Ultra-Wide-Field Fluorescein Angiographic Features Influencing Visual Prognosis in Coats' Disease.

Purpose: To investigate the retinal vascular abnormalities in both affected and fellow eyes of presumed unilateral Coats' disease patients using ultra-wide-field fluorescein angiography (UWF-FA) and their association with visual prognosis. Methods: A retrospective review of 30 patients diagnosed with presumed unilateral Coats' disease, evaluated with UWF-FA from March 2003 to May 2024 in a tertiary referral hospital. Clinical features and multimodal imaging findings were evaluated and factors related to final visual outcomes were analyzed. Results: All 30 patients were diagnosed with presumed unilateral Coats' disease at presentation, comprising 36.7% childhood-onset and 63.3% adult-onset patients. Retinal vascular telangiectasia was observed in 51.7% of fellow eyes. The extent of telangiectasia and exudate in the affected eyes did not significantly correlate with extent of telangiectasia in the fellow eyes. In the more affected eyes, the childhood-onset group had a significantly greater extent of capillary drop-out compared to the adult-onset group (5.0 vs 2.8 clock hours, p = 0.023). In the fellow eyes, telangiectasia tended to be more frequent in the childhood-onset group (63.6% vs. 44.4%), without significance (p = 0.160). In the multivariable regression analysis, the final best-corrected visual acuity (BCVA) in the more affected eye was significantly associated with initial BCVA. The mean extent of telangiectasia in the temporal and nasal quadrants and the initial BCVA of the more affected eyes were identified as prognostic factors for final moderate to severe visual loss (Snellen BCVA < 20/66) (OR = 12.8, p = 0.043; OR = 11.8, p = 0.024, respectively). Conclusions: About half of presumed unilateral Coats' disease cases exhibited features of bilateral disease. Visual prognosis is associated with the peripheral retinal telangiectasia in the temporal and nasal quadrants as well as initial BCVA in the affected eyes while it is not associated with retinal vascular abnormalities in the fellow eyes.

Wide-Field Optical Coherence Tomography in Patients with Diabetic Macular Edema.

Background: The goal of the study was to analyze variations in central, perifoveal, and peripheral retinal thickness (RT) and choroidal thickness (CT) in patients with diabetic macular edema (DME) measured with ultra-wide-field optical coherence tomography (UWF-OCT). Additionally, correlations between RT and CT in the central, perifoveal, and peripheral sectors and the presence of selected systemic factors were evaluated. Methods: A total of 74 consecutive adult diabetic patients with DME and 75 healthy controls were included. Study participants were divided into three groups: DME patients without panretinal photocoagulation (PRP; 84 eyes), DME patients after PRP (56 eyes), and healthy controls (125 eyes). RT and CT were analyzed in three zones: a central circle of 3 mm diameter (central), a ring contained between a centered 9 mm circle and the central 3 mm circle (perifoveal), and a second, more peripheral ring between centered 18 mm and 9 mm circles (peripheral). Additionally, DME subgroups were analyzed according to the correlation of RT and CT with age, axial length, best corrected visual acuity (BCVA), diabetes duration, insulin therapy duration, body mass index (BMI), glycosylated hemoglobin (HbA1c) values, intravitreal injection (IVI) count, and the advancement of retinopathy assessed by the simplified diabetic retinopathy severity scale (DRSS). Results: The increase in RT in the far peripheral sectors in DME patients was not significant. The increases in central and perifoveal RT and lower values of CT in PRP-naive DME patients were strongly associated with poorer BCVA. Patients with DME after PRP presented with BCVA improvements significantly related to the number of IVIs. The amount of DME and RT in peripheral sectors were both independent of systemic factors such as BMI, duration of diabetes, duration of insulin intake, retinopathy severity, and HbA1c levels. Conclusions: Peripheral retinal sectors in DME patients are less affected in terms of increase in their thickness compared to central ones. Functional and morphological associations of DME with UWF-OCT testing refer to central and perifoveal sectors.

Choroidal and Retinal Thicknesses in Healthy Eyes Measured with Ultra-Wide-Field Optical Coherence Tomography.

Ultra-wide-field optical coherence tomography (UWF-OCT) has been recently introduced into clinical ophthalmological practice. To date, there are few data on the reference values of the retinal thickness (RT) and choroidal thickness (CT) measured with this technique. This study aimed to analyze the variance in RT and CT in the healthy eyes of white Caucasian patients with UWF-OCT tests performed with the largest available scan size of 23 × 20 mm. The data were analyzed with reference to the patients' age and gender and the axial length of the eyeball. The results of UWF-OCT scanning enabled us to visualize the shape of the retina and choroid in a large portion of the eyeball. Both anatomical entities became significantly thinner at the periphery. The peripheral CT was greater in the upper and temporal sectors; the RT was higher in the nasal compared to the temporal sectors. Both the choroid and retina showed a reduced thickness with age; however, the CT and RT did not show a statistically significant correlation with the axial length after adjusting for age and gender. Age-related variations in thickness were especially prominent in the choroid. The CT in UWF-OCT testing was significantly greater in females, while the RT was greater in males. UWF-OCT testing provides additional information on the anatomical structure of the retina and choroid compared to standard-field OCT.

Retinal vascular morphological characteristics in diabetic retinopathy: an artificial intelligence study using a transfer learning system to analyze ultra-wide field images.

AIM: To investigate the morphological characteristics of retinal vessels in patients with different severity of diabetic retinopathy (DR) and in patients with or without diabetic macular edema (DME). METHODS: The 239 eyes of DR patients and 100 eyes of healthy individuals were recruited for the study. The severity of DR patients was graded as mild, moderate and severe non-proliferative diabetic retinopathy (NPDR) according to the international clinical diabetic retinopathy (ICDR) disease severity scale classification, and retinal vascular morphology was quantitatively analyzed in ultra-wide field images using RU-net and transfer learning methods. The presence of DME was determined by optical coherence tomography (OCT), and differences in vascular morphological characteristics were compared between patients with and without DME. RESULTS: Retinal vessel segmentation using RU-net and transfer learning system had an accuracy of 99% and a Dice metric of 0.76. Compared with the healthy group, the DR group had smaller vessel angles (33.68±3.01 vs 37.78±1.60), smaller fractal dimension (Df) values (1.33±0.05 vs 1.41±0.03), less vessel density (1.12±0.44 vs 2.09±0.36) and fewer vascular branches (206.1±88.8 vs 396.5±91.3), all P<0.001. As the severity of DR increased, Df values decreased, P=0.031. No significant difference between the DME and non-DME groups were observed in vascular morphological characteristics. CONCLUSION: In this study, an artificial intelligence retinal vessel segmentation system is used with 99% accuracy, thus providing with relatively satisfactory performance in the evaluation of quantitative vascular morphology. DR patients have a tendency of vascular occlusion and dropout. The presence of DME does not compromise the integral retinal vascular pattern.

Cross-modality transfer learning with knowledge infusion for diabetic retinopathy grading.

Background: Ultra-wide-field (UWF) fundus photography represents an emerging retinal imaging technique offering a broader field of view, thus enhancing its utility in screening and diagnosing various eye diseases, notably diabetic retinopathy (DR). However, the application of computer-aided diagnosis for DR using UWF images confronts two major challenges. The first challenge arises from the limited availability of labeled UWF data, making it daunting to train diagnostic models due to the high cost associated with manual annotation of medical images. Secondly, existing models' performance requires enhancement due to the absence of prior knowledge to guide the learning process. Purpose: By leveraging extensively annotated datasets within the field, which encompass large-scale, high-quality color fundus image datasets annotated at either image-level or pixel-level, our objective is to transfer knowledge from these datasets to our target domain through unsupervised domain adaptation. Methods: Our approach presents a robust model for assessing the severity of diabetic retinopathy (DR) by leveraging unsupervised lesion-aware domain adaptation in ultra-wide-field (UWF) images. Furthermore, to harness the wealth of detailed annotations in publicly available color fundus image datasets, we integrate an adversarial lesion map generator. This generator supplements the grading model by incorporating auxiliary lesion information, drawing inspiration from the clinical methodology of evaluating DR severity by identifying and quantifying associated lesions. Results: We conducted both quantitative and qualitative evaluations of our proposed method. In particular, among the six representative DR grading methods, our approach achieved an accuracy (ACC) of 68.18% and a precision (pre) of 67.43%. Additionally, we conducted extensive experiments in ablation studies to validate the effectiveness of each component of our proposed method. Conclusion: In conclusion, our method not only improves the accuracy of DR grading, but also enhances the interpretability of the results, providing clinicians with a reliable DR grading scheme.

Deep learning system for screening AIDS-related cytomegalovirus retinitis with ultra-wide-field fundus images.

Background: Ophthalmological screening for cytomegalovirus retinitis (CMVR) for HIV/AIDS patients is important to prevent lifelong blindness. Previous studies have shown good properties of automated CMVR screening using digital fundus images. However, the application of a deep learning (DL) system to CMVR with ultra-wide-field (UWF) fundus images has not been studied, and the feasibility and efficiency of this method are uncertain. Methods: In this study, we developed, internally validated, externally validated, and prospectively validated a DL system to detect AIDS-related from UWF fundus images from different clinical datasets. We independently used the InceptionResnetV2 network to develop and internally validate a DL system for identifying active CMVR, inactive CMVR, and non-CMVR in 6960 UWF fundus images from 862 AIDS patients and validated the system in a prospective and an external validation data set using the area under the curve (AUC), accuracy, sensitivity, and specificity. A heat map identified the most important area (lesions) used by the DL system for differentiating CMVR. Results: The DL system showed AUCs of 0.945 (95 % confidence interval [CI]: 0.929, 0.962), 0.964 (95 % CI: 0.870, 0.999) and 0.968 (95 % CI: 0.860, 1.000) for detecting active CMVR from non-CMVR and 0.923 (95 % CI: 0.908, 0.938), 0.902 (0.857, 0.948) and 0.884 (0.851, 0.917) for detecting active CMVR from non-CMVR in the internal cross-validation, external validation, and prospective validation, respectively. Deep learning performed promisingly in screening CMVR. It also showed the ability to differentiate active CMVR from non-CMVR and inactive CMVR as well as to identify active CMVR and inactive CMVR from non-CMVR (all AUCs in the three independent data sets >0.900). The heat maps successfully highlighted lesion locations. Conclusions: Our UWF fundus image-based DL system showed reliable performance for screening AIDS-related CMVR showing its potential for screening CMVR in HIV/AIDS patients, especially in the absence of ophthalmic resources.

Bilateral sequential ischemic retinopathy and optic neuropathy in IgG1 heavy chain deposition disease.

PURPOSE: To report a case of progressive ischemic retinopathy and optic neuropathy in a patient with heavy chain deposition disease (HCDD), a rare form of monoclonal immunoglobulin deposition disease (MIDD). OBSERVATIONS: Our case describes a 74-year-old woman diagnosed with IgG1 lambda HCDD. After treatment with daratumumab and intravenous IVIG therapy, the patient developed worsening ischemic retinopathy and optic neuropathy, neovascular glaucoma, and bilateral sequential vitreous hemorrhages, necessitating surgical intervention. We present multimodal imaging from the onset of ischemic retinopathy to end-stage maculopathy illustrated by optical coherence tomography (OCT) angiography. Despite discontinuing treatment with daratumumab and providing maximal ocular interventions to control the complications of neovascular disease, the patient's condition progressed, resulting in profound vision loss. CONCLUSIONS AND IMPORTANCE: Our case illustrates the potential for HCDD to cause end-organ disease, including ischemic retinopathy and optic neuropathy, possibly worsened by the patient's underlying cardiovascular risk factor status and medications. Daratumumab, a humanized IgG1 kappa monoclonal antibody that binds to CD38 used to treat specific blood cancers, has been reported to cause disturbances in retinal blood flow, including retinal artery and vein occlusions. It remains to be determined whether careful patient selection or dose adjustments and timing of HCDD treatments could protect vision by reducing the risk of these rare yet severe ocular complications.

Source-free active domain adaptation for diabetic retinopathy grading based on ultra-wide-field fundus images.

Domain adaptation (DA) is commonly employed in diabetic retinopathy (DR) grading using unannotated fundus images, allowing knowledge transfer from labeled color fundus images. Existing DAs often struggle with domain disparities, hindering DR grading performance compared to clinical diagnosis. A source-free active domain adaptation method (SFADA), which generates features of color fundus images by noise, selects valuable ultra-wide-field (UWF) fundus images through local representation matching, and adapts models using DR lesion prototypes, is proposed to upgrade DR diagnostic accuracy. Importantly, SFADA enhances data security and patient privacy by excluding source domain data. It reduces image resolution and boosts model training speed by modeling DR grade relationships directly. Experiments show SFADA significantly improves DR grading performance, increasing accuracy by 20.90% and quadratic weighted kappa by 18.63% over baseline, reaching 85.36% and 92.38%, respectively. This suggests SFADA's promise for real clinical applications.

A Case of Posterior Polar Hemispheric Choroidal Dystrophy Successfully Diagnosed With Ultra-Widefield Fundus Autofluorescence and Optical Coherence Tomography Angiography.

We report a case of a 78-year-old man presenting with uncertain visual field loss, ultimately identified as posterior polar hemispheric choroidal dystrophy (PPHCD) using ultra-widefield fundus autofluorescence (FAF) and optical coherence tomography angiography (OCTA). The patient initially reported blurred vision in the left eye and had a previous diagnosis of suspected bilateral normal tension glaucoma based on optic nerve head excavation and static perimetry measurements. Detailed examination revealed suspicious retinal atrophy. Notably, the patient had a tigroid fundus, which complicated the correlation between visual field defect and chorioretinal atrophy. Ultra-widefield FAF highlighted mosaic/patchy hypofluorescent areas, emphasizing this atrophy. OCTA images confirmed choriocapillaris loss in the hemispheric choroidal atrophy and parafoveal atrophy. The combination of these imaging techniques enabled a definitive diagnosis of PPHCD. Long-term follow-up and continued investigation with these imaging modalities may hold promise for a better understanding of disease progression and management in similar cases.

Deep Learning for prediction of late recurrence of retinal detachment using preoperative and postoperative ultra-wide field imaging.

PURPOSE: To elaborate a deep learning (DL) model for automatic prediction of late recurrence (LR) of rhegmatogenous retinal detachment (RRD) using pseudocolor and fundus autofluorescence (AF) ultra-wide field (UWF) images obtained preoperatively and postoperatively. MATERIALS AND METHODS: We retrospectively included patients >18 years who underwent either scleral buckling (SB) or pars plana vitrectomy (PPV) for primary or recurrent RRD with a post-operative follow-up >2 years. Records of RRD recurrence between 6 weeks and 2 years after surgery served as a ground truth for the training of the deep learning (DL) models. Four separate DL models were trained to predict LR within the 2 postoperative years (binary outputs) using, respectively, UWF preoperative and postoperative pseudocolor images and UWF preoperative and postoperative AF images. RESULTS: A total of 412 eyes were included in the study (332 eyes treated with PPV and 80 eyes with SB). The mean follow-up was 4.0 ± 2.1 years. The DL models based on preoperative and postoperative pseudocolor UWF imaging predicted recurrence with 85.6% (sensitivity 86.7%, specificity 85.4%) and 90.2% accuracy (sensitivity 87.0%, specificity 90.8%) in PPV-treated eyes, and 87.0% (sensitivity 86.7%, specificity 87.0%) and 91.1% (sensitivity 88.2%, specificity 91.9%) in SB-treated eyes, respectively. The DL models using preoperative and postoperative AF-UWF imaging predicted recurrence with 87.6% (sensitivity 84.0% and specificity 88.3%) and 91.0% (sensitivity 88.9%, specificity 91.5%) accuracy in PPV eyes, and 86.5% (sensitivity 87.5%; specificity 86.2%) and 90.6% (sensitivity 90.0%, specificity 90.7%) in SB eyes, respectively. Among the risk factors detected with visualisation methods, potential novel ones were extensive laser retinopexy and asymmetric staphyloma. CONCLUSIONS: DL can accurately predict the LR of RRD based on UWF images (especially postoperative ones), which can help refine follow-up strategies. Saliency maps might provide further insight into the dynamics of RRD recurrence.