Skip to content

Retinal Layer Segmentation in Optical Coherence Tomography

Optical Coherence Tomography (OCT) has dramatically changed diagnostics in ophthalmology.  The first publication of cross-sectional images of the human retina occurred in [Huang 1991], and its commercial introduction soon followed in 1996.  Such cross-sectional images of the retina allow clinicians to quantify retinal thickness changes, which relates directly to macular pathologies.  Retinal layer segmentation is subsequently the underlying technology facilitating this quantification of retinal layer thicknesses critical in the diagnosis and studying of ocular diseases.

A good overview of the work can be found in [Debuc 2010].  Thorough though this review is, emphasis is not really afforded to the graph-theoretic approaches that are proving to be a very effective means of layer segmentation, less prone to initialization and parameter tuning than the active contour methods.  Leading the charge has been the group at Iowa led by Professor Sonka, who were among the first to apply this method to OCT images in 2008.  Based on the Min-Cut/Max-Flow algorithm of [Boykov 2004], they added a special, layer-based parameterization which encoded a smoothness constraint into the optimization [Li 2006].  The initial cost function was gradient based and the resultant graph cuts machinery chugged away with very nice results [Garvin 2008].  The catch here is that these nice results do come at a hefty computation price.  Despite the efficiency of the optimization process, running graph cuts for multi-layer segmentations on large 3-d OCT data sets takes many minutes to run meaning that they are not clinically applicable.  Progressive evolutions to the cost functions, multi-resolution approaches and various initialization schemes have since occurred, but the computational overheads restrict the approach’s wider – i.e., commercial – adoption and do not seem to be going away.

One scheme used to speed up the convergence was to use a 2-d algorithm using graph traversal to find the initial surfaces.  Such graph traversal algorithms, using, for example, Dijkstra’s or Viterbi’s algorithm, have a far lower computation cost; the down-side being they are inherently 2-d.  Nonetheless, all the current excitement in multi-layer retinal image segmentation stems from such methods.  [Chiu 2010] showed eight layers of segmentation in 2-d, and then extended the work to the anterior segment [Chiu 2011], and quantification of drusen [Chiu 2012].  [Yang 2010] published very similar work yet extended the approach to 2½-d, but only showed results on averaged B-scans.

Along with the groups from Iowa and Duke, the Pattern Recognition Lab at the University of Erlangen-Nuremburg has published some exciting results [Mayer 2010].  Following initial estimates for the layer segmentation based on the raw 1-d intensity profiles, their algorithm also involves the minimization of an energy term that encodes smoothness and edge information and is minimized iteratively.  What is especially encouraging is that their software can be downloaded here such that the interested researcher is able to evaluate performance themselves.

The true test of any such algorithm is clinical utility.  Ultimately, therefore, one must look to clinical journals to understand what algorithms are being used and how they are performing.  There is tremendous interest in both the academic and commercial world to improve the robustness of the commercial algorithms that are released, with particular emphasis now coming from the field of neuro-ophthalmology and the group at Johns Hopkins in particular.  But, as Professor Drexler, a pioneer of OCT over the last 20 years, admitted in a recent webinar, the analysis algorithms have lagged the hardware development.


[Mayer 2010] Markus A. Mayer, Ralf. P. Tornow, Christian Y Mardin, Ralf P. Tornow: “Retinal Nerve Fiber Layer Segmentation on FD-OCT Scans of Normal Subjects and Glaucoma Patients”, Biomedical Optics Express 1 (2010) No. 5 pp. 1358-1383.

[Boykov 2004] An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision. Yuri Boykov, Vladimir Kolmogorov. In IEEE transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 26, no. 9, pp. 1124-1137, Sept. 2004.

[Chiu 2010] Automatic Segmentation of Retinal Layers in SDOCT Congruent with Expert Manual Segmentation, S.J. Chiu, X.T. Li, P. Nicholas, C.A. Toth, J.A. Izatt, S. Farsiu. Optics Express. Vol. 18, No. 18, pp. 19413-19428, August 2010.

[Chiu 2011] Robust Automatic Segmentation of Corneal Layer Boundaries in SDOCT Images using Graph Theory and Dynamic Programming, F. LaRocca, S.J. Chiu, R.P. McNabb, A.N. Kuo, J.A. Izatt, S. Farsiu. Biomedical Optics Express. Vol. 2, No. 6, pp. 1524-1538, June 2011.

[Chiu 2012] Validated Automatic Segmentation of AMD Pathology including Drusen and Geographic Atrophy in SDOCT Images, S.J. Chiu, J.A. Izatt, R.V. O’Connell, K.P. Winter, C.A. Toth, S. Farsiu.  Investigative Ophthalmology & Visual Science. Vol. 53, No. 1, pp. 53-61, January 2012.

[Debuc  2010] A Review of Algorithms for Segmentation of Retinal Image Data Using Optical Coherence Tomography, Delia Cabrera Debuc. The paper is available at this link.

[Garvin 2008] Garvin et al. Intraretinal Layer Segmentation of Macular Optical Coherence Tomography Images Using Optimal 3-D Graph Search, IEEE TMI, Vol. 27, No. 10, October 2008

[Huang 1991] Science 22 November 1991: Vol. 254 no. 5035 pp. 1178-1181 DOI: 10.1126/science.1957169

[Li 2006] “System and Methods for Image Segmentation in N-Dimensional Space.” Kang Li, Xiaodong Wu, Danny Z. Chen, and Milan Sonka. U.S. Patent 20070058865. June 2006.

[Yang 2010] Automated layer segmentation of macular OCT images using dual-scale gradient information, Qi Yang, Charles A. Reisman et al., Optics Express, Vol. 18, Issue 20, pp. 21293-21307 (2010).