Papers/2609.26924
🧪 Test?View on arXiv

nnFoundation: 3D Foundation Models for Radiology

Not specified in the provided content

3D imagingfoundation modelsradiologytransfer learning
2609.26924
Builder Relevance
80%
1d ago

Abstract

nnFoundation presents complementary convolutional and transformer-based 3D radiological foundation models that outperform prior models across various tasks.

Reality Card

Core Claim

nnFoundation models establish state-of-the-art performance for radiological imaging across 108 tasks, demonstrating that performance is influenced by the interplay of scalable pretraining, complementary architectures, and dataset-aware adaptation.

Method / Result

Trained on 2.1 million CT, MRI, and PET image volumes from 125 datasets, achieving superior performance compared to prior models.

Limitations

The performance is task-dependent, which may complicate generalization across all tasks.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers