Biomarcadores de oclusiones venosas retinianas mediante estrategia de aprendizaje profundo aplicada en imágenes adquiridas por OCT angiografía

Abstract

Propósito: Desarrollar un método computacional basado en Deep Learning (DL) para detectar automáticamente biomarcadores de oclusiones de venas retinianas en imágenes adquiridas por angiografía por tomografía de coherencia óptica (OCT-A) Diseño: Desarrollo de algoritmo para detectar biomarcadores de oclusiones de venas retinianas utilizando datos retrospectivos. (Texto tomado de la fuente)

Purpose: To develop a computational method based on Deep Learning (DL) to automatically detect biomarkers of retinal vein occlusions in images acquired by optical coherence tomography angiography (OCT- A) Design: Algorithm development for detect biomarkers of retinal vein occlusions using retrospective data. Participants: Images of the superficial, deep, en face, choriocapillaris and outer retina to choriocapillaris (ORCC) layers obtained from 254 patients attended in an Ophthalmology Clinic were used to train and test an artificial intelligence (AI) model. Methods: The OCT-A scans were manually annotated with four biomarkers (BMs): disruption of the perifoveal capillary plexus, non-perfusion areas (NPAs), vascular tortuosity and cystoid spaces. Segmentation and identification were subsequently provided to build and training the DL model using Deep Convolutional Neural Networks (DNN) Main Outcome Measures: detection rate and jaccard index Results: The detection rate of the model for disruption of the perifoveal capillary plexus, non-perfusion areas (NPAs), vascular tortuosity and cystoid spaces were 93%, 92%, 91% and 84% respectively. The Jaccard index values were 0.85, 0.77, 0.72 and 0.73 respectively Conclusion: The proposed DL model may id