Erika Tátrai

Reliability and reproducibility of macular segmentation using a custom-built optical coherence tomography retinal image analysis software

We determine the reliability and reproducibility of retinal thickness measurements with a custom-built OCT retinal image analysis software (OCTRIMA). Ten eyes of five healthy subjects undergo repeated standard macular thickness map scan sessions by two experienced examiners using a Stratus OCT device. Automatic/semi automatic thickness quantification of the macula and intraretinal layers is performed using OCTRIMA software. Intraobserver, interobserver, and intervisit repeatability and reproducibility coefficients, and intraclass correlation coefficients (ICCs) per scan are calculated. Intraobserver, interobserver, and intervisit variability combined account for less than 5% of total variability for the total retinal thickness measurements and less than 7% for the intraretinal layers except the outer segment/ retinal pigment epithelium (RPE) junction. There is no significant difference between scans acquired by different observers or during different visits. The ICCs obtained for the intraobserver and intervisit variability tests are greater than 0.75 for the total retina and all intraretinal layers, except the inner nuclear layer intraobserver and interobserver test and the outer plexiform layer, intraobserver, interobserver, and intervisit test. Our results indicate that thickness measurements for the total retina and all intraretinal layers (except the outer segment/RPE junction) performed using OCTRIMA are highly repeatable and reproducible.

Macular morphology assessed by optical coherence tomography image segmentation after femtosecond laser–assisted and standard cataract surgery

PURPOSE: To evaluate and compare thickness changes in the retinal layers in the macula with optical coherence tomography (OCT) segmentation software after femtosecond laser–assisted phacoemulsification (study group) and conventional phacoemulsification (control group). SETTING: Department of Ophthalmology, Semmelweis University, Budapest, Hungary. DESIGN: Case‐control study. METHODS: Total retinal thickness of the macula was evaluated using Stratus OCT 4 to 8 weeks postoperatively. The OCT images were segmented using OCT retinal image analysis software. Regional thickness data in the central area, inner rings, and outer rings were obtained and absolute and relative thicknesses of the individual retinal layers in the 2 study groups compared. Relative thickness was calculated as the ratio of the retinal layer to the total retinal thickness. RESULTS: All surgeries were uneventful. Statistically significant differences were found in absolute outer nuclear layer thickness and relative outer nuclear layer thickness in the inner and outer macular rings between the 2 groups. After adjusting for effective phaco time in multivariate modeling, type of surgery showed a significantly lower relative outer nuclear layer ratio in the inner retinal ring (0.26 with 95% confidence interval [CI], 0.25‐0.27 versus 0.28 with 95% CI, 0.27‐0.29; P=.03) and in the outer retinal ring (0.27 with 95% CI, 0.25‐0.28 versus 0.29 with 95% CI, 0.28‐0.31; P=.02) in the study group. CONCLUSION: After cataract surgery, macular edema was detectable mainly in the outer nuclear layer in both groups but was significantly less using the femtosecond laser platform. Financial Disclosure: Dr. Nagy is a consultant to Alcon‐LenSx Lasers, Inc. The University of Miami and Dr. Cabrera DeBuc hold a pending patent used in the study (U.S. patent 61/139,082) and have the potential for financial benefit from its future commercialization. Drs. Ecsedy, Kovács, Takács, Tátrai, and Somfai have no financial or proprietary interest in any material or method mentioned.

In vivo evaluation of retinal neurodegeneration in patients with multiple sclerosis.

Objective To evaluate macular morphology in the eyes of patients with multiple sclerosis (MS) with or without optic neuritis (ON) in previous history. Methods Optical coherence tomography (OCT) examination was performed in thirty-nine patients with MS and in thirty-three healthy subjects. The raw macular OCT data were processed using OCTRIMA software. The circumpapillary retinal nerve fiber layer (RNFL) thickness and the weighted mean thickness of the total retina and 6 intraretinal layers were obtained for each eye. The eyes of MS patients were divided into a group of 39 ON-affected eyes, and into a group of 34 eyes with no history of ON for the statistical analyses. Receiver operating characteristic (ROC) curves were constructed to determine which parameter can discriminate best between the non-affected group and controls. Results The circumpapillary RNFL thickness was significantly decreased in the non-affected eyes compared to controls group only in the temporal quadrant (p = 0.001) while it was decreased in the affected eyes of the MS patients in all quadrants compared to the non-affected eyes (p<0.05 in each comparison). The thickness of the total retina, RNFL, ganglion cell layer and inner plexiform layer complex (GCL+IPL) and ganglion cell complex (GCC, comprising the RNFL and GCL+IPL) in the macula was significantly decreased in the non-affected eyes compared to controls (p<0.05 for each comparison) and in the ON-affected eyes compared to the non-affected eyes (p<0.001 for each comparison). The largest area under the ROC curve (0.892) was obtained for the weighted mean thickness of the GCC. The EDSS score showed the strongest correlation with the GCL+IPL and GCC thickness (p = 0.007, r = 0.43 for both variables). Conclusions Thinning of the inner retinal layers is present in eyes of MS patients regardless of previous ON. Macular OCT image segmentation might provide a better insight into the pathology of neuronal loss and could therefore play an important role in the diagnosis and follow-up of patients with MS.

Improving image segmentation performance and quantitative analysis via a computer-aided grading methodology for optical coherence tomography retinal image analysis

We demonstrate quantitative analysis and error correction of optical coherence tomography (OCT) retinal images by using a custom-built, computer-aided grading methodology. A total of 60 Stratus OCT (Carl Zeiss Meditec, Dublin, California) B-scans collected from ten normal healthy eyes are analyzed by two independent graders. The average retinal thickness per macular region is compared with the automated Stratus OCT results. Intergrader and intragrader reproducibility is calculated by Bland-Altman plots of the mean difference between both gradings and by Pearson correlation coefficients. In addition, the correlation between Stratus OCT and our methodology-derived thickness is also presented. The mean thickness difference between Stratus OCT and our methodology is 6.53 microm and 26.71 microm when using the inner segment/outer segment (IS/OS) junction and outer segment/retinal pigment epithelium (OS/RPE) junction as the outer retinal border, respectively. Overall, the median of the thickness differences as a percentage of the mean thickness is less than 1% and 2% for the intragrader and intergrader reproducibility test, respectively. The measurement accuracy range of the OCT retinal image analysis (OCTRIMA) algorithm is between 0.27 and 1.47 microm and 0.6 and 1.76 microm for the intragrader and intergrader reproducibility tests, respectively. Pearson correlation coefficients demonstrate R(2)>0.98 for all Early Treatment Diabetic Retinopathy Study (ETDRS) regions. Our methodology facilitates a more robust and localized quantification of the retinal structure in normal healthy controls and patients with clinically significant intraretinal features.

The structure and function of the macula in patients with advanced retinitis pigmentosa.

PURPOSE To assess the structure and function of the macula in advanced retinitis pigmentosa (RP). METHODS Twenty-nine eyes of 22 patients with RP were compared against 17 control eyes. Time-domain optical coherence tomography (OCT) data were processed using OCTRIMA (optical coherence tomography retinal image analysis) as a means of quantifying commercial OCT system images. The thickness of the retinal nerve fiber layer (RNFL), ganglion cell layer and inner plexiform layer complex (GCL+IPL), inner nuclear layer and outer plexiform layer complex (INL+OPL), and the outer nuclear layer (ONL) were measured. Multifocal electroretinography (mfERG) was performed; two groups were formed based on the mfERG findings. Fourteen eyes had no detectable central retinal function (NCRF) on mfERG; detectable but abnormal retinal function (DRF) was present in the mfERG of the other 15 eyes. RESULTS The thickness of the ONL in the central macular region was significantly less in the NCRF eyes compared with that in both DRF eyes and controls. The ONL was significantly thinner in the pericentral region in both patient groups compared with that in controls, whereas the thickness of the GCL+IPL and INL+OPL was significantly decreased only in the NCRF eyes. The RNFL in the peripheral region was significantly thicker, whereas the thickness of the GCL+IPL and ONL was significantly thinner in both patient groups compared with that in controls. CONCLUSIONS The results are consistent with degeneration of the outer retina preceding inner retinal changes in RP. OCT image segmentation enables objective evaluation of retinal structural changes in RP, with potential use in the planning of therapeutic interventions and conceivably as an outcome measure.

Comparison of retinal thickness by Fourier-domain optical coherence tomography and OCT retinal image analysis software segmentation analysis derived from Stratus optical coherence tomography images

PURPOSE To compare thickness measurements between Fourier-domain optical coherence tomography (FD-OCT) and time-domain OCT images analyzed with a custom-built OCT retinal image analysis software (OCTRIMA). METHODS Macular mapping (MM) by StratusOCT and MM5 and MM6 scanning protocols by an RTVue-100 FD-OCT device are performed on 11 subjects with no retinal pathology. Retinal thickness (RT) and the thickness of the ganglion cell complex (GCC) obtained with the MM6 protocol are compared for each early treatment diabetic retinopathy study (ETDRS)-like region with corresponding results obtained with OCTRIMA. RT results are compared by analysis of variance with Dunnett post hoc test, while GCC results are compared by paired t-test. RESULTS A high correlation is obtained for the RT between OCTRIMA and MM5 and MM6 protocols. In all regions, the StratusOCT provide the lowest RT values (mean difference 43 ± 8 μm compared to OCTRIMA, and 42 ± 14 μm compared to RTVue MM6). All RTVue GCC measurements were significantly thicker (mean difference between 6 and 12 μm) than the GCC measurements of OCTRIMA. CONCLUSION High correspondence of RT measurements is obtained not only for RT but also for the segmentation of intraretinal layers between FD-OCT and StratusOCT-derived OCTRIMA analysis. However, a correction factor is required to compensate for OCT-specific differences to make measurements more comparable to any available OCT device.

Fractal-based analysis of optical coherence tomography data to quantify retinal tissue damage

BackgroundThe sensitivity of Optical Coherence Tomography (OCT) images to identify retinal tissue morphology characterized by early neural loss from normal healthy eyes is tested by calculating structural information and fractal dimension. OCT data from 74 healthy eyes and 43 eyes with type 1 diabetes mellitus with mild diabetic retinopathy (MDR) on biomicroscopy was analyzed using a custom-built algorithm (OCTRIMA) to measure locally the intraretinal layer thickness. A power spectrum method was used to calculate the fractal dimension in intraretinal regions of interest identified in the images. ANOVA followed by Newman-Keuls post-hoc analyses were used to test for differences between pathological and normal groups. A modified p value of <0.001 was considered statistically significant. Receiver operating characteristic (ROC) curves were constructed to describe the ability of each parameter to discriminate between eyes of pathological patients and normal healthy eyes.ResultsFractal dimension was higher for all the layers (except the GCL + IPL and INL) in MDR eyes compared to normal healthy eyes. When comparing MDR with normal healthy eyes, the highest AUROC values estimated for the fractal dimension were observed for GCL + IPL and INL. The maximum discrimination value for fractal dimension of 0.96 (standard error =0.025) for the GCL + IPL complex was obtained at a FD ≤ 1.66 (cut off point, asymptotic 95% Confidence Interval: lower-upper bound = 0.905-1.002). Moreover, the highest AUROC values estimated for the thickness measurements were observed for the OPL, GCL + IPL and OS. Particularly, when comparing MDR eyes with control healthy eyes, we found that the fractal dimension of the GCL + IPL complex was significantly better at diagnosing early DR, compared to the standard thickness measurement.ConclusionsOur results suggest that the GCL + IPL complex, OPL and OS are more susceptible to initial damage when comparing MDR with control healthy eyes. Fractal analysis provided a better sensitivity, offering a potential diagnostic predictor for detecting early neurodegeneration in the retina.

A Morphological Study of Retinal Changes in Unilateral Amblyopia Using Optical Coherence Tomography Image Segmentation

Objective The purpose of this study was to evaluate the possible structural changes of the macula in patients with unilateral amblyopia using optical coherence tomography (OCT) image segmentation. Patients and Methods 38 consecutive patients (16 male; mean age 32.4±17.6 years; range 6–67 years) with unilateral amblyopia were involved in this study. OCT examinations were performed with a time-domain OCT device, and a custom-built OCT image analysis software (OCTRIMA) was used for OCT image segmentation. The axial length (AL) was measured by a LenStar LS 900 device. Macular layer thickness, AL and manifest spherical equivalent refraction (MRSE) of the amblyopic eye were compared to that of the fellow eye. We studied if the type of amblyopia (strabismus without anisometropia, anisometropia without strabismus, strabismus with anisometropia) had any influence on macular layer thickness values. Results There was significant difference between the amblyopic and fellow eyes in MRSE and AL in all subgroups. Comparing the amblyopic and fellow eyes, we found a statistically significant difference only in the thickness of the outer nuclear layer in the central region using linear mixed model analysis keeping AL and age under control (p = 0.032). There was no significant difference in interocular difference in the thickness of any macular layers between the subgroups with one-way between-groups ANCOVA while statistically controlling for interocular difference in AL and age. Conclusions According to our results there are subtle changes in amblyopic eyes affecting the outer nuclear layer of the fovea suggesting the possible involvement of the photoreceptors. However, further studies are warranted to support this hypothesis.

Automated classifiers for early detection and diagnosis of retinopathy in diabetic eyes

BackgroundArtificial neural networks (ANNs) have been used to classify eye diseases, such as diabetic retinopathy (DR) and glaucoma. DR is the leading cause of blindness in working-age adults in the developed world. The implementation of DR diagnostic routines could be feasibly improved by the integration of structural and optical property test measurements of the retinal structure that provide important and complementary information for reaching a diagnosis. In this study, we evaluate the capability of several structural and optical features (thickness, total reflectance and fractal dimension) of various intraretinal layers extracted from optical coherence tomography images to train a Bayesian ANN to discriminate between healthy and diabetic eyes with and with no mild retinopathy.ResultsWhen exploring the probability as to whether the subject’s eye was healthy (diagnostic condition, Test 1), we found that the structural and optical property features of the outer plexiform layer (OPL) and the complex formed by the ganglion cell and inner plexiform layers (GCL + IPL) provided the highest probability (positive predictive value (PPV) of 91% and 89%, respectively) for the proportion of patients with positive test results (healthy condition) who were correctly diagnosed (Test 1). The true negative, TP and PPV values remained stable despite the different sizes of training data sets (Test 2). The sensitivity, specificity and PPV were greater or close to 0.70 for the retinal nerve fiber layer’s features, photoreceptor outer segments and retinal pigment epithelium when 23 diabetic eyes with mild retinopathy were mixed with 38 diabetic eyes with no retinopathy (Test 3).ConclusionsA Bayesian ANN trained on structural and optical features from optical coherence tomography data can successfully discriminate between healthy and diabetic eyes with and with no retinopathy. The fractal dimension of the OPL and the GCL + IPL complex predicted by the Bayesian radial basis function network provides better diagnostic utility to classify diabetic eyes with mild retinopathy. Moreover, the thickness and fractal dimension parameters of the retinal nerve fiber layer, photoreceptor outer segments and retinal pigment epithelium show promise for the diagnostic classification between diabetic eyes with and with no mild retinopathy.

Performance evaluation of automated segmentation software on optical coherence tomography volume data

Over the past two decades a significant number of OCT segmentation approaches have been proposed in the literature. Each methodology has been conceived for and/or evaluated using specific datasets that do not reflect the complexities of the majority of widely available retinal features observed in clinical settings. In addition, there does not exist an appropriate OCT dataset with ground truth that reflects the realities of everyday retinal features observed in clinical settings. While the need for unbiased performance evaluation of automated segmentation algorithms is obvious, the validation process of segmentation algorithms have been usually performed by comparing with manual labelings from each study and there has been a lack of common ground truth. Therefore, a performance comparison of different algorithms using the same ground truth has never been performed. This paper reviews research-oriented tools for automated segmentation of the retinal tissue on OCT images. It also evaluates and compares the performance of these software tools with a common ground truth.