Niroj Kumar Sahoo

Objectives: To validate a deep learning-based algorithm for automated detection, segmentation, and quantitative assessment of retinal fluid on optical coherence tomography (OCT) across multiple retinal diseases. Methods: In this retrospective validation study, spectral-domain OCT volume scans from eyes with neovascular age-related macular degeneration (nAMD), diabetic macular edema (DME), and macular telangiectasia type 2 (MacTel) were analyzed. Automated segmentation was performed using the fluid analyzer on Skopix by NetraMind Innovations, a deep learning-based framework trained to identify intraretinal fluid (IRF), subretinal fluid (SRF), pigment epithelial detachment (PED), and subretinal hyperreflective material (SHRM). Automated segmentations were reviewed and manually corrected by two masked experienced retina graders, with discrepancies adjudicated by a senior retina specialist. Scan-level detection performance was evaluated using accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), area under the receiver operating characteristic curve (AUC), and Gwet’s first-order agreement coefficient (AC1). Spatial segmentation agreement across all B-scans was assessed using the Dice coefficient. Quantitative agreement between automated and manually corrected fluid volumes was evaluated using correlation and Bland–Altman analyses. Inter-grader reliability was assessed using the intraclass correlation coefficient (ICC). Results: A total of 98 OCT volumes comprising 31 nAMD, 25 DME, and 42 MacTel eyes were included. In nAMD, IRF detection demonstrated a sensitivity of 81.8%, specificity of 83.0%, and AUC of 0.876, while SRF demonstrated a sensitivity of 81.4%, specificity of 96.7%, and AUC of 0.901. In DME, sensitivity, specificity, and AUC were 99.6%, 97.3%, and 0.989 for IRF and 98.4%, 96.4%, and 0.978 for SRF, respectively. In MacTel, IRF demonstrated a sensitivity of 87.3%, specificity of 95.1%, and AUC of 0.927, while SRF demonstrated a sensitivity of 86.8%, specificity of 98.4%, and AUC of 0.929. Segmentation agreement between automated and manually corrected annotations was high across disease groups, with Dice coefficients of 0.829 and 0.922 for IRF and SRF in nAMD, 0.858 and 0.941 in DME, and 0.908 and 0.97 in MacTel, respectively. Automated fluid volumes demonstrated strong correlations with manually corrected measurements, with minimal systematic bias on Bland–Altman analysis. Conclusions: The automated segmentation algorithm demonstrated strong validation performance for the detection and quantitative assessment of retinal fluid across nAMD, DME, and MacTel. High segmentation agreement, particularly for IRF and SRF, and strong volumetric agreement with expert-corrected measurements support the potential use of automated OCT fluid quantification in clinical practice and research.

Purpose: To validate an automated pipeline to detect and quantify focal retinal and choroidal pulsation areas that are synchronous with the cardiac cycle in video indocyanine green angiography (ICGA). Design: Retrospective, observational, hypothesis-generating validation study Subjects, Participants: Consecutive patients with a diagnosis of central serous chorioretinopathy (CSCR) in one or both eyes. Methods: Videos were acquired on Heidelberg HRA+OCT. The pipeline consisted of three steps: signal extraction, foci detection, and quantification. After registration of the constituent frames, each pixel’s intensity signal was analyzed at the presumed cardiac frequency (tested from a sample of three detectable frequencies). A synchrony score combining local phase coherence with oscillation amplitude was then derived and computed using a standard deviation (σ) above each video’s background oscillation value. Two masked graders marked the retinal and choroidal pulsation areas twice. We compared detection of the pulsation areas against grader consensus using a receiver operating characteristic curve (using multiple grid sizes to divide the scan area) and, separately, using a signal-based area-reduction method to obtain an optimum σ value. Main Outcome Measures: Agreement between the automated algorithm and human graders in detection of pulsation foci, and the optimum threshold multiplier (σ). Results: We studied 20 ICGA videos from 20 eyes. At the 16-pixel grid size, the pipeline achieved a mean area under the curve (AUC) of 0.914, sensitivity of 0.86, and specificity of 0.80. Grader agreement improved with larger grid size, reaching substantial-to-strong levels for choroidal annotations. The two independent validation methods demonstrated similar σ values that differed by 0.62σ, supporting σ=4.0 as the optimum value. Conclusions: We report the first automated method to quantify retinal and choroidal vascular pulsation on video ICGA. It measures pixels that oscillate over time with the presumed cardiac cycle and works reliably at the spatial scale (grid level) where experts agree. Pulsatile hemodynamics may add a new vascular biomarker for glaucoma, diabetes, hypertension, and pachychoroid diseases.

Purpose: To compare baseline characteristics and outcomes of central serous chorioretinopathy (CSCR) between people who identify as Black and those who identify as White. Methods: This retrospective, multicenter study from the MICRoN study group, included Black and White patients with CSCR. Demographic information and multimodal imaging parameters were analyzed and compared in the two groups. Regression models were used to identify factors affecting visual outcomes, anatomical changes, and disease recurrence/persistence. Results: We included a total of 450 patients (312 males and 138 females), of whom 100 were Black patients, and 350 were White patients. Black patients were significantly older (51.9 versus 48.8 years, p=0.03) but had shorter symptom duration at presentation (1 versus 3 months, p=0.003). They demonstrated worse baseline visual acuity (0.3±0.3 versus 0.2±0.2 logMAR, p<0.001), greater retinal detachment height (157.9 versus 107.5 μm, p=0.002), and more frequent peripapillary retinal pigment epithelium changes (27% versus 9.4%, p<0.001). During a median follow-up of 24 months (IQR 10 to 60 months), White patients experienced significantly higher rates of disease recurrence (35.7% versus 19%, p=0.002), persistent subretinal fluid (13.1% versus 4%, p=0.01), and macular neovascularization development (21.1% versus 4%, p<0.001). Multivariable regression confirmed that Black patients were associated with reduced recurrence risk (OR 0.52, p=0.03). Conclusions: Despite presenting with more severe morphological changes and worse initial vision, Black patients demonstrate substantially lower rates of recurrences and sequelae, suggesting biological differences in disease pathophysiology.

Purpose: To compare baseline characteristics and clinical course between Hispanic and non-Hispanic patients with Central Serous Chorioretinopathy (CSC). Methods: This retrospective, multicentre study from the Macula Society CSC Research Network (MICRoN) included Hispanic and non-Hispanic patients with CSC. Demographic characteristics and multimodal imaging variables were compared between groups. Regression analyses identified factors associated with visual outcomes, structural changes, and disease recurrence/persistence. Results: A total of 480 patients were included (130 Hispanic, 350 non-Hispanic). Non-Hispanic patients were significantly older at presentation (48.8±11.1 vs 45.3±11.6 years, p=0.003) and had better baseline best recorded visual acuity (BRVA; 20/25 vs 20/40, p<0.001). A significantly higher percentage of Hispanic patients presented with complex CSC (73.8% vs 28.3%, p<0.001), multifocal RPE alterations (58.5% vs 9.7%, p<0.001), and greater neurosensory detachment height (NSD; 193 [IQR 100–301] vs 113 [IQR 66–193] microns, p<0.001). Conversely, non-Hispanic patients demonstrated larger areas of RPE alteration (1.5 [IQR 1–3] vs 1 [IQR 0.25–1.5] disc areas, p<0.001). At last follow-up, both groups showed significant improvement in BRVA (Hispanics: 20/40 to 20/25, p<0.001; non-Hispanics: 20/25 to 20/20, p<0.001), with no significant difference in rates of recurrence (40% vs 35.7%, p=0.08) or persistence (11.5% vs 13.1%, p=0.08). Conclusion: In our cohort, Hispanic patients more commonly presented with complex CSC, multifocal RPE alterations, and greater NSD height, while non-Hispanic patients were older with better baseline vision and larger areas of RPE alteration. Despite these differences, visual outcomes improved meaningfully in both groups, with comparable rates of recurrence and persistence.

Purpose: To describe the long-term follow-up of large and medium-sized choroidal vessels in eyes with age-related macular degeneration (AMD) and polypoidal choroidal vasculopathy (PCV) Methods: This was a retrospective, observational analysis of eyes with AMD or PCV, with a minimum of five years of follow-up of indocyanine green angiography (ICGA). Qualitative analysis of the choroidal vessels was carried out at baseline until the final visit. Results: We analysed ten eyes of five patients diagnosed with either AMD or PCV with a follow-up duration ranging from seven to sixteen years. Eyes with active disease received various treatment modalities. On serial follow-up of ICGA images, remodelling of medium and large choroidal vessels was seen. The changes included large choroidal vessel attenuation, prominence/ dilatation of pre-existing choroidal vessels connecting the neovascular complex and formation of new anastomotic channels. These changes appeared adjacent to present or future neovascular complex locations. One uninvolved fellow eye showed minimal changes on follow-up. Conclusion: We report the long-term changes in large and medium-sized choroidal vessels in eyes with AMD and PCV with serial ICGA images. These vascular alterations suggest the possible role played by these vessels in the pathogenesis of choroidal neovascular complexes.