A Foundation Model for Brain MRI with Dynamic Modality Integration (Student Abstract)
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41290-41292
DOI: 10.1609/aaai.v40i48.42245 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Minh Sao Khue Luu und 1 weiteren Autor:innen.
Abstract (Originalsprache)
We introduce a single–backbone foundation model for brain MRI that supports dynamic modality integration: it operates with arbitrary, possibly unseen, combinations of MRI sequences at pretrain and transfer. The encoder is conditioned by text-derived modality embeddings via conditional layer normalization, while a variance–covariance penalty discourages feature collapse. Unlike expert-based designs that grow with each new sequence, our approach scales without adding modality-specific branches. Pretrained self-supervised on ∼60,000 heterogeneous MRIs, the model learns modality-aware yet modality-agnostic features. We outline evaluation on segmentation and classification under missing/unseen modalities and cross-center shifts, and present early feasibility on multiple sclerosis lesion segmentation under limited data. This work moves toward robust, protocol-agnostic MRI foundation models suited to real clinical variability.
Zitieren
APA
Luu, M. S. K., & Tuchinov, B. N. (2026). A Foundation Model for Brain MRI with Dynamic Modality Integration (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41290-41292. https://doi.org/10.1609/aaai.v40i48.42245
Vancouver
Luu MSK, Tuchinov BN. A Foundation Model for Brain MRI with Dynamic Modality Integration (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41290-41292. doi:10.1609/aaai.v40i48.42245
BibTeX
@article{Luu2026,
author = {Luu, Minh Sao Khue and Tuchinov, Bair N.},
title = {A Foundation Model for Brain MRI with Dynamic Modality Integration (Student Abstract)},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41290--41292},
doi = {10.1609/aaai.v40i48.42245}
}
EUVIMED