Integrating Machine Learning and Traditional Survival Analysis to Identify Key Predictors of Foveal Involvement in Geographic Atrophy.

Purpose: The purpose of this study was to investigate the incidence of foveal involvement in geographic atrophy (GA) secondary to age-related macular degeneration (AMD), using machine learning to assess the importance of risk factors. Methods: Retrospective, longitudinal cohort study. Patients diagnosed with foveal-sparing GA, having GA size ≥ 0.049 mm² and follow-up ≥ 6 months, were included. Baseline GA area, distance from the fovea, and perilesional patterns were measured using fundus autofluorescence. Optical coherence tomography assessed foveal involvement, structural biomarkers, and outer retinal layers thickness. Onset of foveal involvement was recorded. Foveal survival rates were estimated using Kaplan-Meier curves. Hazard ratios (HRs) were assessed with mixed model Cox regression. Variable Importance (VIMP) was ranked with Random Survival Forests (RSF), with higher scores indicating greater predictive significance. Results: One hundred sixty-seven eyes (115 patients, average age = 75.8 ± 9.47 years) with mean follow-up of 50 ± 29 months, were included in this study. Median foveal survival time was 45 months (95% confidence interval [CI] = 38-55). Incidences of foveal involvement were 26% at 24 months and 67% at 60 months. Risk factors were GA proximity to the fovea (HR = 0.97 per 10-µm increase, 95% CI = 0.96-0.98), worse baseline visual acuity (HR = 1.37 per 0.1 LogMAR increase, 95% CI = 1.21-1.53), and thinner outer nuclear layer (HR = 0.59 per 10-µm increase, 95% CI = 0.46-0.74). RSF analysis confirmed these as main predictors (VIMP = 16.7, P = 0.002; VIMP = 6.2, P = 0.003; and VIMP = 3.4, P = 0.01). Lesser baseline GA area (HR = 1.09 per 1-mm2 increase, 95% CI = 1.01-1.16) and presence of a double layer sign (HR = 0.42, 95% CI = 0.20-0.88) were protective but less influential. Conclusions: This study identifies anatomic and functional factors impacting the risk of foveal involvement in GA. These findings may help identify at-risk patients, enabling tailored preventive strategies.

Assessment of area and structural irregularity of retinal layers in diabetic retinopathy using machine learning and image processing techniques.

Diabetes retinopathy prevention necessitates early detection, monitoring, and treatment. Non-invasive optical coherence tomography (OCT) shows structural changes in the retinal layer. OCT image evaluation necessitates retinal layer segmentation. The ability of our automated retinal layer segmentation to distinguish between normal, non-proliferative (NPDR), and proliferative diabetic retinopathy (PDR) was investigated in this study using quantifiable biomarkers such as retina layer smoothness index (SI) and area (S) in horizontal and vertical OCT images for each zone (fovea, superior, inferior, nasal, and temporal). This research includes 84 eyes from 57 individuals. The study shows a significant difference in the Area (S) of inner nuclear layer (INL) and outer nuclear layer (ONL) in the horizontal foveal zone across the three groups (p < 0.001). In the horizontal scan, there is a significant difference in the smoothness index (SI) of the inner plexiform layer (IPL) and the upper border of the outer plexiform layer (OPL) among three groups (p < 0.05). There is also a significant difference in the area (S) of the OPL in the foveal zone among the three groups (p = 0.003). The area (S) of the INL in the foveal region of horizontal slabs performed best for distinguishing diabetic patients (NPDR and PDR) from normal individuals, with an accuracy of 87.6%. The smoothness index (SI) of IPL in the nasal zone of horizontal foveal slabs was the most accurate at 97.2% in distinguishing PDR from NPDR. The smoothness index of the top border of the OPL in the nasal zone of horizontal slabs was 84.1% accurate in distinguishing NPDR from PDR. Smoothness index of IPL in the temporal zone of horizontal slabs was 89.8% accurate in identifying NPDR from PDR patients. In conclusion, optical coherence tomography can assess the smoothness index and irregularity of the inner and outer plexiform layers, particularly in the nasal and temporal regions of horizontal foveal slabs, to distinguish non-proliferative from proliferative diabetic retinopathy. The evolution of diabetic retinopathy throughout severity levels and its effects on retinal layer irregularity need more study.

Comparison of stereopsis and foveal microstructure after internal limiting membrane peeling and inverted internal limiting membrane flap techniques in patients with macular hole.

PURPOSE: To compare stereopsis and foveal microstructure after internal limiting membrane peeling and inverted internal limiting membrane flap technique in patients with macular hole. DESIGN: Retrospective observational study. METHODS: Sixty-six patients with macular hole were included, of whom 41 underwent 25-gauge pars-plana vitrectomy with complete internal limiting membrane peeling (Peeling group) and 25 with the inverted flap technique (Inverted group). We evaluated stereopsis using the Titmus Stereo Test and the TNO stereo test, best-corrected visual acuity, macular hole closure rate, and foveal microstructure with optical coherence tomography before and at 3, 6, and 12 months after surgery. MAIN OUTCOME MEASURES: Stereopsis and foveal microstructure. RESULTS: Preoperatively, no difference was observed in the base and minimum diameters of macular hole, Titmus Stereo Test score, TNO stereo test score, and best-corrected visual acuity between the Peeling and Inverted groups. The macular hole closure rate in the Peeling and Inverted groups were 97.6% and 100%, respectively, with no significant difference between groups. At 12 months postoperatively, Titmus Stereo Test score (2.1 ± 0.4 in the peeling and 2.2 ± 0.4 in the inverted groups), TNO stereo test score (2.3 ± 0.4 and 2.2± 0.5), and best-corrected visual acuity (0.20 ± 0.18 and 0.24 ± 0.25) were not significantly different between groups (p = 0.596, 0.332, respectively). The defect of the external limiting membrane was more common in the Inverted group than in the Peeling group at 6 months after surgery (5.4 vs. 28.0%; p < 0.05). No statistically significant inter-group differences were noted in the ellipsoid zone defect ratio throughout the follow-up period. CONCLUSIONS: There was no difference in postoperative stereopsis nor foveal microstructure between the internal limiting membrane peeling group and the inverted group in patients with macular hole.

Alignment, calibration, and validation of an adaptive optics scanning laser ophthalmoscope for high-resolution human foveal imaging.

In prior art, advances in adaptive optics scanning laser ophthalmoscope (AOSLO) technology have enabled cones in the human fovea to be resolved in healthy eyes with normal vision and low to moderate refractive errors, providing new insight into human foveal anatomy, visual perception, and retinal degenerative diseases. These high-resolution ophthalmoscopes require careful alignment of each optical subsystem to ensure diffraction-limited imaging performance, which is necessary for resolving the smallest foveal cones. This paper presents a systematic and rigorous methodology for building, aligning, calibrating, and testing an AOSLO designed for imaging the cone mosaic of the central fovea in humans with cellular resolution. This methodology uses a two-stage alignment procedure and thorough system testing to achieve diffraction-limited performance. Results from retinal imaging of healthy human subjects under 30 years of age with refractive errors of less than 3.5 diopters using either 680 nm or 840 nm light show that the system can resolve cones at the very center of the fovea, the region where the cones are smallest and most densely packed.

Macular Imaging Characteristics in Children with Myelinated Retinal Nerve Fiber and High Myopia Syndrome.

Objectives: To investigate the macular imaging features in patients with unilateral myelinated retinal nerve fiber (MRNF) and high myopia syndrome. Materials and Methods: Six patients with unilateral MRNF and high myopia syndrome and 13 myopic controls were enrolled in this study. Spectral domain (SD) optical coherence tomography (OCT), SD enhanced depth imaging OCT, and OCT angiography (OCTA) imaging results of MRNF-affected eyes were compared with the fellow eyes and myopic controls. Results: All patients had abnormal foveal reflex and/or ectopia. No significant difference in retinal thickness parameters were noted between the groups. In OCT scans, posterior vitreous detachment (PVD) was observed in 4 out of the 6 MRNF-affected eyes. Regarding OCTA parameters, only a significant increase in acircularity index was noted in myelinated eyes (p=0.01). Conclusion: All patients demonstrated normal foveal contours, macular structure, and OCTA features except for a higher acircularity index. The incidence of PVD was notably increased in the myelinated eyes.

Inter- and intra-observer agreement in the measurement of macular holes by optical coherence tomography.

BACKGROUND AND OBJECTIVE: A full-thickness macular hole ("FTMH") is a foveal lesion caused by a defect in the full thickness of the neurosensory retina. Its diagnosis and the indication for surgical treatment take into account the measurement of the hole according to the tool provided by the OCT. This measurement can be performed by several ophthalmologists during the follow-up of a patient. The aim of this study is to find out whether there is intra-individual and inter-individual variability in these measurements. MATERIAL AND METHODS: Retrospective review of OCT b-scan images with a diagnosis of FTMH. Measurements of the minimum diameter of the FTMH were performed using the hand-held tool available on the DRI-Triton (Topcon, Japan) at 1:1 and 1:2 scales, on different days, by 2 retina specialists and 2 residents. These measurements were compared to assess inter-observer and intra-observer correspondence. RESULTS: Thirty-four images were analysed. For intra-observer variability, a correlation index higher than 0.98 was obtained in all cases. For inter-observer variability, the intra-class correlation coefficient was 0.94 (95% CI: 0.91-0.97) for the 1:1 scale, and 0.94 (95% CI: 0.91-0.97) for the 1:2 scale. CONCLUSIONS: OCT-measured AMEC size values are reproducible between ophthalmic specialists and residents and are independent of the imaging scale at which the measurement is made.

Retinal Artery Angles in High Axial Myopia and Its Relationship With Visual Function.

Purpose: To evaluate the retinal artery angles in high axial myopia and assess the correlation with other morphometric and functional parameters. Methods: This cross-sectional study included 112 eyes of 112 patients with high axial myopia. Based on axial length (AL), the participants were divided into three groups: group 1 (26 ≤ AL < 28 mm), group 2 (28 ≤ AL < 31 mm), and group 3 (≥31 mm). Scanning laser ophthalmoscopy imaging was used to analyze the retinal artery angle (Yugami correlated angle [YCA]). Retinal vascular densities (VDs) in both superficial capillary plexuses (SCPs) and deep capillary plexuses were evaluated. Fixation behavior, including retinal mean sensitivity (MS), macular fovea 2°, 4° fixation rate (P1, P2), and 68.2% bivariate contour ellipse area, were analyzed by microperimetry. Finally, the correlation between YCAs and AL, VDs, best-corrected visual acuity (BCVA), and fixation behavior was assessed. Results: The YCAs showed significant differences among the three groups (all P < 0.001, respectively). Compared to group 1, the YCA decreased in group 2 (P < 0.001) and continued to decrease in group 3 (P = 0.043). The correlation analysis revealed that smaller YCAs (YCA, YCA1/2, YCA1/4) were positively correlated with the longer AL (ρ = 0.580, 0.545, 0.448, P < 0.001) and lower VDs in any sector in SCPs (all P ≤ 0.05). Furthermore, smaller YCAs were positively correlated with decreased BCVA (ρ = 0.392, 0.387, 0.262; all P < 0.001) and reduced MS (ρ= 0.300, 0.269, 0.244; all P < 0.05). Conclusions: Smaller YCAs were correlated with longer AL, lower VD in SCP, decreased BCVA, and reduced MS. The YCAs might reflect vascular deformation caused by axial elongation and could potentially be useful in predicting visual function in high axial myopia. Translational Relevance: The quantitative analysis of YCAs in fundus photography holds potential clinical value in predicting visual function in high axial myopia.

Macular superficial vascular density on optical coherence tomography angiography in children with unilateral anisometropic and bilateral hyperopic amblyopia.

We analyzed whether macular superficial vascular density (SVD) and foveal vascular zone (FAZ) on optical coherence tomography angiography (OCTA) can distinguish between bilateral ametropic and anisometropic amblyopia. We included 42, 33, and 50 eyes in the bilateral ametropic amblyopia, anisometropic amblyopia, and normal control groups, respectively. Using macular swept-source optical coherence tomography angiography, we measured and analyzed the superficial FAZ areas and five sectoral macular SVDs after magnification correction. The anisometropic amblyopic eye group showed significantly increased foveal SVDs (p < 0.001) and significantly decreased superficial FAZ areas (p < 0.001), compared with the remaining groups. Additionally, the bilateral ametropic amblyopia group had significantly decreased nasal SVDs. SVDs and superficial FAZ areas differed among hyperopic amblyopia subtypes. These findings may reflect vascular distribution differences and macular changes in hyperopic amblyopia subtypes compared with normal eyes.

A New Vessel-Based Method to Estimate Automatically the Position of the Nonfunctional Fovea on Altered Retinography From Maculopathies.

Purpose: The purpose of this study was to validate a new automated method to locate the fovea on normal and pathological fundus images. Compared to the normative anatomic measures (NAMs), our vessel-based fovea localization (VBFL) approach relies on the retina's vessel structure to make predictions. Methods: The spatial relationship between the fovea location and vessel characteristics is learnt from healthy fundus images and then used to predict fovea location in new images. We evaluate the VBFL method on three categories of fundus images: healthy images acquired with different head orientations and fixation locations, healthy images with simulated macular lesions, and pathological images from age-related macular degeneration (AMD). Results: For healthy images taken with the head tilted to the side, the NAM estimation error is significantly multiplied by 4, whereas VBFL yields no significant increase, representing a 73% reduction in prediction error. With simulated lesions, VBFL performance decreases significantly as lesion size increases and remains better than NAM until lesion size reaches 200 degrees2. For pathological images, average prediction error was 2.8 degrees, with 64% of the images yielding an error of 2.5 degrees or less. VBFL was not robust for images showing darker regions and/or incomplete representation of the optic disk. Conclusions: The vascular structure provides enough information to precisely locate the fovea in fundus images in a way that is robust to head tilt, eccentric fixation location, missing vessels, and actual macular lesions. Translational Relevance: The VBFL method should allow researchers and clinicians to assess automatically the eccentricity of a newly developed area of fixation in fundus images with macular lesions.

Morphologic analysis of the foveal avascular zone for prediction of postoperative visual acuity in advanced idiopathic epiretinal membrane.

To investigate the preoperative morphology of the foveal avascular zone (FAZ) for prediction of the postoperative visual acuity in advanced idiopathic epiretinal membrane (ERM). 28 patients (28 eyes) with unilateral idiopathic ERM who underwent pars plana vitrectomy with internal limiting membrane peeling were included. Superficial FAZ was measured preoperatively in both eyes using optical coherence tomography angiography. Area, perimeter, and circularity of FAZ were achieved, and the differences between the ERM eyes and the contralateral eyes were evaluated to analyze the degree of FAZ distortion in diseased eyes. The best-corrected visual acuity (BCVA) and central foveal thickness (CFT) were measured at baseline and more than 6 months after surgery. The correlations of the preoperative FAZ with BCVA and CFT were assessed. The FAZ in the eyes with ERM was significantly reduced, and the BCVA was significantly correlated with the FAZ area (FAZa) (P = 0.001) and the FAZ perimeter (FAZp) (P < 0.001) before surgery. LogMAR BCVA and CFT were significantly improved from 0.550 ± 0.221 to 0.354 ± 0.229 (P = 0.008), and from 524.393 ± 93.575 µm to 400.071 ± 75.979 µm (P < 0.001) after surgery. The preoperative FAZa and FAZp were significantly associated with letter score gain (P < 0.001, P < 0.001) and the postoperative final BCVA (P = 0.026, P = 0.006). The preoperative FAZp had correlation with ratio of postoperative to preoperative CFT (P = 0.016). The preoperative FAZp is a predictor of visual acuity and morphological prognosis after surgery in advanced idiopathic ERM.

The Shape of the Foveal Avascular Zone: When a Circle Isn't Round.

Translational Relevance: Quantitative assessment of OCT-A images includes evaluating circularity and roundness of the FAZ. Inconsistent or inaccurate mathematical definitions of these metrics impacts their utility as biomarkers and impairs the ability to combine and compare results across studies.

Normal central foveal thickness in a thousand eyes of healthy patients in sub Saharan Africa using fourier domain optical coherence tomography.

Background: Optical coherence tomography provides high resolution in vivo images of the retina which are essential for diagnosis and follow up of patients with retina disorders like macula edema and exudative age-related macular degeneration. Establishing the normal range of central fovea values in our population provides vital baseline data for comparison. Aim: To report the range of normal central fovea thickness measurements in eyes of healthy hospital patients in sub-Saharan Africa using a commercially available Fourier domain optical coherence tomography (OCT) scan. Patients and Methods: A retrospective non-comparative review of case files of a thousand consecutive healthy patients who had retina OCT scans between January 2015 and December 2019 was done. Results: Data from 1000 consecutive eyes of 500 healthy patients were used for the study. There were 181 females and 319 males. The mean central foveal thickness was 239.48 microns (µm), with a minimum thickness of 200.0 µm and maximum thickness of 297.0 µm. Males had significantly (P < 0.001) thicker mean CFT (mean CFT = 241.77 µm) compared with females (mean CFT = 235.43 µm). The mean CFT increased with age of participants by 0.139 µm (P < 0.001) for every year of life below 70. Conclusion: The mean central foveal thickness (CFT) in eyes of healthy patients in our study was 239.48 µm with a range from 200 µm to 297.0 µm. Males had thicker mean CFT compared with females and there was a significant increase in mean CFT by 0.139 µm (P < 0.001) for every year of life below 70.

Semi-Automated Analysis of Foveal Maturity in Premature and Full-Term Infants Using Handheld Swept-Source Optical Coherence Tomography.

Purpose: To develop a semi-automated method of measuring foveal maturity using investigational handheld swept source-optical coherence tomography (SS-OCT). Methods: In this prospective, observational study, full-term newborns and preterm infants undergoing routine retinopathy of prematurity screening were imaged. Semi-automated analysis measured foveal angle and chorioretinal thicknesses at the central fovea and average two-sided parafovea by three-grader consensus, correlating with OCT features and demographics. Results: One hundred ninety-four imaging sessions from 70 infants were included (47.8% girls, 37.6 ± 3.4 weeks postmenstrual age, 26 preterm infants with birth weight 1057 ± 325.0, gestational age 29.0 ± 3.0 weeks). Foveal angle (96.1 ± 22.0 degrees) steepened with increasing birth weight (P = 0.003), decreasing inner retinal layer thickness, and increasing gestational age, postmenstrual age, and foveal and parafoveal choroidal thickness (all P < 0.001). Inner retinal fovea/parafovea ratio (0.4 ± 0.2) correlated with increasing inner foveal layers, decreasing postmenstrual age, gestational age, and birth weight (all P < 0.001). Outer retinal F/P ratio (0.7 ± 0.2) correlated with ellipsoid zone presence (P < 0.001), increased gestational age (P = 0.002), and birth weight (P = 0.003). Foveal (447.8 ± 120.6 microns) and parafoveal (420.9 ± 109.2) choroidal thicknesses correlated with foveal ellipsoid zone presence (P = 0.007 and P = 0.01, respectively), postmenstrual age, birth weight, gestational age, and decreasing inner retinal layers (all P < 0.001). Conclusions: Foveal development is dynamic and partially observed through semi-automated analysis of handheld SS-OCT imaging. Translational Relevance: Semi-automated analysis of SS-OCT images can identify measures of foveal maturity.

The Influence of Myopia on the Foveal Avascular Zone and Density of Blood Vessels of the Macula-An OCTA Study.

Background and Objectives: Myopia is the most common refractive eye anomaly with a prevalence that is constantly increasing. High myopia is associated with numerous complications that can lead to permanent vision loss. It is believed that the basis of these complications lies in changes in the microvasculature of the retina caused by an increase in the longitudinal axis of the eye. Materials and Methods: Optical coherence tomography angiography (OCTA) was used to analyze differences in macular zone vascular and perfusion density and foveal avascular zone (FAZ) parameters in myopic subjects. The following OCTA parameters were analyzed: the vessel and perfusion density of retinal blood vessels in the superficial plexus; the area, perimeter, and index of circularity of the foveal avascular zone (FAZ); and foveal and ganglion cell complex (GCC) thickness. Results: Subjects with low myopia did not show statistically significant differences compared to the control for any of the analyzed parameters. Groups with moderate and high myopia showed a significant decrease in vessel and perfusion density in the parafoveal and the entire 3 × 3 mm analyzed field. Foveal vessel and perfusion densities in the myopic groups were similar to those of the control regardless of the degree of myopia. The area and perimeter of the FAZ, as well as foveal and mean GCC thickness, did not differ significantly no matter the degree of myopia, while the index of circularity was lower in highly myopic subjects. The minimal thickness of the GCC was also lower in the high myopia group. Conclusions: High and moderate myopia led to a loss of blood vessels in the macular region. Perfusion and vascular densities were preserved in the foveal region and were not affected by different degrees of myopia. The FAZ was not significantly larger in myopic subjects, but its circularity was lower in subjects with high myopia.

Associations between body mass index and choroidal thickness, superficial and deep retinal vascular indices, and foveal avascular zone measured by OCTA.

AIM: The present study explores the effects of Body Mass Index (BMI) on choroidal thickness, the deep and superficial retinal capillary plexuses, and the foveal avascular zone (FAZ). METHODS: The subjects in this prospective study were divided into five groups based on their calculated BMI. Choroidal thickness, superficial and deep retinal capillary plexuses, and FAZ were measured using enhance depth imaging (EDI) and optical coherence tomography angiography (OCTA). The groups were then compared and correlations with BMI were evaluated. RESULTS: The study included 210 eyes of 105 subjects. The comparison of the BMI groups revealed a significant decrease in the mean choroidal thicknesses in the obese groups (p = 0.001), and a significant negative correlation between BMI and mean choroidal thickness (p = 0.02). The results of the analysis of the mean superficial and deep retinal capillary plexuses did not differ between the groups (p = 0.089, p = 0.808 respectively), while the deep FAZ measurements revealed a significant decrease in the obese groups (p = 0.003). CONCLUSION: Choroidal thickness and deep FAZ are significantly negatively correlated with BMI, suggesting potential choroidal and retinal microvascular effects of obesity.

Foveal avascular zone in normal human eyes by optical coherence tomography angiography.

OBJECTIVE: To analyze the influence factors of the area of superficial plexus foveal avascular zone (FAZ) and related indexes of fovea measured with optical coherence tomography angiography (OCT-A) in normal subjects. METHODS: This was a cross-sectional study from November 2020 to May 2021 in the Inner Mongolia Autonomous Region, China. Each subject received related eye examination. The correlation between all the factors and superficial plexus FAZ were analyzed under univariable and multivariable linear regression analysis. RESULTS: Finally, 239 subjects with sufficient data were recruited in the study, including 108 males and 131 females, aged 27.41±4.63 years. The area of superficial plexus FAZ was 0.33±0.16 mm2. In the univariate regression, gender (ß = 41.702, 95%CI: 9.152 to 74.253, P = 0.012), drinking (ß = -66.074, 95%CI: -99.197 to -32.951, P = 0.001) and axial length (ß = -15.874, 95%CI: -29.562 to -2.185, P = 0.023) were associated with superficial plexus FAZ area. In multivariate regression analysis results, drinking (ß = -42.410, 95%CI = -79.388 to -5.432, P = 0.025) was significantly correlated with superficial plexus FAZ area. CONCLUSION: The area of superficial plexus FAZ was not affected by age, gender, systematical and biochemical indicators, but related to the status of drinking.

Analysis of Microvasculature in Children Recovered from COVID-19 Using Swept-Source OCT/OCTA Technology.

PURPOSE: To analyze structural and vascular changes of the retina and choroid in pediatric patients with coronavirus disease 2019 (COVID-19) using optical coherence tomography (OCT)/OCT angiography (OCTA). METHODS: This comparative cross-sectional study consists of the COVID-19 group including pediatric COVID-19 patients and the control group including healthy children. Vessel density (VD), central macular thickness,, and choroidal thickness (ChT) measurements were performed using swept-source OCT/OCTA 12 weeks after the recovery from COVID-19. RESULTS: The mean VD measurements in the central fovea and nasal quadrants of all three retinal layers and choriocapillaris showed insignificantly lower values in the COVID-19 group when compared to the control group (0:002 < p < 0:05 for all). Similar to VD measurements, insignificant lower ChT measurements were obtained in the central fovea and nasal points in the COVID-19 group. CONCLUSION: OCTA can be used as a non-invasive and valid biomarker in the assessment of early microvascular dysfunction associated with COVID-19.