Few-shot out-of-distribution detection for automated screening in retinal OCT images using deep learning

Deep neural networks have been increasingly proposed for automated screening and diagnosis of retinal diseases from optical coherence tomography (OCT), but often provide high-confidence predictions on out-of-distribution (OOD) cases, compromising their clinical usage. With this in mind, we performed...

Descripción completa

Detalles Bibliográficos
Autores principales: Araújo, Teresa, Aresta, Guilherme, Schmidt-Erfurth, Ursula, Bogunović, Hrvoje
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10533534/
https://www.ncbi.nlm.nih.gov/pubmed/37758754
http://dx.doi.org/10.1038/s41598-023-43018-9

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10533534/
https://www.ncbi.nlm.nih.gov/pubmed/37758754
http://dx.doi.org/10.1038/s41598-023-43018-9

Ejemplares similares