Robust automatic segmentation of corneal layer boundaries in SDOCT images using graph theory and dynamic programming

Segmentation of anatomical structures in corneal images is crucial for the diagnosis and study of anterior segment diseases. However, manual segmentation is a time-consuming and subjective process. This paper presents an automatic approach for segmenting corneal layer boundaries in Spectral Domain Optical Coherence Tomography images using graph theory and dynamic programming. Our approach is robust to the low-SNR and different artifact types that can appear in clinical corneal images. We show that our method segments three corneal layer boundaries in normal adult eyes more accurately compared to an expert grader than a second grader—even in the presence of significant imaging outliers.

[1]  A Langenbucher,et al.  Posterior corneal curvature changes after myopic laser in situ keratomileusis. , 2001, Ophthalmology.

[2]  Ronald H. Silverman,et al.  Epithelial Thickness in the Normal Cornea: Three-dimensional Display With Very High Frequency Ultrasound , 2008 .

[3]  W M Petroll,et al.  Epithelial and corneal thickness measurements by in vivo confocal microscopy through focusing (CMTF). , 1997, Current eye research.

[4]  Yan Li,et al.  A longitudinal study of LASIK flap and stromal thickness with high-speed optical coherence tomography. , 2007, Ophthalmology.

[5]  G. Vrensen,et al.  The specific architecture of the anterior stroma accounts for maintenance of corneal curvature , 2001, The British journal of ophthalmology.

[6]  Wolfgang Drexler,et al.  Optical Coherence Tomography (OCT) in ophthalmology: introduction. , 2009, Optics express.

[7]  Sina Farsiu,et al.  Photoreceptor layer thinning over drusen in eyes with age-related macular degeneration imaged in vivo with spectral-domain optical coherence tomography. , 2009, Ophthalmology.

[8]  S. Pflugfelder,et al.  The effects of long-term contact lens wear on corneal thickness, curvature, and surface regularity. , 2000, Ophthalmology.

[9]  Kostadinka Bizheva,et al.  Swelling of the human cornea revealed by high-speed, ultrahigh-resolution optical coherence tomography. , 2010, Investigative ophthalmology & visual science.

[10]  R. Silverman,et al.  Epithelial thickness in the normal cornea: three-dimensional display with Artemis very high-frequency digital ultrasound. , 2008, Journal of refractive surgery.

[11]  Xiaodong Wu,et al.  Automated segmentation of intraretinal layers from macular optical coherence tomography images , 2007, SPIE Medical Imaging.

[12]  Xiaodong Wu,et al.  Automated 3-D Intraretinal Layer Segmentation of Macular Spectral-Domain Optical Coherence Tomography Images , 2009, IEEE Transactions on Medical Imaging.

[13]  R. Silverman,et al.  Epithelial and corneal thickness measurements by high-frequency ultrasound digital signal processing. , 1994, Ophthalmology.

[14]  J. Fujimoto,et al.  Optical Coherence Tomography , 1991 .

[15]  Joseph A. Izatt,et al.  Automatic segmentation of seven retinal layers in SDOCT images congruent with expert manual segmentation , 2010, Optics express.

[16]  Yan Li,et al.  Segmentation of 830- and 1310-nm LASIK corneal optical coherence tomography images , 2002, SPIE Medical Imaging.

[17]  B. Frueh,et al.  Corneal thickness and curvature in normal-tension glaucoma. , 1998, American journal of ophthalmology.

[18]  Ronald H Silverman,et al.  Stromal thickness in the normal cornea: three-dimensional display with artemis very high-frequency digital ultrasound. , 2009, Journal of refractive surgery.

[19]  Zuguo Liu,et al.  Evaluation of corneal thickness and topography in normal eyes using the Orbscan corneal topography system , 1999, The British journal of ophthalmology.

[20]  Milan Sonka,et al.  Segmentation of the Optic Disc in 3-D OCT Scans of the Optic Nerve Head , 2010, IEEE Transactions on Medical Imaging.

[21]  E. Spoerl,et al.  Effect of central corneal thickness, corneal curvature, and axial length on applanation tonometry. , 2006, Archives of ophthalmology.

[22]  J. Izatt,et al.  Real-time optical coherence tomography of the anterior segment at 1310 nm. , 2001, Archives of ophthalmology.

[23]  J. Izatt,et al.  3D refraction correction and extraction of clinical parameters from spectral domain optical coherence tomography of the cornea. , 2010, Optics express.

[24]  David A. Clausi,et al.  A Novel Algorithm for Extraction of the Layers of the Cornea , 2009, 2009 Canadian Conference on Computer and Robot Vision.

[25]  Gary L. Miller,et al.  Automatic Multiple Retinal Layer Segmentation in Spectral Domain OCT Scans via Spectral Rounding , 2008 .

[26]  Yan Li,et al.  Corneal pachymetry mapping with high-speed optical coherence tomography. , 2006, Ophthalmology.

[27]  Edsger W. Dijkstra,et al.  A note on two problems in connexion with graphs , 1959, Numerische Mathematik.

[28]  E A Swanson,et al.  Micrometer-scale resolution imaging of the anterior eye in vivo with optical coherence tomography. , 1994, Archives of ophthalmology.

[29]  T. Cox,et al.  Central corneal thickness in normal, glaucomatous, and ocular hypertensive eyes. , 1997, Archives of ophthalmology.

[30]  Mitsugu Shimmyo,et al.  Intraocular pressure, Goldmann applanation tension, corneal thickness, and corneal curvature in Caucasians, Asians, Hispanics, and African Americans. , 2003, American journal of ophthalmology.