Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xu, Tony, Hosseini, Sepehr, Anderson, Chris, Rinaldi, Anthony, Krishnan, Rahul G., Martel, Anne L., Goubran, Maged
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2501.11755
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917898427039744
author Xu, Tony
Hosseini, Sepehr
Anderson, Chris
Rinaldi, Anthony
Krishnan, Rahul G.
Martel, Anne L.
Goubran, Maged
author_facet Xu, Tony
Hosseini, Sepehr
Anderson, Chris
Rinaldi, Anthony
Krishnan, Rahul G.
Martel, Anne L.
Goubran, Maged
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_11755
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A generalizable 3D framework and model for self-supervised learning in medical imaging
Xu, Tony
Hosseini, Sepehr
Anderson, Chris
Rinaldi, Anthony
Krishnan, Rahul G.
Martel, Anne L.
Goubran, Maged
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title A generalizable 3D framework and model for self-supervised learning in medical imaging
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.11755