Deep Learning Application to Detect Glaucoma with a Mixed Training Approach: Public Database and Expert-Labeled Glaucoma Population.

INTRODUCTION: Artificial intelligence has real potential for early identification of ocular diseases such as glaucoma. An important challenge is the requirement for large databases properly selected, which are not easily obtained. We used a relatively original strategy: a glaucoma recognition algorithm trained with fundus images from public databases and then tested and retrained with a carefully selected patient database. METHODS: The study's supervised deep learning method was an adapted version of the ResNet-50 architecture previously trained from 10,658 optic head images (glaucomatous or non-glaucomatous) from seven public databases. A total of 1,158 new images labeled by experts from 616 patients were added. The images were categorized after clinical examination including visual fields in 304 (26%) control images or those with ocular hypertension and 347 (30%) images with early, 290 (25%) with moderate, and 217 (19%) with advanced glaucoma. The initial algorithm was tested using 30% of the selected glaucoma database and then re-trained with 70% of this database and tested again. RESULTS: The results in the initial sample showed an area under the curve (AUC) of 76% for all images, and 66% for early, 82% for moderate, and 84% for advanced glaucoma. After retraining the algorithm, the respective AUC results were 82%, 72%, 89%, and 91%. CONCLUSION: Using combined data from public databases and data selected and labeled by experts facilitated improvement of the system's precision and identified interesting possibilities for obtaining tools for automatic screening of glaucomatous eyes more affordably.

Neovascularización Coroidea Idiopática y Terapia Antiangiogénica con Recuperación Total de Agudeza Visual: reporte de caso / Idiopathic Choroidal Neovascularization and Antiangiogenic Therapy with Full Recovery of Visual Acuity: case report

Objetivo: presentar el caso de un paciente joven con neovascularización coroidea idiopática, con importante compromiso visual unilateral y que con la inyección intravítrea de aflibercept mensual, por tres meses, recuperó completamente la agudeza visual. Diseño: reporte de caso. Método: se realizó un estudio descriptivo tipo reporte de caso, mediante la recopilación de datos clínicos, estudios imagenológicos y valoraciones postoperatorias. Resultados: mejoría significativa de agudeza visual en paciente con neovascularización coroidea idiopática en ojo izquierdo posterior a tres inyecciones intravítreas de aflibercept mensual. El paciente mejoró de 20/400 a 20/20 al completar el esquema terapéutico. Conclusiones: el esquema de antiangiogénico resultó ser útil para el tratamiento de neovascularización coroidea idiopática en un paciente joven, logrando una recuperación visual y anatómica completa.

Objective: to present the case of a young patient with idiopathic choroidal neovascularization, with significant unilateral visual impairment. He fully recovered visual acuity by appliyng monthly intravitreal aflibercept, for three months. Design: case report. Method: a descriptive, case report study type was performed by collecting clinical data, imaging studies and postoperative evaluations. Results: Significant visual acuity improvement was obtained in the present patient with idiopathic choroidal neovascularization after three monthly intravitreal injections of aflibercept. The patient improved from 20/400 to 20/20 when treatment was completed. Conclusions: antiangiogenic schemev could be useful for the treatment of idiopathic choroidal neovascularization, achieving a complete visual and anatomical recovery.