Radiologist-Level Performance by Using Deep Learning for Segmentation of Breast Cancers on MRI Scans

PURPOSE: To develop a deep network architecture that would achieve fully automated radiologist-level segmentation of cancers at breast MRI. MATERIALS AND METHODS: In this retrospective study, 38 229 examinations (composed of 64 063 individual breast scans from 14 475 patients) were performed in fema...

Descripción completa

Detalles Bibliográficos
Autores principales: Hirsch, Lukas, Huang, Yu, Luo, Shaojun, Rossi Saccarelli, Carolina, Lo Gullo, Roberto, Daimiel Naranjo, Isaac, Bitencourt, Almir G. V., Onishi, Natsuko, Ko, Eun Sook, Leithner, Doris, Avendano, Daly, Eskreis-Winkler, Sarah, Hughes, Mary, Martinez, Danny F., Pinker, Katja, Juluru, Krishna, El-Rowmeim, Amin E., Elnajjar, Pierre, Morris, Elizabeth A., Makse, Hernan A., Parra, Lucas C., Sutton, Elizabeth J.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Radiological Society of North America 2021
Materias:
Original Research
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8823456/
https://www.ncbi.nlm.nih.gov/pubmed/35146431
http://dx.doi.org/10.1148/ryai.200231

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8823456/
https://www.ncbi.nlm.nih.gov/pubmed/35146431
http://dx.doi.org/10.1148/ryai.200231

Ejemplares similares