Rate of Initial Optic Nerve Head Capillary Density Loss and Risk of Visual Field Progression.

Importance: Rapid initial optic nerve head capillary density loss may be used to assess the risk of glaucoma visual field progression. Objective: To investigate the association between the rate of initial optic nerve head capillary density loss from optical coherence tomography angiography (OCTA) and visual field progression. Design, Setting, Participants: This was a retrospective study of a longitudinal cohort at a glaucoma referral center. A total of 167 eyes (96 with primary open-angle glaucoma and 71 with glaucoma suspect) of 109 patients were monitored for a mean (SD) of 5.7 (1.4) years from January 2015 to December 2022. Data analysis was undertaken in April 2023. Main Outcomes and Measures: The rates of initial capillary density and average retinal nerve fiber layer loss were calculated from the first 3 optic nerve head OCTA and OCT scans, respectively, during the initial follow-up (mean [SD], 2.0 [1.0] years). Based on the median rate, eyes were categorized into fast and slow progressor groups. The association between initial capillary density change or retinal nerve fiber layer thinning and visual field progression was evaluated using linear-mixed and time-varying Cox models. Results: A total of 167 eyes of 109 patients (mean [SD] age, 69.0 [11.1] years; 56 [51.4%] female and 53 [48.6%] male) were assessed. Eighty-three eyes were slow OCTA progressors, while 84 eyes were fast with mean capillary density loss of -0.45% per year and -1.17% per year, respectively (mean difference, -0.72%/year; 95% CI,-0.84 to -0.60; P < .001). Similarly, 83 eyes were slow OCT progressors, while 84 eyes were fast with mean retinal nerve fiber layer thinning of -0.09 µm per year and -0.60 µm per year, respectively (mean difference, -0.51 µm/year; 95% CI,-0.59 to -0.43; P < .001). The fast OCTA and OCT progressors were associated with more rapid visual field loss (mean difference, -0.18 dB/year; 95% CI,-0.30 to -0.06; P = .004 and -0.17 dB/year; 95% CI,-0.29 to -0.06; P = .002, respectively). Fast OCTA progressing eyes were more likely to have visual field progression (hazard ratio, 1.96; 95% CI, 1.04-3.69; P = .04). Seventeen of 52 eyes (32.7%; 95% CI, 32.5-32.8) with fast OCTA and OCT progression developed subsequent visual field likely progression. Conclusion and Relevance: Rapid initial optic nerve head capillary density loss from OCTA was associated with a faster rate of visual field progression and a doubling of the risk of developing event progression in this study. These findings may support clinical use of OCTA and OCT optic nerve head measurements for risk assessment of glaucoma progression.

Reduction of Optic Disc Microvasculature and Retinal Nerve Fiber Layer Thinning in Patients with Glaucoma.

PURPOSE: To assess the relationship between the change of optic disc vessel density (ODVD) and retinal nerve fiber layer (RNFL) thinning in primary open-angle glaucoma (POAG) patients. DESIGN: Retrospective case series. METHODS: For 105 POAG patients, ≥ 5 consecutive optical coherence tomography (OCT) and OCT angiography (OCTA) images were obtained during ≥ 2 years of follow-up. Based on enface OCTA imaging, ODVD was calculated as the ratio of pixels occupied by vessels below the internal limiting membrane within the temporal area of the optic cup, and ODVD reduction was determined when there was a statistically significant negative slope (P < 0.05) for any of the global, superior, or inferior sectors. The association between the rates of ODVD change and RNFL thinning was assessed by multivariable longitudinal linear mixed-effects model vs. time. RESULTS: During 2.9 ± 0.3 years of follow-up on the 105 participants with visual field mean deviation at baseline of 5.7 ± 4.8 dB, 46 (43.8%) showed ODVD reduction. Faster global RNFL thinning was associated with the smaller Bruch's membrane opening area (ß = 0.381; 95% confidence interval (CI), 0.120 to 0.646; P = 0.006), optic disc hemorrhage (ß = -0.567; 95% CI, -0.909 to -0.228; P = 0.002) and faster rate of global ODVD change (ß = -0.090; 95% CI, -0.139 to -0.042; P = 0.001). CONCLUSIONS: Reduction of optic disc microvasculature was associated with rapid RNFL thinning in POAG. This suggests a role for deep ONH circulation in the glaucoma pathogenesis.

Racial Differences in Diagnostic Accuracy of Retinal Nerve Fiber Layer Thickness in Primary Open-Angle Glaucoma.

Purpose: To evaluate the diagnostic accuracy of retinal nerve fiber layer thickness (RNFLT) by spectral-domain optical coherence tomography (OCT) in primary open-angle glaucoma (POAG) in eyes of African (AD) and European descent (ED). Design: Comparative diagnostic accuracy analysis by race. Participants: 379 healthy eyes (125 AD and 254 ED) and 442 glaucomatous eyes (226 AD and 216 ED) from the Diagnostic Innovations in Glaucoma Study and the African Descent and Glaucoma Evaluation Study. Methods: Spectralis (Heidelberg Engineering GmbH) and Cirrus (Carl Zeiss Meditec) OCT scans were taken within one year from each other. Main Outcome Measures: Diagnostic accuracy of RNFLT measurements. Results: Diagnostic accuracy for Spectralis-RNFLT was significantly lower in eyes of AD compared to those of ED (area under the receiver operating curve [AUROC]: 0.85 and 0.91, respectively, P=0.04). Results for Cirrus-RNFLT were similar but did not reach statistical significance (AUROC: 0.86 and 0.90 in AD and ED, respectively, P =0.33). Adjustments for age, central corneal thickness, axial length, disc area, visual field mean deviation, and intraocular pressure yielded similar results. Conclusions: OCT-RNFLT has lower diagnostic accuracy in eyes of AD compared to those of ED. This finding was generally robust across two OCT instruments and remained after adjustment for many potential confounders. Further studies are needed to explore the potential sources of this difference.

Diagnostic accuracy of optic nerve head and macula OCT parameters for detecting glaucoma in eyes with and without high axial myopia.

PURPOSE: To characterize structural differences and assess the diagnostic accuracy of optic nerve head (ONH) and macula optical coherence tomography (OCT) parameters to detect glaucoma in eyes with and without high axial myopia. DESIGN: Cross-sectional study METHODS: 368 glaucoma and 411 healthy eyes with no axial myopia, 393 glaucoma and 271 healthy eyes with mild axial myopia and 124 glaucoma and 85 healthy eyes with high axial myopia were included. Global and sectoral peripapillary retinal nerve fiber layer thickness (pRNFLT), Bruch's membrane opening minimum rim width (BMO-MRW), ganglion cell inner plexiform layer thickness (GCIPLT), and macula RNFLT (mRNFLT) were compared and the diagnostic accuracy for glaucoma detection was evaluated using adjusted area under the receiver operating characteristic curve (AUC). RESULTS: Diagnostic accuracy for ONH and macula parameters to detect glaucoma was generally high and differed by myopia group. For ONH parameters the diagnostic accuracy was highest for global (AUC=0.95) and inferotemporal (AUC=0.91) pRNFLT for high myopes and global BMO-MRW for non-myopes (AUC=1.0) and mild myopes (AUC=0.97). For macula parameters, the diagnostic accuracy was higher in high myopes with 6 of the 11 GCIPLT global/sectors having adjusted AUCs > 0.90 compared to non-high myopes with no AUCs > 0.90. In all myopia groups, mRNFLT had lower AUCs than GCIPLT. CONCLUSIONS: The diagnostic accuracy for pRNFL and GCIPL was high for high axial myopic eyes and shows promise for glaucoma detection in high myopes. Further analysis is needed to determine whether the high diagnostic accuracy can be confirmed in other populations.

Optic Disc Microvasculature Dropout in Pre-perimetric Glaucoma.

PURPOSE: To investigate factors associated with optic disc microvasculature dropout (MvD-D) in pre-perimetric primary open-angle glaucoma (PPG) patients. METHODS: 139 eyes of PPG patients were categorized according to the presence of MvD-D with optical coherence tomography angiography (OCTA). Factors including visual field (VF) mean deviation (MD), retinal nerve fiber layer (RNFL) thickness, focal lamina cribrosa (LC) defect, optic disc hemorrhage (DH), and parapapillary deep-layer microvasculature dropout (MvD-P) were compared between eyes with and without MvD-D. RESULTS: MvD-D was observed in 69 PPG eyes (49.6%). Compared with eyes without MvD-D, the ones with MvD-D had a significantly thinner RNFL in all areas except the nasal sector, worse VF MD, and a focal LC defect and MvD-P (P<0.05): male gender also was more highly prevalent. A considerable number of eyes with MvD-D lacked focal LC defect (62.3% (43/69)) or MvD-P (71.0% (49/69)), while a few eyes without MvD-D had focal LC defect (10.0% (7/70)) or MvD-P (2.9% (2/70)). In a multivariable logistic regression analysis, male gender (odds ratio [OR], 3.96; P<0.001), worse VF MD (OR, 1.44; P=0.019), thinner global RNFL (OR, 1.13; P<0.001), higher prevalence of focal LC defect (OR, 3.71; P=0.014) and MvD-P (OR, 7.85; P<0.001) were significantly associated with MvD-D. CONCLUSIONS: MvD-D was related to worse disease severity in PPG patients, and often was not accompanied by focal LC defect or MvD-P. This suggests that impaired optic disc circulation can be an early sign of glaucoma without noticeable changes in functional or structural features (i.e., VF, focal LC defect, MvD-P).

OCT Optic Nerve Head Morphology in Myopia IV: Neural Canal Scleral Flange Remodeling in Highly Myopic Eyes.

PURPOSE: To compare the prevalence, location and magnitude of optic nerve head (ONH) OCT-detected, exposed neural canal (ENC), externally oblique choroidal border tissue (EOCBT) and exposed scleral flange (ESF) regions in 122 highly myopic (Hi-Myo) versus 362 nonhighly myopic healthy (Non-Hi-Myo-Healthy) eyes. DESIGN: Cross-sectional study. METHODS: After OCT radial B-scan, ONH imaging, Bruch's membrane opening (BMO), the anterior scleral canal opening (ASCO), and the scleral flange opening (SFO) were manually segmented in each B-scan and projected to BMO reference plane. The direction and magnitude of BMO/ASCO offset and BMO/SFO offset as well as the location and magnitude of ENC, EOCBT and ESF regions, perineural canal (pNC) retinal nerve fiber layer thickness (RNFLT) and pNC choroidal thickness (CT) were calculated within 30° sectors relative to the Foveal-BMO (FoBMO) axis. Hi-ESF eyes were defined to be those with an ESF region ≥100 µms in at least 1 sector. RESULTS: Hi-Myo eyes more frequently demonstrated Hi-ESF regions (87/122) than Non-Hi-myo-Healthy eyes (73/362) and contained significantly larger ENC, EOCBT, and ESF regions (P < .001) which were greatest in magnitude and prevalence within the inferior-temporal FoBMO sectors where Hi-Myo pNC-RNFLT and pNCCT were thinnest. BMO/ASCO offset and the BMO/SFO offset were both significantly increased (P < .001) in the Hi-Myo eyes, with the latter demonstrating a greater increase. CONCLUSIONS: ENC region tissue remodeling that includes the scleral flange is enhanced in Hi-Myo compared to Non-Hi-Myo-Healthy eyes. Longitudinal studies are necessary to determine whether the presence of an ENC region influences ONH susceptibility to aging and/or glaucoma.

Effects of Deep Optic Nerve Head Structures on Bruch's Membrane Opening- Minimum Rim Width and Peripapillary Retinal Nerve Fiber Layer.

PURPOSE: To explore the effects of deep optic nerve head (ONH) structures on Bruch's membrane opening (BMO)-minimum rim width (MRW) and peripapillary retinal nerve fiber layer thickness (pRNFLT) in healthy eyes. DESIGN: Prospective cross-sectional study. METHODS: Two hundred five healthy eyes of 141 subjects (mean ± standard deviation of age and axial length (AXL): 46.9 ± 10.0 years and 24.79 ± 1.15 mm) were enrolled. Best fit multivariable linear mixed models identified factors associated with BMO-MRW and pRNFLT. Explanatory variables included age, gender, AXL, BMO and anterior scleral canal opening (ASCO) area and ovality, magnitude of BMO and ASCO shift, peripapillary choroidal thickness, lamina cribrosa (LC) parameters, prelaminar thickness, and peripapillary scleral (PPS) angle. RESULTS: Thinner BMO-MRW was associated with older age, smaller ASCO/BMO offset magnitude, larger BMO area, thinner prelaminar thickness, deeper LC, and thinner pRNFLT (P = .011, <.001, .004, <.001, <.001, <.001 respectively). Thinner pRNFLT was associated with shorter AXL, smaller ASCO area, a more posteriorly bowed PPS, shallower LC and thinner BMO-MRW. (P = .030, .002, .035, .012, <.001 respectively) CONCLUSIONS: BMO-MRW and pRNFLT were influenced by several deep ONH structures such as BMO and ASCO position shift, BMO or ASCO area, prelaminar thickness, PPS bowing and LC depth in addition to patient characteristics such as age and AXL. The degree and/or direction of associations varied between deep ONH structures and BMO-MRW or pRNFLT. Despite both BMO-MRW and pRNFLT being surrogate parameters for RGC loss, a complex relationship with ONH deep-layer morphology was indicated.

Proactive Decision Support for Glaucoma Treatment: Predicting Surgical Interventions with Clinically Available Data.

A longitudinal ophthalmic dataset was used to investigate multi-modal machine learning (ML) models incorporating patient demographics and history, clinical measurements, optical coherence tomography (OCT), and visual field (VF) testing in predicting glaucoma surgical interventions. The cohort included 369 patients who underwent glaucoma surgery and 592 patients who did not undergo surgery. The data types used for prediction included patient demographics, history of systemic conditions, medication history, ophthalmic measurements, 24-2 VF results, and thickness measurements from OCT imaging. The ML models were trained to predict surgical interventions and evaluated on independent data collected at a separate study site. The models were evaluated based on their ability to predict surgeries at varying lengths of time prior to surgical intervention. The highest performing predictions achieved an AUC of 0.93, 0.92, and 0.93 in predicting surgical intervention at 1 year, 2 years, and 3 years, respectively. The models were also able to achieve high sensitivity (0.89, 0.77, 0.86 at 1, 2, and 3 years, respectively) and specificity (0.85, 0.90, and 0.91 at 1, 2, and 3 years, respectively) at an 0.80 level of precision. The multi-modal models trained on a combination of data types predicted surgical interventions with high accuracy up to three years prior to surgery and could provide an important tool to predict the need for glaucoma intervention.

Deep Learning Identifies High-Quality Fundus Photographs and Increases Accuracy in Automated Primary Open Angle Glaucoma Detection.

Purpose: To develop and evaluate a deep learning (DL) model to assess fundus photograph quality, and quantitatively measure its impact on automated POAG detection in independent study populations. Methods: Image quality ground truth was determined by manual review of 2815 fundus photographs of healthy and POAG eyes from the Diagnostic Innovations in Glaucoma Study and African Descent and Glaucoma Evaluation Study (DIGS/ADAGES), as well as 11,350 from the Ocular Hypertension Treatment Study (OHTS). Human experts assessed a photograph as high quality if of sufficient quality to determine POAG status and poor quality if not. A DL quality model was trained on photographs from DIGS/ADAGES and tested on OHTS. The effect of DL quality assessment on DL POAG detection was measured using area under the receiver operating characteristic (AUROC). Results: The DL quality model yielded an AUROC of 0.97 for differentiating between high- and low-quality photographs; qualitative human review affirmed high model performance. Diagnostic accuracy of the DL POAG model was significantly greater (P < 0.001) in good (AUROC, 0.87; 95% CI, 0.80-0.92) compared with poor quality photographs (AUROC, 0.77; 95% CI, 0.67-0.88). Conclusions: The DL quality model was able to accurately assess fundus photograph quality. Using automated quality assessment to filter out low-quality photographs increased the accuracy of a DL POAG detection model. Translational Relevance: Incorporating DL quality assessment into automated review of fundus photographs can help to decrease the burden of manual review and improve accuracy for automated DL POAG detection.

Optic neuropathy in high myopia: Glaucoma or high myopia or both?

Due to the increasing prevalence of high myopia around the world, structural and functional damages to the optic nerve in high myopia has recently attracted much attention. Evidence has shown that high myopia is related to the development of glaucomatous or glaucoma-like optic neuropathy, and that both have many common features. These similarities often pose a diagnostic challenge that will affect the future management of glaucoma suspects in high myopia. In this review, we summarize similarities and differences in optic neuropathy arising from non-pathologic high myopia and glaucoma by considering their respective structural and functional characteristics on fundus photography, optical coherence tomography scanning, and visual field tests. These features may also help to distinguish the underlying mechanisms of the optic neuropathies and to determine management strategies for patients with high myopia and glaucoma.

Time to Glaucoma Progression Detection by Optical Coherence Tomography in Individuals of African and European Descents.

PURPOSE: To examine the time to detectable retinal nerve fiber layer thickness (RNFLT) progression by optical coherence tomography (OCT) among glaucoma patients of African descent (AD) and European descent (ED). DESIGN: Retrospective cohort study. METHODS: AD and ED glaucoma eyes from the Diagnostic Innovations in Glaucoma Study (DIGS)/African Descent and Glaucoma Evaluation Study (ADAGES) with ≥2 years/4 visits of optic nerve head RNFLT measurements were included after homogenization on age, diagnosis, and baseline visual field (VF) measurement. RNFLT variability estimates based on linear mixed-effects models were used to simulate longitudinal RNFLT data for both races. Times to trend-based RNFLT progression detection were calculated under standardized scenarios (same RNFLT baseline/thinning rates for both races) and real-world scenarios (AD and ED cohort-specific RNFLT baseline/thinning rates). RESULTS: We included 332 and 542 eyes (216 and 317 participants) of AD and ED, respectively. In standardized scenarios, the time to detect RNFLT progression appeared to be similar (difference, <0.2 years) for AD and ED across different assumed RNFLT thinning rates/baseline. In real-world scenarios, compared to ED, AD had a faster RNFLT thinning rate (-0.8 vs -0.6 µm/y) and thicker baseline RNFLT (84.6 vs 81.8 µm). With a faster thinning rate, the mean (SD) time to progression detection was shorter in AD (4.8 [2.0] vs ED: 5.4 [2.4] years), and the 5-year progression rate appeared to be higher (AD: 59% vs ED: 47%). CONCLUSIONS: Time to progression detection was similar for both races when assuming identical RNFLT baseline/thinning rates, and shorter in AD eyes under real-world simulation when AD had faster RNFLT thinning. In contrast to prior results on VF, which detected progression later in AD eyes than in ED eyes, OCT may detect progression more consistently across these races.

Detection and agreement of event-based OCT and OCTA analysis for glaucoma progression.

OBJECTIVE: To examine event-based glaucoma progression using optical coherence tomography (OCT) and OCT angiography (OCTA). METHODS: In this retrospective study, glaucoma eyes with ≥2-year and 4-visits of OCT/OCTA imaging were included. Peripapillary capillary density (CD) and retinal nerve fibre layer thickness (RNFL) were obtained from 4.5 mm × 4.5 mm optic nerve head (ONH) scans. Event-based OCT/OCTA progression was defined as decreases in ONH measurements exceeding test-retest variability on ≥2 consecutive visits. Visual field (VF) progression was defined as significant VF mean deviation worsening rates on ≥2 consecutive visits. Inter-instrument agreement on progression detection was compared using kappa(κ) statistics. RESULTS: Among 147 eyes (89 participants), OCTA and OCT identified 33(22%) and 25(17%) progressors, respectively. They showed slight agreement (κ = 0.06), with 7(5%) eyes categorized as progressors by both. When incorporating both instruments, the rate of progressors identified increased to 34%. Similar agreement was observed in diagnosis- and severity-stratified analyses (κ < 0.10). Compared to progressors identified only by OCT, progressors identified only by OCTA tended to have thinner baseline RNFL and worse baseline VF. VF progression was identified in 11(7%) eyes. OCT and VF showed fair agreement (κ = 0.26), with 6(4%) eyes categorized as progressors by both. OCTA and VF showed slight agreement (κ = 0.08), with 4(3%) eyes categorized as progressors by both. CONCLUSIONS: OCT and OCTA showed limited agreement on event-based progression detection, with OCT showing better agreement with VF. Both OCT and OCTA detected more progressors than VF. OCT and OCTA may provide valuable, yet different and complementary, information about glaucoma progression.

Racial Differences in the Diagnostic Accuracy of OCT Angiography Macular Vessel Density for Glaucoma.

PURPOSE: To evaluate and compare the diagnostic accuracy of macular vessel density (VD) measured by OCT angiography (OCTA) in individuals of African descent (AD) and European descent (ED) with open-angle glaucoma. DESIGN: Observational, cross sectional study. PARTICIPANTS: A total of 176 eyes of 123 patients with glaucoma and 140 eyes of 88 healthy participants from the Diagnostic Innovations in Glaucoma Study. METHODS: Whole-image ganglion cell complex (wiGCC) thickness and macular VD (parafoveal VD and perifoveal VD) were obtained from 6 × 6 macula scans. Area under the receiver operating characteristic (AUROC) curves were used to evaluate the diagnostic accuracy of macular VD and ganglion cell complex (GCC) thickness in AD and ED participants after adjusting for confounders such as age, visual field mean deviation (VF MD), signal strength index, axial length, self-reported hypertension and diabetes. MAIN OUTCOME MEASURES: Macular VD and wiGCC measurements. RESULTS: Parafoveal and perifoveal VD were significantly lower in ED than AD patients with glaucoma. Parafoveal and perifoveal VD performed significantly worse in AD participants compared with ED participants for detection of glaucoma (adjusted AUROC, 0.75 [95% confidence interval (CI), 0.62, 0.87], 0.85 [95% CI, 0.79, 0.90], P = 0.035; and 0.82 [95% CI, 0.70, 0.92], 0.91 [95% CI, 0.87, 0.94], respectively; P = 0.020). In contrast to VD, diagnostic accuracy of GCC thickness was similar in AD and ED individuals (adjusted AUROC, 0.89 [95% CI, 0.79, 0.96], 0.92 [95% CI, 0.86, 0.96], respectively; P = 0.313). The diagnostic accuracies of both macular VD and GCC thickness for differentiating between glaucoma and healthy eyes increased with increasing VF MD in both AD and ED participants. CONCLUSIONS: Diagnostic performance of OCTA macular VD, but not GCC thickness, for glaucoma detection varies by race. Moreover, macular VD parameters had lower accuracy for detecting glaucoma in AD individuals than in ED individuals. The diagnostic performance of macular VD is race-dependent, and, therefore, race should be taken into consideration when interpreting macular OCTA results. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Central visual field damage in glaucoma eyes with choroidal microvasculature dropout with and without high axial myopia.

PURPOSE: To characterise the relationship between a deep-layer microvasculature dropout (MvD) and central visual field (VF) damage in primary open-angle glaucoma (POAG) patients with and without high axial myopia. DESIGN: Cross-sectional study. METHODS: Seventy-one eyes (49 patients) with high axial myopia and POAG and 125 non-highly myopic POAG eyes (97 patients) were enrolled. Presence, area and angular circumference of juxtapapillary MvD were evaluated on optical coherence tomography angiography B-scans and en-face choroidal images. RESULTS: Juxtapapillary MvD was detected more often in the highly myopic POAG eyes (43 eyes, 86%) than in the non-highly myopic eyes (73 eyes, 61.9%; p=0.002). In eyes with MvD, MvD area and angular circumference (95% CI) were significantly larger in the highly myopic eyes compared with the non-highly myopic eyes (area: (0.69 (0.40, 0.98) mm2 vs 0.31 (0.19, 0.42) mm2, p=0.011) and (angular circumference: 84.3 (62.9, 105.8) vs 74.5 (58.3, 90.9) degrees, p<0.001), respectively. 24-2 VF mean deviation (MD) was significantly worse in eyes with MvD compared with eyes without MvD in both groups (p<0.001). After adjusting for 24-2 MD VF, central VF defects were more frequently found in eyes with MvD compared with eyes without MvD (82.7% vs 60.9%, p<0.001). In multivariable analysis, higher intraocular pressure, worse 24-2 VF MD, longer axial length and greater MvD area and angular circumference were associated with worse 10-2 VF MD. CONCLUSIONS: MvD was more prevalent and larger in POAG eyes with high myopia than in non-highly myopic POAG eyes. In both groups, eyes with MvD showed worse glaucoma severity and more central VF defects.

Association of Bergmeister Papilla and Deep Optic Nerve Head Structures With Prelaminar Schisis of Normal and Glaucomatous Eyes.

PURPOSE: To investigate factors associated with the severity of prelaminar schisis (PLS) in heathy subjects and glaucoma patients. DESIGN: Prospective cross-sectional study. METHODS: A total of 217 eyes of 217 subjects (110 normal eyes and 107 open angle glaucoma eyes) were studied. Frequency and severity of PLS were compared between normal and glaucomatous eyes. Multivariate logistic models were used to assess factors associated with the severity of PLS. Factors considered were age, axial length, glaucomatous damage indices, Bruch membrane opening (BMO) and anterior scleral canal opening parameters, tractional forces (posterior vitreous staging and presence of Bergmeister papilla), circumpapillary choroidal thickness, lamina cribrosa (LC) parameters, and peripapillary scleral (PPS) angle. RESULTS: The frequency of PLS was 70.9% in normal eyes and 72.0% in glaucomatous eyes. There was no difference in frequency and severity between the groups. The presence of Bergmeister papilla was the strongest predictor of a more severe PLS in both normal and glaucomatous eyes (odds ratio [OR] + 9.78, 12.5; both P < .001). A larger PPS angle in normal eyes (OR = 1.19; P = .003) and a larger BMO area and a deeper LC depth in glaucomatous eyes (OR = 1.08, 1.05; both P = .038) were associated with severity of PLS. CONCLUSIONS: The severity of PLS was strongly associated with the presence of Bergmeister papilla, suggesting a traction-related phenomenon. Correlation of PLS severity with larger BMO area and deeper LC depth, which are optic nerve head structures associated with glaucoma, suggested its possible relationship with glaucomatous damage.

One-Vote Veto: Semi-Supervised Learning for Low-Shot Glaucoma Diagnosis.

Convolutional neural networks (CNNs) are a promising technique for automated glaucoma diagnosis from images of the fundus, and these images are routinely acquired as part of an ophthalmic exam. Nevertheless, CNNs typically require a large amount of well-labeled data for training, which may not be available in many biomedical image classification applications, especially when diseases are rare and where labeling by experts is costly. This article makes two contributions to address this issue: 1) It extends the conventional Siamese network and introduces a training method for low-shot learning when labeled data are limited and imbalanced, and 2) it introduces a novel semi-supervised learning strategy that uses additional unlabeled training data to achieve greater accuracy. Our proposed multi-task Siamese network (MTSN) can employ any backbone CNN, and we demonstrate with four backbone CNNs that its accuracy with limited training data approaches the accuracy of backbone CNNs trained with a dataset that is 50 times larger. We also introduce One-Vote Veto (OVV) self-training, a semi-supervised learning strategy that is designed specifically for MTSNs. By taking both self-predictions and contrastive predictions of the unlabeled training data into account, OVV self-training provides additional pseudo labels for fine-tuning a pre-trained MTSN. Using a large (imbalanced) dataset with 66,715 fundus photographs acquired over 15 years, extensive experimental results demonstrate the effectiveness of low-shot learning with MTSN and semi-supervised learning with OVV self-training. Three additional, smaller clinical datasets of fundus images acquired under different conditions (cameras, instruments, locations, populations) are used to demonstrate the generalizability of the proposed methods.

Temporal Optic Disc Microvasculature Dropout in Glaucoma.

Purpose: To assess the clinical characteristics of focal temporal optic disc microvasculature dropout (MvD-D) in primary open-angle glaucoma (POAG) patients. Methods: One hundred and eighty-seven eyes of 187 POAG patients having MvD-D on Swept-Source optical coherence tomography angiography (SS-OCTA) were enrolled. Three groups were categorized according to the presence of temporal MvD-D within the upper and lower 45° of the fovea-Bruch's membrane (BM) opening axis: focal temporal MvD-D (Group 1, isolated focal temporal MvD-D; 44 eyes), supero/inferotemporal MvD-D (Group 2, MvD-D only in superotemporal or inferotemporal sector; 78 eyes), and diffuse temporal MvD-D (Group 3, MvD-D spanning ≥ 2 consecutive sectors, at least one of which being temporal sector; 65 eyes). Results: Group 1 had a significantly longer axial length and ß-zone parapapillary atrophy without BM. There also was a larger horizontal tilt angle and ovality index than the other two groups (P < 0.001). Group 1 had a significantly thinner retinal nerve fiber layer (RNFL) in the temporal sector than did Group 2 (P < 0.001), despite similar thicknesses in all other areas (P > 0.05). Group 3 had significantly worse visual field mean deviation and thinner RNFL than the other two groups in all areas other than the nasal, temporal, and superotemporal sectors (P < 0.05). Conclusions: Focal temporal MvD-D detected by SS-OCTA was associated with a longer axial length and related subsequent morphological changes of the optic disc and parapapillary area. This suggests that stretching of the optic disc consequent on axial elongation may lead to absence of temporal optic disc microvasculature.

Review of Visualization Approaches in Deep Learning Models of Glaucoma.

Glaucoma is a major cause of irreversible blindness worldwide. As glaucoma often presents without symptoms, early detection and intervention are important in delaying progression. Deep learning (DL) has emerged as a rapidly advancing tool to help achieve these objectives. In this narrative review, data types and visualization approaches for presenting model predictions, including models based on tabular data, functional data, and/or structural data, are summarized, and the importance of data source diversity for improving the utility and generalizability of DL models is explored. Examples of innovative approaches to understanding predictions of artificial intelligence (AI) models and alignment with clinicians are provided. In addition, methods to enhance the interpretability of clinical features from tabular data used to train AI models are investigated. Examples of published DL models that include interfaces to facilitate end-user engagement and minimize cognitive and time burdens are highlighted. The stages of integrating AI models into existing clinical workflows are reviewed, and challenges are discussed. Reviewing these approaches may help inform the generation of user-friendly interfaces that are successfully integrated into clinical information systems. This review details key principles regarding visualization approaches in DL models of glaucoma. The articles reviewed here focused on usability, explainability, and promotion of clinician trust to encourage wider adoption for clinical use. These studies demonstrate important progress in addressing visualization and explainability issues required for successful real-world implementation of DL models in glaucoma.

Multimodal Deep Learning Classifier for Primary Open Angle Glaucoma Diagnosis Using Wide-Field Optic Nerve Head Cube Scans in Eyes With and Without High Myopia.

PRCIS: An optical coherence tomography (OCT)-based multimodal deep learning (DL) classification model, including texture information, is introduced that outperforms single-modal models and multimodal models without texture information for glaucoma diagnosis in eyes with and without high myopia. BACKGROUND/AIMS: To evaluate the diagnostic accuracy of a multimodal DL classifier using wide OCT optic nerve head cube scans in eyes with and without axial high myopia. MATERIALS AND METHODS: Three hundred seventy-one primary open angle glaucoma (POAG) eyes and 86 healthy eyes, all without axial high myopia [axial length (AL) ≤ 26 mm] and 92 POAG eyes and 44 healthy eyes, all with axial high myopia (AL > 26 mm) were included. The multimodal DL classifier combined features of 3 individual VGG-16 models: (1) texture-based en face image, (2) retinal nerve fiber layer (RNFL) thickness map image, and (3) confocal scanning laser ophthalmoscope (cSLO) image. Age, AL, and disc area adjusted area under the receiver operating curves were used to compare model accuracy. RESULTS: Adjusted area under the receiver operating curve for the multimodal DL model was 0.91 (95% CI = 0.87, 0.95). This value was significantly higher than the values of individual models [0.83 (0.79, 0.86) for texture-based en face image; 0.84 (0.81, 0.87) for RNFL thickness map; and 0.68 (0.61, 0.74) for cSLO image; all P ≤ 0.05]. Using only highly myopic eyes, the multimodal DL model showed significantly higher diagnostic accuracy [0.89 (0.86, 0.92)] compared with texture en face image [0.83 (0.78, 0.85)], RNFL [0.85 (0.81, 0.86)] and cSLO image models [0.69 (0.63, 0.76)] (all P ≤ 0.05). CONCLUSIONS: Combining OCT-based RNFL thickness maps with texture-based en face images showed a better ability to discriminate between healthy and POAG than thickness maps alone, particularly in high axial myopic eyes.

High Myopia Normative Database of Peripapillary Retinal Nerve Fiber Layer Thickness to Detect Myopic Glaucoma in a Chinese Population.

PURPOSE: To develop and validate the performance of a high myopia (HM)-specific normative database of peripapillary retinal nerve fiber layer (pRNFL) thickness in differentiating HM from highly myopic glaucoma (HMG). DESIGN: Cross-sectional multicenter study. PARTICIPANTS: A total of 1367 Chinese participants (2325 eyes) with nonpathologic HM or HMG were included from 4 centers. After quality control, 1108 eyes from 694 participants with HM were included in the normative database; 459 eyes from 408 participants (323 eyes with HM and 136 eyes with HMG) and 322 eyes from 197 participants (131 eyes with HM and 191 eyes with HMG) were included in the internal and external validation sets, respectively. Only HMG eyes with an intraocular pressure > 21 mmHg were included. METHODS: The pRNFL thickness was measured with swept-source (SS) OCT. Four strategies of pRNFL-specified values were examined, including global and quadrantic pRNFL thickness below the lowest fifth or the lowest first percentile of the normative database. MAIN OUTCOMES MEASURES: The accuracy, sensitivity, and specificity of the HM-specific normative database for detecting HMG. RESULTS: Setting the fifth percentile of the global pRNFL thickness as the threshold, using the HM-specific normative database, we achieved an accuracy of 0.93 (95% confidence interval [CI], 0.90-0.95) and 0.85 (95% CI, 0.81-0.89), and, using the first percentile as the threshold, we acheived an accuracy of 0.85 (95% CI, 0.81-0.88) and 0.70 (95% CI, 0.65-0.75) in detecting HMG in the internal and external validation sets, respectively. The fifth percentile of the global pRNFL thickness achieved high sensitivities of 0.75 (95% CI, 0.67-0.82) and 0.75 (95% CI, 0.68-0.81) and specificities of 1.00 (95% CI, 0.99-1.00) and 1.00 (95% CI, 0.97-1.00) in the internal and external validation datasets, respectively. Compared with the built-in database of the OCT device, the HM-specific normative database showed a higher sensitivity and specificity than the corresponding pRNFL thickness below the fifth or first percentile (P < 0.001 for all). CONCLUSIONS: The HM-specific normative database is more capable of detecting HMG eyes than the SS OCT built-in database, which may be an effective tool for differential diagnosis between HMG and HM. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.