Retinal thickness measurements in optical coherence tomography using a Markov boundary model

We present a highly accurate, robust system for measuring retinal thickness in optical coherence tomography (OCT) images. OCT is a relatively new imaging modality giving cross sectional images that are qualitatively similar to ultrasound but with 10 /spl mu/m resolution. We begin with a 1-dimensional edge detection kernel to yield edge primitives, which are then selected, corrected, and grouped to form a coherent boundary by use of a Markov model of retinal structure. We have tested the system extensively, and only one of 650 evaluation images caused the algorithm to fail. The anticipated clinical application for this work is the automatic determination of retinal thickness. A careful quantitative evaluation of the system performance over a 1 mm region near the fovea reveals that in more than 99% of the cases, the automatic and manual measurements differed by less than 25 /spl mu/m (below clinical significance), and in 89% of the tests the difference was less than 10 /spl mu/m (near the resolution limit). Current clinical practice involves only a qualitative, visual assessment of retinal thickness. Therefore, a robust, quantitatively accurate system should significantly improve patient care.

[1]  PHOTOCOAGULATION FOR DIABETIC MACULAR EDEMA: EARLY TREATMENT DIABETIC RETINOPATHY STUDY REPORT NO. 4 , 1987, International ophthalmology clinics.

[2]  E Reichel,et al.  Topography of diabetic macular edema with optical coherence tomography. , 1998, Ophthalmology.

[3]  Kim L. Boyer,et al.  The laplacian-of-gaussian kernel: A formal analysis and design procedure for fast, accurate convolution and full-frame output , 1989, Comput. Vis. Graph. Image Process..

[4]  Shimon Ullman,et al.  Structural Saliency: The Detection Of Globally Salient Structures using A Locally Connected Network , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[5]  Kim L. Boyer,et al.  Optimal infinite impulse response zero crossing based edge detectors , 1991, CVGIP Image Underst..

[6]  Henry Stark,et al.  Probability, Random Processes, and Estimation Theory for Engineers , 1995 .

[7]  R G Aarnink,et al.  Edge detection in prostatic ultrasound images using integrated edge maps. , 1998, Ultrasonics.

[8]  J. Schuman,et al.  Optical coherence tomography. , 2000, Science.

[9]  Baba C. Vemuri,et al.  Shape Modeling with Front Propagation: A Level Set Approach , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  D. Chauhan,et al.  The interpretation of optical coherence tomography images of the retina. , 1999, Investigative ophthalmology & visual science.

[11]  Guoyu Wang,et al.  A statistical model to describe invariants extracted from a 3-D quadric surface patch and its applications in region-based recognition , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[12]  R Ritch,et al.  Reproducibility of retinal thickness measurements in normal eyes using optical coherence tomography. , 1998, Ophthalmic surgery and lasers.

[13]  R Birngruber,et al.  A comparison of retinal morphology viewed by optical coherence tomography and by light microscopy. , 1997, Archives of ophthalmology.

[14]  E. Herderick,et al.  Intersession repeatability of macular thickness measurements with the Humphrey 2000 OCT. , 2000, Investigative ophthalmology & visual science.

[15]  Bjørn Olstad,et al.  Edge detection in noisy data using finite mixture distribution analysis , 1994, Proceedings of 1st International Conference on Image Processing.

[16]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[17]  Eric A. Swanson,et al.  Quantitative Assessment of Macular Edema With Optical Coherence Tomography , 1995 .

[18]  Pascal Laugier,et al.  Automatic detection of the boundary of the calcaneus from ultrasound parametric images using an active contour model; clinical assessment , 1998, IEEE Transactions on Medical Imaging.

[19]  Roland T. Chin,et al.  On modelling, extraction, detection and classification of deformable contours from noisy images , 1998, Image Vis. Comput..

[20]  F L Ferris,et al.  Macular edema. A complication of diabetic retinopathy. , 1984, Survey of ophthalmology.

[21]  Zhou Zhaoying,et al.  Shape recognition using complex nonlinear exponential autoregressive model , 1995, Proceedings of 1995 IEEE Instrumentation and Measurement Technology Conference - IMTC '95.

[22]  M. J. Paulik,et al.  Classification of planar shapes using multiresolution circular autoregressive models , 1993, Proceedings of 36th Midwest Symposium on Circuits and Systems.

[23]  C.P. Lin,et al.  Optical coherence tomography for ophthalmic imaging: new technique delivers micron-scale resolution , 1995, IEEE Engineering in Medicine and Biology Magazine.

[24]  Philippe Paillou.  Detecting step edges in noisy SAR images: a new linear operator , 1997, IEEE Trans. Geosci. Remote. Sens..

[25]  A. De Santis,et al.  A Bayesian approach to edge detection in noisy images , 1999 .

[26]  David Pycock,et al.  Robust statistical models for cell image interpretation , 1997, Image Vis. Comput..

[27]  R. Moses,et al.  Adler's Physiology of the Eye: , 1970 .

[28]  S. M. Pandit,et al.  Shape mensuration and recognition by DDS approach , 1995, Proceedings., International Conference on Image Processing.

[29]  Jiankang Wang,et al.  A system for segmenting ultrasound images , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).