Prediction of Axial Length From Macular Optical Coherence Tomography Using Deep Learning Model.

Purpose: The purpose of this study was to develop a deep learning model for predicting the axial length (AL) of eyes using optical coherence tomography (OCT) images. Methods: We retrospectively included patients with AL measurements and OCT images taken within 3 months. We utilized a 5-fold cross-validation with the ResNet-152 architecture, incorporating horizontal OCT images, vertical OCT images, and dual-input images. The mean absolute error (MAE), R-squared (R2), and the percentages of eyes within error ranges of ±1.0, ±2.0, and ±3.0 mm were calculated. Results: A total of 9064 eyes of 5349 patients (total image number of 18,128) were included. The average AL of the eyes was 24.35 ± 2.03 (range = 20.53-37.07). Utilizing horizontal and vertical OCT images as dual inputs, deep learning models predicted AL with MAE and R2 of 0.592 mm and 0.847 mm, respectively, in the internal test set (1824 eyes of 1070 patients). In the external test set (171 eyes of 123 patients), the deep learning models predicted AL with MAE and R2 of 0.556 mm and 0.663 mm, respectively. Regarding error margins of ±1.0, ±2.0, and ±3.0 mm, the dual-input models showed accuracies of 83.50%, 98.14%, and 99.45%, respectively, in the internal test set, and 85.38%, 99.42%, and 100.00%, respectively, in the external test set. Conclusions: A deep learning-based model accurately predicts AL from OCT images. The dual-input model showed the best performance, demonstrating the potential of macular OCT images in AL prediction. Translational Relevance: The study provides new insights into the relationship between retinal and choroidal structures and AL elongation using artificial intelligence models.

Clinical features of primary and compound forms of wide macular posterior staphyloma in high myopia.

BACKGROUND: To compare the ocular features of highly myopic eyes with posterior staphyloma of wide macular type according to its morphological complexity. METHODS: In this cross-sectional study, wide macular posterior staphyloma (WMPS) was classified into the primary (Curtin type I) and the compound (Curtin types VI to X) forms based on the configuration within the staphyloma. The grades of myopic maculopathy and the thicknesses of choroid and sclera were compared between the primary and compound forms of WMPS. RESULTS: A total of 154 eyes (103 patients) with primary WMPS and 65 eyes (49 patients) with compound WMPS were included. Eyes with compound WMPS had worse visual acuity (P = 0.001) and greater axial length (P < 0.001) than those with primary WMPS. Compared to primary WMPS, compound WMPS had a higher grade of myopic macular degeneration (P < 0.001) and a higher frequency of lamellar or full-thickness macular hole associated with myopic traction (21.5% vs. 10.4%; P = 0.028) and active or scarred myopic choroidal neovascularization (33.8% vs. 20.1%; P = 0.030). On swept-source optical coherence tomography, eyes with compound WMPS had significantly thinner choroid and sclera. CONCLUSIONS: The compound form of WMPS had more severe myopic macular changes and worse visual prognosis compared to the primary form of WMPS, and these were associated with more structural deformation in the posterior eyeball. Compound WMPS should be considered as an advanced form of staphyloma.

Acute Annular Outer Retinopathy in a Patient Aged 29 Years.

This case report discusses a diagnosis of acute annular outer retinopathy in a 29-year-old female patient who presented with recent onset of visual field defect and photopsia.

MORPHOLOGICAL BIOMARKERS PREDICTING EXUDATIVE CONVERSION IN TYPE 1 NONEXUDATIVE MACULAR NEOVASCULARIZATION USING OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY.

PURPOSE: To investigate the incidence and morphological biomarkers to predict the exudative conversion in eyes with type 1 nonexudative macular neovascularization using swept-source optical coherence tomography angiography. METHODS: Macular neovascularizations were detected using the retinal pigment epithelium-to-retinal pigment epithelium-fit slab of swept-source optical coherence tomography angiography scan. Depending on whether exudation developed within a year, the eyes were divided into two groups: active and silent. Qualitative and quantitative optical coherence tomography angiography parameters of the two groups were evaluated to discriminate the biomarkers associated with exudative conversion. RESULTS: Of the 40 eyes, nine developed exudation within 1 year (incidence rate 22.5%). The active group exhibited a significantly higher "anastomosis and loops" pattern, greater "vessel density," increased "junction density," fewer "number of end points," and lower "lacunarity" compared with the silent group. "Anastomosis and loops" and higher "vessel density" were correlated with the active group in multivariate analyses. A predictive model combining these biomarkers achieved 95% accuracy in predicting exudative conversion. CONCLUSION: At 12 months, the risk of exudation was 22.5%, and "anastomosis and loops" and "vessel density" were useful optical coherence tomography angiography biomarkers for predicting exudative conversion in eyes with type 1 nonexudative macular neovascularization. For eyes with a high risk of exudative conversion, more frequent follow-up is recommended.

Quantitative microvascular analysis in different stages of retinitis pigmentosa using optical coherence tomography angiography.

As retinitis pigmentosa (RP) is chronic and progressive, the chronological sequence of microvascular changes is important for understanding its pathophysiology. We aimed to investigate retinal and choroidal microvascular changes according to the RP stages. The stages of RP were classified into three stages according to the integrity and width of the inner segment ellipsoid zone: early, ≥ 2500 µm; moderate, < 2500 µm; advanced, absence. Using optical coherence tomography angiography, quantitative microvascular parameters were analyzed. In total, 91 eyes from 49 patients were included. For the superficial capillary plexus (SCP) and deep capillary plexus (DCP), perfusion densities (PDs) in the early stage (SCP: 37.32 ± 8.11%; DCP: 21.19 ± 9.15%) were greater than those in moderate (SCP: 34.16 ± 6.65%, P = 0.011; DCP: 15.67 ± 8.85%, P = 0.031) and advanced stages (SCP: 33.71 ± 9.02%, P = 0.030; DCP: 12.83 ± 6.29%, P < 0.001). The choroidal vascularity index in the early stage (0.58 ± 0.03) was greater than those in the moderate (0.57 ± 0.02, P = 0.017) and advanced stage (0.56 ± 0.02, P = 0.033). The area and perimeter of foveal avascular zone (FAZ) in advanced stage (0.44 ± 0.26 mm2, 2.96 ± 0.86 mm, respectively) were larger than those in early (0.26 ± 0.11 mm2, P = 0.020; 2.19 ± 0.53 mm, P = 0.006, respectively) and moderate stage (0.28 ± 0.13 mm2, P = 0.043; 2.24 ± 0.67 mm, P = 0.013, respectively). During RP disease progression, retinal and choroidal microvascular vessel density decreases in the early stage, followed by FAZ enlargement in the advanced stage.

The effect of glycosylated hemoglobin levels on the response to intravitreal dexamethasone implant for treating diabetic macular edema.

This study investigates the impact of glycosylated hemoglobin (HbA1c) on the efficacy of intravitreal dexamethasone (DEX) implants in patients with diabetic macular edema (DME) over a 12-month period. We retrospectively reviewed 90 DME patients treated with DEX implants, categorizing them based on baseline HbA1c levels (≤ 7% and > 7%) and 12-month changes in HbA1c ("improved", "stable", "worsened"). At the 2-month mark, the mean central subfield thickness (CST) reduction in the HbA1c ≤ 7% group was - 147.22 ± 113.79 µm compared to -130.41 ± 124.50 µm in the > 7% group (p = 0.506). Notably, 12-month outcomes between these groups showed no significant difference. The "improved" HbA1c subgroup experienced a more pronounced CST reduction at 2 months (p = 0.042), with outcomes leveling off with other groups by 12 months. Conclusively, DEX implant outcomes in DME were not influenced by either baseline HbA1c levels or their changes over time. This suggests that local alterations in the inflammation milieu may have a potentially stronger impact on DME treatment outcomes, highlighting the importance of considering local factors in DME treatment.

Longer axial length is associated with better prediction for refractive error after sutureless flanged intrascleral fixation of intraocular lens.

OBJECTIVE: To investigate refractive outcomes and associated factors after sutureless flanged intrascleral fixation of intraocular lens (SFIF-IOL). METHODS: We retrospectively reviewed the medical records of consecutive patients who underwent SFIF-IOL at a single centre. The prediction error (PE; difference between the achieved and target refractive error) and absolute PE (APE) were analysed. Risk factors associated with refractive surprise, defined as APE > +0.5 D, were investigated using multivariable logistic regression analysis. RESULTS: Ninety-one eyes were included. At the final follow-up, the mean PE and APE were +0.07 ± 0.88 and +0.68 ± 0.56 D, respectively. Refractive surprise was observed in 44 eyes (54.3%) and was associated with a shorter axial length (AL) [odds ratio, 0.825; 95% confidence interval, 0.688-0.991; P = 0.039]. APE showed a significant correlation with AL at the final visit (⍴ = -0.269, P = 0.010), and eyes with AL ≥ 26 mm had significantly lower APE than did those with AL of 24-26 mm (P = 0.021) and AL < 24 mm (P = 0.0059). CONCLUSIONS: The refractive outcome after SFIF-IOL using manufacturer's A constant was favourable on average. Eyes with a longer AL were more likely to show a smaller deviation from the target refraction.

Preliminary analysis of predicting the first recurrence in patients with neovascular age-related macular degeneration using deep learning.

BACKGROUND: To predict, using deep learning, the first recurrence in patients with neovascular age-related macular degeneration (nAMD) after three monthly loading injections of intravitreal anti-vascular endothelial growth factor (anti-VEGF). METHODS: Optical coherence tomography (OCT) images were obtained at baseline and after the loading phase. The first recurrence was defined as the initial appearance of a new retinal hemorrhage or intra/subretinal fluid accumulation after the initial resolution of exudative changes after three loading injections. Standard U-Net architecture was used to identify the three retinal fluid compartments, which include pigment epithelial detachment, subretinal fluid, and intraretinal fluid. To predict the first recurrence of nAMD, classification learning was conducted to determine whether the first recurrence occurred within three months after the loading phase. The recurrence classification architecture was built using ResNet50. The model with retinal regions of interest of the entire region and fluid region on OCT at baseline and after the loading phase is presented. RESULTS: A total of 1,444 eyes of 1,302 patients were included. The mean duration until the first recurrence after the loading phase was 8.20 ± 15.56 months. The recurrence classification system revealed that the model with the fluid region of OCT after the loading phase provided the highest classification performance, with an area under the receiver operating characteristic curve (AUC) of 0.725 ± 0.012. Heatmap analysis revealed that three pathological fluids, subsided choroidal neovascularization lesions, and hyperreflective foci were important areas for the first recurrence. CONCLUSIONS: The deep learning algorithm allowed for the prediction of the first recurrence for three months after the loading phase with adequate feasibility. An automated prediction system may assist in establishing patient-specific treatment plans and the provision of individualized medical care for patients with nAMD.

Vitreous Fatty Amides and Acyl Carnitines Are Altered in Intermediate Age-Related Macular Degeneration.

Purpose: Age-related macular degeneration (AMD) is the leading cause of visual impairment worldwide. In this study, we aimed to investigate the vitreous humor metabolite profiles of patients with intermediate AMD using untargeted metabolomics. Methods: We performed metabolomics using high-resolution liquid chromatography mass spectrometry on the vitreous humor of 31 patients with intermediate AMD and 30 controls who underwent vitrectomy for epiretinal membrane with or without cataract surgery. Univariate analyses after false discovery rate correction were performed to discriminate the metabolites and identify the significant metabolites of intermediate AMD. For biologic interpretation, enrichment and pathway analysis were conducted using MetaboAnalyst 5.0. Results: Of the 858 metabolites analyzed in the vitreous humor, 258 metabolites that distinguished patients with AMD from controls were identified (P values < 0.05). Ascorbic acid and uric acid levels increased in the AMD group (all P values < 0.05). The acyl carnitines, such as acetyl L-carnitine (1.37-fold), and fatty amides, such as anandamide (0.9-fold) and docosanamide (0.67-fold), were higher in patients with intermediate AMD. In contrast, nicotinamide (-0.55-fold), and succinic acid (-1.69-fold) were lower in patients with intermediate AMD. The metabolic pathway related oxidation of branched chain fatty acids and carnitine synthesis showed enrichment. Conclusions: Multiple metabolites related to fatty amides and acyl carnitine were found to be increased in the vitreous humor of patients with intermediate AMD, whereas succinic acid and nicotinamide were reduced, suggesting that altered metabolites related to fatty amides and acyl carnitines and energy metabolism may be implicated in the etiology of AMD.

Deep Learning-based Prediction of Axial Length Using Ultra-widefield Fundus Photography.

PURPOSE: To develop a deep learning model that can predict the axial lengths of eyes using ultra-widefield (UWF) fundus photography. METHODS: We retrospectively enrolled patients who visited the ophthalmology clinic at the Seoul National University Hospital between September 2018 and December 2021. Patients with axial length measurements and UWF images taken within 3 months of axial length measurement were included in the study. The dataset was divided into a development set and a test set at an 8:2 ratio while maintaining an equal distribution of axial lengths (stratified splitting with binning). We used transfer learning-based on EfficientNet B3 to develop the model. We evaluated the model's performance using mean absolute error (MAE), R-squared (R2), and 95% confidence intervals (CIs). We used vanilla gradient saliency maps to illustrate the regions predominantly used by convolutional neural network. RESULTS: In total, 8,657 UWF retinal fundus images from 3,829 patients (mean age, 63.98 ±15.25 years) were included in the study. The deep learning model predicted the axial lengths of the test dataset with MAE and R2 values of 0.744 mm (95% CI, 0.709-0.779 mm) and 0.815 (95% CI, 0.785-0.840), respectively. The model's accuracy was 73.7%, 95.9%, and 99.2% in prediction, with error margins of ±1.0, ±2.0, and ±3.0 mm, respectively. CONCLUSIONS: We developed a deep learning-based model for predicting the axial length from UWF images with good performance.