Benutzer: Gast  Login
Titel:

Vol2Flow: Segment 3D Volumes Using a Sequence of Registration Flows

Dokumenttyp:
Konferenzbeitrag
Autor(en):
Bitarafan, Adeleh; Azampour, Mohammad Farid; Bakhtari, Kian; Soleymani Baghshah, Mahdieh; Keicher, Matthias; Navab, Nassir
Abstract:
This work proposes a self-supervised algorithm to segment each arbitrary anatomical structure in a 3D medical image produced under various acquisition conditions, dealing with domain shift problems and generalizability. Furthermore, we advocate an interactive setting in the inference time, where the self-supervised model trained on unlabeled volumes should be directly applicable to segment each test volume given the user-provided single slice annotation. To this end, we learn a novel 3D registra...     »
Herausgeber:
Wang, Linwei; Dou, Qi; Fletcher, P. Thomas; Speidel, Stefanie; Li, Shuo
Kongress- / Buchtitel:
Medical Image Computing and Computer Assisted Intervention -- MICCAI 2022
Verlag / Institution:
Springer Nature Switzerland
Verlagsort:
Cham
Jahr:
2022
Seiten:
609--618
Print-ISBN:
978-3-031-16440-8
 BibTeX