A large-scale heterogeneous 3D magnetic resonance brain imaging dataset for self-supervised learning

We present FOMO60K, a large-scale, heterogeneous dataset of 60,529 brain Magnetic Resonance Imaging (MRI) scans from 13,900 sessions and 11,187 subjects, aggregated from 16 publicly available sources. The dataset includes both clinical- and research-grade images, multiple MRI sequences, and a wide range of anatomical and pathological variability, including scans with large brain anomalies. Minimal preprocessing was applied to preserve the original image characteristics while reducing barriers to entry for new users. Accompanying code for self-supervised pretraining and finetuning is provided. FOMO60K is intended to support the development and benchmarking of self-supervised learning methods in medical imaging at scale.

@article{munk2025_2506.14432,
  title={ A large-scale heterogeneous 3D magnetic resonance brain imaging dataset for self-supervised learning },
  author={ Asbjørn Munk and Stefano Cerri and Jakob Ambsdorf and Julia Machnio and Sebastian Nørgaard Llambias and Vardan Nersesjan and Christian Hedeager Krag and Peirong Liu and Pablo Rocamora García and Mostafa Mehdipour Ghazi and Mikael Boesen and Michael Eriksen Benros and Juan Eugenio Iglesias and Mads Nielsen },
  journal={arXiv preprint arXiv:2506.14432},
  year={ 2025 }
}