A generalizable 3D framework and model for self-supervised learning in medical imaging

Current self-supervised learning (SSL) methods for 3D medical imaging rely on simple pretext formulations and organ- or modality-specific datasets, limiting their generalizability and scalability. We present 3DINO, a cutting-edge SSL method adapted to 3D datasets, and pretrain 3DINO-ViT: a general-purpose model for medical imaging, on a ultra-large multimodal dataset of ~100,000 3D scans from over 10 organs. We show 3DINO-ViT outperforms state-of-the-art pretrained models on numerous downstream imaging tasks.

Authors

Institutions

Publication Details

Journal
npj Digital Medicine
Published
2025-11-07
DOI
https://doi.org/10.1038/s41746-025-02035-w
Citations
6
Primary Topic
Domain Adaptation and Few-Shot Learning
Type
article
Field-Weighted Citation Impact
14.89

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A generalizable 3D framework and model for self-supervised learning in medical imaging

Sepehr Hosseini, Anne L. Martel, Tony Xu, Anthony Rinaldi et al.
6 citations
npj Digital Medicine
Domain Adaptation and Few-Shot Learning
14.89
article

A generalizable 3D framework and model for self-supervised learning in medical imaging

Sepehr Hosseini, Anne L. Martel, Tony Xu, Anthony Rinaldi, Maged Goubran, Rahul G. Krishnan, Chris Anderson
article en
6 citations

Abstract

Current self-supervised learning (SSL) methods for 3D medical imaging rely on simple pretext formulations and organ- or modality-specific datasets, limiting their generalizability and scalability. We present 3DINO, a cutting-edge SSL method adapted to 3D datasets, and pretrain 3DINO-ViT: a general-purpose model for medical imaging, on a ultra-large multimodal dataset of ~100,000 3D scans from over 10 organs. We show 3DINO-ViT outperforms state-of-the-art pretrained models on numerous downstream imaging tasks.

npj Digital MedicineVol. 8(1)
Sunnybrook Health Science Centre (CA), University of Toronto (CA), Health Sciences Centre (CA), Vector Institute (CA), Sunnybrook Research Institute
Foundation for the National Institutes of Health, Alzheimer's Association, Bristol-Myers Squibb, Eli Lilly and Company, Pfizer, Biogen, Meso Scale Diagnostics, Alzheimer's Disease Neuroimaging Initiative, BioClinica, Novartis Pharmaceuticals Corporation, University of Ottawa, McMaster University, Northern California Institute for Research and Education, Government of Ontario, Centre for Addiction and Mental Health Foundation, London Health Sciences Foundation, Canada Research Chairs, Queen's University, Eisai, Servier, H. Lundbeck A/S, IXICO, Temerty Family Foundation, Alliance de recherche numérique du Canada, National Institutes of Health, Genentech, University of California, Los Angeles, McDonnell Center for Systems Neuroscience, Canadian Institutes of Health Research, Natural Sciences and Engineering Research Council of Canada, Faculty of Health Sciences, Queen's University
Openalex Percentile: Top 1%
Domain Adaptation and Few-Shot Learning
14.89
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.