Evaluating the Treatment of Diabetic Macular Edema with Aflibercept Based on a Regional Network of Ophthalmologic Care Givers.

Purpose: In Austria, anti-VEGF therapies are reimbursed only in clinical settings. This study aimed to describe the outcome of a treat and extend regimen (TER) with aflibercept for diabetic macular edema (DME) in a network of practitioners. Methods: In a prospective study over 36 months, patients with DME were treated with a loading dose of aflibercept and further on with adjusted treatment intervals based on optical coherence tomography (OCT) findings. All patients were monitored in an outpatient setting by regional ophthalmologists, and the treatment was administered in the clinic. Main outcome parameters were best-corrected visual acuity (BCVA) from baseline to the last regular visit. Number of visits at the practitioner's office as well as the number of injections were secondary outcome parameters. Results: Thirty-three patients completed the study at their final visit. BCVA improved significantly by 5.8 letters between baseline and the final visit from 70.4 letters at baseline (p=0.004). Patients visited the practitioner's office 12.8 times in the observation period of 36 months. 3.7, 5.1, and 3.9 visits were performed, respectively, in the first, second, and third years, and 25.5 ± 7.9 injections were performed. The mean interval of injections over the observation period was 6.2 ± 2.2 in weeks. Conclusion: The treat and extend regimen was valuable for treating patients with DME in this specific setting. The functional results of this study were comparable to those of other real-world evaluations. Adherence to the same treating institution seems to be important to avoid differences in therapeutic decision making and may also increase patient's compliance.

Efficacy of a Disease Management Program of a Tertiary Center and Ophthalmologic Practitioners for the Treatment of Neovascular Age-Related Macular Degeneration.

PURPOSE: The aim of the study was to examine real-world data of patients with neovascular age-related macular degeneration (nAMD) within a disease management program (DMP) treated with anti-VEGF. METHODS: A monocentric, retrospective chart review of 379 eyes of a local DMP was conducted at the Department of Ophthalmology, Kepler University Clinic Linz. Eyes were treated either with bevacizumab or aflibercept using a pro re nata scheme, consisting of 3 injections every 4 weeks in case of presence of disease activity. The observational period was up to 24 months. Disease activity was monitored by visual acuity (VA), clinical examination, and optical coherence tomography (OCT). For (re-)treatments, ophthalmologic practitioners referred patients directly to the intravitreal injection, avoiding redundant examinations. RESULTS: VA improved significantly for all patients after 2 months (logMAR 0.47 ± 0.36; p = 0.000) compared to baseline (0.55 ± 0.37), and for the aflibercept group for up to 6 months (0.36 ± 0.27; p = 0.018). After 12 months, VA remained stable without further significant improvement and decreased by 24 months compared to baseline. The median number of injections was 6 over the first 12 months and 4 in the second year. CONCLUSION: Data revealed the efficacy of a DMP for nAMD involving both ophthalmologic practitioners and a tertiary center. Avoiding redundant examinations increased the efficacy of a clinical setting.

A Swept source optical coherence tomography angiography study: Imaging artifacts and comparison of non-perfusion areas with fluorescein angiography in diabetic macular edema.

PURPOSE: Swept Source Optical coherence tomography angiography (SS-OCTA) is a novel technique to visualize perfusion and vascular changes like ischemia in patients with diabetic retinopathy. The aim of this study was to compare non-perfusion areas on conventional fluorescein angiography (FA) with those on SS-OCTA using detailed manual annotation in patients with diabetic macular edema (DME) and to evaluate possible artifacts caused by DME on SS-OCTA. METHODS: 27 eyes of 21 patients with DME were analyzed in this prospective, cross-sectional study; on all, standard ophthalmological examination, SS-OCTA and FA imaging were performed. Early-phase FA and SS-OCTA images were analyzed for capillary dropout and foveal avascular zone (FAZ) was measured on both modalities. Artifacts in SS-OCTA imaging caused by DME were marked and analyzed. RESULTS: The mean age of the patients was 62.6 ± 11.5 years. On FA the mean size of the annotated non-perfusion areas was 0.14 ± 0.31 mm2 whereas the mean size in SS-OCTA was 0.04 ± 0.13 mm2; areas marked on FA were statistically significantly larger than on SS-OCTA (p<0.01). Mean size of FAZs was similar between FA and OCTA images. (p = 0.91). Seven eyes (25.9 percent) showed imaging artifacts due to DME in SS-OCTA. CONCLUSION: SS-OCTA is a valid tool to analyze capillary perfusion status of patients with DME, although areas of non-perfusion were measured smaller than in conventional FA. More non-perfusion areas were found on SS-OCTA images. FAZ measurements were similar using the two modalities. However, SS-OCTA is prone to artifacts and therefore requires reviewing of imaging results: up to 25 percent of the analyzed eyes showed artifacts on OCTA, which occurred in the areas of diabetic macular edema and did not correspond to capillary drop out.

Early alterations in retinal microvasculature on swept-source optical coherence tomography angiography in acute central serous chorioretinopathy.

The purpose of the study was to evaluate the retinal blood flow in patients with acute central serous chorioretinopathy (CSC) over an observational period of 1 month using swept-source optical coherence tomography (SS-OCTA), focusing especially on changes in the area of subretinal fluid (A-SRF). We correlated these findings with conventional indocyanine green angiography (ICGA). ICGA and SS-OCTA images were collected and analyzed of 12 eyes of 12 patients. The A-SRF was annotated and a qualitative analysis of choriocapillaris, the vessel density (VD) and perfusion density (PD) of the retinal superficial capillary plexus (SCP) and the deep capillary plexus (DCP) was performed in A-SRF and the unaffected remaining area (RA). The VD and PD in the DCP were statistically significantly lower in A-SRF than in the RA at baseline. (VD: p = 0.014; PD: p = 0.036). After 1 month, there was a statistically significant difference in the VD and PD of the DCP (VD: p = 0.015; PD: p = 0.014), and for the PD of the SCP between the A-SRF and the RA (p = 0.015), with lower values in the A-SRF. We found low perfused areas in choriocapillaris corresponding to hypofluorescent areas on ICGA. In conclusion there is a difference in VD and VD of the DCP in the area of SRF in acute CSC. These alterations may lead to a chronic change in the microvasculature and potentially to morphological changes.

Prospective comparison of apex-centered vs standard pupil-centered femtosecond laser-assisted capsulotomy in cataract surgery.

PURPOSE: To compare the lens tilt after apex-centered capsulotomy with standard pupil-centered capsulotomy. SETTING: Clinical practice. DESIGN: Prospective, randomized, investigator-masked trial. METHODS: This prospective, randomized, investigator masked study included 40 patients with age-related cataract scheduled for femtosecond laser-assisted cataract surgery (FLACS) in both eyes. The main outcome was the tilt of the intraocular lens (IOL), measured with the IOLMaster 700. RESULTS: The study enrolled 80 eyes of 40 patients. The mean distance from the center of the apex-centered capsulotomy to the pupil-centered capsulotomy was 175.8 ± 97.2 µm. The amount of IOL tilt was not significantly reduced with the new technique (P > .05). Tilt orientation was more stable in eyes treated with apex-centered capsulotomy. CONCLUSIONS: Centration of the capsulotomy on the lens apex in FLACS does not influence the amount of IOL tilt but the orientation stability. The clinical importance of this finding has to be further elucidated.

Differences in swept-source OCT angiography of the macular capillary network in high tension and normal tension glaucoma.

AIM OF THE STUDY: The purpose of the present study was to determine if swept-source optical coherence tomography angiography (OCTA) of the superficial plexus in the macular region can detect differences between high-tension open-angle glaucoma (HTG) and normal-tension glaucoma (NTG). MATERIALS AND METHODS: In this prospective study 60 eyes from 60 patients (40 HTG; 20 NTG) underwent fovea centred 3 × 3 mm cube macula OCTA imaging by a swept-source OCTA device (Plex Elite, Zeiss, Jena, Germany). Quantitative analysis of the vasculature at the superficial plexus was performed by assessing the Perfusion Density (PD), defined as the total area of perfused vasculature per unit area in a region of measurement, for each group, respectively. Besides, macular ganglion cell layer thickness and mean deviation from visual field testing was assessed and correlated with PD. RESULTS: Average superficial PD of the measured 3 × 3 mm field was comparable between HTG and NTG (P = .567). In both groups a significant relation of PD and age (HTG: r = -0.48, p = .002; NTG: r = -0.615; p = .004) was shown, indicating reduced PD with increasing age. For both groups a positive correlation between PD and mean deviation (MD) (HTG: r = 0.492, p = .003; NTG: r = 0.530, p = .029) as well as PD and GCL thickness was shown (r = 0.486, p = .002 vs. r = 0.389; p = .09). However, the latter did not reach statistical significance in the NTG group. CONCLUSION: PD at the central 3 mm around the fovea is comparable between HTG and NTG. Significant correlation with age and MD was shown in both groups.

Effects of three intravitreal injections of aflibercept on the ocular circulation in eyes with age-related maculopathy.

AIMS: To investigate changes in ocular perfusion following three consecutive intravitreal injections with aflibercept for treatment of neovascular age-related macular degeneration (nAMD). METHODS: The study included 20 eyes from 20 Caucasian patients with unilateral nAMD and 20 fellow eyes. All nAMD eyes were treated with standard intravitreal injection of aflibercept (IVA; 2 mg). Measurements of ocular perfusion at the optic nerve head (ONH) and the choroid were performed with laser speckle flowgraphy (LSFG). Measurements were conducted at baseline, 1 week after the first injection, at the time point of the second and third injection as well as 1 month after the third injection. RESULTS: In treated eyes, mean blur rate (the main output parameter of LSFG) in the ONH microvasculature and in the choroid was significantly reduced 1 week after the first IVA treatment. The effect persisted throughout the entire follow-up period (p<0.001). No change in ocular perfusion was observed in fellow eyes. CONCLUSIONS: IVA for treatment of nAMD leads to a reduction in perfusion of the ONH and the choroid in the treated eye with no apparent effect on the fellow eye.

Patterns of morphologic alteration correlate with vision in diabetic macular oedema: a cross-sectional evaluation of patients using the SAVE II protocol.

PURPOSE: We sought to describe and evaluate patients with clinically significant diabetic macular oedema (CSME) according to the improved SAVE II protocol and correlate findings with visual acuity and systemic parameters in the outpatient clinic for DR (diabetic retinopathy) management. METHODS: This was a cross-sectional case series study of patients with CSME, regardless of prior treatment. Visual acuity testing was performed according to the Early Treatment of Diabetic Retinopathy Study (ETDRS) protocol. Optical coherence tomography (OCT) and fluorescence angiography (FA) were performed. All imaging data were evaluated according to an improved version of the SAVE grading protocol for CSME (SAVE II). The main outcome measures were SAVE II oedema types and best-corrected visual acuity. Additional parameters of a blood sample (fasting glucose, haemoglobin A1c, serum creatinine, triglycerides, cholesterol, low-density lipoproteins, and high-density lipoproteins) were taken. RESULTS: In total, 66 eyes of 66 patients were included. The mean age of the patients was 64.9 ± 8.2 years. Two eyes were classified as SAVE oedema type 1, 19 eyes as SAVE oedema type 2, 28 eyes as SAVE oedema type 3, and 28 eyes as SAVE oedema type 4, respectively. Central retinal thickness and laboratory parameters were not significantly different between the groups. There was a statistically significant difference in ETDRS visual acuity between the SAVE groups 2 and 4 (p < 0.001) with lower vision in group 4. There was no statistically significant difference between oedema types 2 and 3 (p = 0.065) and oedema types 3 and 4 (p = 0.13). CONCLUSION: There was a significant correlation between the four defined oedema types and visual acuity. Morphologic findings did not correlate with any of the evaluated blood parameters.

Aqueous humour cytokine changes during a loading phase of intravitreal ranibizumab or dexamethasone implant in diabetic macular oedema.

PURPOSE: To determine the effect of intravitreal ranibizumab and a dexamethasone implant on aqueous humour cytokine, protein and enzyme levels and to correlate findings to morphologic and functional changes. METHODS: In a prospective, randomized, controlled, double-blind study, patients with clinically significant diabetic macular oedema (CSME) were randomly allocated to receive either monthly intravitreal injections of ranibizumab (Lucentis, Novartis Pharma) or a single dexamethasone implant (Ozurdex, Pharm-Allergan) at baseline (BL). Aqueous humour samples were collected at BL and weeks 2, 8 and 20. RESULTS: The study included 18 eyes of 18 patients. In the dexamethasone implant group, soluble intercellular adhesion molecule 1 (sICAM-1) (weeks 2 and 8), CXCL9/monokine induced by gamma interferon (MIG) (weeks 2 and 8), soluble vascular cell adhesion protein 1 (sVCAM-1) (weeks 2 and 8) and monocyte chemo-attractant protein 1 (MCP-1) (week 2) levels were significantly decreased compared with baseline. In the ranibizumab group, placental growth factor (PIGF) (week 2) and vascular endothelial growth factor (VEGF) (week 2 and 8) levels were significantly decreased compared with baseline. No significant changes in central retinal thickness (CRT) or Early Treatment Diabetic Retinopathy Study (ETDRS) best corrected visual acuity (BCVA) were observed in the Ozurdex group at any time-points. ETDRS scores significantly increased at week 20 (84.88 ± 8.88 letters) compared with baseline (74.78 ± 14.85 letters), and the CRT decreased significantly at week 4 (381.00 ± 114.64 µm) compared with baseline (440 ± 144 µm) in the Lucentis group. CONCLUSION: The dexamethasone implant affected the aqueous cytokines and proteins MCP-1, sICAM-1, sVCAM-1 and MIG, whereas ranibizumab treatments reduced VEGF and PIGF levels. Morphological changes may diverge from cytokine changes. Results may indicate a rationale for a combination therapy for CSME using both agents, the dexamethasone implant and repeatedly administered ranibizumab injections.

Differences in Optic Nerve Head Blood Flow Regulation in Normal Tension Glaucoma Patients and Healthy Controls as Assessed With Laser Speckle Flowgraphy During the Water Drinking Test.

PRéCIS:: Optic nerve head (ONH) perfusion was not significantly altered in subjects with normal tension glaucoma (NTG) nor in healthy individuals after performing the water drinking test (WDT), because of its limited effect on ocular perfusion pressure (OPP). PURPOSE: ONH blood flow can be maintained stable in healthy individuals because of a physiological phenomenon called autoregulation. Impairment of autoregulation has been shown especially under condition of NTG. The purpose of this study was to investigate the ONH blood flow autoregulation in patients with NTG by influencing the OPP with the WDT. METHODS: The study included 9 eyes from 9 white patients with a diagnosis of NTG and 9 eyes from age-matched and sex-matched healthy individuals. In the glaucoma group, the antiglaucomatous therapy was paused 3 weeks before the investigations. Measurements of ONH blood flow were performed with laser speckle flowgraphy. After baseline measurements, individuals ingested 800 mL of water in <5 minutes. Measurements were repeated after 15, 30, and 45 minutes. RESULTS: The water ingestion led to a significant rise in intraocular pressure (P<0.001) but also mean arterial pressure (P<0.001) in both groups. This resulted in stable OPP (P=0.051) with no significant difference between the groups (P=0.43). ONH blood flow remained stable over time in both groups (P=0.719). No significant interaction of time and group was shown for all parameters. CONCLUSIONS: Our findings show that the WDT does not significantly influence the OPP and therefore has to be considered inferior to other methods used to assess blood flow autoregulation.

Short-term effect on the ocular circulation induced by unilateral intravitreal injection of aflibercept in age-related maculopathy.

PURPOSE: Intravitreal injection of anti-vascular endothelial growth factor (anti-VEGF) is the standard treatment for neovascular age-related macular degeneration (AMD). As VEGF is a physiological key player for regulating retinal vascular tone, questions have been raised whether the application of anti-VEGF could induce alterations in ocular perfusion. METHODS: The study included 20 eyes from 20 Caucasian patients with unilateral neovascular AMD and 20 fellow eyes. All eyes were treated with standard intravitreal injection of aflibercept (IVA). Measurements of blood flow at the optic nerve head (ONH) and the choroid were performed with laser speckle flowgraphy (LSFG). The intraocular pressure (IOP), systolic and diastolic blood pressure, heart rate, mean arterial pressure (MAP) and ocular perfusion pressure (OPP) were analysed. Measurements were performed at baseline and repeated immediately after the injection and 30 and 45 min later. RESULTS: Mean time between injection of aflibercept and first follow-up was 8:56 ± 4:25 min. The injection led to significant rise in IOP. In the injected eyes, mean blur rate (MBR, i.e. a relative measure of perfusion and the main outcome parameter of LSFG) within the major vessels of the ONH as well as at the entire ONH region decreased significantly (p < 0.001). No change in MBR was observed in the fellow eye. Choroidal blood flow was maintained stable in both eyes. CONCLUSION: Intravitreal injection of aflibercept (IVA) led to a short-term reduction in perfusion only in the treated eye. This was independent from IOP, indicating a direct pharmacological effect. No changes in choroidal perfusion were observed during the first 45 min after the injection.

Neuroretinal atrophy following resolution of macular oedema in retinal vein occlusion.

BACKGROUND/AIMS: To characterise neuroretinal atrophy in retinal vein occlusion (RVO). METHODS: We included patients with central/branch RVO (CRVO=196, BRVO=107) who received ranibizumab according to a standardised protocol for 6 months. Retinal atrophy was defined as the presence of an area of retinal thickness (RT) <260 µm outside the foveal centre. Moreover, the thickness of three distinct retinal layer compartments was computed as follows: (1) retinal nerve fibre layer to ganglion cell layer, (2) inner plexiform layer (IPL) to outer nuclear layer (ONL) and (3) inner segment/outer segment junction to retinal pigment epithelium. To characterise atrophy further, we assessed perfusion status on fluorescein angiography and best-corrected visual acuity (BCVA), and compared these between eyes with/without atrophy. RESULTS: 23 patients with CRVO and 11 patients with BRVO demonstrated retinal atrophy, presenting as sharply demarcated retinal thinning confined to a macular quadrant. The mean RT in the atrophic quadrant at month 6 was 249±26 µm (CRVO) and 244±29 µm (BRVO). Individual layer analysis revealed pronounced thinning in the IPL to ONL compartment. Change in BCVA at 6 months was similar between the groups (BRVO, +15 vs +18 letters; CRVO, +14 vs +18 letters). CONCLUSIONS: In this exploratory analysis, we describe the characteristics of neuroretinal atrophy in RVO eyes with resolved macular oedema after ranibizumab therapy. Our analysis shows significant, predominantly retinal thinning in the IPL to ONL compartment in focal macular areas in 11% of patients with RVO. Eyes with retinal atrophy did not show poorer BCVA outcomes.

Laser speckle flowgraphy derived characteristics of optic nerve head perfusion in normal tension glaucoma and healthy individuals: a Pilot study.

The purpose of this prospective, case control study was to investigate the differences in optic nerve head blood flow measured with Laser Speckle Flowgraphy (LSFG) between Caucasian patients with normal tension glaucoma and healthy subjects. It included 20 eyes from 20 Caucasian patients with diagnosis of normal tension glaucoma and 20 eyes from age- and sex-matched healthy individuals. In the glaucoma group the antiglaucomatous therapy was paused 3 weeks prior to the investigations. Measurement of optic nerve head blood flow was performed with LSFG. The mean blur rate was obtained for different vascular compartments of the optic nerve head. Parameters for the characterization of pulse-waveform of the mean blur rate were calculated. It was shown that the mean blur rate was significantly lower in the glaucoma group compared to the control group (P < 0.001). The significant differences in the pulse-waveform parameters blow out time (P = 0.028) and flow acceleration time index (P < 0.001) indicate a flatter curve in NTG patients. In conclusion, LSFG can detect differences in optic nerve head blood flow between eyes with normal tension glaucoma and healthy eyes.

Fully Automated Detection and Quantification of Macular Fluid in OCT Using Deep Learning.

PURPOSE: Development and validation of a fully automated method to detect and quantify macular fluid in conventional OCT images. DESIGN: Development of a diagnostic modality. PARTICIPANTS: The clinical dataset for fluid detection consisted of 1200 OCT volumes of patients with neovascular age-related macular degeneration (AMD, n = 400), diabetic macular edema (DME, n = 400), or retinal vein occlusion (RVO, n = 400) acquired with Zeiss Cirrus (Carl Zeiss Meditec, Dublin, CA) (n = 600) or Heidelberg Spectralis (Heidelberg Engineering, Heidelberg, Germany) (n = 600) OCT devices. METHODS: A method based on deep learning to automatically detect and quantify intraretinal cystoid fluid (IRC) and subretinal fluid (SRF) was developed. The performance of the algorithm in accurately identifying fluid localization and extent was evaluated against a manual consensus reading of 2 masked reading center graders. MAIN OUTCOME MEASURES: Performance of a fully automated method to accurately detect, differentiate, and quantify intraretinal and SRF using area under the receiver operating characteristics curves, precision, and recall. RESULTS: The newly designed, fully automated diagnostic method based on deep learning achieved optimal accuracy for the detection and quantification of IRC for all 3 macular pathologies with a mean accuracy (AUC) of 0.94 (range, 0.91-0.97), a mean precision of 0.91, and a mean recall of 0.84. The detection and measurement of SRF were also highly accurate with an AUC of 0.92 (range, 0.86-0.98), a mean precision of 0.61, and a mean recall of 0.81, with superior performance in neovascular AMD and RVO compared with DME, which was represented rarely in the population studied. High linear correlation was confirmed between automated and manual fluid localization and quantification, yielding an average Pearson's correlation coefficient of 0.90 for IRC and of 0.96 for SRF. CONCLUSIONS: Deep learning in retinal image analysis achieves excellent accuracy for the differential detection of retinal fluid types across the most prevalent exudative macular diseases and OCT devices. Furthermore, quantification of fluid achieves a high level of concordance with manual expert assessment. Fully automated analysis of retinal OCT images from clinical routine provides a promising horizon in improving accuracy and reliability of retinal diagnosis for research and clinical practice in ophthalmology.

Spatial Correspondence Between Intraretinal Fluid, Subretinal Fluid, and Pigment Epithelial Detachment in Neovascular Age-Related Macular Degeneration.

Purpose: To identify the spatial distribution of exudative features of choroidal neovascularization in neovascular age-related macular degeneration (nAMD) based on the localization of intraretinal cystoid fluid (IRC), subretinal fluid (SRF), and pigment-epithelial detachment (PED). Methods: This retrospective cross-sectional study included spectral-domain optical coherence tomography volume scans (6 × 6 mm) of 1341 patients with treatment-naïve nAMD. IRC, SRF, and PED were detected on a per-voxel basis using fully automated segmentation algorithms. Two subsets of 37 volumes each were manually segmented to validate the automated results. The spatial correspondence of components was quantified by computing proportions of IRC-, SRF-, or PED-presenting A-scans simultaneously affected by the respective other pathomorphologic components on a per-patient basis. The median across the population is reported. Odds ratios between pairs of lesions were calculated and tested for significance pixel wise. Results: Automated image segmentation was successful in 1182 optical coherence tomography volumes, yielding more than 61 million A-scans for analysis. Overall, 81% of eyes showed IRC, 95% showed SRF, and 92% showed PED. IRC-presenting A-scans also showed SRF in a median 2.5%, PED in 32.9%. Of the SRF-presenting A-scans, 0.3% demonstrated IRC, 1.4% PED. Of the PED-presenting A-scans, 5.2% contained IRC, 2.0% SRF. Similar patterns were observed in the manually segmented subsets and via pixel-wise odds ratio analysis. Conclusions: Automated analyses of large-scale datasets in a cross-sectional study of 1182 patients with active treatment-naïve nAMD demonstrated low spatial correlation of SRF with IRC and PED in contrast to increased colocalization of IRC and PED. These morphological associations may contribute to our understanding of functional deficits in nAMD.

Evaluating the impact of vitreomacular adhesion on anti-VEGF therapy for retinal vein occlusion using machine learning.

Vitreomacular adhesion (VMA) represents a prognostic biomarker in the management of exudative macular disease using anti-vascular endothelial growth factor (VEGF) agents. However, manual evaluation of VMA in 3D optical coherence tomography (OCT) is laborious and data on its impact on therapy of retinal vein occlusion (RVO) are limited. The aim of this study was to (1) develop a fully automated segmentation algorithm for the posterior vitreous boundary and (2) to study the effect of VMA on anti-VEGF therapy for RVO. A combined machine learning/graph cut segmentation algorithm for the posterior vitreous boundary was designed and evaluated. 391 patients with central/branch RVO under standardized ranibizumab treatment for 6/12 months were included in a systematic post-hoc analysis. VMA (70%) was automatically differentiated from non-VMA (30%) using the developed method combined with unsupervised clustering. In this proof-of-principle study, eyes with VMA showed larger BCVA gains than non-VMA eyes (BRVO: 15 ± 12 vs. 11 ± 11 letters, p = 0.02; CRVO: 18 ± 14 vs. 9 ± 13 letters, p < 0.01) and received a similar number of retreatments. However, this association diminished after adjustment for baseline BCVA, also when using more fine-grained VMA classes. Our study illustrates that machine learning represents a promising path to assess imaging biomarkers in OCT.

Impact of B-Scan Averaging on Spectralis Optical Coherence Tomography Image Quality before and after Cataract Surgery.

BACKGROUND AND OBJECTIVE: To determine optimal image averaging settings for Spectralis optical coherence tomography (OCT) in patients with and without cataract. STUDY DESIGN/MATERIAL AND METHODS: In a prospective study, the eyes were imaged before and after cataract surgery using seven different image averaging settings. Image quality was quantitatively evaluated using signal-to-noise ratio, distinction between retinal layer image intensity distributions, and retinal layer segmentation performance. Measures were compared pre- and postoperatively across different degrees of averaging. RESULTS: 13 eyes of 13 patients were included and 1092 layer boundaries analyzed. Preoperatively, increasing image averaging led to a logarithmic growth in all image quality measures up to 96 frames. Postoperatively, increasing averaging beyond 16 images resulted in a plateau without further benefits to image quality. Averaging 16 frames postoperatively provided comparable image quality to 96 frames preoperatively. CONCLUSION: In patients with clear media, averaging 16 images provided optimal signal quality. A further increase in averaging was only beneficial in the eyes with senile cataract. However, prolonged acquisition time and possible loss of details have to be taken into account.

Multivendor Spectral-Domain Optical Coherence Tomography Dataset, Observer Annotation Performance Evaluation, and Standardized Evaluation Framework for Intraretinal Cystoid Fluid Segmentation.

Development of image analysis and machine learning methods for segmentation of clinically significant pathology in retinal spectral-domain optical coherence tomography (SD-OCT), used in disease detection and prediction, is limited due to the availability of expertly annotated reference data. Retinal segmentation methods use datasets that either are not publicly available, come from only one device, or use different evaluation methodologies making them difficult to compare. Thus we present and evaluate a multiple expert annotated reference dataset for the problem of intraretinal cystoid fluid (IRF) segmentation, a key indicator in exudative macular disease. In addition, a standardized framework for segmentation accuracy evaluation, applicable to other pathological structures, is presented. Integral to this work is the dataset used which must be fit for purpose for IRF segmentation algorithm training and testing. We describe here a multivendor dataset comprised of 30 scans. Each OCT scan for system training has been annotated by multiple graders using a proprietary system. Evaluation of the intergrader annotations shows a good correlation, thus making the reproducibly annotated scans suitable for the training and validation of image processing and machine learning based segmentation methods. The dataset will be made publicly available in the form of a segmentation Grand Challenge.

Choroidal thickness maps from spectral domain and swept source optical coherence tomography: algorithmic versus ground truth annotation.

BACKGROUND/AIMS: The purpose of the study was to create a standardised protocol for choroidal thickness measurements and to determine whether choroidal thickness measurements made on images obtained by spectral domain optical coherence tomography (SD-OCT) and swept source (SS-) OCT from patients with healthy retina are interchangeable when performed manually or with an automatic algorithm. METHODS: 36 grid cell measurements for choroidal thickness for each volumetric scan were obtained, which were measured for SD-OCT and SS-OCT with two methods on 18 eyes of healthy volunteers. Manual segmentation by experienced retinal graders from the Vienna Reading Center and automated segmentation on >6300 images of the choroid from both devices were statistically compared. RESULTS: Model-based comparison between SD-OCT/SS-OCT showed a systematic difference in choroidal thickness of 16.26±0.725 µm (p<0.001) for manual segmentation and 21.55±0.725 µm (p<0.001) for automated segmentation. Comparison of automated with manual segmentations revealed small differences in thickness of -0.68±0.513 µm (p=0.1833). The correlation coefficients for SD-OCT and SS-OCT measures within eyes were 0.975 for manual segmentation and 0.955 for automatic segmentation. CONCLUSION: Choroidal thickness measurements of SD-OCT and SS-OCT indicate that these two devices are interchangeable with a trend of choroidal thickness measurements being slightly thicker on SD-OCT with limited clinical relevance. Use of an automated algorithm to segment choroidal thickness was validated in healthy volunteers.

Spatio-Temporal Signatures to Predict Retinal Disease Recurrence.

We propose a method to predict treatment response patterns based on spatio-temporal disease signatures extracted from longitudinal spectral domain optical coherence tomography (SD-OCT) images. We extract spatio-temporal disease signatures describing the underlying retinal structure and pathology by transforming total retinal thickness maps into a joint reference coordinate system. We formulate the prediction as a multi-variate sparse generalized linear model regression based on the aligned signatures. The algorithm predicts if and when recurrence of the disease will occur in the future. Experiments demonstrate that the model identifies predictive and interpretable features in the spatio-temporal signature. In initial experiments recurrence vs. non-recurrence is predicted with a ROC AuC of 0.99. Based on observed longitudinal morphology changes and a time-to-event based Cox regression model we predict the time to recurrence with a mean absolute error (MAE) of 1.25 months comparing favorably to elastic net regression (1.34 months), demonstrating the benefit of a spatio-temporal survival model.