Search

Abstract To assess the choroidal vessels in healthy eyes using a novel three-dimensional (3D) deep learning approach. In this cross-sectional retrospective study, swept-source OCT 6 × 6 mm scans on Plex Elite 9000 device were obtained. Automated segmentation of the choroidal layer was achieved using a deep-learning ResUNet model along with a volumetric smoothing approach. Phansalkar thresholding was employed to binarize the choroidal vasculature. The choroidal vessels were visualized in 3D maps, and divided into five sectors: nasal, temporal, superior, inferior, and central. Choroidal thickness (CT) and choroidal vascularity index (CVI) of the whole volumes were calculated using the automated software. The three vessels for each sector were measured, to obtain the mean choroidal vessel diameter (MChVD). The inter-vessel distance (IVD) was defined as the distance between the vessel and the nearest non-collateral vessel. The choroidal biomarkers obtained were compared between different age groups (18 to 34 years old, 35 to 59 years old, and ≥ 60) and sex. Linear mixed models and univariate analysis were used for statistical analysis. A total of 80 eyes of 53 patients were included in the analysis. The mean age of the patients was 44.7 ± 18.5 years, and 54.7% were females. Overall, 44 eyes of 29 females and 36 eyes of 24 males were included in the study. We observed that 33% of the eyes presented at least one choroidal vessel larger than 200 μm crossing the central 3000 μm of the macula. Also, we observed a significant decrease in mean CVI with advancing age (p 0.05). Furthermore, CVI was increased in females compared to males in each sector, with a significant difference in the temporal sector (p

Abstract Background Applications for artificial intelligence (AI) in ophthalmology are continually evolving. Fundoscopy is one of the oldest ocular imaging techniques but remains a mainstay in posterior segment imaging due to its prevalence, ease of use, and ongoing technological advancement. AI has been leveraged for fundoscopy to accomplish core tasks including segmentation, classification, and prediction. Main body In this article we provide a review of AI in fundoscopy applied to representative chorioretinal pathologies, including diabetic retinopathy and age-related macular degeneration, among others. We conclude with a discussion of future directions and current limitations. Short conclusion As AI evolves, it will become increasingly essential for the modern ophthalmologist to understand its applications and limitations to improve patient outcomes and continue to innovate.

Abstract Purpose was to study 3-dimensional choroidal contour at choroidal inner boundary (CIB) and choroidal outer boundary (COB) in healthy eyes. Healthy eyes imaged on wide field swept-source optical coherence tomography were included. Delineation of CIB and COB was done based on our previously reported methods. Quantitative analysis of the surfaces of CIB and COB was based on analyzing best fit spherical radius (R) (overall and sectoral). One hundred and seven eyes of 74 subjects with a mean age of 46.4 ± 19.3 years were evaluated. Overall, R COB (mean ± SD: 22.5 ± 4.8 mm)

Eye diseases such as age-related macular degeneration (AMD) are major causes of irreversible vision loss. Early and accurate detection of these diseases is essential for effective management. Optical coherence tomography (OCT) imaging provides clinicians with in vivo, cross-sectional views of the retina, enabling the identification of key pathological features. However, manual interpretation of OCT scans is labor-intensive and prone to variability, often leading to diagnostic inconsistencies. To address this, we leveraged the RETFound model, a foundation model pretrained on 1.6 million unlabeled retinal OCT images, to automate the classification of key disease signatures on OCT. We finetuned RETFound and compared its performance with the widely used ResNet-50 model, using single-task and multitask modes. The dataset included 1770 labeled B-scans with various disease features, including subretinal fluid (SRF), intraretinal fluid (IRF), drusen, and pigment epithelial detachment (PED). The performance was evaluated using accuracy and AUC-ROC values, which ranged across models from 0.75 to 0.77 and 0.75 to 0.80, respectively. RETFound models display comparable specificity and sensitivity to ResNet-50 models overall, making it also a promising tool for retinal disease diagnosis. These findings suggest that RETFound may offer improved diagnostic accuracy and interpretability for specific tasks, potentially aiding clinicians in more efficient and reliable OCT image analysis.

ObjectivesVarious imaging features on optical coherence tomography (OCT) are crucial for identifying and defining disease progression. Establishing a consensus on these imaging features is essential, particularly for training deep learning models for disease classification. This study aims to analyze the inter-rater reliability in labeling the quality and common imaging signatures of retinal OCT scans.Methods500 OCT scans obtained from CIRRUS HD-OCT 5000 devices were displayed at 512x1024x128 resolution on a customizable, in-house annotation software. Each patient's eye was represented by 16 random scans. Two masked reviewers independently labeled the quality and specific pathological features of each scan. Evaluated features included overall image quality, presence of fovea, and disease signatures including subretinal fluid (SRF), intraretinal fluid (IRF), drusen, pigment epithelial detachment (PED), and hyperreflective material. The raw percentage agreement and Cohen's kappa (κ) coefficient were used to evaluate concurrence between the two sets of labels.ResultsOur analysis revealed κ = 0.60 for the inter-rater reliability of overall scan quality, indicating substantial agreement. In contrast, there was slight agreement in determining the cause of poor image quality (κ = 0.18). The binary determination of presence and absence of retinal disease signatures showed almost complete agreement between reviewers (κ = 0.85). Specific retinal pathologies, such as the foveal location of the scan (0.78), IRF (0.63), drusen (0.73), and PED (0.87), exhibited substantial concordance. However, less agreement was found in identifying SRF (0.52), hyperreflective dots (0.41), and hyperreflective foci (0.33).ConclusionsOur study demonstrates significant inter-rater reliability in labeling the quality and retinal pathologies on OCT scans. While some features show stronger agreement than others, these standardized labels can be utilized to create automated machine learning tools for diagnosing retinal diseases and capturing valuable pathological features in each scan. This standardization will aid in the consistency of medical diagnoses and enhance the accessibility of OCT diagnostic tools.

Abstract We provide an automated analysis of the pigment epithelial detachments (PEDs) in neovascular age-related macular degeneration (nAMD) and estimate areas of serous, neovascular, and fibrous tissues within PEDs. A retrospective analysis of high-definition spectral-domain OCT B-scans from 43 eyes of 37 patients with nAMD with presence of fibrovascular PED was done. PEDs were manually segmented and then filtered using 2D kernels to classify pixels within the PED as serous, neovascular, or fibrous. A set of PED composition indices were calculated on a per-image basis using relative PED area of serous (PEDCI-S), neovascular (PEDCI-N), and fibrous (PEDCI-F) tissue. Accuracy of segmentation and classification within the PED were graded in masked fashion. Mean overall intra-observer repeatability and inter-observer reproducibility were 0.86 ± 0.07 and 0.86 ± 0.03 respectively using intraclass correlations. The mean graded scores were 96.99 ± 8.18, 92.12 ± 7.97, 91.48 ± 8.93, and 92.29 ± 8.97 for segmentation, serous, neovascular, and fibrous respectively. Mean (range) PEDCI-S, PEDCI-N, and PEDCI-F were 0.253 (0–0.952), 0.554 (0–1), and 0.193 (0–0.693). A kernel-based image processing approach demonstrates potential for approximating PED composition. Evaluating follow up changes during nAMD treatment with respect to PEDCI would be useful for further clinical applications.

Purpose: The aim of this study was to evaluate differences in the iris and angle parameters in psuedoexfoliation syndrome (PXF) and pseudoexfoliation glaucoma (PXG) using anterior segment optical coherence tomography (ASOCT). Methods: Patients with PXF or PXG were compared using ASOCT with primary open-angle glaucoma POAG eyes as controls in this noninterventional comparative study conducted at a tertiary eye care center in East India. All angle parameters, TM length, and iris thickness were analyzed from the enhanced depth imaging (EDI) single scans obtained. Quadrant scans were used for the calculation of iris volume using a custom-built in-house software. In particular, the software performs multiple operations including edge detection, connected components, and thresholding to localize and segment the iris. Differences in the iris volume/thickness and TM length in PXF and PXG with POAG were analyzed. Results: A total of 225 eyes were included, which included 75 PXG and 98 PXF cases and 52 POAG with a mean age of 67 ± 9.7 years at presentation. The algorithm repeatability and reproducibility was also established with correlation coefficients more than 99% which was substantiated with Bland-Altman plots. The iris volume (calculated in 197 images of 225 eyes) did not differ significantly in PXF and PXG eyes, although both had significantly greater volume compared to POAG eyes. The iris volume or other angle parameters including TM length did not correlate with clinical variables such as IOP, age, or visual field indices. Conclusion: Iris parameters or TM length do not explain pathogenesis of glaucoma in pseudoexfoliation.

AIM: To compare the difference of capsulotomy produced by precision pulse capsulotomy (PPC), manual (M-CCC), and femtosecond laser assisted capsulotomy (FLAC) in relation to intraocular lens (IOL) centration, circularity and its effect on visual outcomes. METHODS: Prospective, non-randomized comparative study conducted at LV Prasad Eye Institute, Hyderabad, India. Sixty eyes of 52 patients were grouped into 3 (FLAC, PPC and M-CCC) based on capsulotomy techniques used. Twenty consecutive eyes with uneventful phacoemulsification and with no comorbidities affecting the capsulotomy or visual outcome were included in each group. The main outcome measure was IOL centration in relation to capsulotomy and pupil. Secondary outcome measures were post-operative visual acuity, manifest refraction and aberration profile between groups. RESULTS: At 5wk the visual, refractive outcomes and endothelial cell density were comparable between the 3 groups. The median circularity index of FLAC was statistically significantly different to M-CCC or PPC (1-10) groups (P

Purpose: To investigate choroidal hyper-reflective foci (HRF) in subjects with retinal dystrophy [Stargardt's disease (SGD) and retinitis pigmentosa (RP)] and their association with demographics, visual acuity, choroidal thickness (CT), and choroidal vascularity index (CVI). Methods: Single center retrospective study of subjects with previously diagnosed SGD or RP. Swept-source optical coherence tomography images were analyzed for the presence of choroidal HRFs and CVI using previously validated automated algorithm. A Spearman's rank correlation coefficient was used to evaluate the correlation between the number of HRF and various baseline parameters including age, visual acuity, intraocular pressure, and other optical coherence tomography (OCT) parameters (CT, choroidal area, and CVI) were evaluated in these subjects. Results: This study included 46 eyes (23 subjects) and 55 eyes (28 subjects) with previously diagnosed RP and SGD, respectively. In the RP group, the mean number of HRFs was 247.9 ± 57.1 and mean CVI was 0.56 ± 0.04. In SGD group, mean HRF was 192.5 ± 44.3 and mean CVI was 0.41 ± 0.04. Mean HRF was significantly greater in the RP group (0.02), however, the mean CVI was not statistically different. In RP, mean HRF were correlated only with CVI (r = 0.49; P = 0.001), however, in SGD, it correlated with only choroidal area (r = 0.27; P = 0.04). Conclusion: Choroidal HRF were present in both RP and SGD subjects with more HRFs in those with RP. These HRFs were associated with alteration in choroidal vascularity, which further adds into the pathogenesis of these diseases.

Abstract Background Tissue derived biomarkers may offer utility as indicators of accumulated damage. Reduced thickness of retinal neuronal tissue and the vascular choroid have previously been associated with vascular damage and diabetes. We evaluated associations between retinal thickness, retinal microvascular and choroidal measures, and renal function in a population with a high burden of comorbidity. Methods Participants were recruited from nuclear cardiology or renal medicine clinics. Retinal and choroidal thickness were measured from spectral-domain optical coherence tomograms. Retinal microvascular parameters were assessed from digital fundus photographs using a semi-automated software package. Main Outcome Measure: Chronic kidney disease (CKD) categorised as: CKD stages 1–2, eGFR ≥60 ml/min/1.73m2; CKD stage 3, eGFR 30–59 ml/min/1.73m2, and CKD stages 4–5, eGFR ≤29 ml/min/1.73m2. Results Participants (n = 241) had a mean age of 65 years and a mean eGFR of 66.9 ml/min/1.73m2. Thirty–nine % of the cohort had diabetes and 27% were using diuretics. Thinning of the inner retina and changes to its microvascular blood supply were associated with lower eGFR and CKD stages 4 and 5, while no associations were found between the outer retinal layers or their choroidal blood supply and CKD of any stage. These associations remained following adjustment for age, mean arterial blood pressure, diabetes status, low-density lipoprotein, body mass index, and sex. Conclusions Inner retinal thinning and retinal microvascular variation is associated with advanced CKD (stages 4 & 5) independent of important confounding factors, but not with earlier stage CKD (stage 3) and, therefore, its utility as a biomarker for early CKD is not supported in this study.

Purpose: To report the diurnal variation in choroidal vascularity index (CVI) in subfoveal (SF-CVI) and peripapillary area in healthy eyes. Methods: The study was a cross-sectional study including 12 healthy subjects. Swept-source optical coherence tomography scans were taken at 9 am, 11 am, 1 pm, 3 pm, and 5 pm. Subfoveal choroidal thickness (SFCT) and CVI were calculated using automated segmentation techniques and previously validated algorithms. Systemic parameters including systolic blood pressure (SBP), diastolic blood pressure, mean arterial pressure, and mean ocular perfusion pressure were calculated and correlated with SFCT and CVI. Results: A total of 12 eyes (right eye) of 12 patients (mean age: 26 ± 3.77 years) were analyzed. The mean (±standard deviation) amplitude of SFCT and SF-CVI variation was 35.91 ± 14.8 μm (range, 15–69 μm) and 0.05 ± 0.02 (range, 0.02–0.08). The mean CVI showed a significant diurnal variation in the temporal quadrant of the peripapillary region (P = 0.02). Conclusion: SFCT and SF-CVI showed a significant diurnal variation in amplitude (peak–trough analysis) and SF-CVI correlated well with SBP suggestive of a direct influence of blood pressure on choroidal vascularity. The mean peripapillary CVI in the temporal quadrant also showed a significant diurnal variation with no significant change in other quadrants.

Purpose: To report the prevalence of pachydrusen and their relationship with subfoveal choroidal thickness (SFCT) and large choroidal vessel layer thickness (SF-LCVT) in eyes with polypoidal choroidal vasculopathy (PCV) and their fellow eyes. Methods: The case records of 50 patients (99 eyes; 59 PCV and 40 fellow eyes) were retrospectively analyzed for the presence of pachydrusen and other drusen types such as soft drusen. The diagnosis was established using colour fundus photography and optical coherence tomography (OCT). SFCT and SF-LCVT were measured and correlated with the different types of drusen. Results: The mean age of the study cohort was 62.26 ± 10.67 years and included 27 males and 23 females. Pachydrusen and soft drusen were seen in 14 (PCV: 8 and fellow eyes: 6) and 8 eyes (PCV: 2 and fellow eyes: 6) respectively. The mean SFCT and SF-LCVT in the eyes with and without pachydrusen was not significanty different (280.29 ± 103.11 μ vs. 292.63 ± 87.17 μ; P = 0.63 and 180.57 ± 59.20 vs. 173.73 ± 54.86 μ; P = 0.67, respectively). The pachydrusen were most commonly located near the vascular arcades and showed scattered distribution pattern. Though SFCT and SF-LCVT was lower in the eyes with soft drusen compared to eyes with pachydrusen, it failed to reach statistical significance (SFCT, P = 0.1 and SF-LCVT, P = 0.06). Conclusion: The prevalence of pachydrusen in PCV and their fellow eyes is lower in Indian population suggestive of ethnic variations. SFCT and SF-LCVT was not noted to vary signifcantly in eyes with and without pachydrusen in this study cohort.

Abstract Background To evaluate the retinal and choroidal alterations in steroid-associated central serous chorioretinopathy (CSC) in comparison to idiopathic CSC. Methods In this retrospective cohort study, swept source optical coherence tomography scans of eyes with steroid-associated CSC (group A) were compared with the same in idiopathic CSC (group B). The key features included central subfield retinal thickness, subfoveal choroidal thickness, subfoveal large choroidal vessel diameter, subretinal deposits, retinal pigment epithelial irregularities, double layer sign, hyperreflective dots, intraretinal fluid, and choroidal vascularity index (ratio of choroidal luminal area and total choroidal area, measured on a high definition horizontal 9 mm OCT B-scan. Results There were 20 eyes in group A and 30 in group B. Group A had a higher female proportion (60 vs. 16.67%; P

Purpose: This study aims to compare the effect of laser photocoagulation or observation on choroidal vascularity in acute central serous chorioretinopathy (CSCR). Methods: A retrospective analysis of 30 patients with acute CSCR treated either with laser photocoagulation (16 eyes) or sham laser (14 eyes) was performed. Demographic details, visual acuity (VA) assessment, and other relevant clinical data were considered from baseline to the 3rd and 6th month follow-up visits. Participants with chronic CSCR and missing follow-up or inadequate data were excluded. Choroidal analysis including choroidal thickness and choroidal vascularity index (CVI) assessment was done for each visit using Spectral Domain (SD) Optical Coherence Tomography (OCT) images. Results: In laser arm group, there was a statistically significant change in VA, contrast sensitivity and central macular thickness (CMT) and neurosensory detachment (NSD) (P < 0.05) at the 3rd and 6th month visits. However, there was no statistically significant difference in subfoveal choroidal thickens (SFCT) and CVI (P > 0.05) at both the visits. In sham laser group, similarly, there was a significant improvement in VA, contrast sensitivity, CMT, and CVI (P < 0.05) at the 3rd and 6th month visits. There was significant reduction in NSD at the 3rd month; however, it was not statistically significant at the 6th month visit. SFCT did not change significantly at both the visits. There was no significant difference for the changes in parameters between the groups at the 6th month. Regression analysis showed no significant correlation with final VA with any of the baseline parameters. Conclusion: Early laser photocoagulation does lead to change in choroidal morphology, though insignificant, in comparison to observation. The present data, yet again, support no additional benefit of early laser photocoagulation in acute CSCR.

Abstract Background Hard exudates (HEs) are the classical sign of diabetic retinopathy (DR) which is one of the leading causes of blindness, especially in developing countries. Accordingly, disease screening involves examining HEs qualitatively using fundus camera. However, for monitoring the treatment response, quantification of HEs becomes crucial and hence clinicians now seek to measure the area of HEs in the digital colour fundus (CF) photographs. Against this backdrop, we proposed an algorithm to quantify HEs using CF images and compare with previously reported technique using ImageJ. Methods CF photographs of 30 eyes (20 patients) with diabetic macular edema were obtained. A robust semi-automated algorithm was developed to quantify area covered by HEs. In particular, the proposed algorithm, a two pronged methodology, involved performing top-hat filtering, second order statistical filtering, and thresholding of the colour fundus images. Subsequently, two masked observers performed HEs measurements using previously reported ImageJ-based protocol and compared with those obtained through proposed method. Intra and inter-observer grading was performed for determining percentage area of HEs identified by the individual algorithm. Results Of the 30 subjects, 21 were males and 9 were females with a mean age of the 50.25 ± 7.80 years (range 33–66 years). The correlation between the two measurements of semi-automated and ImageJ were 0.99 and 0.99 respectively. Previously reported method detected only 0–30% of the HEs area in 9 images, 30–60% in 12 images and 60–90% in remaining images, and more than 90% in none. In contrast, proposed method, detected 60–90% of the HEs area in 13 images and 90–100% in remaining 17 images. Conclusion Proposed method semi-automated algorithm achieved acceptable accuracy, qualitatively and quantitatively, on a heterogeneous dataset. Further, quantitative analysis performed based on intra- and inter-observer grading showed that proposed methodology detects HEs more accurately than previously reported ImageJ-based technique. In particular, we proposed algorithm detect faint HEs also as opposed to the earlier method.

Purpose. To analyse the vascular density of the choroid in a keratoconus (KC) population using swept-source optical coherence tomography (SS-OCT). Methods. Prospective, noninterventional study that analysed 97 eyes from 52 KC patients and 145 eyes from 89 healthy controls. The sample was divided in four different age groups. Inclusion criteria were topographic diagnosis of KC using Pentacam, axial length shorter than 26 mm, good quality of the images, and no other systemic or ocular diseases. A 12 mm horizontal single-line SS-OCT b-scan was performed to create a choroidal thickness (CT) profile. Validated automated segmentation and binarization were used in order to analyse choroidal, stromal, and vascular areas. Results. The percentage of choroidal vascularity (vascular area/total area) was 56.6% in KC patients vs. 49.4% in controls. Aged-adjusted choroidal, stromal, and vascular areas and corrected choroidal percentage of vascularity are statistically increased in KC patients when compared with healthy controls (p

Background: To map the choroidal vascularity index and compare two eyes in patients with unilateral central serous chorioretinopathy (CSCR). Methods: This was a retrospective, observational study performed in patients with unilateral CSCR. Choroidal thickness (CT) and Choroidal vascularity index (CVI) were measured and mapped in various zones according to the early treatment diabetic retinopathy (ETDRS) grid. Results: A total of 20 CSCR patients (20 study and 20 fellow eyes) were included in the study. Outer nasal region CT was seen to be significantly lower than central CT (p = 0.042) and inner nasal CT (p = 0.007); outer ring CT was significantly less than central (p = 0.04) and inner ring (p = 0.01) CT in CSCR eyes. On potting all the CVI values against the corresponding CT values, a positive correlation was seen in CSCR eyes (r = 0.54, p < 0.01), which was slightly weaker in fellow eyes (r = 0.3, p < 0.01) and a negative correlation was seen in healthy eyes (r = −0.262, p < 0.01). Conclusions: Correlation between CVI and CT was altered in CSCR eyes as compared to fellow and normal eyes with increasing CVI towards the center of the macula and superiorly in CSCR eyes.

Cystoid spaces (CSs) are a common retinal finding in choroideremia (CHM) patients. The aim of this study was to analyze the vascular features of the choroid associated with the presence of CSs in patients with confirmed genetic diagnosis of CHM. A total of 33 patients (33 eyes) were enrolled in this retrospective cross-sectional study and divided into two groups based on the presence (17 eyes) or absence (16 eyes) of CSs. Choroidal features were evaluated on spectral-domain optical coherence tomography including subfoveal choroidal thickness (CT), total choroidal area (TCA), luminal choroidal area (LCA), and stromal choroidal area (SCA). The choroidal vascularity index (CVI) was then calculated in all study eyes. All structural choroidal parameters were calculated both on the entire length of the B-scan and in the central subfoveal 1500 μm. The average age was 37.3 ± 11.6 and 31.4 ± 16.7 years (p = 0.25) and mean logMAR best-corrected visual acuity was 0.11 ± 0.20 and 0.20 ± 0.57 (p = 0.54) in the CHM groups with and without CSs, respectively. There were no significant differences in subfoveal CT, and TCA, LCA, SCA, and CVI evaluated on either the entire scan or in the central 1500 μm (all p > 0.05). All choroidal vasculature parameters exhibited no significant differences between CHM eyes with and without CSs. Our results suggest that the choroid may not be involved in the development of CSs in patients with CHM.

To develop an algorithm for automated quantification of Haller's layer in choroid using swept-source optical coherence tomography (OCT).So far, to understand the association of various diseases with structural changes of choroid, only gross indicators such as thickness, volume and vascularity index have been examined. However, certain diseases affect specific sublayers of the choroid. Accordingly, a need for targeted quantitation arises. In particular, there is significant interest in understanding Haller's layer, a choroidal sublayer comprising relatively large blood vessels. Unfortunately, its intricate vasculature makes, manual quantitation difficult, tedious, and error-prone. To surmount this difficulty, it is imperative to develop an algorithmic method.The primary contribution of this work consists in developing an approach for detecting the boundary between Haller's and Sattler's layers, the latter comprising medium-sized vessels. The proposed algorithm estimates vessel cross-sections using exponentiation-based binarization, and labels a vessel large if its cross-section exceeds certain statistically determined threshold. Finally, the desired boundary is obtained as a smooth curve joining the innermost points of such large vessels. On 50 OCT B-scans (of 50 healthy eyes), our algorithm was validated both qualitatively and quantitatively, by comparing with intra-observer variability. Extensive statistical analysis was performed using metrics including Dice coefficient (DC), correlation coefficient (CC) and absolute difference (AD).The proposed algorithm achieved a mean DC of 89.48% (SD:5.03%) in close agreement with the intra-observer repeatability of 89.12% (SD:5.68%). Corresponding mean AD and mean CC were of 17.54 μm (SD:16.45μm) and 98.10% (SD:1.60%) which too approximate the respective intra-observer repeatability values 19.19 μm (SD:17.69 μm) and 98.58% (SD:1.12%).High correlation between algorithmic and manual delineations indicates suitability of our algorithm for clinically analyzing choroid in greater finer details, especially, in diseased eyes.