Assessing the Efficacy of Synthetic Optic Disc Images for Detecting Glaucomatous Optic Neuropathy Using Deep Learning.

Purpose: Deep learning architectures can automatically learn complex features and patterns associated with glaucomatous optic neuropathy (GON). However, developing robust algorithms requires a large number of data sets. We sought to train an adversarial model for generating high-quality optic disc images from a large, diverse data set and then assessed the performance of models on generated synthetic images for detecting GON. Methods: A total of 17,060 (6874 glaucomatous and 10,186 healthy) fundus images were used to train deep convolutional generative adversarial networks (DCGANs) for synthesizing disc images for both classes. We then trained two models to detect GON, one solely on these synthetic images and another on a mixed data set (synthetic and real clinical images). Both the models were externally validated on a data set not used for training. The multiple classification metrics were evaluated with 95% confidence intervals. Models' decision-making processes were assessed using gradient-weighted class activation mapping (Grad-CAM) techniques. Results: Following receiver operating characteristic curve analysis, an optimal cup-to-disc ratio threshold for detecting GON from the training data was found to be 0.619. DCGANs generated high-quality synthetic disc images for healthy and glaucomatous eyes. When trained on a mixed data set, the model's area under the receiver operating characteristic curve attained 99.85% on internal validation and 86.45% on external validation. Grad-CAM saliency maps were primarily centered on the optic nerve head, indicating a more precise and clinically relevant attention area of the fundus image. Conclusions: Although our model performed well on synthetic data, training on a mixed data set demonstrated better performance and generalization. Integrating synthetic and real clinical images can optimize the performance of a deep learning model in glaucoma detection. Translational Relevance: Optimizing deep learning models for glaucoma detection through integrating DCGAN-generated synthetic and real-world clinical data can be improved and generalized in clinical practice.

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.

Assessing the efficacy of 2D and 3D CNN algorithms in OCT-based glaucoma detection.

Glaucoma is a progressive neurodegenerative disease characterized by the gradual degeneration of retinal ganglion cells, leading to irreversible blindness worldwide. Therefore, timely and accurate diagnosis of glaucoma is crucial, enabling early intervention and facilitating effective disease management to mitigate further vision deterioration. The advent of optical coherence tomography (OCT) has marked a transformative era in ophthalmology, offering detailed visualization of the macula and optic nerve head (ONH) regions. In recent years, both 2D and 3D convolutional neural network (CNN) algorithms have been applied to OCT image analysis. While 2D CNNs rely on post-prediction aggregation of all B-scans within OCT volumes, 3D CNNs allow for direct glaucoma prediction from the OCT data. However, in the absence of extensively pre-trained 3D models, the comparative efficacy of 2D and 3D-CNN algorithms in detecting glaucoma from volumetric OCT images remains unclear. Therefore, this study explores the efficacy of glaucoma detection through volumetric OCT images using select state-of-the-art (SOTA) 2D-CNN models, 3D adaptations of these 2D-CNN models with specific weight transfer techniques, and a custom 5-layer 3D-CNN-Encoder algorithm. The performance across two distinct datasets is evaluated, each focusing on the macula and the ONH, to provide a comprehensive understanding of the models' capabilities in identifying glaucoma. Our findings demonstrate that the 2D-CNN algorithm consistently provided robust results compared to their 3D counterparts tested in this study for glaucoma detection, achieving AUC values of 0.960 and 0.943 for the macular and ONH OCT test images, respectively. Given the scarcity of pre-trained 3D models trained on extensive datasets, this comparative analysis underscores the overall utility of 2D and 3D-CNN algorithms in advancing glaucoma diagnostic systems in ophthalmology and highlights the potential of 2D algorithms for volumetric OCT image-based glaucoma detection.

PallorMetrics: Software for Automatically Quantifying Optic Disc Pallor in Fundus Photographs, and Associations With Peripapillary RNFL Thickness.

Purpose: We sough to develop an automatic method of quantifying optic disc pallor in fundus photographs and determine associations with peripapillary retinal nerve fiber layer (pRNFL) thickness. Methods: We used deep learning to segment the optic disc, fovea, and vessels in fundus photographs, and measured pallor. We assessed the relationship between pallor and pRNFL thickness derived from optical coherence tomography scans in 118 participants. Separately, we used images diagnosed by clinical inspection as pale (n = 45) and assessed how measurements compared with healthy controls (n = 46). We also developed automatic rejection thresholds and tested the software for robustness to camera type, image format, and resolution. Results: We developed software that automatically quantified disc pallor across several zones in fundus photographs. Pallor was associated with pRNFL thickness globally (ß = -9.81; standard error [SE] = 3.16; P < 0.05), in the temporal inferior zone (ß = -29.78; SE = 8.32; P < 0.01), with the nasal/temporal ratio (ß = 0.88; SE = 0.34; P < 0.05), and in the whole disc (ß = -8.22; SE = 2.92; P < 0.05). Furthermore, pallor was significantly higher in the patient group. Last, we demonstrate the analysis to be robust to camera type, image format, and resolution. Conclusions: We developed software that automatically locates and quantifies disc pallor in fundus photographs and found associations between pallor measurements and pRNFL thickness. Translational Relevance: We think our method will be useful for the identification, monitoring, and progression of diseases characterized by disc pallor and optic atrophy, including glaucoma, compression, and potentially in neurodegenerative disorders.

Fundus Tessellation and Parapapillary Atrophy, as Ocular Characteristics of Spontaneously High Myopia in Macaques: The Non-Human Primates Eye Study.

Purpose: This study aimed to evaluate the ocular characteristics associated with spontaneously high myopia in adult nonhuman primates (NHPs). Methods: A total of 537 eyes of 277 macaques with an average age of 18.53 ± 3.01 years (range = 5-26 years), raised in a controlled environment, were included. We measured ocular parameters, including spherical equivalent (SE), axial length (AXL), and intraocular pressure. The 45-degree fundus images centered on the macula and the disc assessed the fundus tessellation and parapapillary atrophy (PPA). Additionally, optical coherence tomography (OCT) was used to measure the thickness of the retinal nerve fiber layer (RNFL). Results: The mean SE was -1.58 ± 3.71 diopters (D). The mean AXL was 18.76 ± 0.86 mm. The prevalence rate of high myopia was 17.7%. As myopia aggravated, the AXL increased (r = -0.498, P < 0.001). Compared with non-high myopia, highly myopic eyes had a greater AXL (P < 0.001), less RNFL thickness (P = 0.004), a higher incidence of PPA (P < 0.001), and elevated grades of fundus tessellation (P < 0.001). The binary logistic regression was performed, which showed PPA (odds ratio [OR] = 4.924, 95% confidence interval [CI] = 2.375-10.207, P < 0.001) and higher grades of fundus tessellation (OR = 1.865, 95% CI = 1.474-2.361, P < 0.001) were independent risk characteristics for high myopia. Conclusions: In NHPs, a higher grade of fundus tessellation and PPA were significant biomarkers of high myopia. Translational Relevance: The study demonstrates adult NHPs raised in conditioned rooms have a similar prevalence and highly consistent fundus changes with human beings, which strengthens the foundation for utilizing macaques as an animal model in high myopic studies.

Evaluation of optical coherence tomography findings in patients with multiple sclerosis and glaucoma.

PURPOSE: Glaucoma and multiple sclerosis (MS) can cause optic disc pathology and, in this way, affect optical coherence tomography (OCT) data. In this context, the objective of this study is to investigate the changes in the mean, quadrant, and sector data measured by OCT in glaucoma and MS patients. METHODS: The sample of this prospective cohort study consisted of 42 MS patients (84 eyes), 34 Primary open-angle glaucomas patients (67 eyes), and 24 healthy control subjects (48 eyes). The MS group was divided into two groups according to the presence of a history of optic neuritis. Accordingly, those with a history of optic neuritis were included in the MS ON group, and those without a history of optic neuritis were included in the MS NON group. The differences between these groups in the mean, quadrant, and sector data related to the retinal nerve fiber layer (RNFL) and ganglion cell complex (GCC) were evaluated. RESULTS: Superior nasal (SN), superior temporal (ST), inferior nasal (IN), and superior quadrant (SUP) values were significantly lower in the glaucoma group than in the MS group (p < 0.05). The mean superior GCC (GCC SUP) value was significantly lower in the MS ON group than in the glaucoma group (p < 0.05). On the other hand, SN, ST, inferior temporal (IT), IN, average RNFL (AVE RNFL), semi-average superior RNFL (SUP AVE RNFL), semi-average inferior RNFL (INF AVE RNFL), SUP, and inferior quadrant RNFL (INF) values were significantly lower in the glaucoma group than in the MS NON group (p < 0.05). CONCLUSION: RNFL and GCC parameters get thinner in MS and glaucoma patients. While the inferior and superior RNFL quadrants are more frequently affected in glaucoma patients, the affected quadrants vary according to the presence of a history of optic neuritis in MS patients. It is noteworthy that the GCC superior quadrant was thin in MS ON patients. The findings of this study indicate that OCT data may be valuable in the differential diagnosis of glaucoma and MS.

Modernizing the evaluation of infantile nystagmus: the role of handheld optical coherence tomography.

BACKGROUND: Infantile nystagmus syndrome can be associated with an afferent problem (anterior or posterior segment) or constitute an isolated idiopathic disorder. With a normal ophthalmic examination, current guidelines recommend electroretinography (ERG) rather than magnetic resonance (MRI) for preliminary workup. Given the limited use of optical coherence tomography (OCT) in preverbal children, the purpose of this study was to evaluate the role of handheld OCT (HH-OCT) in the initial diagnostic evaluation of infantile nystagmus. METHODS: In this cross-sectional case series, the medical records of all children with infantile nystagmus and HH-OCT imaging at the Duke Eye Center from August 2016 to July 2021 were retrospectively reviewed. Children with anterior segment disorders or obvious retina/optic nerve structural pathology, bilateral ophthalmoplegia, or Down syndrome were excluded. Two masked pediatric ophthalmologists graded HH-OCT images for optic nerve head and macular abnormalities. A neuro-ophthalmologist reviewed clinical findings of each patient's presenting visit and recommended appropriate testing (MRI vs ERG), initially without, and again with HH-OCT image review. RESULTS: A total of 39 cases were included, with mean presenting age of 1.3 years. Final diagnoses included retinal or foveal abnormalities (7), optic nerve pathology (13), idiopathic (10), or unknown (9). HH-OCT findings included optic nerve hypoplasia (1), optic nerve elevation (3), persistence of the inner layers at the fovea (9), thin ganglion cell layer (8), ellipsoid zone abnormality (3), and thin choroid (1). HH-OCT findings altered initial clinical-only management in 16 cases (41%), including avoiding MRI (5) and ERG (10) testing. CONCLUSIONS: Our results suggest that HH-OCT has the potential to augment and streamline the evaluation of infantile nystagmus.

Longitudinal changes in optic disc cupping from the baseline in chiasmal lesion optic neuropathy and glaucoma.

We aimed to investigate the changes in cupping in chiasmal lesion optic neuropathy (chON) compared to baseline optic disc and glaucoma. We used a novel study design to enroll patients who had fundus photographs incidentally taken during routine health check-ups prior to the onset of optic neuropathy. In 31 eyes (21 patients) with chON and 33 eyes (30 patients) with glaucoma, we investigated the change in cup-to-disc (C/D) area from the baseline to overt cupping using flicker analysis. Compared to the baseline, 23 eyes (74.2%) had increased cup size and 3 (9.7%) had vascular configuration changes in the chONgroup; in contrast, all glaucoma eyes exhibited changes in cup size and vascular configuration. The increase in C/D area ratio was significantly smaller in chON (0.04 ± 0.04) compared to glaucoma (0.10 ± 0.04, P < 0.001); the minimum residual neuroretinal rim width showed a more pronounced difference (29.7 ± 8.2% vs 7.1 ± 3.9%, P < 0.001). The changes distributed predominantly towards the nasal direction in chON, contrasting the changes to the arcuate fibers in glaucoma. In conclusion, our results provide the first longitudinal evidence of true pathological cupping in chONcompared to photographically disease-free baseline. The marked difference in the residual minimum rim width reaffirms the importance of rim obliteration in the differential diagnosis between the two diseases.

Effect of intravitreal injections due to neovascular age-related macular degeneration on retinal nerve fiber layer thickness and minimum rim width: a cross sectional study.

PURPOSE: The present study tested the hypothesis that repeated anti-VEGF injections are associated with reduced retinal nerve fiber layer (RNFL) and minimum rim width (MRW) of the optic nerve head. PATIENTS AND METHODS: Sixty-six patients with a history of intravitreal injections due to neovascular age-related macular degeneration were included. RNFL and MRW were measured using optical coherence tomography (Spectralis OCT, Heidelberg Engineering, Heidelberg, Germany). RESULTS: Mean global RNFL was 90.62 µm and both RNFL as well as MRW significantly decreased with advanced age (p = 0.005 and p = 0.019, respectively). Correlating for the number of injections, no significant impact on RNFL was found globally (p = 0.642) or in any of the sectors. In contrast, however, global MRW was significantly reduced with increasing numbers of intravitreal injections (p = 0.012). The same holds true when adjusted for the confounding factor age (RNFL p = 0.566 and MRW p = 0.023). CONCLUSION: Our study shows that repeated intravitreal injections due to choroidal neovascularization seem to have a deleterious effect on MRW but not on RNFL. This suggests that MRW is a more sensitive marker than RNFL for evaluating the effect of frequent intravitreal injections on the optic nerve head since it seems to be the first structure affected.

Imaging Assessment of Peripapillary Vessel Diameters in Postmortem Eyes.

PURPOSE: Proof of concept of ex vivo retinal vessel diameter measurements in human postmortem eyes. METHODS: En face near-infrared (IR) images and optical coherence tomography (OCT) of the optic nerve head (ONH) were captured ex vivo with a Heidelberg Engineering Spectralis (Spectralis, version 7.0.4, Image Capture Module, version 1.2.4, Heidelberg Heidelberg, Germany) device, using a custom-made eye chamber holding and positioning the eyes during the image process. Thirty-two formaldehyde-fixated eyes of 16 patients were imaged. In the IR images, two independent graders measured retinal vessel diameters at the intersection of a drawn circle centered on the ONH with diameters of 2.0 mm and 3.4 mm, respectively. The anatomically corresponding measurements between both graders were statistically analyzed using a Wilcoxon signed-rank test. RESULTS: A total of 246 matched measurements of both graders were analyzed across all 32 imaged eyes. Statistically significant differences between the graders were found for arterioles at 2 mm from the ONH. The other measurements did not show statistically significant intergrader differences. The mean values for arteriole diameters were 72.2 µm at 2.0 mm and 61.5 µm at 3.4 mm for grader 1, and 66.4 µm at 2.0 mm and 63.2 µm at 3.4 mm for grader 2. The mean diameter for venules were 75.5 µm at 2.0 mm and 79.3 µm at 3.4 mm for grader 1, and 67.4 µm at 2 mm and 79.1 µm at 3.4 mm for grader 2. CONCLUSION: To the best of our knowledge, this is the first study to present IR image-based retinal vessel diameters in ex vivo postmortem eyes. Retinal IR/OCT imaging is possible, and measurements are reproducible in formaldehyde-fixated human eyes. Fixation artefacts result in lower image quality, and this can impose challenges in correctly detecting, classifying, and measuring retinal vessels.

Characteristics of beta parapapillary atrophy in primary angle-closure suspect.

OBJECTIVE: To investigate the characteristics of beta parapapillary atrophy (ß-PPA) in patients with primary angle-closure suspect (PACS). METHODS AND ANALYSIS: In total, 215 and 259 eyes with PACS and non-PACS (NPACS), respectively, were enrolled in this observational, cross-sectional study. Stereoscopic fundus and optical coherence tomography images were used to characterise ß-PPA; the former was also used to measure the major ß-PPA parameters. Univariate and multiple logistic regression analyses were used to identify the factors correlated with the presence of ß-PPA and with ß-PPA parameters. RESULTS: The ß-PPA occurrence rates were 48.80% and 44.40% in the PACS and NPACS groups, respectively, with no significant difference between groups. Compared with that in the NPACS group, the ß-PPA area was significantly larger (p=0.005) in the PACS group, but the angular extent and maximum radial length did not differ between groups (p=0.110 and 0.657, respectively) after adjusting for age and axial length. The presence of ß-PPA was associated with older age (OR 1.057, 95% CI 1.028 to 1.088, p<0.001) and larger disc area (OR 1.716, 95% CI 1.170 to 2.517, p=0.006). A larger ß-PPA area was associated with older age (p=0.014), greater vertical cup-to-disc ratio (p=0.028), larger disc area (p<0.001) and PACS diagnosis (p=0.035). CONCLUSION: 48.80% of participants with PACS had ß-PPA, which is slightly larger than NPACS. The area of ß-PPA was larger in PACS, while the angular extent and maximum radial length did not differ between groups.

A new segmentation algorithm for peripapillary atrophy and optic disk from ultra-widefield Photographs1.

BACKGROUND AND OBJECTIVE: The prevalence of myopia and high myopia is increasing globally, underscoring the growing importance of diagnosing high myopia-related pathologies. While existing image segmentation models, such as U-Net, UNet++, ResU-Net, and TransUNet, have achieved significant success in medical image segmentation, they still face challenges when dealing with ultra-widefield (UWF) fundus images. This study introduces a novel automatic segmentation algorithm for the optic disc and peripapillary atrophy (PPA) based on UWF fundus images, aimed at assisting ophthalmologists in more accurately diagnosing high myopia-related diseases. METHODS: In this study, we developed a segmentation model leveraging a Transformer-based network structure, complemented by atrous convolution and selective boundary aggregation modules, to elevate the accuracy of segmenting the optic disc and PPA in UWF photography. The atrous convolution module adeptly manages multi-scale features, catering to the variances in target sizes and expanding the deep network's receptive field. Concurrently, the incorporation of the selective boundary aggregation module in the skip connections of the model significantly improves the differentiation of boundary information between segmentation targets. Moreover, the comparison of our proposed algorithm with classical segmentation models like U-Net, UNet++, ResU-Net, and TransUNet highlights its considerable advantages in processing UWF photographs. RESULTS: The experimental results show that, compared to the other four models, our algorithm demonstrates substantial improvements in segmenting the optic disc and PPA in UWF photographs. In PPA segmentation, our algorithm improves by 0.8% in Dice, 1.8% in sensitivity, and 1.3% in intersection over union (IOU). In optic disc segmentation, our algorithm improves by 0.3% in Dice, 0.6% in precision, and 0.4% in IOU. CONCLUSION: Our proposed method improves the segmentation accuracy of PPA and optic disks based on UWF photographs, which is valuable for diagnosing high myopia-related diseases in ophthalmology clinics.

Apoptosis in glaucoma: A new direction for the treatment of glaucoma (Review).

Glaucoma is a group of progressive optic nerve disorders characterized by the loss of retinal ganglion cells, a thinner retinal nerve fibre layer and cupping of the optic disk. Apoptosis is a physiological cell death process regulated by genes and plays a crucial role in maintaining tissue homeostasis, ensuring the natural development and immune defence of organisms. Apoptosis has been associated with glaucoma and inhibiting apoptosis by activating phosphatidylinositol 3-kinase­protein kinase B or other medicines can rescue pathological changes in glaucoma. Due to the complex crosstalk of apoptosis pathways, the pathophysiological mechanism of apoptosis in glaucoma needs to be fully elucidated. The present review aimed to discuss the mechanism of cell apoptosis in glaucoma, improve the understanding of the pathophysiology of glaucoma, summarize new directions for the treatment of glaucoma and lay the foundation for new treatment strategies for glaucoma.

Myelin Oligodendrocyte Glycoprotein Antibody Disease Optic Neuritis: A Structure-Function Paradox?

BACKGROUND: Myelin oligodendrocyte glycoprotein antibody disease (MOGAD) is a demyelinating disorder that most commonly presents with optic neuritis (ON) and affects children more often than adults. We report 8 pediatric patients with MOG-associated ON and characterize focal optical coherence tomography (OCT) abnormalities over time that help distinguish this condition from the trajectories of other demyelinating disorders. These OCT findings are examined in the context of longitudinal visual function testing. METHODS: This is a retrospective case series of 8 pediatric patients with MOG-associated ON who were referred for neuro-ophthalmic evaluation. Longitudinal data for demographics, clinical history, physical examination, and OCT obtained in the course of clinical evaluations were collected through retrospective medical record review. RESULTS: Patients demonstrated acute peripapillary retinal nerve fiber layer (RNFL) thickening in one or both eyes, consistent with optic disc swelling. This was followed by steady patterns of average RNFL thinning, with 9 of 16 eyes reaching significantly low RNFL thickness using OCT platform reference databases ( P < 0.01), accompanied by paradoxical recovery of high-contrast visual acuity (HCVA) in every patient. There was no correlation between HCVA and any OCT measures, although contrast sensitivity (CS) was associated with global thickness, PMB thickness, and nasal/temporal (N/T) ratio, and color vision was associated with PMB thickness. There was a lower global and papillomacular bundle (PMB) thickness ( P < 0.01) in clinically affected eyes compared with unaffected eyes. There was also a significantly higher N:T ratio in clinically affected eyes compared with unaffected eyes in the acute MOG-ON setting ( P = 0.03), but not in the long-term setting. CONCLUSIONS: MOG shows a pattern of prominent retinal atrophy, as demonstrated by global RNFL thinning, with remarkable preservation of HCVA but remaining deficits in CS and color vision. These tests may be better clinical markers of vision changes secondary to MOG-ON. Of the OCT parameters measured, PMB thickness demonstrated the most consistent correlation between structural and functional measures. Thus, it may be a more sensitive marker of clinically significant retinal atrophy in MOG-ON. The N:T ratio in acute clinically affected MOG-ON eyes in our study was higher than the N:T ratio of neuromyelitis optica (NMO)-ON eyes and similar to the N:T ratio in multiple sclerosis (MS)-ON eyes as presented in the prior literature. Therefore, MOG may share a more similar pathophysiology to MS compared with NMO.

Development of a deep learning model to distinguish the cause of optic disc atrophy using retinal fundus photography.

The differential diagnosis for optic atrophy can be challenging and requires expensive, time-consuming ancillary testing to determine the cause. While Leber's hereditary optic neuropathy (LHON) and optic neuritis (ON) are both clinically significant causes for optic atrophy, both relatively rare in the general population, contributing to limitations in obtaining large imaging datasets. This study therefore aims to develop a deep learning (DL) model based on small datasets that could distinguish the cause of optic disc atrophy using only fundus photography. We retrospectively reviewed fundus photographs of 120 normal eyes, 30 eyes (15 patients) with genetically-confirmed LHON, and 30 eyes (26 patients) with ON. Images were split into a training dataset and a test dataset and used for model training with ResNet-18. To visualize the critical regions in retinal photographs that are highly associated with disease prediction, Gradient-Weighted Class Activation Map (Grad-CAM) was used to generate image-level attention heat maps and to enhance the interpretability of the DL system. In the 3-class classification of normal, LHON, and ON, the area under the receiver operating characteristic curve (AUROC) was 1.0 for normal, 0.988 for LHON, and 0.990 for ON, clearly differentiating each class from the others with an overall total accuracy of 0.93. Specifically, when distinguishing between normal and disease cases, the precision, recall, and F1 scores were perfect at 1.0. Furthermore, in the differentiation of LHON from other conditions, ON from others, and between LHON and ON, we consistently observed precision, recall, and F1 scores of 0.8. The model performance was maintained until only 10% of the pixel values of the image, identified as important by Grad-CAM, were preserved and the rest were masked, followed by retraining and evaluation.

Visual field progression patterns in the ocular hypertension treatment study correspond to vulnerability regions of the disc.

OBJECTIVES: To determine the locations on the 24-2 visual field (VF) testing grid that are most likely to progress in patients with ocular hypertension (OHTN). Based on a structural model of superior and inferior areas of relative vulnerability at the optic disc, we hypothesized that the nasal and paracentral regions are more prone to show a reduction in sensitivity. METHODS: Posthoc analysis of data collected in phases 1 and 2 of the Ocular Hypertension Treatment Study (OHTS). A pointwise analysis was applied to determine the progression patterns in the early and delayed treatment groups. Each group's progression rate and frequency were calculated for each of the 52 locations corresponding to the 24-2 VF strategy, using trend- and event-based analyses, respectively. RESULTS: For the event-based analysis, the events were most commonly found in the nasal and paracentral regions. The same regions, with some modest variation, were found to have the fastest rates of progression (ROP) measured with trend analysis. A similar pattern of progression was observed in both the early and delayed treatment groups. The difference in event rates and ROP between the early and delayed treatment groups was also greatest in the nasal and paracentral regions. CONCLUSIONS: Development of VF loss in ocular hypertensive eyes appears to be consistent with the vulnerability zones previously described in glaucomatous eyes with established VF loss. Ocular hypotensive treatment likely helps to slow the rate of progression in these regions. This suggests that careful monitoring of these locations may be useful.

Normative body mass-adjusted reference ranges of magnetic resonance imaging signs commonly used in diagnosing idiopathic intracranial hypertension in a healthy standard population.

Patients with chronic daily headaches (CDH) are often a diagnostic challenge and frequently undergo neuroimaging. One common underlying cause of CDH is idiopathic intracranial hypertension (IIH). However, certain neuroimaging abnormalities that suggest IIH, such as optic nerve sheath diameters (ONSD), pituitary gland height, and venous sinus diameter, require interpretation due to the absence of established normative values. Notably, intracranial pressure is known to varies with age, sex and weight, further complicating the determination of objectively abnormal findings within a specific patient group. This study aims to assist clinical neuroradiologists in differentiating neuroimaging results in CDH by providing weight-adjusted normative values for imaging characteristics of IIH. In addition to age and BMI we here assessed 1924 population-based T1-weighted MRI datasets of healthy participants for relevant MRI aspects of IIH. Association to BMI was analyzed using linear/logistic regression controlled for age and stratified for sex. ONSD was 4.3 mm [2.8; 5.9]/4.6 mm [3.6; 5.7] and diameter of transverse sinus was 4.67 mm [1.6; 6.5]/4.45 mm [3.0; 7.9]. Height of pituitary gland was 5.1 mm [2.2;8.1]/4.6 mm [1.9;7.1] for female and male respectively. Values generally varied with BMI with regression slopes spanning 0.0001 to 0.05 and were therefor presented as normative values stratified by BMI. Protrusion of ocular papilla, empty sella and transverse sinus occlusion were rare in total. Our data show an association between BMI and commonly used MRI features for diagnosing IIH. We provide categorized normative BMI values for ONSD, pituitary gland height, and transverse sinus diameter. This distinction helps objectively identify potential IIH indicators compared to regular population norms, enhancing diagnostic accuracy for suspected IIH patients. Notably, optic nerve head protrusion, empty sella, and transverse sinus occlusion are rare in healthy individuals, solidifying their importance as imaging markers regardless of BMI.

Prediction of Visual Field Progression with Baseline and Longitudinal Structural Measurements Using Deep Learning.

PURPOSE: Identifying glaucoma patients at high risk of progression based on widely available structural data is an unmet task in clinical practice. We test the hypothesis that baseline or serial structural measures can predict visual field (VF) progression with deep learning (DL). DESIGN: Development of a DL algorithm to predict VF progression. METHODS: 3,079 eyes (1,765 patients) with various types of glaucoma and ≥5 VFs, and ≥3 years of follow-up from a tertiary academic center were included. Serial VF mean deviation (MD) rates of change were estimated with linear-regression. VF progression was defined as negative MD slope with p<0.05. A Siamese Neural Network with ResNet-152 backbone pre-trained on ImageNet was designed to predict VF progression using serial optic-disc photographs (ODP), and baseline retinal nerve fiber layer (RNFL) thickness. We tested the model on a separate dataset (427 eyes) with RNFL data from different OCT. The Main Outcome Measure was Area under ROC curve (AUC). RESULTS: Baseline average (SD) MD was 3.4 (4.9)dB. VF progression was detected in 900 eyes (29%). AUC (95% CI) for model incorporating baseline ODP and RNFL thickness was 0.813 (0.757-0.869). After adding the second and third ODPs, AUC increased to 0.860 and 0.894, respectively (p<0.027). This model also had highest AUC (0.911) for predicting fast progression (MD rate <1.0 dB/year). Model's performance was similar when applied to second dataset using RNFL data from another OCT device (AUC=0.893; 0.837-0.948). CONCLUSIONS: DL model predicted VF progression with clinically relevant accuracy using baseline RNFL thickness and serial ODPs and can be implemented as a clinical tool after further validation.

Differentiating Ischemic Optic Neuropathy from Glaucoma Using Diagnostic Tests.

INTRODUCTION: Anterior ischemic optic neuropathy (AION) can mimic glaucoma and consequently cause difficulties in differential diagnosis. The purpose of this paper was to summarize differences in diagnostic tests that can help perform a correct diagnosis. METHODS: The search strategy was performed according to the PRISMA 2009 guidelines, and four databases were used: MEDLINE, Embase, Web of Science, and Cochrane. Totally, 772 references were eligible; 39 were included after screening with respect to inclusion criteria that included English language and published in the 20 years before search date. RESULTS: Ninety percent (n = 35) of included studies used optical coherence tomography (OCT). Glaucomatous eyes had a significantly greater cup area, volume and depth, cup-to-disk ratio, a lower rim volume and area, and a thinner Bruch's membrane opening-minimum rim width. Retinal nerve fiber layer (RNFL) thinning in glaucomatous eyes occurred primarily at the superotemporal, inferotemporal, and inferonasal sectors, while AION eyes demonstrated mostly superonasal thinning. Glaucoma eyes showed greater macular ganglion cell layer thickness, except at the inferotemporal sector. OCT angiography measurements demonstrated a significant decrease in superficial and deep macular vessel density (VD) in glaucoma compared to AION with similar degree of visual field damage; the parapapillary choroidal VD was spared in AION eyes compared to glaucomatous eyes. CONCLUSION: By use of OCT imaging, optic nerve head parameters seem most informative to distinguish between glaucoma and AION. Although both diseases affect the RNFL thickness, it seems to do so in different sectors. Differences in structure and vascularity of the macula can also help in making the differential diagnosis.