Improved Fine-Tuning of In-Domain Transformer Model for Inferring COVID-19 Presence in Multi-Institutional Radiology Reports

Building a document-level classifier for COVID-19 on radiology reports could help assist providers in their daily clinical routine, as well as create large numbers of labels for computer vision models. We have developed such a classifier by fine-tuning a BERT-like model initialized from RadBERT, its...

Descripción completa

Detalles Bibliográficos
Autores principales: Chambon, Pierre, Cook, Tessa S., Langlotz, Curtis P.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer International Publishing 2022
Materias:
Original Paper
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9629758/
https://www.ncbi.nlm.nih.gov/pubmed/36323915
http://dx.doi.org/10.1007/s10278-022-00714-8

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9629758/
https://www.ncbi.nlm.nih.gov/pubmed/36323915
http://dx.doi.org/10.1007/s10278-022-00714-8

Ejemplares similares