The brain tumor sequence registration (BraTS-Reg) challenge for establishing correspondence between pre-operative and follow-up MRI scans of diffuse glioma patients

Abstract Registration of longitudinal brain MRI scans containing pathologies remains a challenging problem, due to substantial changes in tissue appearance. While medical image registration methods have advanced considerably, they often lack the required precision and robustness. To address this gap, we introduced the brain tumor sequence registration (BraTS-Reg) challenge, the first public benchmark specifically designed for deformable registration between pre-operative and follow-up scans of patients with adult-type diffuse gliomas. Conducted in conjunction with ISBI-2022 and MICCAI-2022, BraTS-Reg provides de-identified, multi-institutional, multi-parametric MRI data accompanied by expert-annotated landmark points across time. Training data with ground truth annotations were publicly released for algorithm development, while validation data without annotations enabled pre-testing. Submitted containerized algorithms were evaluated on hidden testing cases. Quantitative evaluation was based on median Euclidean error (MEE), Robustness, and the determinant of Jacobian of the displacement field. Top-ranked methods demonstrated comparable performance and shared key features, including pre-alignment of scans, deep neural networks, inverse consistency analysis, and per-case test-time optimization. The best method achieved MEE comparable to inter-rater variability for 63% of landmarks, underscoring the need for further improvements in accuracy and robustness relative to human experts. BraTS-Reg serves as a three-fold active resource for research on image registration, providing a publicly available dataset, a framework for a community benchmark, and online evaluation tools, accessible at https://bratsreg.github.io/ .

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-15
DOI
https://doi.org/10.1038/s41598-026-74112-3
Citations
84
Primary Topic
Medical Image Segmentation Techniques
Type
article
Field-Weighted Citation Impact
19.55

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

The brain tumor sequence registration (BraTS-Reg) challenge for establishing correspondence between pre-operative and follow-up MRI scans of diffuse glioma patients

Bjoern H. Menze, Aristeidis Sotiras, Bhakti Baheti, Mina S. Mousa et al.
84 citations
Scientific Reports
Medical Image Segmentation Techniques
19.55
article

The brain tumor sequence registration (BraTS-Reg) challenge for establishing correspondence between pre-operative and follow-up MRI scans of diffuse glioma patients

Bjoern H. Menze, Aristeidis Sotiras, Bhakti Baheti, Mina S. Mousa, Michel Bilello, Satrajit Chakrabarty, Marek Wodziński, Brian Avants, Hastings Greer, Oliver Burgert, Daniel S. Marcus, Christos A. Davatzikos, Benedikt Wiestler, Julian Schwarting, Evan Calabrese, Spyridon Bakas, Javier E. Villanueva-Meyer, Nicholas James Tustison, Jeffrey D. Rudie, Alessa Hering, Diana Waldmannstetter, Hamed Akbari
article en
84 citations

Abstract

Abstract Registration of longitudinal brain MRI scans containing pathologies remains a challenging problem, due to substantial changes in tissue appearance. While medical image registration methods have advanced considerably, they often lack the required precision and robustness. To address this gap, we introduced the brain tumor sequence registration (BraTS-Reg) challenge, the first public benchmark specifically designed for deformable registration between pre-operative and follow-up scans of patients with adult-type diffuse gliomas. Conducted in conjunction with ISBI-2022 and MICCAI-2022, BraTS-Reg provides de-identified, multi-institutional, multi-parametric MRI data accompanied by expert-annotated landmark points across time. Training data with ground truth annotations were publicly released for algorithm development, while validation data without annotations enabled pre-testing. Submitted containerized algorithms were evaluated on hidden testing cases. Quantitative evaluation was based on median Euclidean error (MEE), Robustness, and the determinant of Jacobian of the displacement field. Top-ranked methods demonstrated comparable performance and shared key features, including pre-alignment of scans, deep neural networks, inverse consistency analysis, and per-case test-time optimization. The best method achieved MEE comparable to inter-rater variability for 63% of landmarks, underscoring the need for further improvements in accuracy and robustness relative to human experts. BraTS-Reg serves as a three-fold active resource for research on image registration, providing a publicly available dataset, a framework for a community benchmark, and online evaluation tools, accessible at https://bratsreg.github.io/ .

Scientific Reports
University of North Carolina at Charlotte (US), University of North Carolina at Chapel Hill (US), University of Geneva (CH), The University of Sydney (AU), Harvard University (US), University of Padua (IT), Emory University (US), Santa Clara University (US), Indian Institute of Technology Bombay (IN), HES-SO University of Applied Sciences and Arts Western Switzerland (CH), University of Bremen (DE), University of California, San Francisco (US), Friedrich-Alexander-Universität Erlangen-Nürnberg (DE), Shanghai Jiao Tong University (CN), Hong Kong University of Science and Technology (HK), University of Washington (US), University of Zurich (CH), Washington University in St. Louis (US), Université Paris-Saclay (FR), TUM Klinikum (DE), Radboud University Medical Center (NL), Helmholtz Zentrum München (DE), University Hospital Regensburg (DE), University of California San Diego (US), Massachusetts General Hospital (US), Harvard–MIT Division of Health Sciences and Technology (US), CentraleSupélec (FR), Duke Medical Center (US), Athinoula A. Martinos Center for Biomedical Imaging (US), Fraunhofer Institute for Digital Medicine (DE), Indiana University Indianapolis (US), Indiana University Melvin and Bren Simon Comprehensive Cancer Center (US), Indiana University School of Medicine (US), MIT Computer Science and Artificial Intelligence Laboratory (US), University of Virginia (US), Reutlingen University (DE), Technical University of Munich (DE), Menoufia University (EG), Massachusetts Institute of Technology (US), AGH University of Krakow (PL), University of Pennsylvania (US), University of Lübeck (DE)
Radiological Society of North America, University of Pennsylvania, Deutsche Forschungsgemeinschaft, Instituto Tecnológico de Costa Rica, National Institutes of Health, National Cancer Institute, National Institute of Neurological Disorders and Stroke, National Institute of Biomedical Imaging and Bioengineering, International Graduate School of Science and Engineering
Good health and well-being
Openalex Percentile: Top 1%
Medical Image Segmentation Techniques
19.55
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon