The Temporal Relation Between Rates of Retinal Nerve Fiber Layer and Minimum Rim Width Changes in Glaucoma.

Purpose: This study aims to determine whether OCT-derived rates of change in minimum rim width (MRW) are associated with and can potentially predict corresponding alterations in retinal nerve fiber layer thickness (RNFLT) in people with glaucoma. Methods: The rates of change between six-monthly visits were taken from 568 eyes of 278 participants in the P3 Study. Structural equation models (SEM) assessed whether one parameter was predicted by the concurrent or previous rate of the other parameter, after adjusting for its own rate in the previous time interval. Root mean square error of approximation (RMSEA, with 90% confidence intervals [CI]), Tucker Lewis index (TLI) and the comparative fit index (CFI) assessed goodness of fit. Results: Models without a time lag provided a better fit for the data (RMSEA = 0.101 [CI, 0.089, 0.113]), compared to a model featuring a time lag in RNFLT (RMSEA = 0.114 [CI, 0.102, 0.126]) or MRW (RMSEA = 0.114 [CI, 0.102, 0.127]). The SEMs indicated that rates for both MRW and RNFLT were predicted by their own rate in the previous time interval and by the other measure's change in the concurrent time interval (P > 0.001 for all). No evidence of a clinically significant time lag for either parameter was determined. Conclusions: MRW and RNFLT exhibit concurrent changes over time in patients with glaucoma, with no clinically significant time lag determined. Translational Relevance: RNFLT may be more useful than MRW in early glaucoma assessment because of its previously reported lower variability and reduced sensitivity to intraocular pressure changes.

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.

Morphological differences of the neuroretinal rim between temporally tilted and non-tilted optic discs in healthy eyes.

This study aimed to compare morphological differences of the neuroretinal rim between the temporally tilted and non-tilted optic discs in healthy eyes. We prospectively enrolled participants aged 20-40 years with temporally tilted or non-tilted optic discs. The optic nerve head parameters were analyzed using spectral domain-optical coherence tomography. The angle between the Bruch's membrane opening (BMO) plane and BMO-minimum rim width (BMO-MRW) was termed "BMO-MRW angle". Peripapillary retinal nerve fiber layer thickness (pRNFLT) and BMO-based parameters were compared between the temporally tilted and non-tilted disc groups. As a result, 55 temporally tilted disc eyes and 38 non-tilted disc eyes were analyzed. Global pRNFLT, global BMO-MRW, and total BMO-minimum rim area (BMO-MRA) were similar between the two groups (p = 0.138, 0.161, and p = 0.410, respectively). In the sectoral analysis, temporally tilted disc group exhibited thicker BMO-MRW in the temporal sector (p = 0.032) and thinner in the nasal superior and nasal sectors (p = 0.025 and p = 0.002, respectively). Temporally tilted disc group showed larger BMO-MRA in the temporal, temporal superior, and temporal inferior sectors (p < 0.001, p < 0.001, and p < 0.016, respectively), alongside a higher BMO-MRW angle in the temporal sector and lower in the nasal superior and nasal sectors. In conclusion, the neuroretinal rim, represented by BMO-MRW and BMO-MRA, showed morphological differences between temporally tilted and non-tilted optic discs in healthy eyes. BMO-MRW and BMO-MRA showed temporalization in the same manner as pRNFLT in the temporally tilted disc eyes. The BMO-MRW angle showed that in temporally tilted disc eyes, optic nerve fibers met the BMO plane steeply in the nasal sector and gently in the temporal sector than in non-tilted disc eyes, suggesting potential stress region of optic nerve fibers in temporally tilted disc eyes.

Clinical Perspectives on the Use of Computer Vision in Glaucoma Screening.

Glaucoma is one of the leading causes of irreversible blindness in the world. Early diagnosis and treatment increase the chances of preserving vision. However, despite advances in techniques for the functional and structural assessment of the retina, specialists still encounter many challenges, in part due to the different presentations of the standard optic nerve head (ONH) in the population, the lack of explicit references that define the limits of glaucomatous optic neuropathy (GON), specialist experience, and the quality of patients' responses to some ancillary exams. Computer vision uses deep learning (DL) methodologies, successfully applied to assist in the diagnosis and progression of GON, with the potential to provide objective references for classification, avoiding possible biases in experts' decisions. To this end, studies have used color fundus photographs (CFPs), functional exams such as visual field (VF), and structural exams such as optical coherence tomography (OCT). However, it is still necessary to know the minimum limits of detection of GON characteristics performed through these methodologies. This study analyzes the use of deep learning (DL) methodologies in the various stages of glaucoma screening compared to the clinic to reduce the costs of GON assessment and the work carried out by specialists, to improve the speed of diagnosis, and to homogenize opinions. It concludes that the DL methodologies used in automated glaucoma screening can bring more robust results closer to reality.

Optical Coherence Tomography Angiography Assessment of the Optic Nerve Head in Patients Hospitalized Due to COVID-19 Bilateral Pneumonia.

Background and objectives: We aimed to investigate changes in the radial peripapillary capillary (RPC) network using optical coherence tomography angiography (OCTA) in patients who recovered from coronavirus disease 2019 (COVID-19). Materials and Methods: This was a prospective study of patients hospitalized due to COVID-19 bilateral pneumonia between March and May 2021. The control group included healthy individuals matched for age and sex. Two months after discharge, the patients underwent ophthalmological examination, including optical coherence tomography (OCT) imaging. The RPC network and retinal nerve fiber layer (RNFL) of the optic disc (RNFL optic disc) were automatically evaluated and compared between the study groups. Additionally, the RPC parameters were compared between the men and women in the COVID-19 group, and correlations between the RPC and RNFL optic disc parameters were assessed. Results: A total of 63 patients (120 eyes) with bilateral pneumonia caused by severe acute respiratory syndrome coronavirus 2 infection were examined. No ophthalmic symptoms were reported by the patients. No significant differences were observed in the RPC parameters between the patients from the COVID-19 group and the 43 healthy controls. Moreover, the RPC parameters did not differ between the men and women in the COVID-19 group. A positive correlation was found between the RPC and RNFL optic disc parameters in the COVID-19 patients (p < 0.001). Conclusions: No changes in the RPC network were observed among the patients with COVID-19 bilateral pneumonia in the early period after hospital discharge. However, a longer follow-up is needed to monitor COVID-19-related changes in the microvasculature of the optic nerve head.

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.

Self-supervised pre-training for joint optic disc and cup segmentation via attention-aware network.

Image segmentation is a fundamental task in deep learning, which is able to analyse the essence of the images for further development. However, for the supervised learning segmentation method, collecting pixel-level labels is very time-consuming and labour-intensive. In the medical image processing area for optic disc and cup segmentation, we consider there are two challenging problems that remain unsolved. One is how to design an efficient network to capture the global field of the medical image and execute fast in real applications. The other is how to train the deep segmentation network using a few training data due to some medical privacy issues. In this paper, to conquer such issues, we first design a novel attention-aware segmentation model equipped with the multi-scale attention module in the pyramid structure-like encoder-decoder network, which can efficiently learn the global semantics and the long-range dependencies of the input images. Furthermore, we also inject the prior knowledge that the optic cup lies inside the optic disc by a novel loss function. Then, we propose a self-supervised contrastive learning method for optic disc and cup segmentation. The unsupervised feature representation is learned by matching an encoded query to a dictionary of encoded keys using a contrastive technique. Finetuning the pre-trained model using the proposed loss function can help achieve good performance for the task. To validate the effectiveness of the proposed method, extensive systemic evaluations on different public challenging optic disc and cup benchmarks, including DRISHTI-GS and REFUGE datasets demonstrate the superiority of the proposed method, which can achieve new state-of-the-art performance approaching 0.9801 and 0.9087 F1 score respectively while gaining 0.9657 D C disc and 0.8976 D C cup . The code will be made publicly available.

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.

Computational study on the effects of central retinal blood vessels with asymmetric geometries on optic nerve head biomechanics.

Optic nerve head (ONH) biomechanics are associated with glaucoma progression and have received considerable attention. Central retinal vessels (CRVs) oriented asymmetrically in the ONH are the single blood supply source to the retina and are believed to act as mechanically stable elements in the ONH in response to intraocular pressure (IOP). However, these mechanical effects are considered negligible in ONH biomechanical studies and received less attention. This study investigated the effects of CRVs on ONH biomechanics taking into consideration three-dimensional asymmetric CRV geometries. A CRV geometry was constructed based on CRV centerlines extracted from optical coherence tomography ONH images in eight healthy subjects and superimposed in the idealized ONH geometry established in previous studies. Mechanical analyses of the ONH in response to the IOP were conducted in the cases with and without CRVs for comparison. Obtained results demonstrated that the CRVs induced anisotropic ONH deformation, particularly in the lamina cribrosa and the associated upper neural tissues (prelamina) with wide ranges of spatial strain distributions. These results indicated that the CRVs result in anisotropic deformation with local strain concentration, rather than function to mechanically support in response to the IOP as in the conventional thinking in ophthalmology.

Automated vertical cup-to-disc ratio determination from fundus images for glaucoma detection.

Glaucoma is the leading cause of irreversible blindness worldwide. Often asymptomatic for years, this disease can progress significantly before patients become aware of the loss of visual function. Critical examination of the optic nerve through ophthalmoscopy or using fundus images is a crucial component of glaucoma detection before the onset of vision loss. The vertical cup-to-disc ratio (VCDR) is a key structural indicator for glaucoma, as thinning of the superior and inferior neuroretinal rim is a hallmark of the disease. However, manual assessment of fundus images is both time-consuming and subject to variability based on clinician expertise and interpretation. In this study, we develop a robust and accurate automated system employing deep learning (DL) techniques, specifically the YOLOv7 architecture, for the detection of optic disc and optic cup in fundus images and the subsequent calculation of VCDR. We also address the often-overlooked issue of adapting a DL model, initially trained on a specific population (e.g., European), for VCDR estimation in a different population. Our model was initially trained on ten publicly available datasets and subsequently fine-tuned on the REFUGE dataset, which comprises images collected from Chinese patients. The DL-derived VCDR displayed exceptional accuracy, achieving a Pearson correlation coefficient of 0.91 (P = 4.12 × 10-412) and a mean absolute error (MAE) of 0.0347 when compared to assessments by human experts. Our models also surpassed existing approaches on the REFUGE dataset, demonstrating higher Dice similarity coefficients and lower MAEs. Moreover, we developed an optimization approach capable of calibrating DL results for new populations. Our novel approaches for detecting optic discs and optic cups and calculating VCDR, offers clinicians a promising tool that significantly reduces manual workload in image assessment while improving both speed and accuracy. Most importantly, this automated method effectively differentiates between glaucoma and non-glaucoma cases, making it a valuable asset for glaucoma detection.

An Atypical Optic Nerve Head Mass.

A 47-year-old man presented with a sudden decrease in vision in the right eye and a history of binocular diplopia, bilateral cranial nerve 6 palsies, and an undifferentiated pontine mass. Examination revealed a large optic nerve head mass with optic disc hyperemia, scattered dot hemorrhages, a placoid lesion in the posterior pole, and a mass protruding out of the optic nerve head. What would you do next?

Individual vs simultaneous macular and optic disc measurements with spectral domain optical coherence tomography in glaucoma and healthy eyes.

We assessed the repeatability and agreement of ganglion cell complex (GCC) in the macular area and the peripapillary retinal nerve fiber layer (ppRNFL) with individual and combined macula and disc scans. The macular GCC and ppRNFL thicknesses from 34 control eyes and 43 eyes with glaucoma were measured with the Canon Optical Coherence Tomography (OCT) HS-100. Two repeated measurements were performed with both scan modes. The repeatability limit (Rlim) and agreement analysis were performed. The individual scan showed better repeatability than the combined scan in both groups. However, the differences in the Rlim for the GCC in most sectors were lower than 3 µm (axial resolution of the OCT), and this was larger than 3 µm for most of the ppRNFL sectors. The mean differences in the thickness between both scan modes for the GCC and ppRNFL measurements were less than 3 and 6 µm, respectively. The interval of the limits of agreement was about 10 µm in some sectors for the GCC, and about 40 and 60 µm in some sectors in controls and glaucoma eyes, respectively. Both scan modes showed good repeatability in both groups. The agreement results suggest that the scan modes cannot be used interchangeably.

Are Macula or Optic Nerve Head Structures Better at Diagnosing Glaucoma? An Answer Using Artificial Intelligence and Wide-Field Optical Coherence Tomography.

Purpose: We wanted to develop a deep-learning algorithm to automatically segment optic nerve head (ONH) and macula structures in three-dimensional (3D) wide-field optical coherence tomography (OCT) scans and to assess whether 3D ONH or macula structures (or a combination of both) provide the best diagnostic power for glaucoma. Methods: A cross-sectional comparative study was performed using 319 OCT scans of glaucoma eyes and 298 scans of nonglaucoma eyes. Scans were compensated to improve deep-tissue visibility. We developed a deep-learning algorithm to automatically label major tissue structures, trained with 270 manually annotated B-scans. The performance was assessed using the Dice coefficient (DC). A glaucoma classification algorithm (3D-CNN) was then designed using 500 OCT volumes and corresponding automatically segmented labels. This algorithm was trained and tested on three datasets: cropped scans of macular tissues, those of ONH tissues, and wide-field scans. The classification performance for each dataset was reported using the area under the curve (AUC). Results: Our segmentation algorithm achieved a DC of 0.94 ± 0.003. The classification algorithm was best able to diagnose glaucoma using wide-field scans, followed by ONH scans, and finally macula scans, with AUCs of 0.99 ± 0.01, 0.93 ± 0.06 and 0.91 ± 0.11, respectively. Conclusions: This study showed that wide-field OCT may allow for significantly improved glaucoma diagnosis over typical OCTs of the ONH or macula. Translational Relevance: This could lead to mainstream clinical adoption of 3D wide-field OCT scan technology.

Features of Peripapillary Hyperreflective Ovoid Mass-Like Structures in Nonarteritic Anterior Ischemic Optic Neuropathy Patients and Normal Controls.

Purpose: To determine the characteristics of peripapillary hyperreflective ovoid mass-like structures (PHOMS) in patients with nonarteritic anterior ischemic optic neuropathy (NAION) and in normal adults. Methods: A total of 406 included eyes were divided into four groups: acute NAION group, chronic NAION group, unaffected group, and normal eyes group. PHOMS were detected on optical coherence tomography slices from optical coherence tomography angiography scans centered on the optic nerve head (ONH). The differences in age, sex, and ONH parameters were investigated between eyes with PHOMS and eyes without PHOMS among groups. Results: The prevalence of PHOMS in acute eyes (43.48%) and fellow eyes (28.20%) was significantly higher than that in normal eyes (11.76%) (acute vs. normal, P < 0.001; fellow vs. normal, P = 0.014). In the acute group, the PHOMS score of size was negatively correlated with age in acute eyes (r = -0.486, P = 0.03). The size of PHOMS was negatively correlated with age and cup/disc ratio and positively correlated with retinal nerve fiber layer thickness in the nasal and inferior sectors in the normal groups. No differences in age, sex, ONH parameters, or visual field defects were found between eyes with PHOMS and eyes without PHOMS. Conclusions: The prevalence of PHOMS increased significantly in acute nonoptic disc drusen (NODD)-NAION eyes and fellow eyes. PHOMS could also be found among normal adults. PHOMS may be a nonspecific sign secondary to ONH edema and axoplasmic stasis. Translational Relevance: The high prevalence of PHOMS in acute NODD-NAION eyes may indicate axoplasmic stasis secondary to tissue edema.

Which OCT Measure of the Optic Nerve Head Improves Fastest? Towards Optimizing Early Detection of Resolving Papilledema in Children.

Purpose: Optical coherence tomography (OCT) has been used to monitor papilledema. This study aims to determine which OCT-derived measures of the optic nerve head (ONH) detect resolving papilledema in children faster than standard OCT measures. Methods: Children (≤18 years of age) with papilledema who completed optic nerve SD-OCT pretreatment and had evidence of treatment response on one or more follow-up OCTs within 4 months were included. Standard (mean circumpapillary retinal nerve fiber layer [cpRNFL] thickness), device-derived (per-quadrant cpRNFL) and custom (ONH height, maximum Bruch's membrane displacement [BMD], ONH volume [ONHV], and BMD volume) OCT measures were calculated. Per-eye generalized estimating equations (GEEs) modelled changes in device-derived and custom measures as a function of mean cpRNFL to identify those measures that resolved faster during early (0-2 months) follow-up. Mean cpRNFL coefficients of greater than 1 indicated faster resolving papilledema. Results: We included 52 eyes of 29 children (mean age, 12.8 years; 72.4% female). In analysis of early follow-up visits (38 eyes from 22 children), nasal cpRNFL and maximum BMD in each quadrant resolved faster than mean cpRNFL (GEE coefficients range, 1.14-3.37). Inferior cpRNFL, superior, nasal, and inferior ONH heights and ONHV resolved slower than mean cpRNFL (GEE coefficients range, 0.67-0.87). Conclusions: Nasal cpRNFL is a promising device-derived OCT measure for the early detection of resolving papilledema in children compared with mean cpRNFL. Maximum BMD, a custom measure, also shows promise, but its calculation has not yet been incorporated into commercial OCT devices. Translational Relevance: This study guides the optimal use of OCT in capturing resolving papilledema in children.

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.

Open Fundus Photograph Dataset with Pathologic Myopia Recognition and Anatomical Structure Annotation.

Pathologic myopia (PM) is a common blinding retinal degeneration suffered by highly myopic population. Early screening of this condition can reduce the damage caused by the associated fundus lesions and therefore prevent vision loss. Automated diagnostic tools based on artificial intelligence methods can benefit this process by aiding clinicians to identify disease signs or to screen mass populations using color fundus photographs as inputs. This paper provides insights about PALM, our open fundus imaging dataset for pathological myopia recognition and anatomical structure annotation. Our databases comprises 1200 images with associated labels for the pathologic myopia category and manual annotations of the optic disc, the position of the fovea and delineations of lesions such as patchy retinal atrophy (including peripapillary atrophy) and retinal detachment. In addition, this paper elaborates on other details such as the labeling process used to construct the database, the quality and characteristics of the samples and provides other relevant usage notes.

Automated optic disk segmentation for optic disk edema classification using factorized gradient vector flow.

One significant ocular symptom of neuro-ophthalmic disorders of the optic disk (OD) is optic disk edema (ODE). The etiologies of ODE are broad, with various symptoms and effects. Early detection of ODE can prevent potential vision loss and fatal vision problems. The texture of edematous OD significantly differs from the non-edematous OD in retinal images. As a result, techniques that usually work for non-edematous cases may not work well for edematous cases. We propose a fully automatic OD classification of edematous and non-edematous OD on fundus image collections containing a mixture of edematous and non-edematous ODs. The proposed algorithm involved localization, segmentation, and classification of edematous and non-edematous OD. The factorized gradient vector flow (FGVF) was used to segment the ODs. The OD type was classified using a linear support vector machine (SVM) based on 27 features extracted from the vessels, GLCM, color, and intensity line profile. The proposed method was tested on 295 images with 146 edematous cases and 149 non-edematous cases from three datasets. The segmentation achieves an average precision of 88.41%, recall of 89.35%, and F1-Score of 86.53%. The average classification accuracy is 99.40% and outperforms the state-of-the-art method by 3.43%.

Deep learning-based optic disc classification is affected by optic-disc tilt.

We aimed to determine the effect of optic disc tilt on deep learning-based optic disc classification. A total of 2507 fundus photographs were acquired from 2236 eyes of 1809 subjects (mean age of 46 years; 53% men). Among all photographs, 1010 (40.3%) had tilted optic discs. Image annotation was performed to label pathologic changes of the optic disc (normal, glaucomatous optic disc changes, disc swelling, and disc pallor). Deep learning-based classification modeling was implemented to develop optic-disc appearance classification models with the photographs of all subjects and those with and without tilted optic discs. Regardless of deep learning algorithms, the classification models showed better overall performance when developed based on data from subjects with non-tilted discs (AUC, 0.988 ± 0.002, 0.991 ± 0.003, and 0.986 ± 0.003 for VGG16, VGG19, and DenseNet121, respectively) than when developed based on data with tilted discs (AUC, 0.924 ± 0.046, 0.928 ± 0.017, and 0.935 ± 0.008). In classification of each pathologic change, non-tilted disc models had better sensitivity and specificity than the tilted disc models. The optic disc appearance classification models developed based all-subject data demonstrated lower accuracy in patients with the appearance of tilted discs than in those with non-tilted discs. Our findings suggested the need to identify and adjust for the effect of optic disc tilt on the optic disc classification algorithm in future development.