README.md

---
datasets:
- Elsafty
- Chula
- DSE
library_name: timm
license: cc-by-4.0
pipeline_tag: image-feature-extraction
tags:
- red-blood-cells
- hematology
- medical-imaging
- vision-transformer
- dino
- dinov2
- feature-extraction
- foundation-model
model-index:
- name: RedDino-base
  results:
  - task:
      type: image-classification
      name: RBC Shape Classification
    dataset:
      name: Elsafty
      type: Classification
    metrics:
    - type: Weighted F1
      value: 88.1
    - type: Balanced Accuracy
      value: 89.3
    - type: Accuracy
      value: 88.2
    - type: Weighted F1
      value: 83.8
    - type: Balanced Accuracy
      value: 78.6
    - type: Accuracy
      value: 83.8
    - type: Weighted F1
      value: 85.9
    - type: Balanced Accuracy
      value: 57.9
    - type: Accuracy
      value: 86.0
---

# RedDino-base

**RedDino** is a self-supervised Vision Transformer foundation model specifically designed for **red blood cell (RBC)** image analysis.  
It leverages a tailored version of the **DINOv2** framework, trained on a meticulously curated dataset of **1.25 million RBC images** from diverse acquisition modalities and sources.  
This model excels at extracting robust, general-purpose features for downstream hematology tasks such as **shape classification**, **morphological subtype recognition**, and **batch-effect–robust analysis**.

Unlike general-purpose models pretrained on natural images, RedDino incorporates hematology-specific augmentations, architectural tweaks, and RBC-tailored data preprocessing, enabling **state-of-the-art performance** on multiple RBC benchmarks.

> 🧠 Developed by [Luca Zedda](https://orcid.org/0009-0001-8488-1612), [Andrea Loddo](https://orcid.org/0000-0002-6571-3816), [Cecilia Di Ruberto](https://orcid.org/0000-0003-4641-0307), and [Carsten Marr](https://orcid.org/0000-0003-2154-4552)  
> 🏥 University of Cagliari & Helmholtz Munich  
> 📄 Preprint: [arXiv:2508.08180](https://arxiv.org/abs/2508.08180)  
> 💻 Code: [https://github.com/Snarci/RedDino](https://github.com/Snarci/RedDino)

---

## Model Details

-   **Architecture:** ViT-base, patch size 14
-   **SSL framework:** DINOv2 (customized for RBC morphology)
-   **Pretraining dataset:** 1.25M RBC images from 18 datasets
-   **Embedding size:** 768
-   **Applications:** RBC morphology classification, feature extraction, batch-effect–robust 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/RedDino-base", pretrained=True)
model.eval()
device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)

# Load and preprocess image
image = Image.open("path/to/rbc_image.jpg").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)

# Extract features
with torch.no_grad():
    embedding = model(input_tensor)
```
## 📝 Citation

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

**RedDino: A foundation model for red blood cell analysis**  
Luca Zedda, Andrea Loddo, Cecilia Di Ruberto, Carsten Marr — 2025  
Preprint: arXiv:2508.08180. https://arxiv.org/abs/2508.08180

```bibtex
@misc{zedda2025reddinofoundationmodelred,
      title={RedDino: A foundation model for red blood cell analysis}, 
      author={Luca Zedda and Andrea Loddo and Cecilia Di Ruberto and Carsten Marr},
      year={2025},
      eprint={2508.08180},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2508.08180}, 
}
```