Ranibizumab intravítreo para el tratamiento de oclusiones vasculares retinianas: análisis mediante tomografía de coherencia óptica / Intravitreal Ranibizumab for the Treatment of Retinal Vascular Occlusions: Analysis Using Optical Coherence Tomography

Introducción: El uso del medicamento ranibizumab intravítreo favorece la reducción del edema macular generador de las oclusiones vasculares retinianas causantes de la pérdida visual. Objetivo: Evaluar la eficacia y seguridad de la administración intravítreo de ranibizumab en el cambio de espesor macular central en las oclusiones vasculares retinianas analizado mediante tomografía de coherencia óptica. Material y métodos: Se desarrolló un estudio de tipo retrospectivo, analítico, correlacional y observacional de campo con diseño no experimental en 125 pacientes mayores de 30 años con oclusión vascular retiniana diagnosticados en la consulta de oftalmología del Hospital "Teodoro Maldonado Carbó" durante enero de 2017 a junio de 2018. La técnica ANOVA compara las medias para determinar mediante el proceso de contraste de hipótesis si existen diferencias estadísticamente significativas entre estas. Resultados: El análisis de la agudeza visual con escala logMAR demostró diferencias estadísticamente significativas entre los promedios obtenidos 3 meses antes y después de la aplicación del tratamiento (p=0,0001). Se encontró 28,8 por ciento de efectos adversos. Con frecuencia en aumento de presión intraocular (4 por ciento), sequedad ocular (16 por ciento) y hemorragia conjuntival (11,2 por ciento). Conclusiones: El ranibizumab en oclusiones vasculares retinianas proporciona una mejor agudeza visual corregida en relación con el grosor macular, favorece el desarrollo de nuevos vasos sanguíneos a partir de vasos preexistentes desde migración de células endoteliales(AU)

Introduction: The use of the intravitreal ranibizumab favors the reduction of the macular edema that generates retinal vascular occlusions that cause visual loss. Objective: To evaluate the efficacy and safety of the intravitreal administration of ranibizumab in the change in central macular thickness in retinal vascular occlusions analyzed by optical coherence tomography. Material and methods: A retrospective, analytical, correlational and observational field study with a non-experimental design was carried out on 125 patients over 30 years of age diagnosed with retinal vascular occlusion in the Ophthalmology Service of "Teodoro Maldonado Carbó" Hospital during the period between January 2017 and June 2018. The ANOVA technique was used to compare means in order to determine, through the hypothesis contrast process, if there are statistically significant differences between them. Results: Visual acuity analysis using the logMAR scale showed statistically significant differences between the averages obtained 3 months before and after the application of the treatment (p =0.0001). In addition, 28,8 percent of adverse effects were found. The most frequent ones included increased intraocular pressure (4 percent), dry eyes (16 percent), and conjunctival hemorrhage (11,2 percent). Conclusions: In retinal vascular occlusions, Ranibizumab provides a better corrected visual acuity in relation to macular thickness, favors the development of new blood vessels from pre-existing vessels from endothelial cell migration(AU)

Automatic detection of retinal regions using fully convolutional networks for diagnosis of abnormal maculae in optical coherence tomography images.

In conventional retinal region detection methods for optical coherence tomography (OCT) images, many parameters need to be set manually, which is often detrimental to their generalizability. We present a scheme to detect retinal regions based on fully convolutional networks (FCN) for automatic diagnosis of abnormal maculae in OCT images. The FCN model is trained on 900 labeled age-related macular degeneration (AMD), diabetic macular edema (DME) and normal (NOR) OCT images. Its segmentation accuracy is validated and its effectiveness in recognizing abnormal maculae in OCT images is tested and compared with traditional methods, by using the spatial pyramid matching based on sparse coding (ScSPM) classifier and Inception V3 classifier on two datasets: Duke dataset and our clinic dataset. In our clinic dataset, we randomly selected half of the B-scans of each class (300 AMD, 300 DME, and 300 NOR) for training classifier and the rest (300 AMD, 300 DME, and 300 NOR) for testing with 10 repetitions. Average accuracy, sensitivity, and specificity of 98.69%, 98.03%, and 99.01% are obtained by using ScSPM classifier, and those of 99.69%, 99.53%, and 99.77% are obtained by using Inception V3 classifier. These two classification algorithms achieve 100% classification accuracy when directly applied to Duke dataset, where all the 45 OCT volumes are used as test set. Finally, FCN model with or without flattening and cropping and its influence on classification performance are discussed.