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

Tony Xu, Sepehr Hosseini, Chris Anderson, Anthony Rinaldi, Rahul G. Krishnan +2 more
1/20/2025
eess.IVcs.CV

No official code found. Best implementation: AICONSlab/3DINO (171 stars, last commit 2025-11-07).

Abstract

Current self-supervised learning 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 use it to pretrain 3DINO-ViT: a general-purpose medical imaging model, on an exceptionally large, multimodal, and multi-organ dataset of ~100,000 3D medical imaging scans from over 10 organs. We validate 3DINO-ViT using extensive experiments on numerous medical imaging segmentation and classification tasks. Our results demonstrate that 3DINO-ViT generalizes across modalities and organs, including out-of-distribution tasks and datasets, outperforming state-of-the-art methods on the majority of evaluation metrics and labeled dataset sizes. Our 3DINO framework and 3DINO-ViT will be made available to enable research on 3D foundation models or further finetuning for a wide range of medical imaging applications.

View on arXivView PDF

Code Implementations(1)

AICONSlab/3DINOCommunity100%

[npj Digital Medicine] A generalizable 3D framework and model for self-supervised learning in medical imaging

17116Python, Jupyter NotebookMar 20, 202511 months agoNOASSERTION

Similar Papers

VIS-MAE: An Efficient Self-supervised Learning Approach on Medical Image Segmentation and Classification

90% match1 repo72024

Exploring Intrinsic Properties of Medical Images for Self-Supervised Binary Semantic Segmentation

90% match2024

MedMAE: A Self-Supervised Backbone for Medical Imaging Tasks

89% match1 repo102024

Multimodal, Multi-Disease Medical Imaging Foundation Model (MerMED-FM)

87% match1 repo62025

Adaptation of Foundation Models for Medical Image Analysis: Strategies, Challenges, and Future Directions

87% match2025

Multi-organ Self-supervised Contrastive Learning for Breast Lesion Segmentation

87% match2024

Cite this paper

@article{xu2025generalizable,
  title  = {A generalizable 3D framework and model for self-supervised learning in medical imaging},
  author = {Tony Xu and Sepehr Hosseini and Chris Anderson and Anthony Rinaldi and Rahul G. Krishnan and Anne L. Martel and Maged Goubran},
  year   = {2025},
  eprint = {2501.11755},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.11755v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.11755.svg)](https://codeofpaper.com/paper/2501.11755)

Discussion