Transfer Learning for Automated OCTA Detection of Diabetic Retinopathy

PURPOSE: To test the feasibility of using deep learning for optical coherence tomography angiography (OCTA) detection of diabetic retinopathy. METHODS: A deep-learning convolutional neural network (CNN) architecture, VGG16, was employed for this study. A transfer learning process was implemented to...

Descripción completa

Detalles Bibliográficos
Autores principales: Le, David, Alam, Minhaj, Yao, Cham K., Lim, Jennifer I., Hsieh, Yi-Ting, Chan, Robison V. P., Toslak, Devrim, Yao, Xincheng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Association for Research in Vision and Ophthalmology 2020
Materias:
Special Issue
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7424949/
https://www.ncbi.nlm.nih.gov/pubmed/32855839
http://dx.doi.org/10.1167/tvst.9.2.35

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7424949/
https://www.ncbi.nlm.nih.gov/pubmed/32855839
http://dx.doi.org/10.1167/tvst.9.2.35

Ejemplares similares