Variable fraunhofer MEVIS RegLib comprehensively applied to Learn2Reg challenge

Stephanie Häger; Stefan Heldmann; Alessa Hering; Sven Kuckertz; Annkristin Lange

Variable fraunhofer MEVIS RegLib comprehensively applied to Learn2Reg challenge

Stephanie Häger, Stefan Heldmann, Alessa Hering^*, Sven Kuckertz, Annkristin Lange

^*Corresponding author for this work

Institute of Mathematics and Image Computing

Fraunhofer MEVIS

Abstract

In this paper, we present our contribution to the learn2reg challenge. We applied the Fraunhofer MEVIS registration library RegLib comprehensively to all 4 tasks of the challenge. For tasks 1–3, we used a classic iterative registration method with NGF distance measure, second order curvature regularizer, and a multi-level optimization scheme. For task 4, a deep learning approach with a weakly supervised trained U-Net was applied using the same cost function as in the iterative approach.

Original language	English
Title of host publication	International Conference on Medical Image Computing and Computer-Assisted Intervention : MICCAI 2020: Segmentation, Classification and Registration of Multi-modality Medical Imaging Data
Publication date	13.03.2021
Publication status	Published - 13.03.2021

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Cite this

@inproceedings{2b768098d0904abcb2e973cfd51829fc,

title = "Variable fraunhofer MEVIS RegLib comprehensively applied to Learn2Reg challenge",

abstract = "In this paper, we present our contribution to the learn2reg challenge. We applied the Fraunhofer MEVIS registration library RegLib comprehensively to all 4 tasks of the challenge. For tasks 1–3, we used a classic iterative registration method with NGF distance measure, second order curvature regularizer, and a multi-level optimization scheme. For task 4, a deep learning approach with a weakly supervised trained U-Net was applied using the same cost function as in the iterative approach.",

author = "Stephanie H{\"a}ger and Stefan Heldmann and Alessa Hering and Sven Kuckertz and Annkristin Lange",

note = "Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG.",

year = "2021",

month = mar,

day = "13",

language = "English",

booktitle = "International Conference on Medical Image Computing and Computer-Assisted Intervention",

}

Variable fraunhofer MEVIS RegLib comprehensively applied to Learn2Reg challenge. / Häger, Stephanie ; Heldmann, Stefan; Hering, Alessa et al.
International Conference on Medical Image Computing and Computer-Assisted Intervention: MICCAI 2020: Segmentation, Classification and Registration of Multi-modality Medical Imaging Data. 2021.

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Variable fraunhofer MEVIS RegLib comprehensively applied to Learn2Reg challenge

AU - Häger, Stephanie

AU - Heldmann, Stefan

AU - Hering, Alessa

AU - Kuckertz, Sven

AU - Lange, Annkristin

PY - 2021/3/13

Y1 - 2021/3/13

N2 - In this paper, we present our contribution to the learn2reg challenge. We applied the Fraunhofer MEVIS registration library RegLib comprehensively to all 4 tasks of the challenge. For tasks 1–3, we used a classic iterative registration method with NGF distance measure, second order curvature regularizer, and a multi-level optimization scheme. For task 4, a deep learning approach with a weakly supervised trained U-Net was applied using the same cost function as in the iterative approach.

AB - In this paper, we present our contribution to the learn2reg challenge. We applied the Fraunhofer MEVIS registration library RegLib comprehensively to all 4 tasks of the challenge. For tasks 1–3, we used a classic iterative registration method with NGF distance measure, second order curvature regularizer, and a multi-level optimization scheme. For task 4, a deep learning approach with a weakly supervised trained U-Net was applied using the same cost function as in the iterative approach.

M3 - Conference contribution

BT - International Conference on Medical Image Computing and Computer-Assisted Intervention

ER -

Variable fraunhofer MEVIS RegLib comprehensively applied to Learn2Reg challenge

Abstract

UN SDGs

Fingerprint

Cite this