Deep learning-based simultaneous registration and unsupervised non-correspondence segmentation of medical images with pathologies

PURPOSE: The registration of medical images often suffers from missing correspondences due to inter-patient variations, pathologies and their progression leading to implausible deformations that cause misregistrations and might eliminate valuable information. Detecting non-corresponding regions simu...

Descripción completa

Detalles Bibliográficos
Autores principales: Andresen, Julia, Kepp, Timo, Ehrhardt, Jan, Burchard, Claus von der, Roider, Johann, Handels, Heinz
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer International Publishing 2022
Materias:
Original Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8948150/
https://www.ncbi.nlm.nih.gov/pubmed/35239133
http://dx.doi.org/10.1007/s11548-022-02577-4

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8948150/
https://www.ncbi.nlm.nih.gov/pubmed/35239133
http://dx.doi.org/10.1007/s11548-022-02577-4

Ejemplares similares