Your browser doesn't support javascript.
loading
[Deep learning to support therapy decisions for intravitreal injections]. / Deep Learning zur Unterstützung der Therapieentscheidung bei intravitrealen Injektionen.
Prahs, P; Märker, D; Mayer, C; Helbig, H.
Afiliación
  • Prahs P; Klinik und Poliklinik für Augenheilkunde, Universität Regensburg, Franz-Josef-Strauss-Allee 11, 93042, Regensburg, Deutschland. philipp.prahs@ukr.de.
  • Märker D; Klinik und Poliklinik für Augenheilkunde, Universität Regensburg, Franz-Josef-Strauss-Allee 11, 93042, Regensburg, Deutschland.
  • Mayer C; Klinik für Augenheilkunde, Technische Universität München, München, Deutschland.
  • Helbig H; Klinik und Poliklinik für Augenheilkunde, Universität Regensburg, Franz-Josef-Strauss-Allee 11, 93042, Regensburg, Deutschland.
Ophthalmologe ; 115(9): 722-727, 2018 Sep.
Article en De | MEDLINE | ID: mdl-29713804
Significant progress has been made in artificial intelligence and computer vision research in recent years. Machine learning methods excel in a wide variety of tasks where sufficient data are available. We describe the application of a deep convolutional neural network for the prediction of treatment indication with anti-vascular endothelial growth factor (VEGF) medications based on central retinal optical coherence tomography (OCT) scans. The neural network classifier was trained with OCT images acquired during routine treatment at the University of Regensburg over the years 2008-2016. In over 95% of the cases the treatment indication was accurately predicted based on a singular OCT B scan without human intervention. Despite promising classification the results of deep learning techniques, should always be controlled by the treating physician because false classification can never be excluded due to the probabilistic nature of the method.
Asunto(s)
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Aprendizaje Profundo Tipo de estudio: Prognostic_studies Límite: Humans Idioma: De Revista: Ophthalmologe Asunto de la revista: OFTALMOLOGIA Año: 2018 Tipo del documento: Article Pais de publicación: Alemania

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Aprendizaje Profundo Tipo de estudio: Prognostic_studies Límite: Humans Idioma: De Revista: Ophthalmologe Asunto de la revista: OFTALMOLOGIA Año: 2018 Tipo del documento: Article Pais de publicación: Alemania