TY  - JOUR
T1  - Learn2Reg 2024: New Benchmark Datasets Driving Progress on New Challenges
A1  - Hansen, Lasse
A1  - Heyer, Wiebke
A1  - Grossbröhmer, Christoph
A1  - Madesta, Frederic
A1  - Sentker, Thilo
A1  - Jiazheng, Wang
A1  - Zhang, Yuxi
A1  - Zhang, Hang
A1  - Liu, Min
A1  - Wang, Junyi
A1  - Zhu, Xi
A1  - Li, Yuhua
A1  - Wang, Liwen
A1  - Morozov, Daniil
A1  - Houachine, Nazim
A1  - Honkamaa, Joel
A1  - Marttinen, Pekka
A1  - Zhou, Yichao
A1  - Tan, Zuopeng
A1  - Wang, Zhuoyuan
A1  - Wang, Yi
A1  - Zhou, Hongchao
A1  - Hu, Shunbo
A1  - Zhang, Yi
A1  - Tao, Qian
A1  - Förner, Lukas
A1  - Wendler, Thomas
A1  - Jian, Bailiang
A1  - Wachinger, Christian
A1  - Kim, Jin
A1  - Ruan, Dan
A1  - Wodzinski, Marek
A1  - Müller, Henning
A1  - Mok, Tony Chi Wing
A1  - Jia, Xi
A1  - Duan, Jinming
A1  - Brudfors, Mikael
A1  - Ahmadi, Seyed-Ahmad
A1  - Zhu, Yunzheng
A1  - Hsu, William
A1  - Kapur, Tina
A1  - Wells, William M.
A1  - Golby, Alexandra
A1  - Carass, Aaron
A1  - Bai, Harrison
A1  - Liu, Yihao
A1  - Paul-Gilloteaux, Perrine
A1  - Lindblad, Joakim
A1  - Sladoje, Natasa
A1  - Walter, Andreas
A1  - Chen, Junyu
A1  - Dorent, Reuben
A1  - Hering, Alessa
A1  - Heinrich, Mattias
JA  - Hansen et al. 2025 / Melba Journal - Machine Learning for Biomedical Imaging
Y1  - 2025
VL  - Volume 3
M2  - doi: https://doi.org/10.59275/j.melba.2025-gc8c
KW  - Data Challenges · (Bio-) Medical Image Registration
N2  - Medical image registration is critical for clinical applications, and fair benchmarking of different methods is essential for monitoring ongoing progress in the field. To date, the Learn2Reg 2020-2023 challenges have released several complementary datasets and established metrics for evaluations. Building on this foundation, the 2024 edition expands the challenge’s scope to cover a wider range of registration scenarios, particularly in terms of modality diversity and task complexity, by introducing three new tasks, including large-scale multi-modal registration and unsupervised inter-subject brain registration, as well as the first microscopy-focused benchmark within Learn2Reg. The new datasets also inspired new method developments, including invertibility constraints, pyramid features, keypoints alignment and instance optimisation.
ER  -