Structured report data can be used to develop deep learning algorithms: a proof of concept in ankle radiographs

BACKGROUND: Data used for training of deep learning networks usually needs large amounts of accurate labels. These labels are usually extracted from reports using natural language processing or by time-consuming manual review. The aim of this study was therefore to develop and evaluate a workflow fo...

Descripción completa

Detalles Bibliográficos
Autores principales: Pinto dos Santos, Daniel, Brodehl, Sebastian, Baeßler, Bettina, Arnhold, Gordon, Dratsch, Thomas, Chon, Seung-Hun, Mildenberger, Peter, Jungmann, Florian
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer Berlin Heidelberg 2019
Materias:
Original Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6777645/
https://www.ncbi.nlm.nih.gov/pubmed/31549305
http://dx.doi.org/10.1186/s13244-019-0777-8

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6777645/
https://www.ncbi.nlm.nih.gov/pubmed/31549305
http://dx.doi.org/10.1186/s13244-019-0777-8

Ejemplares similares