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. Visit Learn2Reg at https://learn2reg.grand-challenge.org.
@article{arxiv.2509.01217,
title = {Learn2Reg 2024: New Benchmark Datasets Driving Progress on New Challenges},
author = {Lasse Hansen and Wiebke Heyer and Christoph Großbröhmer and Frederic Madesta and Thilo Sentker and Wang Jiazheng and Yuxi Zhang and Hang Zhang and Min Liu and Junyi Wang and Xi Zhu and Yuhua Li and Liwen Wang and Daniil Morozov and Nazim Haouchine and Joel Honkamaa and Pekka Marttinen and Yichao Zhou and Zuopeng Tan and Zhuoyuan Wang and Yi Wang and Hongchao Zhou and Shunbo Hu and Yi Zhang and Qian Tao and Lukas Förner and Thomas Wendler and Bailiang Jian and Christian Wachinger and Jin Kim and Dan Ruan and Marek Wodzinski and Henning Müller and Tony C. W. Mok and Xi Jia and Jinming Duan and Mikael Brudfors and Seyed-Ahmad Ahmadi and Yunzheng Zhu and William Hsu and Tina Kapur and William M. Wells and Alexandra Golby and Aaron Carass and Harrison Bai and Yihao Liu and Perrine Paul-Gilloteaux and Joakim Lindblad and Nataša Sladoje and Andreas Walter and Junyu Chen and Reuben Dorent and Alessa Hering and Mattias P. Heinrich},
journal= {arXiv preprint arXiv:2509.01217},
year = {2026}
}
Comments
Accepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://melba-journal.org/2025:034