BRSET: A Brazilian Multilabel Ophthalmological Dataset of Retina Fundus Photos.

INTRODUCTION: The Brazilian Multilabel Ophthalmological Dataset (BRSET) addresses the scarcity of publicly available ophthalmological datasets in Latin America. BRSET comprises 16,266 color fundus retinal photos from 8,524 Brazilian patients, aiming to enhance data representativeness, serving as a research and teaching tool. It contains sociodemographic information, enabling investigations into differential model performance across demographic groups. METHODS: Data from three São Paulo outpatient centers yielded demographic and medical information from electronic records, including nationality, age, sex, clinical history, insulin use, and duration of diabetes diagnosis. A retinal specialist labeled images for anatomical features (optic disc, blood vessels, macula), quality control (focus, illumination, image field, artifacts), and pathologies (e.g., diabetic retinopathy). Diabetic retinopathy was graded using International Clinic Diabetic Retinopathy and Scottish Diabetic Retinopathy Grading. Validation used a ConvNext model trained during 50 epochs using a weighted cross entropy loss to avoid overfitting, with 70% training (20% validation), and 30% testing subsets. Performance metrics included area under the receiver operating curve (AUC) and Macro F1-score. Saliency maps were calculated for interpretability. RESULTS: BRSET comprises 65.1% Canon CR2 and 34.9% Nikon NF5050 images. 61.8% of the patients are female, and the average age is 57.6 (± 18.26) years. Diabetic retinopathy affected 15.8% of patients, across a spectrum of disease severity. Anatomically, 20.2% showed abnormal optic discs, 4.9% abnormal blood vessels, and 28.8% abnormal macula. A ConvNext V2 model was trained and evaluated BRSET in four prediction tasks: "binary diabetic retinopathy diagnosis (Normal vs Diabetic Retinopathy)" (AUC: 97, F1: 89); "3 class diabetic retinopathy diagnosis (Normal, Proliferative, Non-Proliferative)" (AUC: 97, F1: 82); "diabetes diagnosis" (AUC: 91, F1: 83); "sex classification" (AUC: 87, F1: 70). DISCUSSION: BRSET is the first multilabel ophthalmological dataset in Brazil and Latin America. It provides an opportunity for investigating model biases by evaluating performance across demographic groups. The model performance of three prediction tasks demonstrates the value of the dataset for external validation and for teaching medical computer vision to learners in Latin America using locally relevant data sources.

BRSET: A Brazilian Multilabel Ophthalmological Dataset of Retina Fundus Photos.

Introduction: The Brazilian Multilabel Ophthalmological Dataset (BRSET) addresses the scarcity of publicly available ophthalmological datasets in Latin America. BRSET comprises 16,266 color fundus retinal photos from 8,524 Brazilian patients, aiming to enhance data representativeness, serving as a research and teaching tool. It contains sociodemographic information, enabling investigations into differential model performance across demographic groups. Methods: Data from three São Paulo outpatient centers yielded demographic and medical information from electronic records, including nationality, age, sex, clinical history, insulin use, and duration of diabetes diagnosis. A retinal specialist labeled images for anatomical features (optic disc, blood vessels, macula), quality control (focus, illumination, image field, artifacts), and pathologies (e.g., diabetic retinopathy). Diabetic retinopathy was graded using International Clinic Diabetic Retinopathy and Scottish Diabetic Retinopathy Grading. Validation used Dino V2 Base for feature extraction, with 70% training and 30% testing subsets. Support Vector Machines (SVM) and Logistic Regression (LR) were employed with weighted training. Performance metrics included area under the receiver operating curve (AUC) and Macro F1-score. Results: BRSET comprises 65.1% Canon CR2 and 34.9% Nikon NF5050 images. 61.8% of the patients are female, and the average age is 57.6 years. Diabetic retinopathy affected 15.8% of patients, across a spectrum of disease severity. Anatomically, 20.2% showed abnormal optic discs, 4.9% abnormal blood vessels, and 28.8% abnormal macula. Models were trained on BRSET in three prediction tasks: "diabetes diagnosis"; "sex classification"; and "diabetic retinopathy diagnosis". Discussion: BRSET is the first multilabel ophthalmological dataset in Brazil and Latin America. It provides an opportunity for investigating model biases by evaluating performance across demographic groups. The model performance of three prediction tasks demonstrates the value of the dataset for external validation and for teaching medical computer vision to learners in Latin America using locally relevant data sources.

Large colloid drusen analyzed with structural en face optical coherence tomography.

Drusen are extracellular deposits between the basal lamina of the retinal pigment epithelium (RPE) and the inner collagenous layer of Bruch's membrane. Large colloid drusen (LCD) are located below the RPE and are characterized by multiple, large, dome-shaped RPE detachments, with marked attenuation of the ellipsoid zone overlaying the drusen. This report presents the structural en face optical coherence tomography (OCT) findings of LCD and relates them to findings from fluorescein and indocyanine green angiography. We describe the case of a 55-year-old woman who presented with the chief complaint of a 5-year history of progressively worsening vision. Her best-corrected visual acuities were 20/40 and 20/400 in the right eye and the left eye, respectively. Fundus examination showed large bilateral, symmetrical, sub-retinal, yellowish lesions compatible with LCD. We describe the structural en face OCT characteristics and angiographic findings from this patient.

Large colloid drusen analyzed with structural en face optical coherence tomography / Análise de drusas grandes coloidais através de OCT en face estrutural

ABSTRACT Drusen are extracellular deposits between the basal lamina of the retinal pigment epithelium (RPE) and the inner collagenous layer of Bruch's membrane. Large colloid drusen (LCD) are located below the RPE and are characterized by multiple, large, dome-shaped RPE detachments, with marked attenuation of the ellipsoid zone overlaying the drusen. This report presents the structural en face optical coherence tomography (OCT) findings of LCD and relates them to findings from fluorescein and indocyanine green angiography. We describe the case of a 55-year-old woman who presented with the chief complaint of a 5-year history of progressively worsening vision. Her best-corrected visual acuities were 20/40 and 20/400 in the right eye and the left eye, respectively. Fundus examination showed large bilateral, symmetrical, sub-retinal, yellowish lesions compatible with LCD. We describe the structural en face OCT characteristics and angiographic findings from this patient.

RESUMO Drusas são depósitos extracelulares localizados entre a lâmina basal do epitélio pig mentado da retina (RPE) e a camada colágena interna da membrana de Bruch. Drusas grandes coloidais (LCD) estão localizadas abaixo do EPR, e são caracterizadas por múltiplos descolamentos cupuliformes do EPR com atenuação da zona elipsoide sobrejacente às drusas. O objetivo deste relato é apresentar os achados de tomografia de coerência óptica (OCT en face estrutural em uma paciente com LCD, bem como correlacioná-los com angiografia fluoresceínica e angiografia com indocianina verde. Descrevemos o caso de uma paciente do sexo feminino, 55 anos, que referiu baixa acuidade visual em ambos os olhos há 5 anos. Sua acuidade visual corrigida era de 20/40 no olho direito e 20/400 no olho esquerdo. Ao exame fundoscópico a paciente apresentava lesões compatíveis com drusas grandes coloidais. As características tomográficas e angiográficas também são descritas neste relato de caso.