SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining

Despite advances in data augmentation and transfer learning, convolutional neural networks (CNNs) difficultly generalise to unseen domains. When segmenting brain scans, CNNs are highly sensitive to changes in resolution and contrast: even within the same MRI modality, performance can decrease across...

Descripción completa

Detalles Bibliográficos
Autores principales: Billot, Benjamin, Greve, Douglas N., Puonti, Oula, Thielscher, Axel, Van Leemput, Koen, Fischl, Bruce, Dalca, Adrian V., Iglesias, Juan Eugenio
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10154424/
https://www.ncbi.nlm.nih.gov/pubmed/36857946
http://dx.doi.org/10.1016/j.media.2023.102789

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10154424/
https://www.ncbi.nlm.nih.gov/pubmed/36857946
http://dx.doi.org/10.1016/j.media.2023.102789

Ejemplares similares