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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cerri, Stefano, Munk, Asbjørn, Llambias, Sebastian Nørgaard, Ambsdorf, Jakob, Machnio, Julia, Nersesjan, Vardan, Krag, Christian Hedeager, Liu, Peirong, García, Pablo Rocamora, Ghazi, Mostafa Mehdipour, Boesen, Mikael, Benros, Michael Eriksen, Iglesias, Juan Eugenio, Nielsen, Mads
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915982389280768
author Cerri, Stefano
Munk, Asbjørn
Llambias, Sebastian Nørgaard
Ambsdorf, Jakob
Machnio, Julia
Nersesjan, Vardan
Krag, Christian Hedeager
Liu, Peirong
García, Pablo Rocamora
Ghazi, Mostafa Mehdipour
Boesen, Mikael
Benros, Michael Eriksen
Iglesias, Juan Eugenio
Nielsen, Mads
author_facet Cerri, Stefano
Munk, Asbjørn
Llambias, Sebastian Nørgaard
Ambsdorf, Jakob
Machnio, Julia
Nersesjan, Vardan
Krag, Christian Hedeager
Liu, Peirong
García, Pablo Rocamora
Ghazi, Mostafa Mehdipour
Boesen, Mikael
Benros, Michael Eriksen
Iglesias, Juan Eugenio
Nielsen, Mads
contents We present FOMO260K, a large-scale, heterogeneous dataset of 260,927 brain Magnetic Resonance Imaging (MRI) scans from 77,589 MRI sessions and 55,378 subjects, aggregated from 910 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 entry barriers for new users. Companion code for self-supervised pretraining and finetuning is provided, along with pretrained models. FOMO260K is intended to support the development and benchmarking of self-supervised learning methods in medical imaging at scale.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14432
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A large-scale heterogeneous 3D magnetic resonance brain imaging dataset for self-supervised learning
Cerri, Stefano
Munk, Asbjørn
Llambias, Sebastian Nørgaard
Ambsdorf, Jakob
Machnio, Julia
Nersesjan, Vardan
Krag, Christian Hedeager
Liu, Peirong
García, Pablo Rocamora
Ghazi, Mostafa Mehdipour
Boesen, Mikael
Benros, Michael Eriksen
Iglesias, Juan Eugenio
Nielsen, Mads
Image and Video Processing
Computer Vision and Pattern Recognition
We present FOMO260K, a large-scale, heterogeneous dataset of 260,927 brain Magnetic Resonance Imaging (MRI) scans from 77,589 MRI sessions and 55,378 subjects, aggregated from 910 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 entry barriers for new users. Companion code for self-supervised pretraining and finetuning is provided, along with pretrained models. FOMO260K is intended to support the development and benchmarking of self-supervised learning methods in medical imaging at scale.
title A large-scale heterogeneous 3D magnetic resonance brain imaging dataset for self-supervised learning
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.14432