Abstract

This study investigates the impact of self-supervised pre- training of 3D semantic segmentation models on a large-scale, domain- specific dataset. We introduce BRAINS-45K, a dataset of 44,756 brain MRI volumes from public sources, the largest public dataset available, and revisit a number of design choices for pretraining modern segmenta- tion architectures by simplifying and optimizing state-of-the-art meth- ods, and combining them with a novel augmentation strategy. The result- ing AMAES framework is based on masked-image-modeling and intensity- based augmentation reversal and balances memory usage, runtime, and finetuning performance. Using the popular U-Net and the recent Med- NeXt architecture as backbones, we evaluate the effect of pretraining on three challenging downstream tasks, covering single-sequence, low- resource settings, and out-of-domain generalization. The results highlight that pretraining on the proposed dataset with AMAES significantly im- proves segmentation performance in the majority of evaluated cases, and that it is beneficial to pretrain the model with augmentations, despite pretraing on a large-scale dataset. Code and model checkpoints for re- producing results, as well as the BRAINS-45K dataset are available at https://github.com/asbjrnmunk/amaes.

Links to Paper and Supplementary Materials

Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/ADSMI2024_118.pdf

SharedIt Link: Not yet available

SpringerLink (DOI): Not yet available

Supplementary Material: https://papers.miccai.org/miccai-2026-sat/supp/ADSMI2024_118_supp.pdf

Link to Open Review

Open Review Page: Not Available

BibTex

@InProceedings{MunAsb_AMAES_MICCAISAT2026,
        author = { Munk, Asbjørn AND Ambsdorf, Jakob AND Llambias, Sebastian AND Nielsen, Mads},
        title = { { AMAES: Augmented Masked Autoencoder Pretraining on Public Brain MRI Data for 3D-Native Segmentation } },
        booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
        year = {2026},
        publisher = {Springer Nature Switzerland},
        volume = {LNCS 17276},
        month = {pending},
        page = {pending}
}


back to top