Retina layer segmentation using kernel graph cuts and continuous max-flow

D. Kaba; Y. Wang; C. Wang; X. Liu; H. Zhu; A. G. Salazar-Gonzalez; Y. Li

doi:10.1364/OE.23.007366

Retina layer segmentation using kernel graph cuts and continuous max-flow

D. Kaba, Y. Wang, C. Wang, X. Liu, H. Zhu, A. G. Salazar-Gonzalez, and Y. Li

Optics Express
Vol. 23,
Issue 6,
pp. 7366-7384
(2015)
•https://doi.org/10.1364/OE.23.007366

Get Citation
Copy Citation Text
D. Kaba, Y. Wang, C. Wang, X. Liu, H. Zhu, A. G. Salazar-Gonzalez, and Y. Li, "Retina layer segmentation using kernel graph cuts and continuous max-flow," Opt. Express 23, 7366-7384 (2015)

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Get PDF (5538 KB)
Set citation alerts
Save article

Related Topics
Table of Contents Category
- Image Processing
Optics & Photonics Topics
?

The topics in this list come from the OSA Optics and Photonics Topics applied to this article.
Previously assigned OCIS codes
- Image analysis (100.2960)
- Image enhancement (100.2980)
- Optical coherence tomography (110.4500)
- Medical and biological imaging (170.3880)

About this Article
History
- Original Manuscript: September 19, 2014
- Revised Manuscript: January 13, 2015
- Manuscript Accepted: January 26, 2015
- Published: March 12, 2015
Virtual Issues
Virtual Journal for Biomedical Optics Vol. 10, Iss. 4

Accessible

Open Access

Abstract

Circular scan Spectral-Domain Optic Coherence Tomography imaging (SD-OCT) is one of the best tools for diagnosis of retinal diseases. This technique provides more comprehensive detail of the retinal morphology and layers around the optic disc nerve head (ONH). Since manual labelling of the retinal layers can be tedious and time consuming, accurate and robust automated segmentation methods are needed to provide the thickness evaluation of these layers in retinal disorder assessments such as glaucoma. The proposed method serves this purpose by performing the segmentation of retinal layers boundaries in circular SD-OCT scans acquired around the ONH. The layers are detected by adapting a graph cut segmentation technique that includes a kernel-induced space and a continuous multiplier based max-flow algorithm. Results from scan images acquired with Spectralis (Heidelberg Engineering, Germany) prove that the proposed method is robust and efficient in detecting the retinal layers boundaries in images. With a mean root-mean-square error (RMSE) of 0.0835 ± 0.0495 and an average Dice coefficient of 0.9468 ± 0.0705 pixels for the retinal nerve fibre layer thickness, the proposed method demonstrated effective agreement with manual annotations.

Full Article | PDF Article

OSA Recommended Articles

FloatingCanvas: quantification of 3D retinal structures from spectral-domain optical coherence tomography

Haogang Zhu, David P. Crabb, Patricio G. Schlottmann, Tuan Ho, and David F. Garway-Heath
Opt. Express 18(24) 24595-24610 (2010)

Retinal Nerve Fiber Layer Segmentation on FD-OCT Scans of Normal Subjects and Glaucoma Patients

Markus A. Mayer, Joachim Hornegger, Christian Y. Mardin, and Ralf P. Tornow
Biomed. Opt. Express 1(5) 1358-1383 (2010)

Automated segmentation of retinal blood vessels in spectral domain optical coherence tomography scans

Matthäus Pilch, Yaroslava Wenner, Elisabeth Strohmayr, Markus Preising, Christoph Friedburg, Erdmuthe Meyer zu Bexten, Birgit Lorenz, and Knut Stieger
Biomed. Opt. Express 3(7) 1478-1491 (2012)

References

View by:
Article Order
|
Year
|
Author
|
Publication

D. Huang, E. A. Swanson, C. P. Lin, J. S. Schuman, W. G. Stinson, W. Chang, M. R. Hee, T. Flotte, K. Gregory, and C. A. Puliafito, “Optical coherence tomography,” Science 254(5035), 1178–1181 (1991).
[Crossref] [PubMed]
J. S. Schuman, M. R. Hee, A. V. Arya, T. Pedut-Kloizman, C. A. Puliafito, J. G. Fujimoto, and E. A. Swanson, “Optical coherence tomography: a new tool for glaucoma diagnosis,” Current opinion in ophthalmology 6(2), 89–95 (1995).
[Crossref] [PubMed]
V. Guedes, J. S. Schuman, E. Hertzmark, G. Wollstein, A. Correnti, R. Mancini, D. Lederer, S. Voskanian, L. Velazquez, and H. M. Pakter, “Optical coherence tomography measurement of macular and nerve fiber layer thickness in normal and glaucomatous human eyes,” Ophthalmology 110, 177–189 (2003).
[Crossref] [PubMed]
A. F. Fercher, C. K. Hitzenberger, G. Kamp, and S. Y. El-Zaiat, “Measurement of intraocular distances by backscattering spectral interferometry,” Optics Communications 117, 43–48 (1995).
[Crossref]
M. Wojtkowski, R. Leitgeb, A. Kowalczyk, A. F. Fercher, and T. Bajraszewski, “In vivo human retinal imaging by Fourier domain optical coherence tomography,” Journal of biomedical optics 7(3), 457–463 (2002).
[Crossref] [PubMed]
D. Koozekanani, K. Boyer, and C. Roberts, “Retinal thickness measurements from optical coherence tomography using a Markov boundary model,” Medical Imaging, IEEE Transactions (IEEE 2001)20(9), 900–916.
H. Ishikawa, D. M. Stein, G. Wollstein, S. Beaton, J. G. Fujimoto, and J. S. Schuman, “Macular segmentation with optical coherence tomography,” Investigative Ophthalmology & Visual Science 46(6), 2012–2017 (2005).
[Crossref]
D. Cabrera Fernández, H. M. Salinas, and C. A. Puliafito, “Automated detection of retinal layer structures on optical coherence tomography images,” Optics Express 13(25), 10200–10216 (2005).
[Crossref] [PubMed]
C. Ahlers, C. Simader, W. Geitzenauer, G. Stock, P. Stetson, S. Dastmalchi, and U. Schmidt-Erfurth, “Automatic segmentation in three-dimensional analysis of fibrovascular pigmentepithelial detachment using high-definition optical coherence tomography,” British Journal of Ophthalmology 92(2), 197–203 (2008).
[Crossref]
M. Mujat, R. Chan, B. Cense, B. Park, C. Joo, T. Akkin, T. Chen, and J. de Boer, “Retinal nerve fiber layer thickness map determined from optical coherence tomography images,” Optics Express 13(23), 9480–9491 (2005).
[Crossref] [PubMed]
A. Yazdanpanah, G. Hamarneh, B. R. Smith, and M. V. Sarunic, “Segmentation of intra-retinal layers from optical coherence tomography images using an active contour approach,” Medical Imaging, IEEE Transactions on (IEEE 2011) 30(2), 484–496 (2011).
J. Novosel, K. A. Vermeer, G. Thepass, H. G. Lemij, and L. J. van Vliet, “Loosely coupled level sets for retinal layer segmentation in optical coherence tomography,” In Biomedical Imaging (ISBI), 2013 IEEE 10th International Symposium on2013, 1010–1013.
H. Zhu, D. P. Crabb, P. G. Schlottmann, T. Ho, and D. F. Garway-Heath, “FloatingCanvas: quantification of 3D retinal structures from spectral-domain optical coherence tomography,” Optics express 18(24), 24595–24610 (2010).
[Crossref] [PubMed]
M. K. Garvin, M. D. Abràmoff, R. Kardon, S. R. Russell, X. Wu, and M. Sonka, “Intraretinal layer segmentation of macular optical coherence tomography images using optimal 3-D graph search,” Medical Imaging, IEEE Transactions on200827(10), 1495–1505.
[Crossref]
M. K. Garvin, M. D. Abràmoff, 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,” Medical Imaging, IEEE Transactions on 200928(9), 1436–1447.
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,” Optics express 18(18), 19413–19428 (2010).
[Crossref] [PubMed]
O. S. Anthony, “Is Imaging Now Standard of Care for Glaucoma?” http://www.revoptom.com/content/c/19985 .
N. j. Tustison, B. B. Avants, P. A. Cook, Y. Zheng, A. Egan, P. A. Yushkevich, and J. C. Gee, “N4ITK: improved N3 bias correction,” Medical Imaging, IEEE Transactions on201029(6), 1310–1320.
[Crossref]
M. B. Salah, A. Mitiche, and I. B. Ayed, “Multiregion image segmentation by parametric kernel graph cuts,” Image Processing, IEEE Transactions on201120(2), 545–557.
[Crossref]
J. Yuan, E. Bae, and X. C. Tai, “A study on continuous max-flow and min-cut approaches,” In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on IEEE2010, 2217–2224.
J. G. Sled, A. P. Zijdenbos, and A. C. Evans, “A nonparametric method for automatic correction of intensity nonuniformity in MRI data,” Medical Imaging, IEEE Transactions on199817, 87–97.
[Crossref]
Y. Y. Boykov and M. P. Jolly, “Interactive graph cuts for optimal boundary & region segmentation of objects in ND images,” In Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on, 1IEEE2001, 105–112.
R. A. Costa, M. Skaf, L. A. Melo, D. Calucci, J. A. Cardillo, J. C. Castro, D. Huang, and M. Wojtkowski, “Retinal assessment using optical coherence tomography,” Progress in retinal and eye research 25(3), 325–353 (2006).
[Crossref] [PubMed]
A. Lang, A. Carass, E. Sotirchos, P. Calabresi, and J. L. Prince, “Segmentation of retinal OCT images using a random forest classifier,” In SPIE Medical Imaging, International Society for Optics and Photonics, 86690R (2013).

2011 (1)

A. Yazdanpanah, G. Hamarneh, B. R. Smith, and M. V. Sarunic, “Segmentation of intra-retinal layers from optical coherence tomography images using an active contour approach,” Medical Imaging, IEEE Transactions on (IEEE 2011) 30(2), 484–496 (2011).

2010 (2)

H. Zhu, D. P. Crabb, P. G. Schlottmann, T. Ho, and D. F. Garway-Heath, “FloatingCanvas: quantification of 3D retinal structures from spectral-domain optical coherence tomography,” Optics express 18(24), 24595–24610 (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,” Optics express 18(18), 19413–19428 (2010).
[Crossref] [PubMed]

2008 (1)

C. Ahlers, C. Simader, W. Geitzenauer, G. Stock, P. Stetson, S. Dastmalchi, and U. Schmidt-Erfurth, “Automatic segmentation in three-dimensional analysis of fibrovascular pigmentepithelial detachment using high-definition optical coherence tomography,” British Journal of Ophthalmology 92(2), 197–203 (2008).
[Crossref]

2006 (1)

R. A. Costa, M. Skaf, L. A. Melo, D. Calucci, J. A. Cardillo, J. C. Castro, D. Huang, and M. Wojtkowski, “Retinal assessment using optical coherence tomography,” Progress in retinal and eye research 25(3), 325–353 (2006).
[Crossref] [PubMed]

2005 (3)

M. Mujat, R. Chan, B. Cense, B. Park, C. Joo, T. Akkin, T. Chen, and J. de Boer, “Retinal nerve fiber layer thickness map determined from optical coherence tomography images,” Optics Express 13(23), 9480–9491 (2005).
[Crossref] [PubMed]

H. Ishikawa, D. M. Stein, G. Wollstein, S. Beaton, J. G. Fujimoto, and J. S. Schuman, “Macular segmentation with optical coherence tomography,” Investigative Ophthalmology & Visual Science 46(6), 2012–2017 (2005).
[Crossref]

D. Cabrera Fernández, H. M. Salinas, and C. A. Puliafito, “Automated detection of retinal layer structures on optical coherence tomography images,” Optics Express 13(25), 10200–10216 (2005).
[Crossref] [PubMed]

2003 (1)

V. Guedes, J. S. Schuman, E. Hertzmark, G. Wollstein, A. Correnti, R. Mancini, D. Lederer, S. Voskanian, L. Velazquez, and H. M. Pakter, “Optical coherence tomography measurement of macular and nerve fiber layer thickness in normal and glaucomatous human eyes,” Ophthalmology 110, 177–189 (2003).
[Crossref] [PubMed]

2002 (1)

M. Wojtkowski, R. Leitgeb, A. Kowalczyk, A. F. Fercher, and T. Bajraszewski, “In vivo human retinal imaging by Fourier domain optical coherence tomography,” Journal of biomedical optics 7(3), 457–463 (2002).
[Crossref] [PubMed]

1995 (2)

A. F. Fercher, C. K. Hitzenberger, G. Kamp, and S. Y. El-Zaiat, “Measurement of intraocular distances by backscattering spectral interferometry,” Optics Communications 117, 43–48 (1995).
[Crossref]

J. S. Schuman, M. R. Hee, A. V. Arya, T. Pedut-Kloizman, C. A. Puliafito, J. G. Fujimoto, and E. A. Swanson, “Optical coherence tomography: a new tool for glaucoma diagnosis,” Current opinion in ophthalmology 6(2), 89–95 (1995).
[Crossref] [PubMed]

1991 (1)

D. Huang, E. A. Swanson, C. P. Lin, J. S. Schuman, W. G. Stinson, W. Chang, M. R. Hee, T. Flotte, K. Gregory, and C. A. Puliafito, “Optical coherence tomography,” Science 254(5035), 1178–1181 (1991).
[Crossref] [PubMed]

Abràmoff, M. D.

M. K. Garvin, M. D. Abràmoff, R. Kardon, S. R. Russell, X. Wu, and M. Sonka, “Intraretinal layer segmentation of macular optical coherence tomography images using optimal 3-D graph search,” Medical Imaging, IEEE Transactions on200827(10), 1495–1505.
[Crossref]

M. K. Garvin, M. D. Abràmoff, 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,” Medical Imaging, IEEE Transactions on 200928(9), 1436–1447.

Ahlers, C.

Akkin, T.

Arya, A. V.

Avants, B. B.

N. j. Tustison, B. B. Avants, P. A. Cook, Y. Zheng, A. Egan, P. A. Yushkevich, and J. C. Gee, “N4ITK: improved N3 bias correction,” Medical Imaging, IEEE Transactions on201029(6), 1310–1320.
[Crossref]

Ayed, I. B.

M. B. Salah, A. Mitiche, and I. B. Ayed, “Multiregion image segmentation by parametric kernel graph cuts,” Image Processing, IEEE Transactions on201120(2), 545–557.
[Crossref]

Bae, E.

J. Yuan, E. Bae, and X. C. Tai, “A study on continuous max-flow and min-cut approaches,” In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on IEEE2010, 2217–2224.

Bajraszewski, T.

Beaton, S.

Boyer, K.

D. Koozekanani, K. Boyer, and C. Roberts, “Retinal thickness measurements from optical coherence tomography using a Markov boundary model,” Medical Imaging, IEEE Transactions (IEEE 2001)20(9), 900–916.

Boykov, Y. Y.

Y. Y. Boykov and M. P. Jolly, “Interactive graph cuts for optimal boundary & region segmentation of objects in ND images,” In Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on, 1IEEE2001, 105–112.

Burns, T. L.

Cabrera Fernández, D.

Calabresi, P.

A. Lang, A. Carass, E. Sotirchos, P. Calabresi, and J. L. Prince, “Segmentation of retinal OCT images using a random forest classifier,” In SPIE Medical Imaging, International Society for Optics and Photonics, 86690R (2013).

Calucci, D.

Carass, A.

Cardillo, J. A.

Castro, J. C.

Cense, B.

Chan, R.

Chang, W.

Chen, T.

Chiu, S. J.

Cook, P. A.

Correnti, A.

Costa, R. A.

Crabb, D. P.

Dastmalchi, S.

de Boer, J.

Egan, A.

El-Zaiat, S. Y.

Evans, A. C.

J. G. Sled, A. P. Zijdenbos, and A. C. Evans, “A nonparametric method for automatic correction of intensity nonuniformity in MRI data,” Medical Imaging, IEEE Transactions on199817, 87–97.
[Crossref]

Farsiu, S.

Fercher, A. F.

Flotte, T.

Fujimoto, J. G.

Garvin, M. K.

Garway-Heath, D. F.

Gee, J. C.

Geitzenauer, W.

Gregory, K.

Guedes, V.

Hamarneh, G.

Hee, M. R.

Hertzmark, E.

Hitzenberger, C. K.

Ho, T.

Huang, D.

Ishikawa, H.

Izatt, J. A.

Jolly, M. P.

Joo, C.

Kamp, G.

Kardon, R.

Koozekanani, D.

Kowalczyk, A.

Lang, A.

Lederer, D.

Leitgeb, R.

Lemij, H. G.

J. Novosel, K. A. Vermeer, G. Thepass, H. G. Lemij, and L. J. van Vliet, “Loosely coupled level sets for retinal layer segmentation in optical coherence tomography,” In Biomedical Imaging (ISBI), 2013 IEEE 10th International Symposium on2013, 1010–1013.

Li, X. T.

Lin, C. P.

Mancini, R.

Melo, L. A.

Mitiche, A.

M. B. Salah, A. Mitiche, and I. B. Ayed, “Multiregion image segmentation by parametric kernel graph cuts,” Image Processing, IEEE Transactions on201120(2), 545–557.
[Crossref]

Mujat, M.

Nicholas, P.

Novosel, J.

Pakter, H. M.

Park, B.

Pedut-Kloizman, T.

Prince, J. L.

Puliafito, C. A.

Roberts, C.

Russell, S. R.

Salah, M. B.

M. B. Salah, A. Mitiche, and I. B. Ayed, “Multiregion image segmentation by parametric kernel graph cuts,” Image Processing, IEEE Transactions on201120(2), 545–557.
[Crossref]

Salinas, H. M.

Sarunic, M. V.

Schlottmann, P. G.

Schmidt-Erfurth, U.

Schuman, J. S.

Simader, C.

Skaf, M.

Sled, J. G.

Smith, B. R.

Sonka, M.

Sotirchos, E.

Stein, D. M.

Stetson, P.

Stinson, W. G.

Stock, G.

Swanson, E. A.

Tai, X. C.

J. Yuan, E. Bae, and X. C. Tai, “A study on continuous max-flow and min-cut approaches,” In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on IEEE2010, 2217–2224.

Thepass, G.

Toth, C. A.

Tustison, N. j.

van Vliet, L. J.

Velazquez, L.

Vermeer, K. A.

Voskanian, S.

Wojtkowski, M.

Wollstein, G.

Wu, X.

Yazdanpanah, A.

Yuan, J.

J. Yuan, E. Bae, and X. C. Tai, “A study on continuous max-flow and min-cut approaches,” In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on IEEE2010, 2217–2224.

Yushkevich, P. A.

Zheng, Y.

Zhu, H.

Zijdenbos, A. P.

British Journal of Ophthalmology (1)

Current opinion in ophthalmology (1)

Investigative Ophthalmology & Visual Science (1)

Journal of biomedical optics (1)

Medical Imaging, IEEE Transactions on (IEEE 2011) (1)

Ophthalmology (1)

Optics Communications (1)

Optics Express (2)

Progress in retinal and eye research (1)

Science (1)

Other (11)

O. S. Anthony, “Is Imaging Now Standard of Care for Glaucoma?” http://www.revoptom.com/content/c/19985 .

M. B. Salah, A. Mitiche, and I. B. Ayed, “Multiregion image segmentation by parametric kernel graph cuts,” Image Processing, IEEE Transactions on201120(2), 545–557.
[Crossref]

J. Yuan, E. Bae, and X. C. Tai, “A study on continuous max-flow and min-cut approaches,” In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on IEEE2010, 2217–2224.

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.

Click here to see a list of articles that cite this paper

Fig. 1 Error in measuring the RNFL thickness. Top left: circular scan. Top right: error in segmentation line at the inferior temporal quadrant indicated by the blue arrow caused by poor scan quality. Bottom right: the inferior temporal RNFL thickness is measured as abnormal shown by the green arrow. Bottom left: The classification chart showing the overall results of the RNFL thickness measurement within normal boundaries. [17].

Download Full Size | PPT Slide | PDF

Fig. 2 D-OCT circular imaging process. (a) Circular scan on the OCT fundus image, (b) Reitnal tissues (Layers) image from the scan, (c) A 2-D OCT cross-sectional image of the layers tissues.

Download Full Size | PPT Slide | PDF

Fig. 3 Algorithm of the segmentation method.

Download Full Size | PPT Slide | PDF

Fig. 4 Pre-processing. (a) SD-OCT circular scan image. (b) Bias image. (c) Bias corrected image.

Download Full Size | PPT Slide | PDF

Fig. 5 Graph illustration. Example of graph construction

Download Full Size | PPT Slide | PDF

Fig. 6 ILM and RNFL-GCL boundaries detection. (a) Circular scan image, (b) Segmented binary image, (c) ILM and RNFL-GCL boundaries in red.

Download Full Size | PPT Slide | PDF

Fig. 7 RPE boundary detection. (a) Hyper-reflectivity pixels in red on RNFL layer, (b) Selection of region of interest, (c) RPE boundary in green.

Download Full Size | PPT Slide | PDF

Fig. 8 Results. (a) Circular scan, (b) Segmentation result of the proposed method, (c) Human manual grading image.

Download Full Size | PPT Slide | PDF

Fig. 9 Results. (a) Circular scan image, (b) Segmentation result of the proposed method, (c) Human manual grading image.

Download Full Size | PPT Slide | PDF

Fig. 10 Results (Top: Normative database of retinal RNFL thickness. Bottom: Proposed method RNFL thickness profile. (a) Healthy retina. (b)retina at risk. (c) Retina with glaucoma.

Download Full Size | PPT Slide | PDF

Fig. 11 Results. (a) RNFL thickness profile of healthy retinal images: Green proposed segmentation method. Blue Manual segmentation (b) Error in RNFL thickness profile of healthy retinal images: black lines the standard deviation.

Download Full Size | PPT Slide | PDF

Fig. 12 Results. (a) RNFL thickness profile of retinal images with risk of glaucoma: Yellow proposed segmentation method. Blue Manual segmentation. (b) Error in RNFL thickness profile of retinal images with risk of glaucoma: black lines the standard deviation.

Download Full Size | PPT Slide | PDF

Fig. 13 Results. (a) RNFL thickness profile of retinal images with glaucoma: red proposed segmentation method. Blue Manual segmentation. (b) Error in RNFL thickness profile of Glaucoma retinal images: red the error. Black lines the standard deviation.

Download Full Size | PPT Slide | PDF

Tables (3)

Table 1 Performance evaluation with RMSE (Standard deviation) and MAD (Standard deviation) for each boundary. The values have units of pixels. - 120 OCT Scans.

View Table | View all tables in this article

Table 2 Performance comparison of healthy versus disease images. -OCT Scans.

View Table | View all tables in this article

Table 3 Performance evaluation of TPR, FPR, Dice coefficient and RMSE, Standard deviation (Std) and the 95% Confidence interval between the estimated RNFL thickness and the true RNFL thickness -OCT Scans.

View Table | View all tables in this article

Equations (10)

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

ε = F_{g} \cup B_{g}, F_{s} \cap B_{t} = \emptyset

E (A) = λ \cdot R (A) + B (A) .

R (A) = \sum_{p \in Ω} R_{p} (A_{p}) = \sum_{A_{p} \in A} \sum_{p \in S_{A_{p}}} - log (I_{p} / S_{A_{p}}) .

R (A) = \sum_{p \in Ω} R_{p} (A_{p}) = \sum_{A_{p} \in A} \sum_{p \in S_{A_{p}}} {(κ_{A_{p}} - I_{p})}^{2} .

\begin{array}{l} B (A) = \sum_{p, q \in N} B_{p, q} \cdot ϕ (A_{p}, A_{q}) \\ For A_{p} \neq A_{q} \\ ϕ (A_{p}, A_{q}) = 1 \\ ϕ (A_{p}, A_{q}) = 0 Otherwise \end{array}

B_{p, q} = \exp (- \frac{{(I_{p} - I q)}^{2}}{2 σ^{2}}) \cdot \frac{1}{dist (p, q)}

E ({κ_{A_{p}}}, A_{p}) = \sum_{A_{p} \in A} \sum_{p \in S_{A_{p}}} D_{F} (I_{p}, κ_{A_{p}}) + λ \sum_{p, q \in N} B_{p, q} \cdot ϕ (A_{p}, A_{q}) .

F (Y, Z) = exp (- \frac{{‖ Y - Z ‖}^{2}}{σ^{2}}) .

\begin{matrix} MA D (GT, SEG) = 0.5 * (\frac{1}{n} \sum_{i = 1}^{n} d (p t_{i}, SEG) + \frac{1}{m} \sum_{i = 1}^{m} d (p s_{i}, GT)) \\ RMSE = \sqrt{\frac{1}{n} \sum_{i = 1}^{n} {({SEG}_{i} - {GT}_{i})}^{2}} \\ Dice = \frac{2 | {GT}_{i} \cap {SEG}_{i} |}{| {GT}_{i} | + | {SEG}_{i} |} \end{matrix}

\begin{array}{l} TPR = \frac{TP}{{GT}_{RNFL pixels}} \\ FPR = \frac{FP}{{GT}_{Non RNFL pixels}} \end{array}

All Images	Mean RMSE	Mean MAD
ILM	0.0453(0.0276)	0.3931(0.2905)
RNFL-GCL	0.0582(0.0329)	1.2785(1.0523)
RPE	0.0124(0.0124)	0.2131(0.3108)

Heathy images	Mean RMSE	Mean MAD

ILM	0.0474(0.0286)	0.4166(0.3023)
RNFL-GCL	0.0610(0.0312)	1.3835(1.0683)
RPE	0.0103(0.0084)	0.1504(0.2565)

Unhealthy images	Mean RMSE	Mean MAD

ILM	0.0346(0.0198)	0.2753(0.1867)
RNFL-GCL	0.0440(0.0382)	0.7536(0.8002)
RPE	0.0072(0.0129)	0.1379(0.2814)

Images	RNFLT	std	conf
Mean TPR	0.9746	0.0665	±0.0119
Mean FPR	0.0867	0.1037	±0.0186
Mean Dice	0.9468	0.0705	±0.0126
Mean RMSE	0.0835	0.0495	±0.0089

Heathy images

Mean TPR	0.9792	0.0230	±0.0045
Mean FPR	0.0919	0.0947	±0.0186
Mean Dice	0.9473	0.0404	±0.0079
Mean RMSE	0.0881	0.0418	±0.0082

Unhealthy images

Mean TPR	0.9859	0.0215	±0.0042
Mean FPR	0.0557	0.0970	±0.0190
Mean Dice	0.9676	0.0401	±0.0079
Mean RMSE	0.0586	0.0521	±0.01021

All Images	Mean RMSE	Mean MAD
ILM	0.0453(0.0276)	0.3931(0.2905)
RNFL-GCL	0.0582(0.0329)	1.2785(1.0523)
RPE	0.0124(0.0124)	0.2131(0.3108)

Heathy images	Mean RMSE	Mean MAD

ILM	0.0474(0.0286)	0.4166(0.3023)
RNFL-GCL	0.0610(0.0312)	1.3835(1.0683)
RPE	0.0103(0.0084)	0.1504(0.2565)

Unhealthy images	Mean RMSE	Mean MAD

ILM	0.0346(0.0198)	0.2753(0.1867)
RNFL-GCL	0.0440(0.0382)	0.7536(0.8002)
RPE	0.0072(0.0129)	0.1379(0.2814)