Weakly supervised segmentation of tumor lesions in PET-CT hybrid imaging

Purpose: We introduce and evaluate deep learning methods for weakly supervised segmentation of tumor lesions in whole-body fluorodeoxyglucose-positron emission tomography (FDG-PET) based solely on binary global labels (“tumor” versus “no tumor”). Approach: We propose a three-step approach based on (...

Descripción completa

Detalles Bibliográficos
Autores principales: Früh, Marcel, Fischer, Marc, Schilling, Andreas, Gatidis, Sergios, Hepp, Tobias
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Society of Photo-Optical Instrumentation Engineers 2021
Materias:
Image Processing
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8510879/
https://www.ncbi.nlm.nih.gov/pubmed/34660843
http://dx.doi.org/10.1117/1.JMI.8.5.054003

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8510879/
https://www.ncbi.nlm.nih.gov/pubmed/34660843
http://dx.doi.org/10.1117/1.JMI.8.5.054003

Ejemplares similares