Limited Number of Cases May Yield Generalizable Models, a Proof of Concept in Deep Learning for Colon Histology

BACKGROUND: Little is known about the effect of a minimum number of slides required in generating image datasets used to build generalizable machine-learning (ML) models. In addition, the assumption within deep learning is that the increased number of training images will always enhance accuracy and...

Descripción completa

Detalles Bibliográficos
Autores principales: Holland, Lorne, Wei, Dongguang, Olson, Kristin A., Mitra, Anupam, Graff, John Paul, Jones, Andrew D., Durbin-Johnson, Blythe, Mitra, Ananya Datta, Rashidi, Hooman H.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Wolters Kluwer - Medknow 2020
Materias:
Original Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7047745/
https://www.ncbi.nlm.nih.gov/pubmed/32175170
http://dx.doi.org/10.4103/jpi.jpi_49_19

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7047745/
https://www.ncbi.nlm.nih.gov/pubmed/32175170
http://dx.doi.org/10.4103/jpi.jpi_49_19

Ejemplares similares