Impact of multi-source data augmentation on performance of convolutional neural networks for abnormality classification in mammography

INTRODUCTION: To date, most mammography-related AI models have been trained using either film or digital mammogram datasets with little overlap. We investigated whether or not combining film and digital mammography during training will help or hinder modern models designed for use on digital mammogr...

Descripción completa

Detalles Bibliográficos
Autores principales: Hwang, InChan, Trivedi, Hari, Brown-Mulry, Beatrice, Zhang, Linglin, Nalla, Vineela, Gastounioti, Aimilia, Gichoya, Judy, Seyyed-Kalantari, Laleh, Banerjee, Imon, Woo, MinJae
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Radiology
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10426498/
https://www.ncbi.nlm.nih.gov/pubmed/37588666
http://dx.doi.org/10.3389/fradi.2023.1181190

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10426498/
https://www.ncbi.nlm.nih.gov/pubmed/37588666
http://dx.doi.org/10.3389/fradi.2023.1181190

Ejemplares similares