README.md

metadata

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

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, Andrea Loddo, Cecilia Di Ruberto, and Carsten Marr
🏥 University of Cagliari & Helmholtz Munich
📄 Preprint: arXiv:2508.08180
💻 Code: 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

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

@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}, 
}