ESASO classification relevance in the diagnosis and evolution in diabetic macular edema patients after dexamethasone implant treatment.

PURPOSE: To assess the clinical relevance of The European School for Advanced Studies in Ophthalmology (ESASO) classification in patients with diabetic macular edema (DME) after their first dexamethasone implant (DEXI) treatment. METHODS: Retrospective real-world study conducted on consecutive DME patients who underwent DEXI treatment and were controlled at month-2. Subjects were initially classified according to the ESASO classification stages. The outcomes were anatomical biomarkers with spectral-domain optical coherence tomography (SD-OCT) and best-corrected visual acuity (BCVA). RESULTS: A total of 128 patients were classified according to ESASO classification stages as early (7; 5.5%), advanced (100; 78.1%), and severe (21; 16.4%). At baseline, there were significant differences between stages in BCVA, central macular thickness (CMT), and tomography anatomical biomarkers (p < 0.05). Initial BCVA (logMAR) was 0.33 ± 0.10, 0.58 ± 0.34, and 0.71 ± 0.35 in the early, advanced, and severe stages, respectively (p < 0.05). At month-2, BCVA was 0.17 ± 0.15, 0.46 ± 0.29, and 0.69 ± 0.27 in those classified as early, advanced, and severe stages, respectively. At month-2, DME was resolved or improved in 6 (85.7%), 60 (60%), and 12 (60%) patients classified as early, advanced, and severe stages, respectively. CONCLUSIONS: There was a good correlation between BCVA and ESASO classification stages. Patients in the severe stage did not achieve visual acuity improvement over the study period.

Optimized deep CNN for detection and classification of diabetic retinopathy and diabetic macular edema.

Diabetic Retinopathy (DR) and Diabetic Macular Edema (DME) are vision related complications prominently found in diabetic patients. The early identification of DR/DME grades facilitates the devising of an appropriate treatment plan, which ultimately prevents the probability of visual impairment in more than 90% of diabetic patients. Thereby, an automatic DR/DME grade detection approach is proposed in this work by utilizing image processing. In this work, the retinal fundus image provided as input is pre-processed using Discrete Wavelet Transform (DWT) with the aim of enhancing its visual quality. The precise detection of DR/DME is supported further with the application of suitable Artificial Neural Network (ANN) based segmentation technique. The segmented images are subsequently subjected to feature extraction using Adaptive Gabor Filter (AGF) and the feature selection using Random Forest (RF) technique. The former has excellent retinal vein recognition capability, while the latter has exceptional generalization capability. The RF approach also assists with the improvement of classification accuracy of Deep Convolutional Neural Network (CNN) classifier. Moreover, Chicken Swarm Algorithm (CSA) is used for further enhancing the classifier performance by optimizing the weights of both convolution and fully connected layer. The entire approach is validated for its accuracy in determination of grades of DR/DME using MATLAB software. The proposed DR/DME grade detection approach displays an excellent accuracy of 97.91%.

Visual Outcome after Anti-Vascular Epithelial Growth Factor Therapy Using New Classification of Diabetic Macular Edema by Optical Coherence Tomography.

INTRODUCTION: The aim of the study was to examine alterations in visual acuity in patients with diabetic macular edema (DME), classified according to the TCED-HFV optical coherence tomography (OCT) system, following anti-vascular epithelial growth factor (VEGF) therapy. METHODS: The medical records of patients with DME receiving anti-VEGF therapy were retrospectively reviewed. Patients were divided into four groups according to the TCED-HFV OCT classification. Patient demographic and clinical characteristics and best-corrected visual acuity (BCVA) before and after treatment were compared among the groups. RESULTS: The BCVA before treatment was 0.49 ± 0.18, 0.81 ± 0.41, 0.83 ± 0.41, and 0.82 ± 0.49 in the early DME, advanced DME, severe DME, and atrophic maculopathy groups, respectively. The BCVA in the early DME group was therefore significantly lower than that in the other three groups (p = 0.042). After treatment, the BCVA improved to 0.15 ± 0.17, 0.52 ± 0.31, 0.62 ± 0.32, and 0.69 ± 0.47 in the early DME, advanced DME, severe DME, and atrophic maculopathy groups, respectively (p < 0.005). There were some differences among patients in the four groups in terms of the duration of diabetes, percentage of hemoglobin A1c, and duration of hypertension. CONCLUSION: The TCED-HFV OCT classification of patients with DME is exact and functional and can allow the severity of DME, and its response to anti-VEGF therapy, to be estimated.

Automated classification of choroidal neovascularization, diabetic macular edema, and drusen from retinal OCT images using vision transformers: a comparative study.

Classifying retinal diseases is a complex problem because the early problematic areas of retinal disorders are quite small and conservative. In recent years, Transformer architectures have been successfully applied to solve various retinal related health problems. Age-related macular degeneration (AMD) and diabetic macular edema (DME), two prevalent retinal diseases, can cause partial or total blindness. Diseases therefore require an early and accurate detection. In this study, we proposed Vision Transformer (ViT), Tokens-To-Token Vision Transformer (T2T-ViT) and Mobile Vision Transformer (Mobile-ViT) algorithms to detect choroidal neovascularization (CNV), drusen, and diabetic macular edema (DME), and normal using optical coherence tomography (OCT) images. The predictive accuracies of ViT, T2T-ViT and Mobile-ViT achieved on the dataset for the classification of OCT images are 95.14%, 96.07% and 99.17% respectively. Experimental results obtained from ViT approaches showed that Mobile-ViT have superior performance with regard to classification accuracy in comparison with the others. Overall, it has been observed that ViT architectures have the capacity to classify with high accuracy in the diagnosis of retinal diseases.

DEVELOPMENT AND VALIDATION OF AN EXPLAINABLE ARTIFICIAL INTELLIGENCE FRAMEWORK FOR MACULAR DISEASE DIAGNOSIS BASED ON OPTICAL COHERENCE TOMOGRAPHY IMAGES.

PURPOSE: To develop and validate an artificial intelligence framework for identifying multiple retinal lesions at image level and performing an explainable macular disease diagnosis at eye level in optical coherence tomography images. METHODS: A total of 26,815 optical coherence tomography images were collected from 865 eyes, and 9 retinal lesions and 3 macular diseases were labeled by ophthalmologists, including diabetic macular edema and dry/wet age-related macular degeneration. We applied deep learning to classify retinal lesions at image level and random forests to achieve an explainable disease diagnosis at eye level. The performance of the integrated two-stage framework was evaluated and compared with human experts. RESULTS: On testing data set of 2,480 optical coherence tomography images from 80 eyes, the deep learning model achieved an average area under curve of 0.978 (95% confidence interval, 0.971-0.983) for lesion classification. In addition, random forests performed accurate disease diagnosis with a 0% error rate, which achieved the same accuracy as one of the human experts and was better than the other three experts. It also revealed that the detection of specific lesions in the center of macular region had more contribution to macular disease diagnosis. CONCLUSION: The integrated method achieved high accuracy and interpretability in retinal lesion classification and macular disease diagnosis in optical coherence tomography images and could have the potential to facilitate the clinical diagnosis.

Spectral domain optical coherence tomography classification of diabetic macular edema: a new proposal to clinical practice.

PURPOSE: To classify the types of diabetic macular edema (DME) and evaluate its morphological features on spectral domain optical coherence tomography (SD-OCT) and determine correlations between visual acuity and OCT findings. METHODS: We assessed 406 eyes of 309 patients with a diagnosis of DME retrospectively. Three types based on SD-OCT were identified: diffuse macular edema, cystoid macular edema, and cystoid degeneration. Morphological features such as serous macular detachment (SMD), vitreomacular interface abnormalities (VMAI), hard exudates, photoreceptor status, and correlations between visual acuity and those morphological features were also evaluated by SD-OCT. RESULTS: The most common type of DME was cystoid edema (68.5%). No statistically significant difference was found between groups in sex (P = 0.40), type of diabetes (P = 0.50), or diabetic retinopathy (P = 0.78). However, the duration of symptoms and BCVA was significantly lower in the group with cystoid degeneration compared with the group with cystoid edema (P < 0.001) and the group with diffuse macular edema (P < 0.001). In the group with cystoid degeneration compared with the groups with cystoid and diffuse edema, the central fovea and central subfield were significantly thicker (both (P < 0.001), the subfoveal choroid was significantly thinner (P = 0.049), rate of serous macular detachment was significantly lower (P < 0.001), and the rate of outer retinal damage was significantly higher (P < 0.001). CONCLUSIONS: Cystoid macular degeneration, which is consistent with poor functional and morphological outcomes, should be differentiated from cystoid macular edema. Serous macular detachment, which is mostly seen in eyes with early stages of DME, should be evaluated as an accompanying morphological finding rather than a type of DME.

DISEASE CLASSIFICATION OF MACULAR OPTICAL COHERENCE TOMOGRAPHY SCANS USING DEEP LEARNING SOFTWARE: Validation on Independent, Multicenter Data.

PURPOSE: To evaluate Pegasus optical coherence tomography (OCT), a clinical decision support software for the identification of features of retinal disease from macula OCT scans, across heterogenous populations involving varying patient demographics, device manufacturers, acquisition sites, and operators. METHODS: Five thousand five hundred and eighty-eight normal and anomalous macular OCT volumes (162,721 B-scans), acquired at independent centers in five countries, were processed using the software. Results were evaluated against ground truth provided by the data set owners. RESULTS: Pegasus-OCT performed with areas under the curve of the receiver operating characteristic of at least 98% for all data sets in the detection of general macular anomalies. For scans of sufficient quality, the areas under the curve of the receiver operating characteristic for general age-related macular degeneration and diabetic macular edema detection were found to be at least 99% and 98%, respectively. CONCLUSION: The ability of a clinical decision support system to cater for different populations is key to its adoption. Pegasus-OCT was shown to be able to detect age-related macular degeneration, diabetic macular edema, and general anomalies in OCT volumes acquired across multiple independent sites with high performance. Its use thus offers substantial promise, with the potential to alleviate the burden of growing demand in eye care services caused by retinal disease.

RETINAL HYPERREFLECTIVE FOCI IN TYPE 1 DIABETES MELLITUS.

PURPOSE: To investigate hyperreflective foci (HF) on spectral-domain optical coherence tomography in patients with Type 1 diabetes mellitus across different stages of diabetic retinopathy (DR) and diabetic macular edema (DME) and to study clinical and morphological characteristics associated with HF. METHODS: Spectral-domain optical coherence tomography scans and color fundus photographs were obtained of 260 patients. Spectral-domain optical coherence tomography scans were graded for the number of HF and other morphological characteristics. The distribution of HF across different stages of DR and DME severity were studied. Linear mixed-model analysis was used to study associations between the number of HF and clinical and morphological parameters. RESULTS: Higher numbers of HF were found in patients with either stage of DME versus patients without DME (P < 0.001). A trend was observed between increasing numbers of HF and DR severity, although significance was only reached for moderate nonproliferative DR (P = 0.001) and proliferative DR (P = 0.019). Higher numbers of HF were associated with longer diabetes duration (P = 0.029), lower high-density lipoprotein cholesterol (P = 0.005), and the presence of microalbuminuria (P = 0.005). In addition, HF were associated with morphological characteristics on spectral-domain optical coherence tomography, including central retinal thickness (P = 0.004), cysts (P < 0.001), subretinal fluid (P = 0.001), and disruption of the external limiting membrane (P = 0.018). CONCLUSION: The number of HF was associated with different stages of DR and DME severity. The associations between HF and clinical and morphological characteristics can be of use in further studies evaluating the role of HF as a biomarker for disease progression and treatment response.

Classification of optical coherence tomography images using a capsule network.

BACKGROUND: Classification of optical coherence tomography (OCT) images can be achieved with high accuracy using classical convolution neural networks (CNN), a commonly used deep learning network for computer-aided diagnosis. Classical CNN has often been criticized for suppressing positional relations in a pooling layer. Therefore, because capsule networks can learn positional information from images, we attempted application of a capsule network to OCT images to overcome that shortcoming. This study is our attempt to improve classification accuracy by replacing CNN with a capsule network. METHODS: From an OCT dataset, we produced a training dataset of 83,484 images and a test dataset of 1000 images. For training, the dataset comprises 37,205 images with choroidal neovascularization (CNV), 11,348 with diabetic macular edema (DME), 8616 with drusen, and 26,315 normal images. The test dataset has 250 images from each category. The proposed model was constructed based on a capsule network for improving classification accuracy. It was trained using the training dataset. Subsequently, the test dataset was used to evaluate the trained model. RESULTS: Classification of OCT images using our method achieved accuracy of 99.6%, which is 3.2 percentage points higher than that of other methods described in the literature. CONCLUSION: The proposed method achieved classification accuracy results equivalent to those reported for other methods for CNV, DME, drusen, and normal images.

OPTICAL COHERENCE TOMOGRAPHY BIOMARKERS TO DISTINGUISH DIABETIC MACULAR EDEMA FROM PSEUDOPHAKIC CYSTOID MACULAR EDEMA USING MACHINE LEARNING ALGORITHMS.

PURPOSE: In diabetic patients presenting with macular edema (ME) shortly after cataract surgery, identifying the underlying pathology can be challenging and influence management. Our aim was to develop a simple clinical classifier able to confirm a diabetic etiology using few spectral domain optical coherence tomography parameters. METHODS: We analyzed spectral domain optical coherence tomography data of 153 patients with either pseudophakic cystoid ME (n = 57), diabetic ME (n = 86), or "mixed" (n = 10). We used advanced machine learning algorithms to develop a predictive classifier using the smallest number of parameters. RESULTS: Most differentiating were the existence of hard exudates, hyperreflective foci, subretinal fluid, ME pattern, and the location of cysts within retinal layers. Using only 3 to 6 spectral domain optical coherence tomography parameters, we achieved a sensitivity of 94% to 98%, specificity of 94% to 95%, and an area under the curve of 0.937 to 0.987 (depending on the method) for confirming a diabetic etiology. A simple decision flowchart achieved a sensitivity of 96%, a specificity of 95%, and an area under the curve of 0.937. CONCLUSION: Confirming a diabetic etiology for edema in cases with uncertainty between diabetic cystoid ME and pseudophakic ME was possible using few spectral domain optical coherence tomography parameters with high accuracy. We propose a clinical decision flowchart for cases with uncertainty, which may support the decision for intravitreal injections rather than topical treatment.

Classification of fundus autofluorescence abnormal patterns in diabetic macular edema.

INTRODUCTION: Patients with diabetic macular edema can develop fundus autofluorescence alterations; thus far, these alterations have been more widely studied with scanning or confocal laser systems. OBJECTIVE: To describe and classify fundus autofluorescence abnormal patterns in patients with diabetic macular edema using the fundus autofluorescence system with a flash camera. METHOD: Observational, retrospective, cross-sectional, descriptive study. Fundus autofluorescence digital images of non-comparative cases with untreated diabetic macular edema, obtained and stored with a flash camera system, were assessed. Inter-observer variability was evaluated. RESULTS: 37 eyes of 20 patients were included. Lens opacity was the most common cause of inadequate image quality. Five different fundus autofluorescence patterns were observed: decreased (13%), normal (40%), single-spot hyper-autofluorescent (17 %), multiple-spot hyper-autofluorescent (22 %) and plaque-like hyper-autofluorescent (8 %). The kappa coefficient was 0.906 (p = 0.000). CONCLUSIONS: Different fundus autofluorescence phenotypic patterns are observed with flash camera systems in patients with diabetic macular edema. A more accurate phenotypic classification could help establish prognostic factors for visual loss or for the design of clinical trials for diabetic macular edema.

Ethnic Differences in the Prevalence and Risk Factors of Diabetic Retinopathy: The Singapore Epidemiology of Eye Diseases Study.

PURPOSE: To evaluate the prevalence and risk factors for diabetic retinopathy (DR) in the Singapore Epidemiology of Eye Diseases (SEED) Study. DESIGN: Population-based, cross-sectional study. PARTICIPANTS: Persons of Malay, Indian, and Chinese ethnicity aged 40+ years, living in Singapore. METHODS: Diabetes was defined as nonfasting plasma glucose ≥200 mg/dl (11.1 mmol/l), glycated hemoglobin A1c (HbA1c) >6.5%, self-reported physician-diagnosed diabetes, or the use of glucose-lowering medication. Retinal photographs, were graded for the presence and severity of DR using the modified Airlie House classification system. MAIN OUTCOME MEASURES: Diabetic retinopathy, diabetic macular edema (DME), vision-threatening diabetic retinopathy (VTDR), defined as the presence of severe nonproliferative or proliferative DR, or clinically significant macular edema (CSME). RESULTS: Of the 10 033 subjects, 2877 (28.7%) had diabetes and gradable photographs for analysis. The overall age-standardized prevalence (95% confidence interval [CI]) was 28.2% (25.9-30.6) for any DR, 7.6% (6.5-9.0) for DME, and 7.7% (6.6-9.0) for VTDR. Indians had a higher prevalence of any DR (30.7% vs. 26.2% in Chinese and 25.5% in Malays, P = 0.012); a similar trend was noted for any DME (P = 0.001) and CSME (P = 0.032). Independent risk factors for any DR were Indian ethnicity (odds ratio [OR], 1.41; 95% CI, 1.09-1.83, vs. Chinese), diabetes duration (OR, 1.10; 95% CI, 1.08-1.11, per year), HbA1c (OR, 1.25; 95% CI, 1.18-1.32, per %), serum glucose (OR, 1.03; 95% CI, 1.00-1.06, per mmol/l), and systolic blood pressure (OR, 1.14; 95% CI, 1.09-1.19, per 10 mmHg). Diastolic blood pressure (OR, 0.74; 95% CI, 0.65-0.84, per 10 mmHg increase), total cholesterol (OR, 0.87; 95% CI, 0.80-0.95, per mmol/l increase), and low-density lipoprotein (LDL) cholesterol (OR, 0.83; 95% CI, 0.74-0.92, per mmol/l increase) were associated with lower odds of any DR. Risk factors were largely similar across the 3 ethnic groups. CONCLUSIONS: Indian Singaporeans have a higher prevalence of DR and DME compared with Chinese and Malays. Major risk factors for DR in this study were similar across the 3 ethnic groups. Addressing these risk factors may reduce the impact of DR in Asia, regardless of ethnicity.

Semi-automated quantification of hard exudates in colour fundus photographs diagnosed with diabetic retinopathy.

BACKGROUND: Hard exudates (HEs) are the classical sign of diabetic retinopathy (DR) which is one of the leading causes of blindness, especially in developing countries. Accordingly, disease screening involves examining HEs qualitatively using fundus camera. However, for monitoring the treatment response, quantification of HEs becomes crucial and hence clinicians now seek to measure the area of HEs in the digital colour fundus (CF) photographs. Against this backdrop, we proposed an algorithm to quantify HEs using CF images and compare with previously reported technique using ImageJ. METHODS: CF photographs of 30 eyes (20 patients) with diabetic macular edema were obtained. A robust semi-automated algorithm was developed to quantify area covered by HEs. In particular, the proposed algorithm, a two pronged methodology, involved performing top-hat filtering, second order statistical filtering, and thresholding of the colour fundus images. Subsequently, two masked observers performed HEs measurements using previously reported ImageJ-based protocol and compared with those obtained through proposed method. Intra and inter-observer grading was performed for determining percentage area of HEs identified by the individual algorithm. RESULTS: Of the 30 subjects, 21 were males and 9 were females with a mean age of the 50.25 ± 7.80 years (range 33-66 years). The correlation between the two measurements of semi-automated and ImageJ were 0.99 and 0.99 respectively. Previously reported method detected only 0-30% of the HEs area in 9 images, 30-60% in 12 images and 60-90% in remaining images, and more than 90% in none. In contrast, proposed method, detected 60-90% of the HEs area in 13 images and 90-100% in remaining 17 images. CONCLUSION: Proposed method semi-automated algorithm achieved acceptable accuracy, qualitatively and quantitatively, on a heterogeneous dataset. Further, quantitative analysis performed based on intra- and inter-observer grading showed that proposed methodology detects HEs more accurately than previously reported ImageJ-based technique. In particular, we proposed algorithm detect faint HEs also as opposed to the earlier method.

CHOROIDAL THICKNESS IN INFANTS WITH RETINOPATHY OF PREMATURITY.

PURPOSE: To evaluate choroidal thickness in premature infants and its relationship with stage of retinopathy of prematurity (ROP) using spectral domain optical coherence tomography (SD-OCT). METHODS: Spectral domain optical coherence tomography imaging for measuring subfoveal choroidal thickness was performed for 80 premature infants. Subfoveal choroidal thickness was defined as the distance from the hyperreflective line of the outermost retinal pigment epithelium (RPE) to the innermost hyperreflective line of the choroidoscleral junction. Each measurement was performed at the central fovea (CF) and 0.75 mm to 1.5 mm nasal (N1 and N2) and temporal (T1 and T2) to the fovea. Subfoveal choroidal thickness and grading of cystoid macular edema (CME) were analyzed statistically. RESULTS: Choroidal thickness of CF was found to be significantly greater than nasal (N1 and N2) and temporal (T1 and T2) choroidal thickness (P < 0.05). There was no significant relationship between stage of ROP and nasal (N1 and N2) choroidal thickness (P = 0.057, P = 0.282, respectively). However, CF and temporal (T1 and T2) choroidal thickness was found to be significantly lower at a higher stage of ROP (P = 0.005, P = 0.01 and P = 0.001). No significant relationship was found between subfoveal choroidal thickness and the grades of cystoid macular edema (P > 0.05). The choroidal thickness of CF was found to be correlated with birth weight (r = 0.267, P = 0.017) but not birth week (r = 0.140, P = 0.217). Maximum stage of ROP was found to be negatively correlated with choroidal thickness, at N1, T1, and T2 (r < -0.250, P < 0.02). CONCLUSION: The subfoveal choroid in premature infants can be effectively evaluated using a portable SD-OCT device. Choroidal thickness gets thinner with the severity of ROP and the decrease is more prominent at the central and temporal location. Cystoid macular edema is not correlated with choroidal thickness in premature infants.

[Effectiveness of diffuse diabetic macular edema treatment in relation to structural changes in macular region]. / Effektivnost' lecheniya diffuznogo diabeticheskogo makulyarnogo oteka v zavisimosti ot strukturnykh izmenenii makulyarnoi oblasti.

AIM: to describe baseline functional and anatomical parameters of the macular region and how they change under ranibizumab therapy depending on the type of diabetic macular edema (DME) determined with optical coherence tomography (OCT). MATERIAL AND METHODS: The study included 100 patients (100 eyes) with diabetes mellitus and DME (38 men and 62 women) aged 61.9±5.6 years with the mean disease duration of 8.48 years. Basing on OCT findings, 4 groups (25 patients each) were formed: sponge-like DME, cystoid DME, DME with serous neuroepithelium detachment (NED), and mixed DME (cystoid DME and serous NED). All patients received 3 consecutive monthly injections of 0.5 mg ranibizumab. The relationship between anatomical, functional, and clinical parameters was analyzed. RESULTS: The lowest visual acuity (VA) at baseline was found in patients with mixed DME (р<0.05). The greatest increase in VA after the 3 injections was noted in patients with sponge-like DME - 0.34±0.18. Retinal thickness was significantly lower (р<0.05) in sponge-like DME as compared to other groups both at baseline and after the treatment. Foveolar thickness decreased after the treatment in all groups, the effect being the most pronounced (the edema got reduced by 42.4%, р<0.05) in cystoid DME. The most significant reduction in macular volume (by 2.7 mm3) as well as its lowest absolute post-treatment values were reported for patients with cystoid edema (9.01 mm3, р<0.05 as compared to sponge-like and mixed DME). Correlation analysis revealed an evident relationship between the improvement in VA (ΔVA) and the decrease in macular volume (р<0.05). Of clinical parameters, only diabetes duration correlated with the extent of VA improvement (r=-0.3; p<0.05). CONCLUSION: The effectiveness of intravitreal ranibizumab therapy for diffuse DME depends on the morphological type of macular edema by OCT. Moreover, it correlates with diabetes duration.

Dominant cystoid macular dystrophy.

OBJECTIVE: To describe the clinical characteristics and long-term follow-up in patients with autosomal dominant cystoid macular dystrophy (DCMD). DESIGN: Retrospective case series. PARTICIPANTS: Ninety-seven patients with DCMD. METHODS: Extensive ophthalmic examination, including visual acuity (VA), fundus photography, fluorescein angiography (FA), fundus autofluorescence (FAF) imaging, optical coherence tomography (OCT), color vision testing, dark adaptation testing, full-field electroretinography (ERG), and electro-oculography (EOG). Blood samples were obtained for DNA extraction and subsequent haplotype analysis. MAIN OUTCOME MEASURES: Age at onset, VA, fundus appearance, and characteristics on FA, FAF, OCT, ERG, and EOG. RESULTS: Cystoid fluid collections (CFCs) were the first retinal abnormalities detectable in DCMD, developing during childhood. At long-term follow-up, the CFCs decreased in size and number, and eventually disappeared with concurrent development of progressive chorioretinal atrophy and hyperpigmented deposits in the posterior pole. Dominant cystoid macular dystrophy could be classified into 3 stages, based on characteristics on ophthalmoscopy, FAF, FA, and OCT, as well as on results of electrophysiologic analysis. The staging system correlated with age and VA. In stage 1 DCMD (20 patients; 22%), patients generally were younger than 20 years and had CFCs with fine folding of the internal limiting membrane and mild pigment changes. In stage 2 DCMD (48 patients; 52%), the CFCs tended to decrease in size, and moderate macular chorioretinal atrophy developed. Patients with stage 3 DCMD (24 patients; 26%) generally were older than 50 years and showed profound chorioretinal atrophy, as well as coarse hyperpigmented deposits in the posterior pole. Most patients were (highly) hyperopic (72 patients; 92%). All DCMD patients shared the disease haplotype at the DCMD locus at 7p15.3. CONCLUSIONS: Dominant cystoid macular dystrophy is a progressive retinal dystrophy, characterized primarily by early-onset cystoid fluid collections in the neuroretina, which distinguishes this disorder from other retinal dystrophies. The phenotypic range of DCMD can be classified into 3 stages. The genetic locus for this retinal dystrophy has been mapped to 7p15.3, but the involved gene is currently unknown.

Relevance of Retinal Thickness Changes in the OCT Inner and Outer Rings to Predict Progression to Clinical Macular Edema: An Attempt of Composite Grading of Macular Edema.

PURPOSE: To characterize the relevance of macular thickness changes in the inner and outer rings in the progression of macular edema in eyes/patients with diabetes type 2. METHODS: A total of 374 type 2 diabetic patients with mild nonproliferative diabetic retinopathy (ETDRS levels 20-35) were included in a 12-month prospective observational study to identify retinopathy progression. Retinal thickness analyses were performed in 194 eyes/patients using Cirrus SD- OCT and 166 eyes/patients using Spectralis SD-OCT. The DRCR.net classification of subclinical and clinical macular edema was used. A composite grading of macular edema is proposed in this study. RESULTS: A total of 317 eyes/patients completed the study. SD-OCT identified clinical macular edema in 24 eyes/patients (6.7%) and subclinical macular edema in 104 eyes/patients (28.9%) at baseline. Increased thickness of the central subfield is the best predictor for the development of clinical macular edema, with 85.7% sensitivity and 71.9% specificity (OR: 2.57, 95% CI: 0.82-7.99). However, the involvement of the inner and outer rings is a cumulative predictor of progression to clinical macular edema (OR: 8.69, 95% CI: 2.85-26.52). CONCLUSIONS: A composite OCT grading of macular edema taking into account the retinal thickness changes in the inner and outer macular rings offers a simple way to characterize macular edema, with added clinical value.

Intravitreal dexamethasone implant in patients with persistent macular edema of variable etiologies.

PURPOSE: To examine the effect of an intravitreal dexamethasone drug delivery system (DEX-DDS) in the treatment of persistent cystoid macular edema (CME) of different etiologies. METHODS: Thirty-seven eyes with persistent CME were treated with DEX-DDS and analyzed for changes in best-corrected visual acuity (BCVA) and optical coherence tomography. Eyes were categorized into three groups: diabetic macular edema (DME, n = 14), vein occlusion (n = 15) and uveitis (n = 7). RESULTS: The mean follow-up was 22 ± 6.9 weeks. BCVA improved from 0.62 ± 0.38 to 0.35 ± 0.29 logMAR (p < 0.0001). Central macular thickness decreased by 184 ± 246 µm from baseline (p < 0.0001). In eyes where CME resolved and recurred, the average CME-free period was 11 weeks. The uveitis group showed faster CME resolution (2 weeks) and a longer CME-free period (20 weeks). Similar efficacy was shown for repeat DEX-DDS injections. The safety profile was good. CONCLUSION: DEX-DDS is beneficial in the treatment of persistent CME. In cases of uveitis, CME resolution is rapid, resulting in the longest effect duration, when compared with other CME etiologies.

Self-supervised category selective attention classifier network for diabetic macular edema classification.

AIMS: This study aims to develop an advanced model for the classification of Diabetic Macular Edema (DME) using deep learning techniques. Specifically, the objective is to introduce a novel architecture, SSCSAC-Net, that leverages self-supervised learning and category-selective attention mechanisms to improve the precision of DME classification. METHODS: The proposed SSCSAC-Net integrates self-supervised learning to effectively utilize unlabeled data for learning robust features related to DME. Additionally, it incorporates a category-specific attention mechanism and a domain-specific layer into the ResNet-152 base architecture. The model is trained using an ensemble of unsupervised and supervised learning techniques. Benchmark datasets are utilized for testing the model's performance, ensuring its robustness and generalizability across different data distributions. RESULTS: Evaluation of the SSCSAC-Net on multiple datasets demonstrates its superior performance compared to existing techniques. The model achieves high accuracy, precision, and recall rates, with an accuracy of 98.7%, precision of 98.6%, and recall of 98.8%. Furthermore, the incorporation of self-supervised learning reduces the dependency on extensive labeled data, making the solution more scalable and cost-effective. CONCLUSIONS: The proposed SSCSAC-Net represents a significant advancement in automated DME classification. By effectively using self-supervised learning and attention mechanisms, the model offers improved accuracy in identifying DME-related features within retinal images. Its robustness and generalizability across different datasets highlight its potential for clinical applications, providing a valuable tool for clinicians in diagnosing DME effectively.

A novel approach for automatic classification of macular degeneration OCT images.

Age-related macular degeneration (AMD) and diabetic macular edema (DME) are significant causes of blindness worldwide. The prevalence of these diseases is steadily increasing due to population aging. Therefore, early diagnosis and prevention are crucial for effective treatment. Classification of Macular Degeneration OCT Images is a widely used method for assessing retinal lesions. However, there are two main challenges in OCT image classification: incomplete image feature extraction and lack of prominence in important positional features. To address these challenges, we proposed a deep learning neural network model called MSA-Net, which incorporates our proposed multi-scale architecture and spatial attention mechanism. Our multi-scale architecture is based on depthwise separable convolution, which ensures comprehensive feature extraction from multiple scales while minimizing the growth of model parameters. The spatial attention mechanism is aim to highlight the important positional features in the images, which emphasizes the representation of macular region features in OCT images. We test MSA-NET on the NEH dataset and the UCSD dataset, performing three-class (CNV, DURSEN, and NORMAL) and four-class (CNV, DURSEN, DME, and NORMAL) classification tasks. On the NEH dataset, the accuracy, sensitivity, and specificity are 98.1%, 97.9%, and 98.0%, respectively. After fine-tuning on the UCSD dataset, the accuracy, sensitivity, and specificity are 96.7%, 96.7%, and 98.9%, respectively. Experimental results demonstrate the excellent classification performance and generalization ability of our model compared to previous models and recent well-known OCT classification models, establishing it as a highly competitive intelligence classification approach in the field of macular degeneration.