FastMRI-Guided Mamba UNet for Real-Time Emergency Brain Lesion Detection
American Journal of Machine Learning · 31.01.2026 · 7 (1) · 84-89
DOI: 10.71465/ajml3629 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal of Machine Learning, online erschienen am 31.01.2026. Verfasst von Julien Martin und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Emergency imaging often relies on fast MRI protocols, which introduce motion artifacts, low resolution, and reduced contrast, posing substantial challenges for lesion detection. TGMamba-UNet enhances robustness under these conditions by integrating temporal guidance vectors learned from high-quality MRI with a Mamba-UNet backbone capable of modeling longrange structural dependencies. The model effectively suppresses artifact-induced distortion and stabilizes predictions in noisy environments. Experiments conducted on 2,280 MRI scans (1,460 with motion artifacts and 820 high-quality references) show that TG-Mamba-UNet improves Dice from 0.812 to 0.894 (+10.1%) and reduces artifact-induced segmentation error by 17.8%.
Zitieren
APA
Martin, J., Dubois, C., Laurent, M., & Bernard, S. (2026). FastMRI-Guided Mamba UNet for Real-Time Emergency Brain Lesion Detection. American Journal of Machine Learning, 7(1), 84-89. https://doi.org/10.71465/ajml3629
Vancouver
Martin J, Dubois C, Laurent M, Bernard S. FastMRI-Guided Mamba UNet for Real-Time Emergency Brain Lesion Detection. American Journal of Machine Learning. 2026;7(1):84-89. doi:10.71465/ajml3629
BibTeX
@article{Martin2026,
author = {Martin, Julien and Dubois, Claire and Laurent, Mathieu and Bernard, Sophie},
title = {FastMRI-Guided Mamba UNet for Real-Time Emergency Brain Lesion Detection},
journal = {American Journal of Machine Learning},
year = {2026},
volume = {7},
number = {1},
pages = {84--89},
doi = {10.71465/ajml3629}
}
EUVIMED