IVCVSep 1, 2025

Learn2Reg 2024: New Benchmark Datasets Driving Progress on New Challenges

arXiv:2509.01217v23 citationsh-index: 47Machine Learning for Biomedical Imaging
Originality Synthesis-oriented
AI Analysis

This work provides incremental improvements to benchmarking for medical image registration, addressing gaps in modality diversity and task complexity for researchers and practitioners.

The paper tackles the limitations of previous medical image registration benchmarks by introducing three new tasks with increased modality diversity and complexity, including large-scale multi-modal registration and a microscopy-focused benchmark, which inspired new method developments.

Medical image registration is critical for clinical applications, and fair benchmarking of different methods is essential for monitoring ongoing progress. To date, the Learn2Reg 2020-2023 challenges have released several complementary datasets and established metrics for evaluations. However, these editions did not capture all aspects of the registration problem, particularly in terms of modality diversity and task complexity. To address these limitations, the 2024 edition introduces 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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes