Abstract
In this paper, we present our contribution to the learn2reg challenge. We applied the Fraunhofer MEVIS registration library RegLib comprehensively to all 3 tasks of the challenge, where we used a classic iterative registration method with NGF distance measure, second order curvature regularizer and a multi-level optimization scheme. We show that with our proposed method robust results can be achieved throughout all tasks resulting in the fourth place overall task and the best accuracy on the lung CT registration task.
Originalsprache | Englisch |
---|---|
Titel | Lecture Notes in Computer Science |
Band | LNIP, volume 13166 |
Erscheinungsdatum | 2022 |
Publikationsstatus | Veröffentlicht - 2022 |