The MAMA-MIA Challenge: Advancing Generalizability and Fairness in Breast MRI Tumor Segmentation and Treatment Response Prediction
IEEE Transactions on Medical Imaging · 2026 · 1-1
DOI: 10.1109/tmi.2026.3733343 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2026. Verfasst von Lidia Garrucho und 45 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Breast cancer is the most frequently diagnosed malignancy among women worldwide and a leading cause of cancer-related mortality. Dynamic contrast-enhanced magnetic resonance imaging plays a central role in tumor characterization and treatment monitoring, particularly in patients receiving neoadjuvant chemotherapy. However, existing artificial intelligence models for breast magnetic resonance imaging are typically developed and evaluated using heterogeneous datasets, study populations, and assessment protocols, making direct comparison difficult and limiting understanding of model robustness across institutions and clinically relevant patient subgroups. The MAMA-MIA Challenge was designed to address these challenges by providing a standardized benchmark for the joint evaluation of primary tumor segmentation and prediction of pathologic complete response using pre-treatment magnetic resonance imaging only. The training cohort comprised 1,506 patients from multiple institutions in the United States, while evaluation was conducted on an external test set of 574 patients from three independent European centers to assess cross-continental and cross-institutional generalization. A unified scoring framework combined predictive performance with subgroup consistency across age, menopausal status, and breast density. Twenty-one international teams participated in the final evaluation phase. Results demonstrate substantial performance variability under a common external evaluation framework and reveal trade-offs between overall accuracy and subgroup fairness. The challenge provides standardized datasets, evaluation protocols, and public resources to promote the development of robust and equitable artificial intelligence systems for breast cancer imaging.
Zitieren
APA
Garrucho, L., Joshi, S., Kushibar, K., Osuala, R., Bobowicz, M., Bargallo, X., Jarusevicius, P., Geissler, K., Schafer, R., Alberb, M., Xu, T., Martel, A., Sleiman, D., Awasthi, N., Awwad, H., Vilanova, J. C., Marti, R., Schouten, D., Lee, J. H., …, & Lekadir, K. (2026). The MAMA-MIA Challenge: Advancing Generalizability and Fairness in Breast MRI Tumor Segmentation and Treatment Response Prediction. IEEE Transactions on Medical Imaging, 1-1. https://doi.org/10.1109/tmi.2026.3733343
Vancouver
Garrucho L, Joshi S, Kushibar K, Osuala R, Bobowicz M, Bargallo X, et al. The MAMA-MIA Challenge: Advancing Generalizability and Fairness in Breast MRI Tumor Segmentation and Treatment Response Prediction. IEEE Transactions on Medical Imaging. 2026:1-1. doi:10.1109/tmi.2026.3733343
BibTeX
@article{Garrucho2026,
author = {Garrucho, Lidia and Joshi, Smriti and Kushibar, Kaisar and Osuala, Richard and Bobowicz, Maciej and Bargallo, Xavier and Jarusevicius, Paulius and Geissler, Kai and Schafer, Raphael and Alberb, Muhammad and Xu, Tony and Martel, Anne and Sleiman, Daniel and Awasthi, Navchetan and Awwad, Hadeel and Vilanova, Joan C and Marti, Robert and Schouten, Daan and Lee, Jeong Hoon and Rusu, Mirabela and Poeta, Eleonora and Vargas, Luisa and Pastor, Eliana and Zuluaga, Maria A and Kachele, Jessica and Bounias, Dimitrios and Ertl, Alexandra and Gwozdziewicz, Katarzyna and Cosaka, Maria-Laura and Abo-Elhoda, Pasant M and Tantawy, Sara W and Sakrana, Shorouq S and Shawky-Abdelfatah, Norhan O and Abdo-Salem, Amr Muhammad and Kozana, Androniki and Divjak, Eugen and Ivanac, Gordana and Nikiforaki, Katerina and Klontzas, Michail E and Garcia-Dosda, Rosa and Gulsun-Akpinar, Meltem and Lafci, Oguz and Martin-Isla, Carlos and Diaz, Oliver and Igual, Laura and Lekadir, Karim},
title = {The MAMA-MIA Challenge: Advancing Generalizability and Fairness in Breast MRI Tumor Segmentation and Treatment Response Prediction},
journal = {IEEE Transactions on Medical Imaging},
year = {2026},
pages = {1--1},
doi = {10.1109/tmi.2026.3733343}
}
EUVIMED