express (2)

Other (3)

K. A. Rezaei and T. W. Stone, “2016 Global Trends in Retina Survey,” American Society of Retina Specialists, Chicago, IL. (2016).

I. Oguz, L. Zhang, M. D. Abrámoff, and M. Sonka, “Optimal retinal cyst segmentation from OCT images,” in “Medical Imaging 2016: Image Processing,” M. A. Styner and Elsa D. Angelini, eds., Proc. SPIE9784, 97841E (2016)
[Crossref]

A. Montuoro, C. Simader, G. Langs, and U. Schmidt-Erfurth, “Rotation invariant eigenvessels and auto-context for retinal vessel detection,” in “Medical Imaging 2015: Image Processing,” S. Ourselin and M. A. Styner, eds., Proc. SPIE941394131F (2015)
[Crossref]

Cited By

OSA participates in Crossref's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (16)

Fig. 1
Fig. 1 Left: B-scan of a SD-OCT volume of a patient with pronounced macular edema. Note the loss of OCT signal below highly absorbing regions such as fluid. Right: Voxel-wise manual annotation of 14 regions.
Fig. 2
Fig. 2 OCT acquisition and the coordinate system. 1D axial scans (A-scan, purple) are combined to form a 2D cross sectional slice (B-scan, red) by scanning through the volume in a raster scan pattern ( blue). Multiple B-scans are then combined to form a complete OCT volume.
Fig. 3
Fig. 3 Overview of the workflow of the proposed method consisting of a base voxel classification stage and a subsequent auto-context loop.
Fig. 4
Fig. 4 The amount of variance in the original data that can be explained by a given number of PCA components. Markers show the number of components used for various scales in the proposed method.
Fig. 5
Fig. 5 PCA eigenvectors, rows: 3 eigenvectors at various scales, columns: slices of eigen-vectors and the corresponding 3D representation.
Fig. 6
Fig. 6 150 relative context locations sampled using a Gaussian distribution (σ = 15 px). For each voxel the samples are taken from the probability map and used as context features.
Fig. 7
Fig. 7 Example of convolution kernel encoding the probability of R8 relative to a R10 sample at scale 613 px. Given that a voxel belongs to the class R8 the highest probability for finding a voxel of class R10 is approx. 15 px above it.
Fig. 8
Fig. 8 Fovea position estimation. Left: Fovea distance prediction; Right: Predicted fovea position, with highlighted points in the distance map that are agreeing with the predicted position.
Fig. 9
Fig. 9 Qualitative results on example image shown in Fig. 1. Left: Segmentation result of the proposed method after one auto-context iteration. Right: Corresponding 3D visualization (data was processed for visualization purposes)
Fig. 10
Fig. 10 Qualitative results on RVO data set. Left: Raw intensity image; Middle: Manually annotated ground truth; Right: Output of the proposed method.
Fig. 11
Fig. 11 Results of surface segmentation on RVO data set for training and test sets. Mean absolute error of individual surfaces without (base) and with auto-context.
Fig. 12
Fig. 12 Result of fovea estimation. Histogram of the absolute Euclidean distance between the predicted fovea position and the manually annotated fovea position on 100 OCT volumes in the RVO data set.
Fig. 13
Fig. 13 2D PCA eigenvectors computed on DME data set at various scales.
Fig. 14
Fig. 14 Results of layer segmentation on DME data set. Mean absolute error of individual layer thicknesses for the method without (base), with auto-context, inter-reader and the method in [11].
Fig. 15
Fig. 15 Segmentation results of subject #1 in the DME data set. Top: Central B-scan and the manual annotations; Bottom: Results of the proposed method and the method presented in [12].
Fig. 16
Fig. 16 Relative feature importance reported by the random forest classifier after one auto-context iteration.

Tables (4)

Tables Icon

Table 1 Structural relationship between surfaces and regions (layers and fluids), where F denotes the foreground and B the background.

Tables Icon

Table 2 Results of region segmentation on RVO data set. Dice coefficients (mean ± std) without (base) and with auto-context.

Tables Icon

Table 3 Structural relationship, surfaces and regions defined for the data set provided in [12].

Tables Icon

Table 4 Results of region segmentation on DME data set. Dice coefficients (mean ± std) for method without (base), with auto-context, inter-reader and the method in [12].

Equations (2)

Equations on this page are rendered with MathJax. Learn more.

C base : train ( f img , labels ) predict ( C base ) extract ( f ctx base ) C ctx 0 : train ( f img + f ctx base , labels ) predict ( C ctx 0 ) extract ( f ctx 0 ) C ctx 1 : train ( f img + f ctx 0 , labels ) predict ( C ctx 1 ) extract ( f ctx 1 ) C ctx n : train ( f img + f ctx n 1 , labels ) predict ( C ctx n ) extract ( f ctx n )
Dice = 2 * T P | true | + | predicted | = 2 * T P ( T P + F N ) ( T P + F P ) = 2 * T P 2 * T P + F N + F P

Metrics