Do comprehensive deep learning algorithms suffer from hidden stratification? A retrospective study on pneumothorax detection in chest radiography

OBJECTIVES: To evaluate the ability of a commercially available comprehensive chest radiography deep convolutional neural network (DCNN) to detect simple and tension pneumothorax, as stratified by the following subgroups: the presence of an intercostal drain; rib, clavicular, scapular or humeral fra...

Descripción completa

Detalles Bibliográficos
Autores principales: Seah, Jarrel, Tang, Cyril, Buchlak, Quinlan D, Milne, Michael Robert, Holt, Xavier, Ahmad, Hassan, Lambert, John, Esmaili, Nazanin, Oakden-Rayner, Luke, Brotchie, Peter, Jones, Catherine M
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BMJ Publishing Group 2021
Materias:
Diagnostics
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8655590/
https://www.ncbi.nlm.nih.gov/pubmed/34876430
http://dx.doi.org/10.1136/bmjopen-2021-053024

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8655590/
https://www.ncbi.nlm.nih.gov/pubmed/34876430
http://dx.doi.org/10.1136/bmjopen-2021-053024

Ejemplares similares