Automated 3-D intraretinal layer segmentation of macular spectral-domain optical coherence tomography images

Early neurodegeneration in the retina of type 2 diabetic patients

PURPOSE

The purpose of this study was to determine whether diabetes type 2 causes thinning of retinal layers as a sign of neurodegeneration and to investigate the possible relationship between this thinning and duration of diabetes mellitus, diabetic retinopathy (DR) status, age, sex, and glycemic control (HbA1c).

METHODS

Mean layer thickness was calculated for retinal layers following automated segmentation of spectral domain optical coherence tomography images of diabetic patients with no or minimal DR and compared with controls. To determine the relationship between layer thickness and diabetes duration, DR status, age, sex, and HbA1c, a multiple linear regression analysis was used.

RESULTS

In the pericentral area of the macula, the retinal nerve fiber layer (RNFL), ganglion cell layer (GCL), and inner plexiform layer (IPL) were thinner in patients with minimal DR compared to controls (respective difference 1.9 μm, 95% confidence interval [CI] 0.3-3.5 μm; 5.2 μm, 95% CI 1.0-9.3 μm; 4.5 μm, 95% CI 2.2-6.7 μm). In the peripheral area of the macula, the RNFL and IPL were thinner in patients with minimal DR compared to controls (respective difference 3.2 μm, 95% CI 0.1-6.4 μm; 3.3 μm, 95% CI 1.2-5.4 μm). Multiple linear regression analysis showed DR status to be the only significant explanatory variable (R = 0.31, P = 0.03) for this retinal thinning.

CONCLUSIONS

This study demonstrated thinner inner retinal layers in the macula of type 2 diabetic patients with minimal DR than in controls. These results support the concept that early DR includes a neurodegenerative component.

The Nature of Macular Damage in Glaucoma as Revealed by Averaging Optical Coherence Tomography Data

PURPOSE

To better understand the nature of glaucomatous damage, especially to the macula, the inner retinal thickness maps obtained with frequency domain optical coherence tomography (fdOCT) were averaged.

METHODS

Frequency domain optical coherence tomography macular and optic disc cube scans were obtained from 54 healthy eyes and 156 eyes with glaucomatous optic neuropathy. A manually corrected algorithm was used for layer segmentation. Patients' eyes were grouped both by mean deviation (MD) and hemifield classification using standard categories and 24-2 (6° grid) visual fields (VFs). To obtain average difference maps, the thickness of retinal nerve fiber (RNF) and retinal ganglion cell plus inner plexiform (RGC+) layers were averaged and subtracted from the average control values.

RESULTS

On the average difference maps, RGC+ and RNF layer thinning was seen in the patient groups with VFs classified as normal. The pattern of the thinning was the same, but the degree of thinning increased with decreased MD and with classification category (from normal to arcuate). This RGC+ thinning was largely within the central four points of the 24-2 (6° grid) field, after correcting for RGC displacement.

CONCLUSION

1. VF categories represent different degrees of the same pattern of RGC+ and RNFL layer thinning. 2. RGC+ damage occurs in the central macula even in patients with VFs classified as normal. 3. The 6° grid (24-2) pattern is not optimally designed to detect macular damage. 4. A schematic model of RGC projections is proposed to explain the pattern of macular loss, including the greater vulnerability of the inferior retinal region.

TRANSLATIONAL RELEVANCE

The 24-2 is not an optimal test pattern for detecting or following glaucomatous damage. Further, we suggest clinical fdOCT reports include RGC+ and RNFL probability plots combined with VF information.

Association of outer retinal layer morphology with visual acuity in patients with retinal vein occlusion: SCORE Study Report 13

PURPOSE

To assess associations between visual acuity (VA) and the status of the photoreceptor inner segment-outer segment (IS-OS) junction in a subset of patients in the Standard Care vs COrticosteroid for REtinal Vein Occlusion (SCORE) Study.

METHODOLOGY

High-resolution time domain optical coherence tomography (OCT) scans of study eyes from a single site participating in the SCORE Study were evaluated. Integrity of the IS-OS junction in the central subfield was evaluated using a three-step scale: absent, abnormal or normal. Associations of the IS-OS status with ETDRS VA letter score and center point thickness (CPT) were investigated.

RESULTS

Baseline OCTs of 42 eyes were evaluated. The IS-OS junction was absent in 30 (71%) and abnormal in 12 (29%). At month 12, the IS-OS junction was absent in 18 (43%), abnormal in 12 (28%), and normal in 12 (28%) eyes. At baseline, IS-OS status was significantly associated with CPT, but not with VA. At month 12, IS-OS status was significantly associated with CPT and VA, that is, absent or abnormal IS-OS was associated with increased CPT and worse VA. Change in IS-OS status was not associated with change in CPT (P=0.8). Worsening of IS-OS status was associated with loss of VA and improvement in IS-OS status to normal was associated with gain in VA (P=0.03).

CONCLUSION

In this data set with long-term follow-up of OCTs as part of the SCORE Study, there is a correlation between change in IS-OS status and VA. This supports further evaluation of outer retinal morphology in larger data sets.

Three-dimensional distribution of the vitelliform lesion, photoreceptors, and retinal pigment epithelium in the macula of patients with best vitelliform macular dystrophy

OBJECTIVE

To describe the anatomical phenotypes of Best vitelliform macular dystrophy (BVMD) with spectral-domain optical coherence tomography (SD-OCT) in a large series of patients with confirmed mutations in the BEST1 gene.

METHODS

In our retrospective observational case series, we assessed 15 patients (30 eyes) with a clinical diagnosis of vitelliform macular dystrophy who were found to have mutations in the BEST1 gene. Color fundus photographs and SD-OCT images were evaluated and compared with those of 15 age-matched controls (30 eyes). Using a validated 3-dimensional SD-OCT segmentation algorithm, we calculated the equivalent thickness of photoreceptors and the equivalent thickness of the retinal pigment epithelium for each patient. The photoreceptor equivalent thickness and the retinal pigment epithelium (RPE) equivalent thickness were compared in all patients, in a region of the macula outside the central lesion for patients with BVMD and outside the fovea in control patients. Paired t tests were used for statistical analysis.

RESULTS

The SD-OCT findings revealed that the vitelliform lesion consists of material above the RPE and below the outer segment tips. Additionally, drusen-like deposition of sub-RPE material was notable, and several patients exhibited a sub-RPE fibrotic nodule. Patients with BVMD had a mean photoreceptor equivalent thickness of 28.3 μm, and control patients had a mean photoreceptor equivalent thickness of 21.8 μm, a mean difference of 6.5 μm (P < .01), whereas the mean RPE equivalent thickness was not statistically different between patients with BVMD and control patients (P = .53).

CONCLUSIONS

The SD-OCT findings suggest that vitelliform material is located in the subretinal space and that BVMD is associated with diffuse photoreceptor outer segment abnormalities overlying a structurally normal RPE.

CLINICAL RELEVANCE

These findings provide new insight into the pathophysiology of BVMD and thus have implications for the development of therapeutic interventions.

2-D pattern of nerve fiber bundles in glaucoma emerging from spectral-domain optical coherence tomography

PURPOSE

To correlate the thicknesses of focal regions of the macular ganglion cell layer with those of the peripapillary nerve fiber layer using spectral-domain optical coherence tomography (SD-OCT) in glaucoma subjects.

METHODS

Macula and optic nerve head SD-OCT volumes were obtained in 57 eyes of 57 subjects with open-angle glaucoma or glaucoma suspicion. Using a custom automated computer algorithm, the thickness of 66 macular ganglion cell layer regions and the thickness of 12 peripapillary nerve fiber layer regions were measured from registered SD-OCT volumes. The mean thickness of each ganglion cell layer region was correlated to the mean thickness of each peripapillary nerve fiber layer region across subjects. Each ganglion cell layer region was labeled with the peripapillary nerve fiber layer region with the highest correlation using a color-coded map.

RESULTS

The resulting color-coded correlation map closely resembled the nerve fiber bundle (NFB) pattern of retinal ganglion cells. The mean r(2) value across all local macular-peripapillary correlations was 0.49 (± 0.11). When separately analyzing the 30 glaucoma subjects from the 27 glaucoma-suspect subjects, the mean r(2) value across all local macular-peripapillary correlations was significantly larger in the glaucoma group (0.56 ± 0.13 vs. 0.37 ± 0.11; P < 0.001).

CONCLUSIONS

A two-dimensional (2-D) spatial NFB map of the retina can be developed using structure-structure relationships from SD-OCT. Such SD-OCT-based NFB maps may enhance glaucoma detection and contribute to monitoring change in the future.

Automated segmentation of intraretinal cystoid fluid in optical coherence tomography

Cystoid macular edema (CME) is observed in a variety of ocular disorders and is strongly associated with vision loss. Optical coherence tomography (OCT) provides excellent visualization of cystoid fluid, and can assist clinicians in monitoring the progression of CME. Quantitative tools for assessing CME may lead to better metrics for choosing treatment protocols. To address this need, this paper presents a fully automated retinal cyst segmentation technique for OCT image stacks acquired from a commercial scanner. The proposed method includes a computationally fast bilateral filter for speckle denoising while maintaining CME boundaries. The proposed technique was evaluated in images from 16 patients with vitreoretinal disease and three controls. The average sensitivity and specificity for the classification of cystoid regions in CME patients were found to be 91% and 96%, respectively, and the retinal volume occupied by cystoid fluid obtained by the algorithm was found to be accurate within a mean and median volume fraction of 1.9% and 0.8%, respectively.

Pathology hinting as the combination of automatic segmentation with a statistical shape model

With improvements in acquisition speed and quality, the amount of medical image data to be screened by clinicians is starting to become challenging in the daily clinical practice. To quickly visualize and find abnormalities in medical images, we propose a new method combining segmentation algorithms with statistical shape models. A statistical shape model built from a healthy population will have a close fit in healthy regions. The model will however not fit to morphological abnormalities often present in the areas of pathologies. Using the residual fitting error of the statistical shape model, pathologies can be visualized very quickly. This idea is applied to finding drusen in the retinal pigment epithelium (RPE) of optical coherence tomography (OCT) volumes. A segmentation technique able to accurately segment drusen in patients with age-related macular degeneration (AMD) is applied. The segmentation is then analyzed with a statistical shape model to visualize potentially pathological areas. An extensive evaluation is performed to validate the segmentation algorithm, as well as the quality and sensitivity of the hinting system. Most of the drusen with a height of 85.5 microm were detected, and all drusen at least 93.6 microm high were detected.

Order preserving and shape prior constrained intra-retinal layer segmentation in optical coherence tomography

We present a probabilistic approach to the segmentation of OCT scans of retinal tissue. By combining discrete exact inference and a global shape prior, accurate segmentations are computed that preserve the physiological order of intra-retinal layers. A major part of the computations can be performed in parallel. The evaluation reveals robustness against speckle noise, shadowing caused by blood vessels, and other scan artifacts.

Macular ganglion cell-inner plexiform layer: automated detection and thickness reproducibility with spectral domain-optical coherence tomography in glaucoma

PURPOSE

To demonstrate the capability of SD-OCT to measure macular retinal ganglion cell-inner plexiform layer (GCIPL) thickness and to assess its reproducibility in glaucomatous eyes.

METHODS

Fifty-one glaucomatous eyes (26 mild, 11 moderate, 14 severe) of 51 patients underwent macular scanning using the Cirrus HD-OCT (Carl Zeiss Meditec, Dublin, CA) macula 200×200 acquisition protocol. Five scans were obtained on 5 days within 2 months. The ganglion cell analysis (GCA) algorithm was used to detect the macular GCIPL and to measure the thickness of the overall average, minimum, superotemporal, superior, superonasal, inferonasal, inferior, and inferotemporal GCIPL. The reproducibility of the measurements was evaluated with intraclass correlation coefficients (ICCs), coefficients of variation (COVs), and test-retest standard deviations (TRTSDs).

RESULTS

Segmentation and measurement of GCIPL thickness were successful in 50 of 51 subjects. All ICCs ranged between 0.94 and 0.98, but ICCs for average and superior GCIPL parameters (0.97-0.98) were slightly higher than for inferior GCIPL parameters (0.94-0.97). All COVs were <5%, with 1.8% for average GCIPL and COVs for superior GCIPL parameters (2.2%-3.0%) slightly lower than those for inferior GCIPL parameters (2.5%-3.6%). The TRTSD was lowest for average GCIPL (1.16 μm) and varied from 1.43 to 2.15 μm for sectoral GCIPL CONCLUSIONS: The Cirrus HD-OCT GCA algorithm can successfully segment macular GCIPL and measure GCIPL thickness with excellent intervisit reproducibility. Longitudinal monitoring of GCIPL thickness may be possible with Cirrus HD-OCT for assessing glaucoma progression.

Automated segmentation of outer retinal layers in macular OCT images of patients with retinitis pigmentosa

To provide a tool for quantifying the effects of retinitis pigmentosa (RP) seen on spectral domain optical coherence tomography images, an automated layer segmentation algorithm was developed. This algorithm, based on dual-gradient information and a shortest path search strategy, delineates the inner limiting membrane and three outer retinal boundaries in optical coherence tomography images from RP patients. In addition, an automated inner segment (IS)/outer segment (OS) contour detection method based on the segmentation results is proposed to quantify the locus of points at which the OS thickness goes to zero in a 3D volume scan. The segmentation algorithm and the IS/OS contour were validated with manual segmentation data. The segmentation and IS/OS contour results on repeated measures showed good within-day repeatability, while the results on data acquired on average 22.5 months afterward demonstrated a possible means to follow disease progression. In particular, the automatically generated IS/OS contour provided a possible objective structural marker for RP progression.

Automated 3-D method for the correction of axial artifacts in spectral-domain optical coherence tomography images

The 3-D spectral-domain optical coherence tomography (SD-OCT) images of the retina often do not reflect the true shape of the retina and are distorted differently along the x and y axes. In this paper, we propose a novel technique that uses thin-plate splines in two stages to estimate and correct the distinct axial artifacts in SD-OCT images. The method was quantitatively validated using nine pairs of OCT scans obtained with orthogonal fast-scanning axes, where a segmented surface was compared after both datasets had been corrected. The mean unsigned difference computed between the locations of this artifact-corrected surface after the single-spline and dual-spline correction was 23.36 ± 4.04 μm and 5.94 ± 1.09 μm, respectively, and showed a significant difference (p < 0.001 from two-tailed paired t-test). The method was also validated using depth maps constructed from stereo fundus photographs of the optic nerve head, which were compared to the flattened top surface from the OCT datasets. Significant differences (p < 0.001) were noted between the artifact-corrected datasets and the original datasets, where the mean unsigned differences computed over 30 optic-nerve-head-centered scans (in normalized units) were 0.134 ± 0.035 and 0.302 ± 0.134, respectively.

Automated segmentation by pixel classification of retinal layers in ophthalmic OCT images

Current OCT devices provide three-dimensional (3D) in-vivo images of the human retina. The resulting very large data sets are difficult to manually assess. Automated segmentation is required to automatically process the data and produce images that are clinically useful and easy to interpret. In this paper, we present a method to segment the retinal layers in these images. Instead of using complex heuristics to define each layer, simple features are defined and machine learning classifiers are trained based on manually labeled examples. When applied to new data, these classifiers produce labels for every pixel. After regularization of the 3D labeled volume to produce a surface, this results in consistent, three-dimensionally segmented layers that match known retinal morphology. Six labels were defined, corresponding to the following layers: Vitreous, retinal nerve fiber layer (RNFL), ganglion cell layer & inner plexiform layer, inner nuclear layer & outer plexiform layer, photoreceptors & retinal pigment epithelium and choroid. For both normal and glaucomatous eyes that were imaged with a Spectralis (Heidelberg Engineering) OCT system, the five resulting interfaces were compared between automatic and manual segmentation. RMS errors for the top and bottom of the retina were between 4 and 6 μm, while the errors for intra-retinal interfaces were between 6 and 15 μm. The resulting total retinal thickness maps corresponded with known retinal morphology. RNFL thickness maps were compared to GDx (Carl Zeiss Meditec) thickness maps. Both maps were mostly consistent but local defects were better visualized in OCT-derived thickness maps.

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.

Reliability of a computer-aided manual procedure for segmenting optical coherence tomography scans

PURPOSE

To assess the within- and between-operator agreement of a computer-aided manual segmentation procedure for frequency-domain optical coherence tomography scans.

METHODS

Four individuals (segmenters) used a computer-aided manual procedure to mark the borders defining the layers analyzed in glaucoma studies. After training, they segmented two sets of scans, an Assessment Set and a Test Set. Each set had scans from 10 patients with glaucoma and 10 healthy controls. Based on an analysis of the Assessment Set, a set of guidelines was written. The Test Set was segmented twice with a ≥1 month separation. Various measures were used to compare test and retest (within-segmenter) variability and between-segmenter variability including concordance correlations between layer borders and the mean across scans (n = 20) of the mean of absolute differences between local border locations of individual scans, MEAN{mean( ΔLBL )}.

RESULTS

Within-segmenter reliability was good. The mean concordance correlations values for an individual segmenter and a particular border ranged from 0.999 ± 0.000 to 0.978 ± 0.084. The MEAN{mean( ΔLBL )} values ranged from 1.6 to 4.7 μm depending on border and segmenter. Similarly, between-segmenter agreement was good. The mean concordance correlations values for an individual segmenter and a particular border ranged from 0.999 ± 0.001 to 0.992 ± 0.023. The MEAN{mean( ΔLBL )} values ranged from 1.9 to 4.0 μm depending on border and segmenter. The signed and unsigned average positions were considerably smaller than the MEAN{mean( ΔLBL )} values for both within- and between-segmenter comparisons. Measures of within-segmenter variability were only slightly larger than those of between-segmenter variability.

CONCLUSIONS

When human segmenters are trained, the within-and between-segmenter reliability of manual border segmentation is quite good. When expressed as a percentage of retinal layer thickness, the results suggest that manual segmentation provides a reliable measure of the thickness of layers typically measured in studies of glaucoma.

Segmentation of intra-retinal layers from optical coherence tomography images using an active contour approach

Optical coherence tomography (OCT) is a noninvasive, depth-resolved imaging modality that has become a prominent ophthalmic diagnostic technique. We present a semi-automated segmentation algorithm to detect intra-retinal layers in OCT images acquired from rodent models of retinal degeneration. We adapt Chan-Vese's energy-minimizing active contours without edges for the OCT images, which suffer from low contrast and are highly corrupted by noise. A multiphase framework with a circular shape prior is adopted in order to model the boundaries of retinal layers and estimate the shape parameters using least squares. We use a contextual scheme to balance the weight of different terms in the energy functional. The results from various synthetic experiments and segmentation results on OCT images of rats are presented, demonstrating the strength of our method to detect the desired retinal layers with sufficient accuracy even in the presence of intensity inhomogeneity resulting from blood vessels. Our algorithm achieved an average Dice similarity coefficient of 0.84 over all segmented retinal layers, and of 0.94 for the combined nerve fiber layer, ganglion cell layer, and inner plexiform layer which are the critical layers for glaucomatous degeneration.

LOGISMOS--layered optimal graph image segmentation of multiple objects and surfaces: cartilage segmentation in the knee joint

A novel method for simultaneous segmentation of multiple interacting surfaces belonging to multiple interacting objects, called LOGISMOS (layered optimal graph image segmentation of multiple objects and surfaces), is reported. The approach is based on the algorithmic incorporation of multiple spatial inter-relationships in a single n-dimensional graph, followed by graph optimization that yields a globally optimal solution. The LOGISMOS method's utility and performance are demonstrated on a bone and cartilage segmentation task in the human knee joint. Although trained on only a relatively small number of nine example images, this system achieved good performance. Judged by dice similarity coefficients (DSC) using a leave-one-out test, DSC values of 0.84 ± 0.04, 0.80 ± 0.04 and 0.80 ± 0.04 were obtained for the femoral, tibial, and patellar cartilage regions, respectively. These are excellent DSC values, considering the narrow-sheet character of the cartilage regions. Similarly, low signed mean cartilage thickness errors were obtained when compared to a manually-traced independent standard in 60 randomly selected 3-D MR image datasets from the Osteoarthritis Initiative database-0.11 ± 0.24, 0.05 ± 0.23, and 0.03 ± 0.17 mm for the femoral, tibial, and patellar cartilage thickness, respectively. The average signed surface positioning errors for the six detected surfaces ranged from 0.04 ± 0.12 mm to 0.16 ± 0.22 mm. The reported LOGISMOS framework provides robust and accurate segmentation of the knee joint bone and cartilage surfaces of the femur, tibia, and patella. As a general segmentation tool, the developed framework can be applied to a broad range of multiobject multisurface segmentation problems.

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

Spectral-domain optical coherence tomography (SD-OCT) provides volumetric images of retinal structures with unprecedented detail. Accurate segmentation algorithms and feature quantification in these images, however, are needed to realize the full potential of SD-OCT. The fully automated segmentation algorithm, FloatingCanvas, serves this purpose and performs a volumetric segmentation of retinal tissue layers in three-dimensional image volume acquired around the optic nerve head without requiring any pre-processing. The reconstructed layers are analyzed to extract features such as blood vessels and retinal nerve fibre layer thickness. Findings from images obtained with the RTVue-100 SD-OCT (Optovue, Fremont, CA, USA) indicate that FloatingCanvas is computationally efficient and is robust to the noise and low contrast in the images. The FloatingCanvas segmentation demonstrated good agreement with the human manual grading. The retinal nerve fibre layer thickness maps obtained with this method are clinically realistic and highly reproducible compared with time-domain StratusOCT(TM).

Graph search with appearance and shape information for 3-D prostate and bladder segmentation

The segmentation of soft tissues in medical images is a challenging problem due to the weak boundary, large deformation and serious mutual influence. We present a novel method incorporating both the shape and appearance information in a 3-D graph-theoretic framework to overcome those difficulties for simultaneous segmentation of prostate and bladder. An arc-weighted graph is constructed corresponding to the initial mesh. Both the boundary and region information is incorporated into the graph with learned intensity distribution, which drives the mesh to the best fit of the image. A shape prior penalty is introduced by adding weighted-arcs in the graph, which maintains the original topology of the model and constraints the flexibility of the mesh. The surface-distance constraints are enforced to avoid the leakage between prostate and bladder. The target surfaces are found by solving a maximum flow problem in low-order polynomial time. Both qualitative and quantitative results on prostate and bladder segmentation were promising, proving the power of our algorithm.

Longitudinal study of retinal degeneration in a rat using spectral domain optical coherence tomography

Rodent models of retinal degenerative diseases are used by vision scientists to develop therapies and to understand mechanisms of disease progression. Measurement of changes to the thickness of the various retinal layers provides an objective metric to evaluate the performance of the therapy. Because invasive histology is terminal and provides only a single data point, non-invasive imaging modalities are required to better study progression, and to reduce the number of animals used in research. Optical Coherence Tomography (OCT) has emerged as a dominant imaging modality for human ophthalmic imaging, but has only recently gained significant attention for rodent retinal imaging. OCT provides cross section images of retina with micron-scale resolution which permits measurement of the retinal layer thickness. However, in order to be useful to vision scientists, a significant fraction of the retinal surface needs to be measured. In addition, because the retinal thickness normally varies as a function of distance from optic nerve head, it is critical to sample all regions of the retina in a systematic fashion. We present a longitudinal study of OCT to measure retinal degeneration in rats which have undergone optic nerve axotomy, a well characterized form of rapid retinal degeneration. Volumetric images of the retina acquired with OCT in a time course study were segmented in 2D using a semi-automatic segmentation algorithm. Then, using a 3D algorithm, thickness measurements were quantified across the surface of the retina for all volume segmentations. The resulting maps of the changes to retinal thickness over time represent the progression of degeneration across the surface of the retina during injury. The computational tools complement OCT retinal volumetric acquisition, resulting in a powerful tool for vision scientists working with rodents.

Automated layer segmentation of macular OCT images using dual-scale gradient information

A novel automated boundary segmentation algorithm is proposed for fast and reliable quantification of nine intra-retinal boundaries in optical coherence tomography (OCT) images. The algorithm employs a two-step segmentation schema based on gradient information in dual scales, utilizing local and complementary global gradient information simultaneously. A shortest path search is applied to optimize the edge selection. The segmentation algorithm was validated with independent manual segmentation and a reproducibility study. It demonstrates high accuracy and reproducibility in segmenting normal 3D OCT volumes. The execution time is about 16 seconds per volume (480x512x128 voxels). The algorithm shows potential for quantifying images from diseased retinas as well.

Automatic segmentation of seven retinal layers in SDOCT images congruent with expert manual segmentation

Segmentation of anatomical and pathological structures in ophthalmic images is crucial for the diagnosis and study of ocular diseases. However, manual segmentation is often a time-consuming and subjective process. This paper presents an automatic approach for segmenting retinal layers in Spectral Domain Optical Coherence Tomography images using graph theory and dynamic programming. Results show that this method accurately segments eight retinal layer boundaries in normal adult eyes more closely to an expert grader as compared to a second expert grader.

Association of visual function and ganglion cell layer thickness in patients with diabetes mellitus type 1 and no or minimal diabetic retinopathy

Diabetic retinopathy (DR) classically presents with micro-aneurysms, small haemorrhages and/or lipoprotein exudates. Several studies have indicated that neural loss occurs in DR even before vascular damage can be observed. This study evaluated the possible relationship between structure (spectral domain-optical coherence tomography) and function (Rarebit visual field test) in patients with type 1 diabetes mellitus and no or minimal diabetic retinopathy (DR). Results demonstrated loss of macular visual function and corresponding thinning of the ganglion cell layer (GCL) in the pericentral area of the macula of diabetic patients (Rs = 0.65, p < 0.001). In multivariable logistic regression analysis, GCL thickness remained an independent predictor of decreased visual function (OR 1.5, 95% CI 1.1-2.1). Early DR seems to include a neurodegenerative component.

Automated segmentation of neural canal opening and optic cup in 3D spectral optical coherence tomography volumes of the optic nerve head

PURPOSE

To develop an automated approach for segmenting the neural canal opening (NCO) and cup at the level of the retinal pigment epithelium (RPE)/Bruch's membrane (BM) complex in spectral-domain optical coherence tomography (SD-OCT) volumes. To investigate the correspondence and discrepancy between the NCO-based metrics and the clinical disc margin on fundus photographs of glaucoma subjects.

METHODS

SD-OCT scans and corresponding stereo fundus photographs of the optic nerve head were obtained from 68 eyes of 34 patients with glaucoma or glaucoma suspicion. Manual planimetry was performed by three glaucoma experts to delineate a reference standard (RS) for cup and disc margins from the images. An automated graph-theoretic approach was used to identify the NCO and cup. NCO-based metrics were compared with the RS.

RESULTS

Compared with the RS disc margin, the authors found mean unsigned and signed border differences of 2.81 ± 1.48 pixels (0.084 ± 0.044 mm) and -0.99 ± 2.02 pixels (-0.030 ± 0.061 mm), respectively, for NCO segmentation. The correlations of the linear cup-to-disc (NCO) area ratio, disc (NCO) area, rim area, and cup area of the algorithm with the RS were 0.85, 0.77, 0.69, and 0.83, respectively.

CONCLUSIONS

In most eyes, the NCO-based 2D metrics, as estimated by the novel automated graph-theoretic approach to segment the NCO and cup at the level of the RPE/BM complex in SD-OCT volumes, correlate well with RS. However, a small discrepancy exists in NCO-based anatomic structures and the clinical disc margin of the RS in some eyes.

Optical coherence tomography (OCT) in optic neuritis and multiple sclerosis

Optical coherence tomography (OCT) is a non-invasive imaging technique routinely used in ophthalmology to visualize and quantify the layers of the retina. It also provides information on optic nerve head topography, peripapillary retinal nerve fiber layer thickness, and macular volume, which correlate with axonal loss. These measurements are of particular interest in optic neuropathies and in multiple sclerosis, and OCT parameters are now used as endpoints in neurologic clinical trials.

Three-dimensional analysis of retinal layer texture: identification of fluid-filled regions in SD-OCT of the macula

Optical coherence tomography (OCT) is becoming one of the most important modalities for the noninvasive assessment of retinal eye diseases. As the number of acquired OCT volumes increases, automating the OCT image analysis is becoming increasingly relevant. In this paper, a method for automated characterization of the normal macular appearance in spectral domain OCT (SD-OCT) volumes is reported together with a general approach for local retinal abnormality detection. Ten intraretinal layers are first automatically segmented and the 3-D image dataset flattened to remove motion-based artifacts. From the flattened OCT data, 23 features are extracted in each layer locally to characterize texture and thickness properties across the macula. The normal ranges of layer-specific feature variations have been derived from 13 SD-OCT volumes depicting normal retinas. Abnormalities are then detected by classifying the local differences between the normal appearance and the retinal measures in question. This approach was applied to determine footprints of fluid-filled regions--SEADs (Symptomatic Exudate-Associated Derangements)--in 78 SD-OCT volumes from 23 repeatedly imaged patients with choroidal neovascularization (CNV), intra-, and sub-retinal fluid and pigment epithelial detachment. The automated SEAD footprint detection method was validated against an independent standard obtained using an interactive 3-D SEAD segmentation approach. An area under the receiver-operating characteristic curve of 0.961 +/- 0.012 was obtained for the classification of vertical, cross-layer, macular columns. A study performed on 12 pairs of OCT volumes obtained from the same eye on the same day shows that the repeatability of the automated method is comparable to that of the human experts. This work demonstrates that useful 3-D textural information can be extracted from SD-OCT scans and--together with an anatomical atlas of normal retinas--can be used for clinically important applications.

Decreased retinal ganglion cell layer thickness in patients with type 1 diabetes

PURPOSE. To determine which retinal layers are most affected by diabetes and contribute to thinning of the inner retina and to investigate the relationship between retinal layer thickness (LT) and diabetes duration, diabetic retinopathy (DR) status, age, glycosylated hemoglobin (HbA1c), and the sex of the individual, in patients with type 1 diabetes who have no or minimal DR. METHODS. Mean LT was calculated for the individual retinal layers after automated segmentation of spectral domain-optical coherence tomography scans of patients with diabetes and compared with that in control subjects. Multiple linear regression analysis was used to determine the relationship between LT and HbA1c, age, sex, diabetes duration, and DR status. RESULTS. In patients with minimal DR, the mean ganglion cell layer (GCL) in the pericentral area was 5.1 mum thinner (95% confidence interval [CI], 1.1-9.1 mum), and in the peripheral macula, the mean retinal nerve fiber layer (RNFL) was 3.7 mum thinner (95% CI, 1.3-6.1 mum) than in the control subjects. There was a significant linear correlation (R = 0.53, P < 0.01) between GCL thickness and diabetes duration in the pooled group of patients. Multiple linear regression analysis (R = 0.62, P < 0.01) showed that DR status was the most important explanatory variable. CONCLUSIONS. This study demonstrates GCL thinning in the pericentral area and corresponding loss of RNFL thickness in the peripheral macula in patients with type 1 diabetes and no or minimal DR compared with control subjects. These results support the concept that diabetes has an early neurodegenerative effect on the retina, which occurs even though the vascular component of DR is minimal.

Retinal imaging and image analysis

Many important eye diseases as well as systemic diseases manifest themselves in the retina. While a number of other anatomical structures contribute to the process of vision, this review focuses on retinal imaging and image analysis. Following a brief overview of the most prevalent causes of blindness in the industrialized world that includes age-related macular degeneration, diabetic retinopathy, and glaucoma, the review is devoted to retinal imaging and image analysis methods and their clinical implications. Methods for 2-D fundus imaging and techniques for 3-D optical coherence tomography (OCT) imaging are reviewed. Special attention is given to quantitative techniques for analysis of fundus photographs with a focus on clinically relevant assessment of retinal vasculature, identification of retinal lesions, assessment of optic nerve head (ONH) shape, building retinal atlases, and to automated methods for population screening for retinal diseases. A separate section is devoted to 3-D analysis of OCT images, describing methods for segmentation and analysis of retinal layers, retinal vasculature, and 2-D/3-D detection of symptomatic exudate-associated derangements, as well as to OCT-based analysis of ONH morphology and shape. Throughout the paper, aspects of image acquisition, image analysis, and clinical relevance are treated together considering their mutually interlinked relationships.

Automated segmentation of 3-D spectral OCT retinal blood vessels by neural canal opening false positive suppression

We present a method for automatically segmenting the blood vessels in optic nerve head (ONH) centered spectral-domain optical coherence tomography (SD-OCT) volumes, with a focus on the ability to segment the vessels in the region near the neural canal opening (NCO). The algorithm first pre-segments the NCO using a graph-theoretic approach. Oriented Gabor wavelets rotated around the center of the NCO are applied to extract features in a 2-D vessel-aimed projection image. Corresponding oriented NCO-based templates are utilized to help suppress the false positive tendency near the NCO boundary. The vessels are identified in a vessel-aimed projection image using a pixel classification algorithm. Based on the 2-D vessel profiles, 3-D vessel segmentation is performed by a triangular-mesh-based graph search approach in the SD-OCT volume. The segmentation method is trained on 5 and is tested on 10 randomly chosen independent ONH-centered SD-OCT volumes from 15 subjects with glaucoma. Using ROC analysis, for the 2-D vessel segmentation, we demonstrate an improvement over the closest previous work with an area under the curve (AUC) of 0.81 (0.72 for previously reported approach) for the region around the NCO and 0.84 for the region outside the NCO (0.81 for previously reported approach).

Retinal imaging and image analysis

Many important eye diseases as well as systemic diseases manifest themselves in the retina. While a number of other anatomical structures contribute to the process of vision, this review focuses on retinal imaging and image analysis. Following a brief overview of the most prevalent causes of blindness in the industrialized world that includes age-related macular degeneration, diabetic retinopathy, and glaucoma, the review is devoted to retinal imaging and image analysis methods and their clinical implications. Methods for 2-D fundus imaging and techniques for 3-D optical coherence tomography (OCT) imaging are reviewed. Special attention is given to quantitative techniques for analysis of fundus photographs with a focus on clinically relevant assessment of retinal vasculature, identification of retinal lesions, assessment of optic nerve head (ONH) shape, building retinal atlases, and to automated methods for population screening for retinal diseases. A separate section is devoted to 3-D analysis of OCT images, describing methods for segmentation and analysis of retinal layers, retinal vasculature, and 2-D/3-D detection of symptomatic exudate-associated derangements, as well as to OCT-based analysis of ONH morphology and shape. Throughout the paper, aspects of image acquisition, image analysis, and clinical relevance are treated together considering their mutually interlinked relationships.

Segmentation of the optic disc in 3-D OCT scans of the optic nerve head

Glaucoma is the second leading ocular disease causing blindness due to gradual damage to the optic nerve and resultant visual field loss. Segmentations of the optic disc cup and neuroretinal rim can provide important parameters for detecting and tracking this disease. The purpose of this study is to describe and evaluate a method that can automatically segment the optic disc cup and rim in spectral-domain 3-D OCT (SD-OCT) volumes. Four intraretinal surfaces were segmented using a fast multiscale 3-D graph search algorithm. After surface segmentation, the retina in each 3-D OCT scan was flattened to ensure a consistent optic nerve head shape. A set of 15 features, derived from the segmented intraretinal surfaces and voxel intensities in the SD-OCT volume, were used to train a classifier that can determine which A-scans in the OCT volume belong to the background, optic disc cup and rim. Finally, prior knowledge about the shapes of the cup and rim was incorporated into the system using a convex hull-based approach. Two glaucoma experts annotated the cup and rim area using planimetry, and the annotations of the first expert were used as the reference standard. A leave-one-subject-out experiment on 27 optic nerve head-centered OCT volumes (14 right eye scans and 13 left eye scans from 14 patients) was performed. Two different types of classification methods were compared, and experimental results showed that the best performing method had an unsigned error for the optic disc cup of 2.52+/-0.87 pixels (0.076+/-0.026 mm) and for the neuroretinal rim of 2.04+/-0.86 pixels (0.061+/-0.026 mm). The interobserver variability as indicated by the unsigned border positioning difference between the second expert observer and the reference standard was 2.54+/-1.03 pixels (0.076+/-0.031 mm for the optic disc cup and 2.14+/-0.80 pixels (0.064+/-0.024 mm for the neuroretinal rim. The unsigned error of the best performing method was not significantly different (p > 0.2) from the interobserver variability.

Automated segmentation of the cup and rim from spectral domain OCT of the optic nerve head

PURPOSE

To evaluate the performance of an automated algorithm for determination of the cup and rim from close-to-isotropic spectral domain (SD) OCT images of the optic nerve head (ONH) and compare to the cup and rim as determined by glaucoma experts from stereo color photographs of the same eye.

METHODS

Thirty-four consecutive patients with glaucoma were included in the study, and the ONH in the left eye was imaged with SD-OCT and stereo color photography on the same day. The cup and rim were segmented in all ONH OCT volumes by a novel voxel column classification algorithm, and linear cup-to-disc (c/d) ratio was determined. Three fellowship-trained glaucoma specialists performed planimetry on the stereo color photographs, and c/d was also determined. The primary outcome measure was the correlation between algorithm-determined c/d and planimetry-derived c/d.

RESULTS

The correlation of algorithm c/d to experts 1, 2, and 3 was 0.90, 0.87, and 0.93, respectively. The c/d correlation of expert 1 to 2, 1 to 3, and 2 to 3, were 0.89, 0.93, and 0.88, respectively.

CONCLUSIONS

In this preliminary study, we have developed a novel algorithm to determine the cup and rim in close-to-isotropic SD-OCT images of the ONH and have shown that its performance for determination of the cup and rim from SD-OCT images is similar to that of planimetry by glaucoma experts. Validation on a larger glaucoma sample as well as normal controls is warranted.