Deep action learning enables robust 3D segmentation of body organs in various CT and MRI images

In this study, we propose a novel point cloud based 3D registration and segmentation framework using reinforcement learning. An artificial agent, implemented as a distinct actor based on value networks, is trained to predict the optimal piece-wise linear transformation of a point cloud for the joint...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhong, Xia, Amrehn, Mario, Ravikumar, Nishant, Chen, Shuqing, Strobel, Norbert, Birkhold, Annette, Kowarschik, Markus, Fahrig, Rebecca, Maier, Andreas
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7870874/
https://www.ncbi.nlm.nih.gov/pubmed/33558570
http://dx.doi.org/10.1038/s41598-021-82370-6

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7870874/
https://www.ncbi.nlm.nih.gov/pubmed/33558570
http://dx.doi.org/10.1038/s41598-021-82370-6

Ejemplares similares