Pachychoroid neovascular membrane in a patient with sickle cell disease trait.

PURPOSE: To describe a rare presentation of pachychoroid neovascular membrane in a patient with sickle cell trait and the accuracy of ruling out hemoglobinopathies in the presentation of pachychoroid spectrum. METHODS: The patient was subjected to physical examinations, multimodal images (fluorescein angiography, optical coherence tomography), hemoglobin electrophoresis, and peripheral blood smear, documenting sickle cell trait. The management included laser treatment to target non-perfusion areas, along with a single dose of anti-VEGF. RESULTS: A 45-year-old male patient with diagnosis of pachychoroid neovascularization treated for 6 years with multiple anti VEGF injections in the left eye. A detailed clinical evaluation included hypochromic conjunctiva, peripheral vascular occlusion with non-perfusion areas led us to suspect sickle cell disease retinopathy. The images of fluorescein angiography showed peripheral arteriovenous anastomosis with non-perfusion areas; the optical coherence tomography revealed a thinner neuroepithelium with a thicker choroid; also, hemoglobin electrophoresis and peripheral blood smear documenting sickle cell trait. The chosen management was photocoagulation of the peripheral retina on the non-perfusion areas and anti VEGF without neovascular activity recurrence in the follow up period. CONCLUSION: Although sickle cell trait is considered a mild form of this pathology without serious retinal manifestations, it has to be noted that in the context of pachychoroid spectrum diseases is a trigger that could perpetuate retinal ischemia and neovascular activity.

Automated machine learning model for fundus image classification by health-care professionals with no coding experience.

To assess the feasibility of code-free deep learning (CFDL) platforms in the prediction of binary outcomes from fundus images in ophthalmology, evaluating two distinct online-based platforms (Google Vertex and Amazon Rekognition), and two distinct datasets. Two publicly available datasets, Messidor-2 and BRSET, were utilized for model development. The Messidor-2 consists of fundus photographs from diabetic patients and the BRSET is a multi-label dataset. The CFDL platforms were used to create deep learning models, with no preprocessing of the images, by a single ophthalmologist without coding expertise. The performance metrics employed to evaluate the models were F1 score, area under curve (AUC), precision and recall. The performance metrics for referable diabetic retinopathy and macular edema were above 0.9 for both tasks and CDFL. The Google Vertex models demonstrated superior performance compared to the Amazon models, with the BRSET dataset achieving the highest accuracy (AUC of 0.994). Multi-classification tasks using only BRSET achieved similar overall performance between platforms, achieving AUC of 0.994 for laterality, 0.942 for age grouping, 0.779 for genetic sex identification, 0.857 for optic, and 0.837 for normality with Google Vertex. The study demonstrates the feasibility of using automated machine learning platforms for predicting binary outcomes from fundus images in ophthalmology. It highlights the high accuracy achieved by the models in some tasks and the potential of CFDL as an entry-friendly platform for ophthalmologists to familiarize themselves with machine learning concepts.

A multimodal approach using fundus images and text meta-data in a machine learning classifier with embeddings to predict years with self-reported diabetes - An exploratory analysis.

AIMS: Machine learning models can use image and text data to predict the number of years since diabetes diagnosis; such model can be applied to new patients to predict, approximately, how long the new patient may have lived with diabetes unknowingly. We aimed to develop a model to predict self-reported diabetes duration. METHODS: We used the Brazilian Multilabel Ophthalmological Dataset. Unit of analysis was the fundus image and its meta-data, regardless of the patient. We included people 40 + years and fundus images without diabetic retinopathy. Fundus images and meta-data (sex, age, comorbidities and taking insulin) were passed to the MedCLIP model to extract the embedding representation. The embedding representation was passed to an Extra Tree Classifier to predict: 0-4, 5-9, 10-14 and 15 + years with self-reported diabetes. RESULTS: There were 988 images from 563 people (mean age = 67 years; 64 % were women). Overall, the F1 score was 57 %. The group 15 + years of self-reported diabetes had the highest precision (64 %) and F1 score (63 %), while the highest recall (69 %) was observed in the group 0-4 years. The proportion of correctly classified observations was 55 % for the group 0-4 years, 51 % for 5-9 years, 58 % for 10-14 years, and 64 % for 15 + years with self-reported diabetes. CONCLUSIONS: The machine learning model had acceptable accuracy and F1 score, and correctly classified more than half of the patients according to diabetes duration. Using large foundational models to extract image and text embeddings seems a feasible and efficient approach to predict years living with self-reported diabetes.

Novel optical coherence tomography findings in a patient with methanol toxicity: a case report.

We report a case of acute methanol toxicity with unique optical coherence tomography findings. A 56-year-old man was referred to our ophthalmology clinic with a history of handmade vodka consumption and vision loss. On ophthalmologic examination, his vision was 20/100 in his right eye and 20/200 in his left eye. Bilateral mild optic disk hyperemia was detected on fundus examination. Because of the severity of systemic symptoms in such cases, it is very difficult to include optical coherence tomography in the ophthalmologic examination. However, we managed to perform optical coherence tomography and recorded shallow subretinal fluid and a prominent middle limiting membrane sign as acute retinal structural changes in the patient. The patient was treated with hemodialysis, intravenous ethanol, and sodium bicarbonate. On the fourth day of treatment, visual acuity improved to 20/20 in both eyes. In addition, the prominent middle limiting membrane sign and subretinal fluid disappeared. In this unusual case, retinal pigment epithelium damage and retinal ischemia may have contributed to the prominent middle limiting membrane and subretinal fluid, which are novel optical coherence tomography findings of methanol toxicity.

Choroidal nevus through a broader vision: Retinal imaging acquisition captured with Broad Line Fundus Imaging technology.

OBJECTIVE: To describe the peculiarities in imaging acquisition of fourteen patients with choroidal nevus using the Broad Line Fundus Imaging (BLFI) technology. METHODS: Single-center, retrospective, cross-sectional analysis. RESULTS: All images were acquired using the BLFI technology. We have found that choroidal nevus is undetectable in the blue channel (BC) (435-500 nm) and the green channel (GC) (500-585 nm). The only visible changes are related to the drusen, which appeared in BC and GC as light focal dots, correlated to the yellowish foci in the true-color image. On the red channel (RC) (585-640 nm), all lesions revealed the same pattern: a well-defined dark spot, with enhanced contrast, allowing the better visualization, measuring, and characterization of the nevus when compared with the other color channels, including the true-color imaging. CONCLUSION: BLFI application in choroidal nevus might be helpful at presentation, refining the diagnostic reliability, and monitoring, as it allows for better detection of alterations in the lesions. The peculiarities of the choroidal nevus are better assessed when using the RC due to its longer wavelength and deeper penetration in the retina and choroid.

Improved predictive diagnosis of diabetic macular edema based on hybrid models: An observational study.

Diabetic Macular Edema (DME) is the most common sight-threatening complication of type 2 diabetes. Optical Coherence Tomography (OCT) is the most useful imaging technique to diagnose, follow up, and evaluate treatments for DME. However, OCT exam and devices are expensive and unavailable in all clinics in low- and middle-income countries. Our primary goal was therefore to develop an alternative method to OCT for DME diagnosis by introducing spectral information derived from spontaneous electroretinogram (ERG) signals as a single input or combined with fundus that is much more widespread. Baseline ERGs were recorded in 233 patients and transformed into scalograms and spectrograms via Wavelet and Fourier transforms, respectively. Using transfer learning, distinct Convolutional Neural Networks (CNN) were trained as classifiers for DME using OCT, scalogram, spectrogram, and eye fundus images. Input data were randomly split into training and test sets with a proportion of 80 %-20 %, respectively. The top performers for each input type were selected, OpticNet-71 for OCT, DenseNet-201 for eye fundus, and non-evoked ERG-derived scalograms, to generate a combined model by assigning different weights for each of the selected models. Model validation was performed using a dataset alien to the training phase of the models. None of the models powered by mock ERG-derived input performed well. In contrast, hybrid models showed better results, in particular, the model powered by eye fundus combined with mock ERG-derived information with a 91 % AUC and 86 % F1-score, and the model powered by OCT and mock ERG-derived scalogram images with a 93 % AUC and 89 % F1-score. These data show that the spontaneous ERG-derived input adds predictive value to the fundus- and OCT-based models to diagnose DME, except for the sensitivity of the OCT model which remains the same. The inclusion of mock ERG signals, which have recently been shown to take only 5 min to record in daylight conditions, therefore represents a potential improvement over existing OCT-based models, as well as a reliable and cost-effective alternative when combined with the fundus, especially in underserved areas, to predict DME.

Branch retinal artery occlusion with paracentral acute middle maculopathy related to a COVID-19 infection in a patient with Anosmia.

PURPOSE: To report a case of paracentral acute middle maculopathy (PAMM) due to branch retinal artery occlusion (BRAO) as a complication of COVID-19. METHODS: A case report evaluated through spectral-domain optical coherence tomography (SD-OCT), fluorescein angiography, and OCT angiography. RESULTS: A 55-year-old man complained of blurred vision in the right eye. He presented with anosmia and tested positive for COVID-19 one week before. Fundus examination revealed a superior temporal whitening of the retina, SD-OCT showed a hyperreflective band-like lesion on the nuclear layer consistent with PAMM. CONCLUSION: COVID-19 infection involves inflammatory and thrombotic events. Even patients with just anosmia may have complications such as BRAO associated with PAMM.

Image quality assessment of retinal fundus photographs for diabetic retinopathy in the machine learning era: a review.

This study aimed to evaluate the image quality assessment (IQA) and quality criteria employed in publicly available datasets for diabetic retinopathy (DR). A literature search strategy was used to identify relevant datasets, and 20 datasets were included in the analysis. Out of these, 12 datasets mentioned performing IQA, but only eight specified the quality criteria used. The reported quality criteria varied widely across datasets, and accessing the information was often challenging. The findings highlight the importance of IQA for AI model development while emphasizing the need for clear and accessible reporting of IQA information. The study suggests that automated quality assessments can be a valid alternative to manual labeling and emphasizes the importance of establishing quality standards based on population characteristics, clinical use, and research purposes. In conclusion, image quality assessment is important for AI model development; however, strict data quality standards must not limit data sharing. Given the importance of IQA for developing, validating, and implementing deep learning (DL) algorithms, it's recommended that this information be reported in a clear, specific, and accessible way whenever possible. Automated quality assessments are a valid alternative to the traditional manual labeling process, and quality standards should be determined according to population characteristics, clinical use, and research purpose.

Encefalomielite aguda disseminada com provável etiologia de Bartonella henselae / Acute disseminated encephalomyelitis with probable Bartonella henselae etiology

RESUMO A encefalomielite aguda disseminada é uma doença rara, aguda, inflamatória e desmielinizante do sistema nervoso central, presumivelmente associada, em mais de três quartos dos casos, a infecções (virais, bacterianas ou inespecíficas) e imunizações ou sem qualquer antecedente indentificável. Habitualmente, apresenta um curso monofásico com início de sintomas inespecíficos na fase prodrómica, podendo evoluir com alterações neurológicas multifocais e até à perda total da acuidade visual. Descrevemos o caso de um menino de 9 anos com quadro inicial de edema de papila causado por encefalomielite aguda disseminada devido a Bartonella henselae. Apesar da gravidade da doença, o diagnóstico e o tratamento precoce proporcionaram bons desfechos.

ABSTRACT Acute disseminated encephalomyelitis is a rare, acute, inflammatory, and demyelinating disease of the central nervous system. Presumably associated in more than three quarters of cases by infections (viral, bacterial, or nonspecific) and immunizations or without any identifiable antecedent. It usually presents a monophasic course with onset of nonspecific symptoms in the prodromal phase and may evolve with multifocal neurological changes and even visual acuity loss. We describe a case of a 9-year-old boy with an initial picture of papillary edema caused by acute disseminated encephalomyelitis due to Bartonella henselae. Despite the severity of the disease, early diagnosis and treatment provided good outcomes.

Diagnóstico da retinopatia diabética por inteligência artificial por meio de smartphone / Diagnosis of diabetic retinopathy by artificial intelligence using smartphone

RESUMO Objetivo: Obter imagens de fundoscopia por meio de equipamento portátil e de baixo custo e, usando inteligência artificial, avaliar a presença de retinopatia diabética. Métodos: Por meio de um smartphone acoplado a um dispositivo com lente de 20D, foram obtidas imagens de fundo de olhos de pacientes diabéticos; usando a inteligência artificial, a presença de retinopatia diabética foi classificada por algoritmo binário. Resultados: Foram avaliadas 97 imagens da fundoscopia ocular (45 normais e 52 com retinopatia diabética). Com auxílio da inteligência artificial, houve acurácia diagnóstica em torno de 70 a 100% na classificação da presença de retinopatia diabética. Conclusão: A abordagem usando dispositivo portátil de baixo custo apresentou eficácia satisfatória na triagem de pacientes diabéticos com ou sem retinopatia diabética, sendo útil para locais sem condições de infraestrutura.

ABSTRACT Introduction: To obtain fundoscopy images through portable and low-cost equipment using artificial intelligence to assess the presence of DR. Methods: Fundus images of diabetic patients' eyes were obtained by using a smartphone coupled to a device with a 20D lens. By using artificial intelligence (AI), the presence of DR was classified by a binary algorithm. Results: 97 ocular fundoscopy images were evaluated (45 normal and 52 with DR). Through AI diagnostic accuracy around was 70% to 100% in the classification of the presence of DR. Conclusion: The approach using a low-cost portable device showed satisfactory efficacy in the screening of diabetic patients with or without diabetic retinopathy, being useful for places without infrastructure conditions.

Infección congénita por citomegalovirus en neonatos muy bajo peso / Congenital cytomegalovirus infection in very low birth weight neonates

Introducción: La infección congénita por el citomegalovirus en neonatos menores de 1500 gramos puede ser causa de morbilidad, mortalidad y discapacidad. Objetivo: Describir el comportamiento de la infección congénita por citomegalovirus en un servicio de neonatología. Métodos: Se realizó un estudio descriptivo y transversal con 61 neonatos. Se les realizó detección de citomegalovirus en la primera semana de vida en suero y orina, mediante reacción en cadena de la polimerasa, para determinar infección congénita. Se evaluaron variables perinatales en todos los neonatos, así como elementos clínicos y resultados de exámenes complementarios en los infectados. Resultados: La incidencia de infección congénita fue de un 10 por ciento (6/61). El 5 por ciento de los estudios fueron positivos (6/122). Ninguna muestra de orina resultó positiva (0/61) y en el 10 por ciento de las muestras de suero (6/61) se detectó el genoma del virus. Se encontró asociación entre valoración nutricional al nacer e infección por citomegalovirus (p< 0,05). El 83 por ciento de los neonatos infectados presentaron algún signo clínico y el síndrome de dificultad respiratoria fue el más frecuente (67 por ciento). En todos los neonatos con infección congénita el ultrasonido cerebral fue normal y en el 33 por ciento se detectó retinopatía de la prematuridad en el fondo de ojo. Conclusiones: La incidencia de infección congénita por citomegalovirus es alta en este grupo de riesgo. Los signos clínicos encontrados y los resultados del fondo de ojo en neonatos con infección congénita se relacionaron con la prematuridad y la valoración nutricional de hipotrófico se asoció con esta infección(AU)

Introduction: Congenital cytomegalovirus infection in neonates weighing less than 1500 grams can be a cause of morbidity, mortality, and disability. Objective: To describe the behavior of congenital cytomegalovirus infection in a neonatal service. Methods: A descriptive and cross-sectional study was conducted with 61 neonates. Cytomegalovirus was detected in the first week of life in serum and urine, by polymerase chain reaction, to determine congenital infection. Perinatal variables were evaluated in all neonates, as well as clinical elements and results of complementary examinations in infected infants. Results: The incidence of congenital infection was 10 percent (6/61). 5 percent of the studies were positive (6/122). No urine samples were positive (0/61) and the virus genome was detected in 10 percent of serum samples (6/61). An association was found between nutritional assessment at birth and cytomegalovirus infection (p < 0.05). A total of 83 percent of infected neonates had some clinical sign, with respiratory distress syndrome being the most common (67 percent). In all neonates with congenital infection, brain ultrasound was normal, and retinopathy of prematurity was detected in 33 percent of patients with fundus retinopathy. Conclusions: The incidence of congenital cytomegalovirus infection is high in this risk group. The clinical signs found and the results of the fundus in neonates with congenital infection were related to prematurity and the nutritional assessment of hypotrophic was associated with this infection(AU)

[Recurrent chronic Vogt-Koyanagi-Harada syndrome or sarcoidosis? A Gloomy diagnosis]. / ¿Síndrome de Vogt-Koyanagi-Harada crónico o sarcoidosis? Un diagnóstico sombrío.

Background: Vogt-Koyanagi-Harada syndrome (VKH) is a systemic disease that affects organs profuse in melanocytes, presenting with a chronic and diffuse bilateral granulomatous panuveitis, as well as neurological, auditory, and cutaneous manifestations. In this article, a systematic approach is presented for the diagnostic management of VKH syndrome, considering relevant diagnostic possibilities to rule out other entities that manifest similar symptoms. Clinical case: 71-year-old man with a long-standing history of vitiligo, who experienced visual loss in his right eye 6 months before his admission, along with bilateral hearing loss predominantly in the right ear. During his hospitalization, he presented with chronic headache, fever, and significant involuntary weight loss. Ophthalmological examination revealed that his right eye only perceived light and had hyperemic bulbar conjunctiva, while the left eye had a visual acuity of 20/200. The right fundus had scattered pigmentation, while the left had an edematous optic disc and right optic atrophy. Conclusions: The diagnosis of VKH syndrome is established by the presence of the 5 diagnostic criteria for complete disease, including retinal depigmentation, neurological alterations, and dermatological manifestations. Since patients can present with a wide variety of symptoms, initial differential diagnosis should be considered, which represents a diagnostic challenge.

Introducción: el síndrome de Vogt-Koyanagi-Harada (VKH) es una enfermedad sistémica que afecta a órganos ricos en melanocitos y se manifiesta con una panuveítis granulomatosa bilateral, crónica y difusa, así como con manifestaciones neurológicas, auditivas y cutáneas. En este artículo se presenta un enfoque sistemático para el abordaje diagnóstico del síndrome de VKH y se consideran las posibilidades diagnósticas relevantes para descartar otras entidades que se presentan con síntomas similares. Caso clínico: hombre de 71 años con antecedentes de vitiligo de larga data, quien experimentó una pérdida visual en su ojo derecho seis meses antes de su ingreso, junto con hipoacusia bilateral, predominantemente en el oído derecho. Durante su hospitalización, presentó cefalea crónica, fiebre y una significativa pérdida involuntaria de peso. En la exploración oftalmológica, el ojo derecho solo percibía luz y presentaba conjuntiva bulbar hiperémica, mientras que el ojo izquierdo tenía una agudeza visual de 20/200. El fondo del ojo derecho presentaba pigmentación dispersa, mientras que el izquierdo tenía una papila edematosa y atrofia óptica derecha. Conclusiones: el diagnóstico del síndrome de VKH se establece mediante la presencia de los 5 criterios diagnósticos para la enfermedad completa, incluida la hipopigmentación retiniana, las alteraciones neurológicas y las manifestaciones dermatológicas. Dado que los pacientes pueden presentar una amplia variedad de síntomas, el diagnóstico diferencial debe considerarse inicialmente, lo que representa un desafío diagnóstico.

Macular Star, Optic Disc Swelling, and Lethargy in a Child.

A 13-year-old girl with a 7-day history of painless vision loss and central scotoma in her left eye was referred to the hospital. Dilated fundus examination revealed a bilateral sectorial macular star that was more extended in the left eye and some faint, small, tan-yellow dots were observed at the level of the retinal pigment epithelium in the posterior pole. What would you do next?

Fundoscopy in the smartphone age: current ophthalmoscopy methods in neurology.

The observation of the human retina in vivo began in 1851 after the invention of the first ophthalmoscope by the German physicist Hermann von Helmholtz. In the following decades, direct and indirect ophthalmoscopy, with the use of ophthalmoscopes and condensing lenses, respectively, became part of the clinical examination, especially in ophthalmology and neurology. Today, over 170 years later, many ophthalmoscopes and condensing lenses exist on the market. Nevertheless, ophthalmoscopy is still not widely adopted as part of the physical exam of general practitioners, and the teaching of ophthalmoscopy in medical school remains challenging. Studies have shown that students prefer using newer ophthalmoscope models or condensing lenses during training, but most do not feel confident in performing ophthalmoscopy afterwards, regardless of the models used. Also, few students acquire ophthalmoscopes for their future practice, and clinical trials have not clearly demonstrated superiority of newer ophthalmoscope models over the conventional ones in diagnostic accuracy. The technological improvement of smartphone cameras in recent years has made it feasible to photograph the fundus of the eye using ophthalmoscopes or condensing lenses, reducing the need for retinographs and similar equipment. Smartphone assisted indirect fundoscopy is becoming increasingly popular. This approach allows adequate identification of the structures of the fundus, is cost-efficient, easy to implement, and permits easy recording and sharing of the images obtained, which is useful for case discussions and medical teaching. However, controlled clinical trials validating this method in the evaluation of optic nerve pathologies are needed.

A observação da retina humana in vivo começou em 1851, após a invenção do primeiro oftalmoscópio pelo físico alemão Hermann von Helmholtz. Nas décadas seguintes, a oftalmoscopia direta e indireta, com o uso de oftalmoscópios e lentes condensadoras, respectivamente, tornou-se parte do exame clínico, especialmente em oftalmologia e neurologia. Hoje, mais de 170 anos depois, diversos oftalmoscópios e lentes condensadoras estão disponíveis no mercado. No entanto, a oftalmoscopia ainda não é amplamente realizada no exame físico de médicos generalistas e o ensino da oftalmoscopia na faculdade de medicina ainda é desafiador. Estudos mostram que estudantes preferem usar modelos novos de oftalmoscópio ou lentes condensadoras durante seu treinamento, porém a maioria dos estudantes não se sente suficientemente confiante em realizar oftalmoscopia mais tarde, mesmo quando utilizam os modelos mais novos. Além disso, poucos alunos adquirem oftalmoscópios para sua prática futura, e ensaios clínicos não demonstraram uma clara superioridade dos novos modelos de oftalmoscópio em relação ao modelo convencional em acurácia diagnóstica. O aperfeiçoamento tecnológico das câmeras de smartphones nos últimos anos tornou possível fotografar o fundo do olho utilizando oftalmoscópios ou lentes condensadoras, reduzindo a necessidade de retinógrafos e equipamentos similares. A fundoscopia indireta realizada com smartphones vem se tornando cada vez mais popular. Esta abordagem permite a adequada identificação das estruturas do fundo do olho, é custo-efetiva, fácil de implementar e permite o fácil registro e compartilhamento das imagens obtidas, o que é útil para discussão de casos clínicos e para o ensino médico. Entretanto, ensaios clínicos controlados para a validação deste método na avaliação de patologias do nervo óptico são necessários.

El fondo de ojo, una ventana a la microvasculatura del paciente hipertenso / The fundus, a window to microvasculature in hypertensive patients

Introducción: La hipertensión arterial constituye una de las enfermedades más frecuentes en la población general. En la actualidad llega a una prevalencia global del 30 al 45 %. La microcirculación retiniana puede considerarse como una representación anatómica de las características fisiológicas y funcionales de la circulación coronaria y cerebral. Objetivos: Profundizar en la relación existente entre los niveles de presión arterial y el daño del órgano diana, específicamente a través del fondo de ojo, así como de las posibles complicaciones oftalmológicas derivadas de la hipertensión arterial, y la comparación de algunas de las clasificaciones existentes sobre los cambios oftalmológicos que esta provoca. Métodos: Se emplearon los métodos de análisis-síntesis y análisis bibliográfico y documental. Los motores de búsqueda utilizados fueron: Google y Google Académico, y las bases de datos Hinari, SciELO Cuba, Pubmed, entre otras. Conclusiones: La retinopatía hipertensiva es una de las complicaciones adversas de la hipertensión arterial aguda o crónica. Por su parte, las oclusiones venosas y la formación de macroaneurismas, constituyen otras de gran envergadura. Mientras más eficaz sea el diagnóstico y seguimiento de los pacientes hipertensos, menos recursos se necesitarán para su tratamiento, y se evitarán así las complicaciones de otros órganos diana como el cerebro y el riñón, lo que provocaría en los pacientes una mayor discapacidad.

Introduction: arterial hypertension is one the most frequent diseases in general population. Nowadays, it reaches a global prevalence of 30 to 45 %. Retinal microcirculation can be considered as an anatomical representation of the physiological and functional characteristics of the coronary and cerebral circulation. Objectives: to delve into the relationship between blood pressure levels and target organ damage, specifically through the fundus, as well as the possible ophthalmological complications derived from arterial hypertension, and the comparison of some of the existing classifications on the ophthalmological changes that it causes. Methods: analysis - synthesis and bibliographic- documentary analyses were the used methods. Google and Google Scholar as well as Hinari, SciELO Cuba, Pubmed and others databases were the search engines. Conclusions: hypertensive retinopathy is one of the adverse complications of acute or chronic arterial hypertension. On the other hand, venous occlusions and the formation of macroaneurysms constitute other serious ones to consider. The more effective the diagnosis and follow-up of hypertensive patients, the fewer resources will be needed for their treatment, thus avoiding complications in other target organs such as the brain and kidney, which would cause greater disability in patients.

Extensive macular atrophy with pseudodrusen-like: Case series and review.

PURPOSE: To describe the clinical characteristics of two patients affected by extensive macular atrophy with pseudodrusen-like (EMAP). METHODS: Two patients affected by EMAP underwent multimodal imaging, including fundus autofluorescence and optical coherence tomography. RESULTS: The patients showed the typical clinical appearance with macular atrophy with larger vertical axis surrounded by pseudodrusen-like deposits involving the midperiphery, associated with paving stone lesions in the retinal periphery. CONCLUSION: EMAP is a complex condition sharing clinical characteristics of age-related macular degeneration. Further studies are warranted to identify the early biomarker of the disease.

Performance analysis of pretrained convolutional neural network models for ophthalmological disease classification.

PURPOSE: This study aimed to evaluate the classification performance of pretrained convolutional neural network models or architectures using fundus image dataset containing eight disease labels. METHODS: A publicly available ocular disease intelligent recognition database has been used for the diagnosis of eight diseases. This ocular disease intelligent recognition database has a total of 10,000 fundus images from both eyes of 5,000 patients for the following eight diseases: healthy, diabetic retinopathy, glaucoma, cataract, age-related macular degeneration, hypertension, myopia, and others. Ocular disease classification performances were investigated by constructing three pretrained convolutional neural network architectures including VGG16, Inceptionv3, and ResNet50 models with adaptive moment optimizer. These models were implemented in Google Colab, which made the task straight-forward without spending hours installing the environment and supporting libraries. To evaluate the effectiveness of the models, the dataset was divided into 70%, 10%, and 20% for training, validation, and testing, respectively. For each classification, the training images were augmented to 10,000 fundus images. RESULTS: ResNet50 achieved an accuracy of 97.1%; sensitivity, 78.5%; specificity, 98.5%; and precision, 79.7%, and had the best area under the curve and final score to classify cataract (area under the curve = 0.964, final score = 0.903). By contrast, VGG16 achieved an accuracy of 96.2%; sensitivity, 56.9%; specificity, 99.2%; precision, 84.1%; area under the curve, 0.949; and final score, 0.857. CONCLUSIONS: These results demonstrate the ability of the pretrained convolutional neural network architectures to identify ophthalmological diseases from fundus images. ResNet50 can be a good architecture to solve problems in disease detection and classification of glaucoma, cataract, hypertension, and myopia; Inceptionv3 for age-related macular degeneration, and other disease; and VGG16 for normal and diabetic retinopathy.

Bilateral symmetrical maculopathy and heterochromia in Waardenburg syndrome / Maculopatia simétrica bilateral e heterocromia na síndrome de Waardenburg

ABSTRACT Waardenburg syndrome is a rare congenital genetic disorder characterized by sensorineural hearing loss and pigmentary abnormalities of the hair, skin, and eyes. Based on the different clinical presentations, it is divided into four subtypes as in WS1 to WS4. This report describes a 15-year-old boy who presented with low vision and bilateral hearing loss. His visual acuity was 20/200 in both eyes. Slit-lamp examination revealed complete iris heterochromia, with one blue iris and one brown iris. Fundus examination showed symmetrical pigmentation of the retina and choroid, with atrophy of the pigment epithelium in the macular region, notably also in the eye with normal iris pigment illustrating the broad spectrum of the iris and fundus pigmentation as part of this syndrome. A carefully clinical and ophthalmological evaluation should be done to differentiate various types of Waardenburg syndrome and other associated auditory-pigmentary syndrome. Early diagnosis in some cases may be crucial for the adequate development of patients affected with this condition.

RESUMO A síndrome de Waardenburg é uma doença genética congênita rara caracterizada por perda auditiva neurossensorial e anormalidades pigmentares do cabelo, da pele e dos olhos. Com base nas diferentes apresentações clínicas, é dividida em quatro subtipos (WS1 a WS4). Este relato descreve o caso de um menino de 15 anos que apresentava baixa visão e perda auditiva bilateral. Sua acuidade visual era de 20/200 em ambos os olhos. O exame em lâmpada de fenda revelou heterocromia completa da íris, com uma íris azul e uma íris marrom. A fundoscopia mostrou pigmentação simétrica da retina e coroide, com atrofia do epitélio pigmentar na região macular, notadamente também no olho com pigmento de íris normal, ilustrando o amplo espectro de pigmentação de íris e fundo como parte dessa síndrome. Uma avaliação clínica e oftalmológica criteriosa deve ser feita para diferenciar os vários tipos de síndrome de Waardenburg e outras síndromes auditivo-pigmentares associadas. O diagnóstico precoce em alguns casos pode ser crucial para o desenvolvimento adequado dos pacientes acometidos por essa condição.