README.md

---
license: cc-by-4.0
tags:
  - radiomics
  - medical-imaging
  - vision-transformer
  - dino
  - dinov2
  - feature-extraction
  - foundation-model
library_name: timm
datasets:
  - medmnist
  - radimagenet
  - BUSI
pipeline_tag: feature-extraction
model-index:
  - name: RadioDINO-b16
    results:
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: BreastMNIST
          type: BreastMNIST
        metrics:
          - type: F1
            value: 87.69
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: PneumoniaMNIST
          type: PneumoniaMNIST
        metrics:
          - type: F1
            value: 93.29
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: OrganAMNIST
          type: OrganAMNIST
        metrics:
          - type: F1
            value: 97.20
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: OrganCMNIST
          type: OrganCMNIST
        metrics:
          - type: F1
            value: 94.57
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: OrganSMNIST
          type: OrganSMNIST
        metrics:
          - type: F1
            value: 78.15
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: BUSI
          type: BUSI
        metrics:
          - type: F1
            value: 91.73
---

# RadioDINO-b16

**RadioDINO-b16** is a self-supervised Vision Transformer foundation model developed for radiomics and medical imaging. It is based on the DINO framework and pretrained on the large-scale **RadImageNet** dataset (1.35 million CT, MRI, and Ultrasound images across 165 classes and 11 anatomical regions). This model is part of the *Radio DINO* family and was created to extract robust, general-purpose features for downstream medical tasks including classification, segmentation, and interpretability analysis.

Unlike traditional radiomics methods that rely on handcrafted features and supervised models pretrained on natural images, RadioDINO-b16 offers a domain-adapted alternative that consistently outperforms previous models on diverse medical benchmarks. It has been rigorously validated on the MedMNISTv2 benchmark suite and shown to be effective even without fine-tuning.

> 🧠 Developed by [Luca Zedda](https://orcid.org/0009-0001-8488-1612), [Andrea Loddo](https://orcid.org/0000-0002-6571-3816), and [Cecilia Di Ruberto](https://orcid.org/0000-0003-4641-0307)  
> 🏥 Department of Mathematics and Computer Science, University of Cagliari  
> 📄 Published in: Computers in Biology and Medicine, 2025

---


## Model Details

- **Architecture:** ViT-base with patch size 16 (`b16`)
- **SSL framework:** DINO (self-distillation without labels)
- **Pretraining dataset:** RadImageNet (1.35M CT/MRI/Ultrasound images)
- **Embedding size:** 768
- **Applications:** Feature extraction, classification backbones, transfer learning, medical imaging analysis

## Example Usage

```python
from PIL import Image
from torchvision import transforms
import timm
import torch

# Load model from Hugging Face Hub
model = timm.create_model("hf_hub:Snarcy/RadioDino-b16", pretrained=True)
model.eval()
device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)

# Load and preprocess a sample image
image = Image.open("path/to/your/image").convert("RGB")
transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406],
                         std=[0.229, 0.224, 0.225]),
])
input_tensor = transform(image).unsqueeze(0).to(device)

# Forward pass to obtain feature embedding
with torch.no_grad():
    embedding = model(input_tensor)

```

## 📝 Citation

If you use this model, please cite the following paper:

**Radio DINO: A foundation model for advanced radiomics and AI-driven medical imaging analysis**  
Luca Zedda, Andrea Loddo, Cecilia Di Ruberto  
Computers in Biology and Medicine, Volume 195, 2025, 110583  
[https://doi.org/10.1016/j.compbiomed.2025.110583](https://doi.org/10.1016/j.compbiomed.2025.110583)

```bibtex
@article{ZEDDA2025110583,
  title = {Radio DINO: A foundation model for advanced radiomics and AI-driven medical imaging analysis},
  journal = {Computers in Biology and Medicine},
  volume = {195},
  pages = {110583},
  year = {2025},
  issn = {0010-4825},
  doi = {https://doi.org/10.1016/j.compbiomed.2025.110583},
  url = {https://www.sciencedirect.com/science/article/pii/S0010482525009345},
  author = {Luca Zedda and Andrea Loddo and Cecilia {Di Ruberto}},
  keywords = {Radiomics, Self-supervised learning, Deep learning, DINO, DINOV2, Medical imaging, Feature extraction, Generalizability},
}
```