Color Fundus Photography Research Articles

Critical Dependence on Area in Relationship between ARMS2/HTRA1 Genotype and Faster Geographic Atrophy Enlargement: Age-Related Eye Disease Study 2 Report Number 33

To analyze ARMS2/HTRA1 as a risk factor for faster geographic atrophy (GA) enlargement according to (1) GA area and (2) contiguous enlargement versus progression to multifocality. Age-Related Eye Disease Study 2 (AREDS2) cohort analysis. Eyes with GA: 546 eyes of 406 participants. Geographic atrophy area was measured from color fundus photographs at annual visits. Mixed-model regression of square root of GA area and proportional hazards regression of progression to multifocality were analyzed by ARMS2 genotype. Change in square root GA area and progression to multifocality. Geographic atrophy enlargement was significantly faster with ARMS2 risk alleles (P < 0.0001) at 0.224 mm/year (95% CI, 0.195-0.252 mm/year), 0.298 mm/year (95% CI, 0.271-0.324 mm/year), and 0.317 mm/year (95% CI, 0.279-0.355 mm/year), for 0 to 2 risk alleles, respectively. However, a significant interaction (P= 0.011) was observed between genotype and baseline area. In eyes with very small area (< 1.9 mm2), enlargement was significantly faster with ARMS2 risk alleles (P < 0.0001) at 0.193 mm/year (95% CI, 0.162-0.225 mm/year) versus 0.304 mm/year (95% CI, 0.280-0.329 mm/year) for 0 versus 1 to 2 risk alleles, respectively. With moderately small (1.9-3.8 mm2) or medium to large (≥ 3.8 mm2) area, enlargement was not significantly faster with ARMS2 risk alleles (P= 0.66 and P= 0.70, respectively). In nonmultifocal GA, enlargement was significantly faster with ARMS2 risk alleles (P= 0.001) at 0.175 mm/year (95% CI, 0.142-0.209 mm/year), 0.226 mm/year (95% CI, 0.193-0.259 mm/year), and 0.287 mm/year (95% CI, 0.237-0.337 mm/year) with 0 to 2 risk alleles, respectively. ARMS2 genotype was not associated significantly with progression to multifocal GA. The relationship between ARMS2/HTRA1 genotype and faster GA enlargement depends critically on GA area: risk alleles represent a strong risk factor for faster enlargement only in eyes with very small area. They increase the growth rate more through contiguous enlargement than progression to multifocality. ARMS2/HTRA1 genotype is more important in increasing risk of progression to GA and initial GA enlargement (contiguously) than in subsequent enlargement or progression to multifocality. These findings may explain some discrepancies between previous studies and have implications for both research and clinical practice. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Modifications in ocular microperfusion after transcatheter aortic valve implantation

Cerebral embolization is a known complication of transcatheter aortic valve implantation (TAVI) but the effect of the procedure on the ocular perfusion is currently unclear. Thus, we investigated post-procedural morphologic and perfusion changes of the retina and choroid, using optical coherence tomography angiography (OCTA) and color fundus photography (CFP) in a prospective cohort study. Ophthalmic examinations were conducted pre- and post-TAVI. OCTA images were analyzed quantitatively based on vessel density and skeleton density of the superficial and deep retinal plexus as well as the signal intensity and flow deficits in the choriocapillaris. CFP images were assessed for presence of acute retinal ischemia, optic nerve swelling, vessel emboli, hemorrhages and cotton wool spots. Data was analyzed using linear mixed models. Twenty patients (9 women; 11 men) at a mean age of 81 ± 6 years were included. Pre- and post-interventional ocular imaging data were available for 32 eyes. The analysis revealed a significant impairment of the choriocapillaris perfusion after TAVI with an increased proportion of flow deficits (p = 0.044). When controlling for blood pressure, the average size of choriocapillaris flow voids was significantly increased (systolic and diastolic, p = 0.039 and 0.029). Qualitatively, focal areas of retinal ischemia were detected on OCTA in 33% of participants. Silent emboli or cotton wool spots were identified on CFP in 21%. Our findings indicate a reduced choroidal perfusion as well as areas of retinal ischemia and embolization in a considerable proportion of patients following TAVI. Pending confirmation in a larger sample, these complications merit monitoring as well as inclusion in consent procedures for TAVI.

Gradeability and Reproducibility of Geographic Atrophy Measurement in GATHER-1, a Phase II/III Randomized Interventional Trial

To validate GATHER-1 inclusion criteria and the study's primary anatomic end point by assessing the reproducibility of geographic atrophy (GA) measurements and factors that affect reproducibility. Post hoc analysis of phase II/III clinical trial. All 286 participants included in the GATHER-1 study. For each subject, blue-light fundus autofluorescence (FAF), color fundus photographs, fluorescein angiograms, and OCT scans were obtained on the study eye and fellow eye. Geographic atrophy area and other lesion characteristics were independently graded by 2 experienced primary readers. If the 2 readers differed on gradeability, GA area (> 10%) or other lesion characteristics, the image was graded by an arbitrator whose measurement or characterization was the final grade. The main outcome measures were gradeability and reproducibility of FAF imaging data. Imaging data included lesion area, confluence of GA with peripapillary atrophy (PPA), whether GA involved the foveal centerpoint, and type of hyperautofluorescence pattern. A total of 2004 images (1002 visits, 286 participants) were analyzed. Gradeability (90.5%) and interreader gradeability concordance (90.2%) were high across all visits. Study eye images were more gradable compared with fellow-eye images. A greater proportion of smaller lesions required arbitration, but interreader reproducibility was consistently high for all images. There was no difference in gradeability, gradeability concordance, or lesion-area concordance for images with PPA-confluent GA compared with those with nonconfluent PPA. Foveal centerpoint-involving lesions had lower gradeability and lesion-area concordance. Images with diffuse patterns of hyperautofluorescence had better gradeability and gradeability concordance than those with nondiffuse patterns but had no difference in lesion-area or lesion-area concordance. There is high gradeability and excellent reproducibility measures across all images. These data support the validity of conclusions from GATHER-1 and the chosen inclusion criteria and end point. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Classification of Color Fundus Photographs Using Fusion Extracted Features and Customized CNN Models.

This study focuses on overcoming challenges in classifying eye diseases using color fundus photographs by leveraging deep learning techniques, aiming to enhance early detection and diagnosis accuracy. We utilized a dataset of 6392 color fundus photographs across eight disease categories, which was later augmented to 17,766 images. Five well-known convolutional neural networks (CNNs)-efficientnetb0, mobilenetv2, shufflenet, resnet50, and resnet101-and a custom-built CNN were integrated and trained on this dataset. Image sizes were standardized, and model performance was evaluated via accuracy, Kappa coefficient, and precision metrics. Shufflenet and efficientnetb0demonstrated strong performances, while our custom 17-layer CNN outperformed all with an accuracy of 0.930 and a Kappa coefficient of 0.920. Furthermore, we found that the fusion of image features with classical machine learning classifiers increased the performance, with Logistic Regression showcasing the best results. Our study highlights the potential of AI and deep learning models in accurately classifying eye diseases and demonstrates the efficacy of custom-built models and the fusion of deep learning and classical methods. Future work should focus on validating these methods across larger datasets and assessing their real-world applicability.

An auxiliary diagnostic tool for common fundus diseases based on fundus color photography and light-weight classification models.

To evaluate the performance of two lightweight neural network models in the diagnosis of common fundus diseases and make comparison to another two classical models. A total of 16,000 color fundus photography were collected, including 2000 each of glaucoma, diabetic retinopathy (DR), high myopia, central retinal vein occlusion (CRVO), age-related macular degeneration (AMD), optic neuropathy, and central serous chorioretinopathy (CSC), in addition to 2000 normal fundus. Fundus photography was obtained from patients or physical examiners who visited the Ophthalmology Department of Beijing Tongren Hospital, Capital Medical University. Each fundus photography has been diagnosed and labeled by two professional ophthalmologists. Two classical classification models (ResNet152 and DenseNet121), and two lightweight classification models (MobileNetV3 and ShufflenetV2), were trained. Area under the curve (AUC), sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were used to evaluate the performance of the four models. Compared with the classical classification model, the total size and number of parameters of the two lightweight classification models were significantly reduced, and the classification speed was sharply improved. Compared with the DenseNet121 model, the ShufflenetV2 model took 50.7% less time to make a diagnosis on a fundus photography. The classical models performed better than lightweight classification models, and Densenet121 showed highest AUC in five out of the seven common fundus diseases. However, the performance of lightweight classification models is satisfying. The AUCs using MobileNetV3 model to diagnose AMD, diabetic retinopathy, glaucoma, CRVO, high myopia, optic atrophy, and CSC were 0.805, 0.892, 0.866, 0.812, 0.887, 0.868, and 0.803, respectively. For ShufflenetV2model, the AUCs for the above seven diseases were 0.856, 0.893, 0.855, 0.884, 0.891, 0.867, and 0.844, respectively. The training of light-weight neural network models based on color fundus photography for the diagnosis of common fundus diseases is not only fast but also has a significant reduction in storage size and parameter number compared with the classical classification model, and can achieve satisfactory accuracy.

Strabismus in Retinopathy of Prematurity: Risk Factors and the Effect of Macular Ectopia.

This study aimed to examine factors associated with strabismus in patients with retinopathy of prematurity (ROP) and the relationship between strabismus and macular ectopia. Patients with ROP were divided into three groups: Group 1, patients with spontaneous regression (n=45); Group 2, patients who received laser treatment (n=70); and Group 3, patients who underwent surgical treatment (n=91). Rates of anisometropia, amblyopia, nystagmus, macular ectopia, and retinal pathologies were evaluated and their impacts on strabismus development were determined. Disc-to-fovea distance (DFD) was measured from color fundus photographs and the correlation of macular ectopia with severity of strabismus was evaluated. A total of 206 patients were included. Rates of anisometropia, amblyopia, nystagmus, macular ectopia, retinal pathologies causing vision loss, and strabismus were higher in Group 3 (p=0.0001) and correlated with higher stages of ROP (p=0.0001). Macular ectopia (p=0.005), retinal pathologies (p=0.005), and amblyopia (p=0.012) had the strongest impact on strabismus development in ROP patients. DFD and strabismus severity were not significantly correlated (p=0.364). Mean visual acuity (VA) was significantly higher in orthophoric patients compared to those with esotropia and exotropia (p=0.027). Esotropic patients had lower VA compared to patients with exotropia, but this finding was not statistically significant (p=0.729). Presence of macular ectopia, retinal pathologies, and amblyopia were the most strongly correlated risk factors for strabismus development in ROP patients. DFD was not associated with severity of strabismus. Exotropia was mostly related to higher DFD and a possible relationship between esotropia and lower VA was observed.

Comparison of Color Fundus Photography and Multicolor Fundus Imaging for Detection of Lesions in Diabetic Retinopathy and Retinal Vein Occlusion.

To evaluate the agreement between conventional fundus photography (CFP) and multicolor fundus imaging (MFI) for the detection of lesions of diabetic retinopathy (DR) and retinal vein occlusion (RVO). Cross-sectional analysis of eyes with DR or RVO who underwent CFP and MFI. All images were independently analyzed by two observers (O1 and O2), and the evaluated lesions were classified as "present" or "absent". Then, a paired comparison between both exams of the same eye was performed, to assess which made it easier to detect the lesions. Considering DR, the agreement was substantial for cotton wool spots and photocoagulation scars for both observers (O1: κ=0.75 and κ=0.67; O2: κ=0.71 and κ=0.64, respectively) and for hard exudates for O1 (κ=0.80). These lesions were detected more frequently on MFI. Regarding RVO, the agreement was considered substantial for venous sheathing by O1 (κ=0.64) and moderate for optociliary shunts by O2 (κ=0.60). Optociliary shunts were detected more frequently in CPF by both observers and venous sheathing on MFI by O1. For microaneurysms, retinal hemorrhages, retinal neovascularization, and proliferative membranes, in DR, and retinal hemorrhages, venous engorgement, and retinal neovascularization in RVO, the agreement was almost perfect (κ>0.82). In the paired analysis, both observers considered that, in DR, microaneurysms and retinal hemorrhages were easier to detect on CFP and that retinal neovascularization, cotton wool spots, and photocoagulation scars were easier to identify on MFI. Regarding RVO, optocilliary shunts were easier to identify on CFP and venous engorgement on MFI. The agreement of MFI and CFP was substantial to almost perfect for most lesions. MFI seems better to detect cotton wool spots and photocoagulations scars in DR and venous sheathing in RVO. Optocilliary shunts seem easier to detect on CFP.

Retromode Imaging Technology for Detecting Drusen-Like Deposits in Healthy Adults

To investigate the ability of retromode imaging technology to visualize drusen-like deposits (DLDs) in the macular region of healthy individuals without retinal diseases. Additionally, the correlation between subject age and the density of DLDs was assessed and their topographic distribution was evaluated. Prospective, observational, cross-sectional study SUBJECTS: Healthy volunteers (aged ≥ 35 years) without macular diseases. This study evaluated macular images in healthy adults using color fundus photography (FP) and retromode imaging. Two masked graders counted the number of DLDs identifiable with each modality. The standardized ETDRS concentric rings were adopted to divide DLDs based on their topographic distribution. Comparison of the number of DLDs detected with each imaging modality. The association between DLDs and age. The topographic distribution of macular DLDs with retromode imaging. The study included 91 eyes of 52 healthy volunteers (mean ± standard deviation age, 57.9 ± 10.9 years; range, 36-82 years). Overall, at least 1 DLD was present in 63.74% of eyes on color FP and 96.71% on retromode. Retromode imaging allowed detection of significantly more DLDs compared with color FP within the ETDRS grid (median [interquartile range], 4 [1-14] vs. 0 [0-0] respectively; P < 0.001). The density of DLDs was higher in the outer and inner rings compared with the central subfield (relative risk [RR], 16.70; 95% confidence interval [CI], 10.3-27.3 vs. RR 17.1; 95% CI, 10.5-27.6, respectively). Age was significantly correlated with DLDs density in all 3 sectors (all P < 0.05). Retromode technology allowed the detection of a significantly higher number of DLDs compared with FP in the macula of healthy individuals. This noninvasive imaging modality could be used to investigate the effect of the aging process on the macula, fostering a better understanding of the pathophysiology of age-related macular diseases. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

One-shot Retinal Artery and Vein Segmentation via Cross-modality Pretraining

To perform one-shot retinal artery and vein segmentation with cross-modality artery-vein (AV) soft-label pretraining. Cross-sectional study. The study included 6479 color fundus photography (CFP) and arterial-venous fundus fluorescein angiography (FFA) pairs from 1964 participants for pretraining and 6 AV segmentation data sets with various image sources, including RITE, HRF, LES-AV, AV-WIDE, PortableAV, and DRSplusAV for one-shot finetuning and testing. We structurally matched the arterial and venous phase of FFA with CFP, the AV soft labels were automatically generated by utilizing the fluorescein intensity difference of the arterial and venous-phase FFA images, and the soft labels were then used to train a generative adversarial network to learn to generate AV soft segmentations using CFP images as input. We then finetuned the pretrained model to perform AV segmentation using only one image from each of the AV segmentation data sets and test on the remainder. To investigate the effect and reliability of one-shot finetuning, we conducted experiments without finetuning and by finetuning the pretrained model on an iteratively different single image for each data set under the same experimental setting and tested the models on the remaining images. The AV segmentation was assessed by area under the receiver operating characteristic curve (AUC), accuracy, Dice score, sensitivity, and specificity. After the FFA-AV soft label pretraining, our method required only one exemplar image from each camera or modality and achieved similar performance with full-data training, with AUC ranging from 0.901 to 0.971, accuracy from 0.959 to 0.980, Dice score from 0.585 to 0.773, sensitivity from 0.574 to 0.763, and specificity from 0.981 to 0.991. Compared with no finetuning, the segmentation performance improved after one-shot finetuning. When finetuned on different images in each data set, the standard deviation of the segmentation results across models ranged from 0.001 to 0.10. This study presents the first one-shot approach to retinal artery and vein segmentation. The proposed labeling method is time-saving and efficient, demonstrating a promising direction for retinal-vessel segmentation and enabling the potential for widespread application. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Plasma Metabolites Associated with OCT Features of Age-Related Macular Degeneration

The most widely used classifications of age-related macular degeneration (AMD) and its severity stages still rely on color fundus photographs (CFPs). However, AMD has a wide phenotypic variability that remains poorly understood and is better characterized by OCT. We and others have shown that patients with AMD have a distinct plasma metabolomic profile compared with controls. However, all studies to date have been performed solely based on CFP classifications. This study aimed to assess if plasma metabolomic profiles are associated with OCT features commonly seen in AMD. Prospectively designed, cross-sectional study. Subjects with a diagnosis of AMD and a control group (> 50 years old) from Boston, United States, and Coimbra, Portugal. All participants were imaged with CFP, used for AMD staging (Age-Related Eye Disease Study 2 classification scheme), and with spectral domain OCT (Spectralis, Heidelberg). OCT images were graded by 2 independent graders for the presence of characteristic AMD features, according to a predefined protocol. Fasting blood samples were collected for metabolomic profiling (using nontargeted high-resolution mass spectrometry by Metabolon Inc). Analyses were conducted using logistic regression models including the worst eye of each patient (AREDS2 classification) and adjusting for confounding factors. Each cohort (United States and Portugal) was analyzed separately and then results were combined by meta-analyses. False discovery rate (FDR) was used to account for multiple comparisons. Plasma metabolite levels associated with OCT features. We included data on 468 patients, 374 with AMD and 94 controls, and on 725 named endogenous metabolites. Meta-analysis identified significant associations (FDR < 0.05) between plasma metabolites and 3 OCT features: hyperreflective foci (6), atrophy (6), and ellipsoid zone disruption (3). Most associations were seen with amino acids, and all but 1 metabolite presented specific associations with the OCT features assessed. To our knowledge, we show for the first time that plasma metabolites have associations with specific OCT features seen in AMD. Our results support that the wide spectrum of presentations of AMD likely include different pathophysiologic mechanisms by identifying specific pathways associated with each OCT feature. Proprietary or commercial disclosure may be found after the references.

Self-supervised anomaly detection, staging and segmentation for retinal images.

Unsupervised anomaly detection (UAD) is to detect anomalies through learning the distribution of normal data without labels and therefore has a wide application in medical images by alleviating the burden of collecting annotated medical data. Current UAD methods mostly learn the normal data by the reconstruction of the original input, but often lack the consideration of any prior information that has semantic meanings. In this paper, we first propose a universal unsupervised anomaly detection framework SSL-AnoVAE, which utilizes a self-supervised learning (SSL) module for providing more fine-grained semantics depending on the to-be detected anomalies in the retinal images. We also explore the relationship between the data transformation adopted in the SSL module and the quality of anomaly detection for retinal images. Moreover, to take full advantage of the proposed SSL-AnoVAE and apply towards clinical usages for computer-aided diagnosis of retinal-related diseases, we further propose to stage and segment the anomalies in retinal images detected by SSL-AnoVAE in an unsupervised manner. Experimental results demonstrate the effectiveness of our proposed method for unsupervised anomaly detection, staging and segmentation on both retinal optical coherence tomography images and color fundus photograph images.

Deep learning system for distinguishing optic neuritis from non-arteritic anterior ischemic optic neuropathy at acute phase based on fundus photographs.

To develop a deep learning system to differentiate demyelinating optic neuritis (ON) and non-arteritic anterior ischemic optic neuropathy (NAION) with overlapping clinical profiles at the acute phase. We developed a deep learning system (ONION) to distinguish ON from NAION at the acute phase. Color fundus photographs (CFPs) from 871 eyes of 547 patients were included, including 396 ON from 232 patients and 475 NAION from 315 patients. Efficientnet-B0 was used to train the model, and the performance was measured by calculating the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Also, Cohen's kappa coefficients were obtained to compare the system's performance to that of different ophthalmologists. In the validation data set, the ONION system distinguished between acute ON and NAION achieved the following mean performance: time-consuming (23 s), AUC 0.903 (95% CI 0.827-0.947), sensitivity 0.796 (95% CI 0.704-0.864), and specificity 0.865 (95% CI 0.783-0.920). Testing data set: time-consuming (17 s), AUC 0.902 (95% CI 0.832-0.944), sensitivity 0.814 (95% CI 0.732-0.875), and specificity 0.841 (95% CI 0.762-0.897). The performance (κ = 0.805) was comparable to that of a retinal expert (κ = 0.749) and was better than the other four ophthalmologists (κ = 0.309-0.609). The ONION system performed satisfactorily distinguishing ON from NAION at the acute phase. It might greatly benefit the challenging differentiation between ON and NAION.

HISTOLOGY, DIMENSIONS, AND FLUORESCEIN STAINING CHARACTERISTICS OF NODULAR AND CUTICULAR DRUSEN IN AGE-RELATED MACULAR DEGENERATION.

To enable in vivo analysis of drusen composition and lifecycle, the macular nodular and cuticular drusen were assessed using histology. Median and interquartile range of base widths of single (nonconfluent) nodular drusen in three sources were determined histologically: 43 eyes of 43 clinically undocumented donors, in an online resource; one eye with punctate hyperfluorescence in fluorescein angiography; and two eyes of one patient with bilateral "starry sky" cuticular drusen. All tissues were processed for high-resolution epoxy-resin histology and for cuticular drusen, transmission electron microscopy. All drusen localized between the retinal pigment epithelium basal lamina and inner collagenous layer of the Bruch membrane. They were solid, globular, homogeneously stained with toluidine blue, and uncovered by basal laminar deposit and basal mounds. Median base widths were 13.0 µ m (Source 1, N = 128 drusen, interquartile range 7.7, 20.0 µ m), 15.3 µ m (Source 2, N = 87, interquartile range 10.6, 20.5 µ m), and 7.3 µ m (Source 3, N = 78, interquartile range 3.9, 14.1 µ m). In three samples, >90% of solitary nodular drusen were <30 µ m, the visibility threshold in color fundus photography; these drusen are hyperfluorescent in fluorescein angiography. Whether these progress to soft drusen, known as high-risk from epidemiology studies and hypofluorescent, may be determinable from multimodal imaging datasets that include fluorescein angiography.

Transformer-based cross-modal multi-contrast network for ophthalmic diseases diagnosis

Automatic diagnosis of various ophthalmic diseases from ocular medical images is vital to support clinical decisions. Most current methods employ a single imaging modality, especially 2D fundus images. Considering that the diagnosis of ophthalmic diseases can greatly benefit from multiple imaging modalities, this paper further improves the accuracy of diagnosis by effectively utilizing cross-modal data. In this paper, we propose Transformer-based cross-modal multi-contrast network for efficiently fusing color fundus photograph (CFP) and optical coherence tomography (OCT) modality to diagnose ophthalmic diseases. We design multi-contrast learning strategy to extract discriminate features from cross-modal data for diagnosis. Then channel fusion head captures the semantically shared information across different modalities and the similarity features between patients of the same category. Meanwhile, we use a class-balanced training strategy to cope with the situation that medical datasets are usually class-imbalanced. Our method is evaluated on public benchmark datasets for cross-modal ophthalmic disease diagnosis. The experimental results demonstrate that our method outperforms other approaches. The codes and models are available at https://github.com/ecustyy/tcmn.

Clinical and Genetic Findings in Korean Patients with Choroideremia.

We share and analyze the clinical presentations and genotypes of Korean male patients and female carriers who visited our clinic. Six male patients and three female carriers with comprehensive ophthalmic examinations and next-generation sequencing were included. Detailed clinical features were identified using visual field (VF) test and multimodal imaging including color fundus photography, fundus autofluorescence (FAF), optical coherence tomography (OCT). Six male patients were diagnosed with choroideremia at the median age of 25 years. Before genetic testing, three (50.0%) patients were clinically diagnosed with choroideremia, while the other three (50.0%) patients with retinitis pigmentosa (RP). Patients showed different types of hemizygous CHM mutation, including two nonsense mutations (c.715C>T, p.Arg239Ter; c.799C>T, p.Arg267Ter), two frameshift mutations (c.1584_1587del, p.Val529HisfsTer7; c.403_404delGA, p.Asp135PhefsTer9), one splicing mutation (c.1511-28_1511-2del), and one exon duplication (2-9). The latter three mutations are novel findings. Two female carriers showed exon duplication (2-9) and the other one female carrier showed nonsense mutations (c.715C>T, p.Arg239Ter) in heterozygote form. Fundus showed diffuse yellow-whitish scleral reflex and granular pigmented lesions. FAF showed multiple patchy hypofluorescence lesions, sparing macula. OCT showed thinning of outer nuclear layer, ellipsoid zone, RPE layer, choroid thickness, interlaminar bridges (ILBs), outer retinal tubulations (ORTs), and microcysts in the inner nuclear layer. VF showed ring scotoma pattern with small amount of remaining central field. Asymptomatic female carriers showed variable fundus findings and mild changes in OCT. A detailed description of the genotypes with three novel mutations and phenotypes of six choroideremia patients and three CHM mutation female carriers are presented.

An Analysis of the Usage of Retinal Imaging Technology in the Detection of Age-Related Macular Degeneration.

Age-related macular degeneration (AMD) is a disease that worsens the central vision of numerous individuals across the globe. Ensuring that patients are diagnosed accurately and that their symptoms are carefully monitored is essential to ensure that adequate care is delivered. To accomplish this objective, retinal imaging technology is necessary to assess the pathophysiology that is required to give an accurate diagnosis of AMD. The purpose of this review is to assess the ability of various retinal imaging technologies such as optical coherence tomography (OCT), color fundus retinal photography, fluorescein angiography, and fundus photography. The statistical methods that were conducted yielded results that suggested that using OCT in conjunction with other imaging technologies results in a higher detection of symptoms among patients that have AMD. Further investigation should be conducted to ascertain the validity of the conclusions that were stated within the review.

Longitudinal Assessment of Retinal Nerve Fiber Layer and Ganglion Cell Complex Thicknesses in Patients With Large Optic Disc Cups and Normal Intraocular Pressure and Visual Fields.

The thicknesses of the circumpapillary retinal nerve fiber layer (cpRNFL) and ganglion cell complex (GCC) did not change during 5 years in physiological large disc cupping. We evaluated longitudinal changes in the thicknesses of the cpRNFL and GCC in large disc cupping with a normal intraocular pressure (IOP) (<21mmHg) and visual field. This retrospective, consecutive case series study included 269 eyes of 269 patients with large disc cupping and normal IOP. We analyzed patient demographics, IOP, central corneal thickness, vertical cup-to-disc ratios using color fundus photography, the thicknesses of the cpRNFL and GCC using RTVue-100, and mean deviation using visual field examinations. The differences in IOP, vertical cup-to-disc ratios, and mean deviation between the baseline and each follow-up visit were not statistically significant. The baseline average and mean average at 60 months follow-up of the cpRNFL thickness were 106.5±8.5 and 105.1±9.3μm, respectively; differences between the baseline and each follow-up visit were not statistically significant. The baseline average and mean average at 60 months follow-up of the GCC thickness were 82.8±9. and 81.5±9.2μm, respectively; differences between baseline and each follow-up visit were not statistically significant. The thicknesses of the cpRNFL and GCC did not change in well-maintained optic nerve head findings with normal IOP and visual field during a 5-year follow-up period. Optical coherence tomography evaluations of the thicknesses of the cpRNFL and GCC help accurately diagnose physiological optic disc cupping.

DeepDrRVO: A GAN-auxiliary two-step masked transformer framework benefits early recognition and differential diagnosis of retinal vascular occlusion from color fundus photographs

Retinal vascular occlusion (RVO) are common causes of visual impairment. Accurate recognition and differential diagnosis of RVO are unmet medical needs for determining appropriate treatments and health care to properly manage the ocular condition and minimize the damaging effects. To leverage deep learning as a potential solution to detect RVO reliably, we developed a deep learning model on color fundus photographs (CFPs) using a two-step masked SwinTransformer with a Few-Sample Generator (FSG)-auxiliary training framework (called DeepDrRVO) for early and differential RVO diagnosis. The DeepDrRVO was trained on the training set from the in-house cohort and achieved consistently high performance in early recognition and differential diagnosis of RVO in the validation set from the in-house cohort with an accuracy of 86.3%, and other three independent multi-center cohorts with the accuracy of 92.6%, 90.8%, and 100%. Further comparative analysis showed that the proposed DeepDrRVO outperforms conventional state-of-the-art classification models, such as ResNet18, ResNet50d, MobileNetv3, and EfficientNetb1. These results highlight the potential benefits of the deep learning model in automatic early RVO detection and differential diagnosis for improving clinical outcomes and providing insights into diagnosing other ocular diseases with a few-shot learning challenge. The DeepDrRVO is publicly available on https://github.com/ZhouSunLab-Workshops/DeepDrRVO.

Multimodal Imaging Techniques in Monitoring a Patient with Ocular Decompression Retinopathy

Ocular decompression retinopathy (ODR) is characterized by multiple retinal hemorrhages. It is a rare complication associated with rapid decrease of intraocular pressure (IOP). The course of ODR is usually asymptomatic and self-limiting, which was confirmed by the observation of our patient. In this study, we present a 5-month follow up of a 77-year-old woman with acute right eye (RE) filtration angle closure who developed symptoms of ODR. Clinical examination and multimodal imaging modalities, including color fundus photography, optical coherence tomography (OCT), OCT angiography (OCTA) and fluorescein angiography (FA), were used to confirm the diagnosis and performed regularly in monitoring the course of the disease. Fundus lesions in the RE included diffuse intraretinal hemorrhages in the posterior pole, which gradually resolved during follow-up time. The fundus of the left eye (LE) was normal. The patient underwent conservative therapy, laser therapy and surgery, achieving stabilization of the IOP and improvement of the local condition in the RE. Of the various multimodal imaging techniques, color fundus photography and OCT seemed to be the most specific and helpful in monitoring the patient with ODR.

Hyperreflective material in patients with non-neovascular pachychoroid disease

BackgroundThis study aimed to report eleven cases of non-neovascular pachychoroid disease with hyperreflective material (HRM) that occurred in Japanese patients.MethodsA retrospective review of data from eleven patients who had non-neovascular retinal pigment epithelium (RPE) protrusion with HRM in the neurosensory retina between March 2017 and June 2022 was conducted. Clinical examination, color fundus photography, fluorescein angiography, spectral-domain optical coherence tomography (SD-OCT), and OCT angiography data were analyzed. Main outcome measures were patient characteristics, changes in SD-OCT findings, and symptom outcomes.ResultsAll cases had RPE protrusion and HRM with dilated choroidal veins, which were characteristic of pachychoroid disease. However, none of the cases had macular neovascularization (MNV). In 9 eyes (81.8%), HRM improved spontaneously without intervention and resulted in alterations in RPE, referred to as pachychoroid pigment epitheliopathy (PPE) or focal choroidal excavation (FCE). In these cases, symptoms such as metamorphopsia and distortion improved without treatment. In the remaining two cases (18.2%), HRM still persisted during the follow-up period.ConclusionThere are some cases of non-neovascular pachychoroid disorder with HRM, which might be a new entity of pachychoroid spectrum disease or an early stage of PPE or FCE. These cases should not be misdiagnosed as MNV, and careful observation is necessary.