Fundus Photography Research Articles

Genetic Characteristics of 63 Patients with Non-syndromic Retinitis Pigmentosa at a Single Korean Institution

Purpose: To investigate the genetic characteristics of patients with non-syndromic retinitis pigmentosa (RP) analyzed at a single institution.Methods: We conducted a retrospective analysis of 63 patients clinically diagnosed with non-syndromic RP who underwent genetic testing. The clinical features of patients exhibiting the most common mutations, <i>EYS</i> and <i>USH2A</i>, were further assessed through routine ophthalmic examinations.Results: Of the 63 patients, 22 (34.9%) exhibited significant mutations. Notably, <i>EYS</i> and <i>USH2A</i> mutations were each found in 5 patients (7.9%); <i>RP1</i> mutations were found in 4 patients (6.3%). The average ages at diagnosis were 38.8 years for <i>EYS</i> mutations and 41.8 years for <i>USH2A</i> mutations. The average best-corrected visual acuities were logMAR 0.08 for <i>EYS</i> mutations and logMAR 0.51 for <i>USH2A</i> mutations. Both mutation types showed a decrease in the normal macular area in fundus photographs with increasing age. In <i>USH2A</i> mutations, optical coherence tomography revealed a more pronounced reduction in central macular thickness and central foveal ellipsoid length compared with <i>EYS</i> mutations. Visual field tests indicated a reduction within the central 10° in 40% of <i>EYS</i> mutations and 60% of <i>USH2A</i> mutations. Electroretinography showed non-detectable responses in 2 individuals with <i>EYS</i> mutations and 4 individuals with <i>USH2A</i> mutations (40% and 80%, respectively).Conclusions: <i>EYS</i> and <i>USH2A</i> mutations represented 45% of the genetically identified cases; affected patients typically were diagnosed in their 40s. <i>EYS</i> mutations tended to preserve retinal function and central foveal structure better than <i>USH2A</i> mutations.

Early applicability of retinopathy of prematurity score (ROPScore) and serum insulin growth factor-1 (IGF-1) for predicting treatment-requiring retinopathy of prematurity: a prospective cohort study

BackgroundRetinopathy of prematurity is a leading cause of blindness especially in developing countries where the accessibility to screening may not be available. Therefore, early prediction could help reallocate the resources for those at high risk.ObjectivesThis study aimed to evaluate the accuracy of the retinopathy of prematurity score (ROPScore) and serum insulin-like growth factor-1 (IGF-1) for predicting treatment-requiring retinopathy of prematurity.MethodsThis prospective cohort study included 87 preterm neonates (≤ 32 weeks). Neonates were screened using digital fundus photography with indirect ophthalmoscopy performed when retinopathy of prematurity changes was detected. Serum insulin-like growth factor-1 was measured in the 3rd week of life.ResultsNine cases (10.3%) developed treatment-requiring retinopathy of prematurity, while 78 patients had mild retinopathy of prematurity. According to logistic regression analysis, lower birth weight and longer duration of assisted ventilation were independent risk factors for treatment-requiring retinopathy of prematurity. At the 2nd week of life, cut-off value of 14.95 for the retinopathy of prematurity score showed a sensitivity of 100% and a specificity of 67.9% for predicting treatment-requiring retinopathy of prematurity. Moreover, serum insulin-like growth factor-1 was significantly lower in patients with treatment-requiring retinopathy of prematurity (p < 0.001).ConclusionsROPScore applied at week 2 and week 6 of life showed the same sensitivity and specificity to predict treatment-requiring retinopathy of prematurity. Furthermore, serum insulin-like growth factor-1 in the 3rd week of life was significantly lower in patients with treatment-requiring retinopathy of prematurity.

Machine learning in ocular oncology and oculoplasty: Transforming diagnosis and treatment

In the domains of ocular oncology and oculoplasty, machine learning (ML) has become a game-changing technology, providing previously unheard-of levels of precision in diagnosis, treatment planning, and outcome prediction. Using imaging modalities, genomic data, and clinical characteristics, this chapter investigates the integration of machine learning algorithms in the detection and treatment of ocular tumours, including retinoblastoma and uveal melanoma. Through predictive modelling and real-time decision-making, it also emphasises how ML might improve surgical outcomes in oculoplasty, including orbital reconstruction and eyelid correction. Automated examination of fundus photographs, histological slides, and 3D imaging has been made possible by methods like deep learning and natural language processing, which have improved individualised therapeutic approaches and decreased diagnostic errors. Additionally, the use of augmented reality and machine learning in robotics and surgery is a significant development in precision oculoplasty. Notwithstanding its potential, issues including data heterogeneity, algorithm interpretability, and ethical considerations are significant roadblocks that need to be addressed. This chapter explores cutting-edge developments, real-world uses, and potential future paths, offering researchers and doctors a thorough resource.Dipali Vikas Mane, Associate Professor, Shriram Shikshan Sanstha’s College of Pharmacy, Paniv-413113

Analysis of macular retinal thickness in polyarteritis nodosa using spectral domain optical coherence tomography

PurposeTo identify the macular retinal layer thickness changes in polyarteritis nodosa (PAN) patients without pathological findings appearing in color fundus photography (CFP), and to investigate the correlations with disease durations.MethodsA total of 24 PAN patients who had been for 3 years or more and underwent SD-OCT were recruited from the UK Biobank, with exclusions for diabetes, eye disease, or abnormal CFP findings. Only the right eyes were included, with each PAN patient paired one-to-one with a control matched for age, sex, and ethnicity. Paired t-tests or Wilcoxon Signed-Rank tests were used to assess the differences in thickness of different retinal layers between groups, followed by linear regression analysis to evaluate the correlations with disease durations.ResultsPAN patients had significantly thinner retinal nerve fiber layer (RNFL) by 12.27% (mean ± standard deviation = 27.39 ± 8.94 μm for PAN patients and 31.22 ± 5.57 μm for controls, p = 0.048) and thinner outer plexiform and outer nuclear layers (OPL-ONL complex) by 10.67% (44.93 ± 6.59 μm for PAN patients and 50.31 ± 7.60 μm for controls, p = 0.032). Visual acuity and the whole macular thickness showed no statistical difference. The RNFL was thinned by 1.22 μm per year of disease progression (95% confidence interval: 0.12, 2.32, p = 0.042).ConclusionsPAN patients without visual impairments or abnormal CFP findings may exhibit significant thinning in RNFL and OPL-ONL complex. SD-OCT may serve as a useful tool for early screening of ophthalmic changes in PAN.

Predictive Value of Ocular Fundus Hemorrhage for Severe Coronary Artery Disease Assessed via SYNTAX Score

Aims/Background The relationship between retinal fundus hemorrhage and the severity of coronary artery lesions remains unclear. This study aimed to explore the incidence of fundus hemorrhage in patients at high risk of coronary heart disease (CHD) and to examine its correlation with the SYNTAX score, a tool used to assess the complexity of coronary artery disease. Methods This retrospective study consecutively enrolled patients undergoing coronary angiography (CAG) at Beijing Anzhen Hospital Hospital from June 2019 to January 2020. Bilateral non-mydriatic fundus photography was performed to detect fundus hemorrhages. The SYNTAX score was calculated to quantify the severity of coronary artery lesions, and patients were divided into two groups: a high SYNTAX score (hSS) group (≥23 points) and a low SYNTAX score (lSS) group (≤22 points). Baseline demographic and clinical data were collected, along with relevant laboratory tests. Results A total of 878 patients were included in the study, with 177 in the hSS group and 701 in the lSS group. Fundus hemorrhage was observed in 91 patients (incidence: 10.36%, 95% confidence interval (CI): 8.35%–12.38%). The incidence of fundus hemorrhage was significantly higher in the hSS group compared to the lSS group (21.47% [38/177] vs. 7.56% [53/701], p &lt; 0.001). Multivariate logistic regression analysis identified fundus hemorrhage, body mass index (BMI), and low-density lipoprotein cholesterol (LDL-C) as independent predictors of high SYNTAX scores. Conclusion Fundus hemorrhage is significantly associated with a higher SYNTAX score and may serve as a potential predictor of severe coronary artery lesions in clinical practice.

Comparison of a Novel Ultra-Widefield Three-Color Scanning Laser Ophthalmoscope to Other Retinal Imaging Modalities in Chorioretinal Lesion Imaging.

To compare the assessment of clinically relevant retinal and choroidal lesions as well as optic nerve pathologies using a novel three-wavelength ultra-widefield (UWF) scanning laser ophthalmoscope with established retinal imaging techniques for ophthalmoscopic imaging. Eighty eyes with a variety of retinal and choroidal lesions were assessed on the same time point using Topcon color fundus photography (CFP) montage, Optos red/green (RG), Heidelberg SPECTRALIS MultiColor 55-color montage (MCI), and novel Optos red/green/blue (RGB). Paired images of the optic nerve, retinal, or choroidal lesions were initially diagnosed based on CFP imaging. The accuracy of the imaging was then evaluated in comparison to CFP using a grading scale ranging from -1 (losing imaging information) to +1 (gaining imaging information). Eighty eyes of 43 patients with 116 retinal or choroidal pathologies, as well as 59 eyes with optic nerve imaging using CFP, MCI, RG, and RGB, were included in this study. Across all subgroups, RGB provided significantly more accurate clinical imaging with CFP as ground truth and compared to other modalities. This was true comparing RGB to both RG (P = 0.0225) and MCI (P < 0.001) overall. Although RGB provided more accurate clinical information overall, it was inferior to RG for melanocytic choroidal lesions (P = 0.011). RGB can be considered as a useful tool to detect characteristics of central, midperipheral, and peripheral retinal lesions. Regarding melanocytic choroidal lesions, RGB was inferior to RG, and MCI was inferior to both RG and RGB modalities due to color changes. Traditional retinal ultra-widefield imaging uses two wavelengths. Here, we evaluated three wavelengths for ultra-widefield imaging. We examined new optics (basic science) effect on patient imaging (clinical care).

Characterization of the Disorganization of the Inner Retinal Layers in Diabetics Using Increased Axial Resolution Optical Coherence Tomography.

To compare a novel high-resolution optical coherence tomography (OCT) with improved axial resolution (High-Res OCT) with conventional spectral-domain OCT (SD-OCT) with regard to their capacity to characterize the disorganization of the retinal inner layers (DRIL) in diabetic maculopathy. Diabetic patients underwent multimodal retinal imaging (SD-OCT, High-Res OCT, and color fundus photography). Best-corrected visual acuity and diabetes characteristics were recorded. DR was graded using the international clinical diabetic retinopathy severity scale (DRSS). In each OCT B-scan, retinal layers were segmented and the loss of discernibility was annotated. DRIL areas were analyzed in en face projection using FIJI plugins. The Wilcoxon test and regression models were used for statistical analysis. In 93 eyes of 93 patients (mean age, 61.8 ± 12.9 years) DRIL was identified in 48 eyes. DRIL was most frequent in the central subfield (27%). In DRIL eyes, DRSS was significantly higher (4.43 ± 1.01 vs. 2.12 ± 1.66; P < 0.001), BCVA was significantly worse (0.34 ± 0.38 vs. 0.13 ± 0.22; P < 0.001), and the loss of discernibility of the individual inner retinal layers was significantly smaller in High-Res OCT compared with SD-OCT (0.21 ± 0.29 vs. 1.21 ± 1.21mm2; P < 0.001). The discernibility loss was greatest in the retinal nerve fiber layer and ganglion cell layer. DRIL occurs in eyes with advanced diabetic retinopathy, with a characteristic spread: from the inner toward the outer retina. High-Res OCT shows significantly smaller DRIL areas compared with SD-OCT, because of a more precise delineation of the inner retinal layers. Using OCT with increased axial resolution could enhance our understanding of DRIL development and progression, providing deeper insights into pathophysiological aspects, including malperfusion in the inner capillary plexus.

Transforming Non-Digital, Clinical Workflows to Detect and Track Vision-Threatening Diabetic Retinopathy via a Digital Platform Integrating Artificial Intelligence: Implementation Research.

Screening diabetic retinopathy (DR) for timely management can reduce global blindness. Many existing DR screening programs worldwide are non-digital, standalone, and deployed with grading retinal photographs by trained personnel. To integrate the screening programs, with or without artificial intelligence (AI), into hospital information systems to improve their effectiveness, the non-digital workflow must be transformed into digital. We developed a cloud-based digital platform and implemented it in an existing DR screening program. We conducted the following processes in the platform for prospective DR screening at a community hospital: capturing patients' retinal photographs, uploading them for grading by AI or trained personnel on alternate weeks for 32weeks, and referring vision-threatening DR to a referral center. At this center, the platform was applied for the assessment of potential missed referrals via remote over-reading by a retinal specialist and tracking referrals. Implementational outcomes, such as detecting positive cases, agreement between AI and over-reading, and referral adherence were assessed. Of 645 patients screened by AI, 201 (31.2%) were referrals, 129 (64.2%) of which were true positives agreeable by over-reading; 115 of these true positives (89.1%) had referral adherence. False negatives judged by over-reading were 1.1% (5/444). Of 730 patients in manual screening, 175 (24.0%) were potential referrals, 11 (6.3%) of which were referred at the point-of-screening; eight of these (72.7%) adhered to referral. The remaining 164 cases were appointed for later examination by a visiting general ophthalmologist; 11 of these 116 examined (9.5%) were referred for non-DR-related eye conditions with 81.8% (9/11) referral adherence. No system failure or interruption was found. The digital platform can be practically integrated into the existing non-digital DR screening programs to implement AI and monitor previously unknown but important indicators, such as referral adherence, to improve the effectiveness of the programs. ClinicalTrials.gov. (registration number: NCT05166122).

Exploring the correlations between six serological inflammatory markers and different stages of type 2 diabetic retinopathy

To determine the correlations between six serological inflammatory markers, namely the systemic immune-inflammation index (SII), systemic inflammatory response index (SIRI), aggregate index of systemic inflammation (AISI), neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), and monocyte-to-lymphocyte ratio (MLR), and various stages of type 2 diabetic retinopathy (T2DR). Additionally, the diagnostic value of these markers in T2DR was evaluated. Clinical data were collected from a total of 397 patients with type 2 diabetes who visited the ophthalmology department at Mian Yang Central Hospital and the Affiliated Hospital of Southwest Medical University from January 2023 to December 2023. Based on the results of fundus photography, patients were categorized into a non-diabetic retinopathy group (NDR, n = 121), a non-proliferative diabetic retinopathy group (NPDR, n = 77), and a proliferative diabetic retinopathy group (PDR, n = 199). General patient information and systemic inflammatory markers, including the SII, SIRI, AIRI, NLR, PLR, and MLR, were compared among the groups, and their correlations with T2DR were analyzed. The SII values were found to be significantly higher in the PDR group compared to the NPDR group, which in turn were higher than those in the NDR group (P < 0.05). Similarly, the AISI values were significantly elevated in the PDR group compared to both the NPDR and NDR groups (P < 0.05). The SIRI and MLR values were significantly higher in the PDR group than in the NDR group (P < 0.05). Furthermore, the NLR and PLR values were significantly higher in the NPDR and PDR groups compared to the NDR group (P < 0.05). The Mantel‒Haenszel chi-square test revealed a significant linear trend between the SII and PLR and the incidence of PDR (P < 0.001), with the incidence of PDR increasing as the quartile levels of the SII and PLR increased. Multivariate logistic regression analysis indicated that, compared with NDR, a higher SII was found to be an independent risk factor for NPDR (ORSII = 1.002, p = 0.001) and PDR (ORSII = 1.002, P < 0.001). The ROC curve analysis suggested that the combined assessment of the six inflammatory indices had the highest accuracy in the evaluation of DR, with an area under the curve (AUC) of 0.69, a sensitivity of 54%, and a specificity of 75%. The results of this study indicate that the SII is an independent risk factor for T2DR. A close correlation was observed between the SII and PLR and the occurrence and progression of T2DR. The high accuracy of the combined diagnosis of T2DR via various serological inflammatory markers underscores their potential as early biological indicators for the diagnosis of T2DR.

Nighttime systolic blood pressure a major factor of retinal vascular caliber changes in patients with newly diagnosed type 2 diabetes mellitus.

Changes in retinal vessel caliber are crucial for detecting early retinopathy, a significant cause of blindness in individuals with Diabetes Mellitus type 2 (T2DM). This study aims to evaluate the changes in retinal vessel caliber and identify factors associated with these changes in recently diagnosed T2DM patients. The study included newly diagnosed T2DM patients (within 6 months of diagnosis) who were free of antidiabetic treatment (except metformin) and matched individuals based on age and blood pressure (BP). Data collected included somatometric measurements, BP (office and 24-hour), hematological data, albuminuria (via 24-hour urine collections), ten-year atherosclerotic cardiovascular disease risk (ASCVD score), endothelial dysfunction (measured by Asymmetric Dimethylarginine, ADMA), retinal microvascular changes, assessed as central retinal arteriolar equivalent (CRAE), central retinal venular equivalent (CRVE), and arteriovenous ratio (AVR) using specialized software on non-mydriatic fundus photographs. The study involved 87 T2DM patients and 90 controls, aged 57±11 years. Key findings include no significant differences in CRAE, CRVE, and AVR between T2DM patients and controls. Age (p=0.019) and nighttime systolic BP (SBP) (p=0.002) were independent predictors of AVR. CRAE was independently associated with nighttime SBP (p=0.048). CRVE was independently associated with age (p=0.016), dipping (p=0.002), and smoking (p=0.018). In normotensive subjects, AVR was significantly lower in T2DM patients (p=0.035). The study concludes that increased nighttime SBP is a more critical factor than hyperglycemia in affecting retinal vascular caliber changes in newly diagnosed T2DM patients. This highlights the importance of managing nocturnal hypertension to prevent retinal damage in this patient population.

An Anatomical Study of Drushtipatal (Retina) with Special Reference to Fundus Photo and its Correlation with Dehaprakruti- An observational study

An Anatomical Study of Drushtipatal (Retina) with Special Reference to Fundus Photo and its Correlation with Dehaprakruti- An observational study

The Associations Between Myopia and Fundus Tessellation in School Children: A Comparative Analysis of Macular and Peripapillary Regions Using Deep Learning.

To evaluate the refractive differences among school-aged children with macular or peripapillary fundus tessellation (FT) distribution patterns, using fundus tessellation density (FTD) quantified by deep learning (DL) technology. The cross-sectional study included 1942 school children aged six to 15 years, undergoing ocular biometric parameters, cycloplegic refraction, and fundus photography. FTD was quantified for both the macular (6 mm) and peripapillary (4 mm) regions, using DL-based image processing applied to 45° color fundus photographs. Eyes exhibiting tessellation were classified into two groups: the macular distribution group had greater FTD in the macular area, while the peripapillary distribution group had higher FTD in the peripapillary area, allowing for a comparative analysis of axial length (AL), corneal radius, and refraction. Participants had a median age of 13years and a median spherical equivalent (SE) of -0.75 D. The macular distribution group exhibited significantly larger AL (24.13mm vs. 23.93mm, P < 0.001) and more myopic refraction (-1.13 D vs. -0.75 D, P < 0.001) compared to the peripapillary group. A higher prevalence of macular-distributed FT was noted in the myopic groups (χ2 = 131.675, P < 0.001). SE negatively correlated with macular (r = -0.238) and peripapillary FTD (r = -0.195), while AL positively correlated with FTD in both regions (r = 0.308; r = 0.265) (all P < 0.001). The macular FT distribution pattern is significantly associated with larger AL and greater myopic refraction in school-aged children, suggesting its potential as a marker for identifying children at risk of progressing myopia. DL analysis precisely identifies FT distribution patterns, potentially enhancing early detection of high-risk myopia in populations.

Estimating Visual Acuity With Spectacle Correction From Fundus Photos Using Artificial Intelligence

Determining spectacle-corrected visual acuity (VA) is essential when managing many ophthalmic diseases. If artificial intelligence (AI) evaluations of macular images estimated this VA from a fundus image, AI might provide spectacle-corrected VA without technician costs, reduce visit time, or facilitate home monitoring of VA from fundus images obtained outside of the clinic. To estimate spectacle-corrected VA measured on a standard eye chart among patients with diabetic macular edema (DME) in clinical practice settings using previously validated AI algorithms evaluating best-corrected VA from fundus photographs in eyes with DME. Retrospective cross-sectional evaluation of deidentified fundus photographs matched to spectacle-corrected VA determined by technicians on eye charts among patients with a history of DME based on optical coherence tomography and at least 2 visits within 1 to 6 months of each other at a university-based clinic between January 2014 and December 2022. Data were analyzed from January 2023 to October 2024. Previously validated AI algorithm evaluation of fundus photographs. AI-determined VA mean absolute error (MAE) compared with actual spectacle-corrected VA. Among 141 patients, the mean (SD) age was 63 (13) years, 71 (50%) were male, 2 (1%) were Asian, 42 (30%) were Black or African American, and 88 (63%) were White. Among 282 eyes at visit 1, 66 had nonproliferative diabetic retinopathy (NPDR) and DME, 38 had proliferative diabetic retinopathy (PDR) and DME, 101 had NPDR and no DME, and 77 had PDR and no DME. Among 564 images (282 eyes) at both initial and follow-up visits, MAE (SD) among eyes with NPDR, with or without center-involved DME (CI-DME), was 1.16 (1.00) lines on the eye chart for VA between 20/10 and 20/20 (67 images), and 1.44 (1.15) lines for between VA 20/25 and 20/80 (231 images). MAE (SD) among eyes with PDR, with or without CI-DME, was 1.92 (1.08) lines for VA between 20/10 and 20/20 (50 images), and 1.42 (0.97) lines for spectacle-corrected VA between 20/25 and 20/80 (150 images). Only 65 images had VA 20/100 or worse, precluding meaningful analyses. In this cross-sectional study, AI evaluation of fundus photographs among patients with DME and VA 20/80 or better estimated spectacle-corrected VA within approximately 1 to 1.5 lines of actual spectacle-corrected VA. These results support use of AI evaluation of fundus photographs to determine spectacle-corrected VA among patients with DME globally, beyond ophthalmology offices.

Topographic changes in macula and its association with visual outcomes in idiopathic epiretinal membrane surgery.

We investigated changes in macular topography and their association with visual acuity and metamorphopsia in the idiopathic epiretinal membrane (iERM). Twenty-four eyes that underwent vitrectomy and ERM removal with internal limiting membrane peeling were included in this study. Best-corrected visual acuity (BCVA) and horizontal/vertical metamorphopsia scores (h and vM-scores in the M-chart) were assessed. The distances of fovea-disc (FD) and fovea-vascular arcade (FV), central subfield macular thickness (CSMT), and foveal location were measured using fundus photography, optical coherence tomography (OCT), and OCT angiography, respectively. The BCVA (logMAR) and vM-scores (P < 0.001, P = 0.014, respectively) improved after surgery. The distance of the FD decreased (P < 0.001) and FVs increased (P < 0.001, both). The fovea moved horizontally toward the disc (P < 0.001). The change in median total FVs (7.114 mm to 7.369 mm, P = 0.001) correlated with the change in BCVA (P = 0.049, Pearson's [r] = -0.404). No topographic parameters were associated with an improvement in the vM score. The macular topography significantly changed after iERM removal; the fovea moved nasally, and the distance between the superior and inferior vascular arcades increased. Such a change was relevant to the improvement in BCVA, but not metamorphopsia.

Robust Diabetic Retinopathy Detection and Grading using Neutrosophic Topological Vector Space on Fundus Imaging

Diabetic retinopathy (DR) is an eye disorder triggered by diabetes that might result in loss of sight. Earlier diagnosis of DR is critical since it might cause loss of sight. Manual diagnoses of DR severity by ophthalmologists are time-consuming and challenging. As a result, there has been considerable attention on designing an automatic technique for DR detection using fundus photographs. In medical science, prognosis and diagnosis are the most challenging tasks due to the presence of fuzziness in medical images and the restricted subjectivity of the experts. Neutrosophic Set (NS) in medical image analysis provides an understanding of the NS concepts, together with knowledge of how to collect, handle, interpret, and analyze clinical images using NS techniques. The neutrosophic set (NS), which is a generality of fuzzy set, provides the overcoming prospect of the restriction of fuzzy-based models for the analysis of medical images. This manuscript develops a Robust Diabetic Retinopathy Detection and Grading using Neutrosophic Topological Vector Space (DRDG-NSTVS) technique on fundus images. The DRDG-NSTVS technique begins with Median Filter (MF) noise removal to optimize the clarity of fundus photographs by successfully eliminating noises. Later, the InceptionV3 is used to perform feature extraction for identifying complicated features and patterns related to DR. The parameter tuning is performed by the moth flame optimization (MFO) technique to ensure superior performance of the model. The final diagnoses and classification of DR are accomplished utilizing the NSTVS classifiers that easily perform the uncertainties inherent in medicinal statistics. The simulation was conducted on a benchmark dataset to examine the proposed model performance. This combined method gives a greatly reliable and accurate solution for the earlier diagnosis and detection of DR

EYE SHAPE DEFORMITY PREDICTS MYOPIC MACULOPATHY PROGRESSION AMONG HIGHLY MYOPIC INDIVIDUALS: A 4-Year Longitudinal Study.

To determine the impact of eye shape using three-dimensional magnetic resonance imaging on myopic maculopathy (MM) progression. At baseline, 67 participants with high myopia were selected. Eye shape was classified into spheroidal, ellipsoidal, temporally distorted, nasally distorted, conical, and barrel-shape identified from three-dimensional magnetic resonance imaging. Spheroidal and ellipsoidal shapes were defined as nondeformity; others were defined as eye deformity. Myopic maculopathy progression was determined through color fundus photography. Within a 4-year follow-up, 17.1% (7/41) of patients with nondeformed eye shape had MM progression, whereas 69.2% (18/26) of patients with eye shape deformity had MM progression. In multivariable analysis, eye shape deformity (odds ratio, 4.35; 95% confidence interval, 1.10-17.29; P = 0.036) and axial length of ≥28 mm (odds ratio, 12.75; 95% confidence interval, 2.27-71.48; P = 0.004) significantly correlated with MM progression. The predictive discrimination of eye shape alone for MM progression did not differ from axial length (area under the curve: 0.765 vs. 0.750, P = 0.486). By incorporating age, sex, axial length, and eye shape, the prediction model achieved an area under the curve of 0.862 for discriminating MM progression. Eye shape deformity assessed by three-dimensional magnetic resonance imaging is a novel predictor for MM progression in high myopia.

RETINAL PIGMENT EPITHELIAL DETACHMENTS DEVOID OF RETINAL PIGMENT EPITHELIUM.

To describe two patients with chronic central serous chorioretinopathy showing what appeared to be retinal pigment epithelium detachments lacking imaging findings consistent with retinal pigment epithelium (RPE) over the elevation. The patients underwent comprehensive ophthalmic examination, including multicolor fundus photography, fundus autofluorescence, and spectral-domain optical coherence tomography. A 70-year-old man and a 58-year-old man, diagnosed with chronic central serous chorioretinopathy, showed pigment epithelium detachment-like lesions that were hypoautofluorescent, suggesting an absence of RPE. Spectral-domain optical coherence tomography B scans showed serous, dome-shaped elevations composed of a narrow, mildly hyperreflective band (9-10- µ m thick) that demonstrated hypertransmission of light. The material that constituted the elevation was contiguous with the outer portion of the RPE band at the lesion borders. Based on the multimodal imaging findings, we hypothesize that these pigment epithelial detachments have lost the RPE. A thin layer of material that could represent a residual layer of basal laminar deposit produced by the RPE remains overlying the detachments, possibly accounting for their dome shape and structural stability.

ANGULAR SIGN OF HENLE FIBER LAYER HYPERREFLECTIVITY IN PURTSCHER AND PURTSCHER-LIKE RETINOPATHY.

Angular sign of Henle fiber layer hyperreflectivity is a marker of Henle fibre layer ischemia. Our aim is to describe angular sign of Henle fiber layer hyperreflectivity as a novel optical coherence tomography sign in Purtscher and Purtscher-like retinopathy. Here, we present three cases, one classical Purtscher retinopathy and two Purtscher-like retinopathy who had angular sign of Henle fiber layer hyperreflectivity on spectral domain optical coherence tomography imaging. Modalities such as color fundus photography, cross-sectional optical coherence tomography, optical coherence tomography angiography, and fluorescein angiography were used. Presence of angular sign of Henle fiber layer hyperreflectivity in Purtscher retinopathy and Purtscher-like retinopathy points toward a deep capillary plexus insult and has prognostic implications.

Quantitative analysis of retinal vascular parameters changes in school-age children with refractive error using artificial intelligence.

To quantitatively analyze the relationship between spherical equivalent refraction (SER) and retinal vascular changes in school-age children with refractive error by applying fundus photography combined with artificial intelligence (AI) technology and explore the structural changes in retinal vasculature in these children. We conducted a retrospective case-control study, collecting data on 113 cases involving 226 eyes of schoolchildren aged 6-12 years who attended outpatient clinics in our hospital between October 2021 and May 2022. Based on the refractive spherical equivalent refraction, we categorized the participants into four groups: 66 eyes in the low myopia group, 60 eyes in the intermediate myopia group, 50 eyes in the high myopia group, and 50 eyes in the control group. All participants underwent a series of examinations, including naked-eye and best-corrected visual acuity, cycloplegic spherical equivalent refraction, intraocular pressure measurement, ocular axial measurement (AL), and color fundus photography. Using fundus photography, we quantitatively analyzed changes in the retinal vascular arteriovenous ratio (AVR), average curvature, and vascular density with AI technology. Data were analyzed using the χ2 test and one-way analysis of variance. The AVR in the low myopia group, moderate myopia group, high myopia group, and control group were 0.80 ± 0.05, 0.80 ± 0.04, 0.76 ± 0.04, and 0.79 ± 0.04, respectively, and the vessel densities were 0.1024 ± 0.0076, 0.1024 ± 0.0074, 0.0880 ± 0.0126, and 0.1037 ± 0.0143, respectively The difference between the AVR and vascular density in the high myopia group was statistically significant compared to the other three groups (p < 0.05). Linear correlation analysis showed a strong negative correlation between the spherical equivalent refraction and the ocular axis (r = -0.874, p < 0001), a moderate positive correlation between the spherical equivalent refraction and the vascular density (r = 0.527, p < 0001), and a moderate negative correlation between the ocular axis and the vascular density (r = -0.452, p < 0001). Schoolchildren with high myopia showed a decreased AVR and decreased vascular density in the retinal vasculature. The AVR and vascular density may be early predictors of myopia progression.

Assessing the documentation of publicly available medical image and signal datasets and their impact on bias using the BEAMRAD tool

AbstractMedical datasets are vital for advancing Artificial Intelligence (AI) in healthcare. Yet biases in these datasets on which deep-learning models are trained can compromise reliability. This study investigates biases stemming from dataset-creation practices. Drawing on existing guidelines, we first developed a BEAMRAD tool to assess the documentation of public Magnetic Resonance Imaging (MRI); Color Fundus Photography (CFP), and Electrocardiogram (ECG) datasets. In doing so, we provide an overview of the biases that may emerge due to inadequate dataset documentation. Second, we examine the current state of documentation for public medical images and signal data. Our research reveals that there is substantial variance in the documentation of image and signal datasets, even though guidelines have been developed in medical imaging. This indicates that dataset documentation is subject to individual discretionary decisions. Furthermore, we find that aspects such as hardware and data acquisition details are commonly documented, while information regarding data annotation practices, annotation error quantification, or data limitations are not consistently reported. This risks having considerable implications for the abilities of data users to detect potential sources of bias through these respective aspects and develop reliable and robust models that can be adapted for clinical practice.