Assessment of a deep-learning system for fracture detection in musculoskeletal radiographs

Missed fractures are the most common diagnostic error in emergency departments and can lead to treatment delays and long-term disability. Here we show through a multi-site study that a deep-learning system can accurately identify fractures throughout the adult musculoskeletal system. This approach m...

Descripción completa

Detalles Bibliográficos
Autores principales: Jones, Rebecca M., Sharma, Anuj, Hotchkiss, Robert, Sperling, John W., Hamburger, Jackson, Ledig, Christian, O’Toole, Robert, Gardner, Michael, Venkatesh, Srivas, Roberts, Matthew M., Sauvestre, Romain, Shatkhin, Max, Gupta, Anant, Chopra, Sumit, Kumaravel, Manickam, Daluiski, Aaron, Plogger, Will, Nascone, Jason, Potter, Hollis G., Lindsey, Robert V.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2020
Materias:
Brief Communication
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7599208/
https://www.ncbi.nlm.nih.gov/pubmed/33145440
http://dx.doi.org/10.1038/s41746-020-00352-w
Descripción
Sumario:Missed fractures are the most common diagnostic error in emergency departments and can lead to treatment delays and long-term disability. Here we show through a multi-site study that a deep-learning system can accurately identify fractures throughout the adult musculoskeletal system. This approach may have the potential to reduce future diagnostic errors in radiograph interpretation.

Ejemplares similares