from transformers import ViTForImageClassification, ViTImageProcessor
from PIL import Image

# Load model
processor = ViTImageProcessor.from_pretrained("PayamFard123/dermaintel-wound-classifier")
model = ViTForImageClassification.from_pretrained("PayamFard123/dermaintel-wound-classifier")

# Classify image
image = Image.open("wound_image.jpg")
inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)
predicted_class = outputs.logits.argmax(-1).item()

Classes

Index	Label
0	Pressure Ulcer/Injury
1	Venous Ulcer
2	Arterial Ulcer
3	Diabetic Ulcer
4	Surgical Wound
5	Traumatic Wound
6	Normal/Healthy Skin

Limitations

This model is intended for clinical decision support, not replacement of clinical judgment
Performance may vary with image quality and lighting conditions
Should be used in conjunction with clinical assessment
Not FDA approved for diagnostic use

Citation

If you use this model, please cite:

bibtex

@misc{dermaintel-wound-classifier,
  title={DermaIntel Wound Type Classifier},
  author={DermaIntel Team},
  year={2024},
  publisher={HuggingFace},
  url={https://huggingface.co/PayamFard123/dermaintel-wound-classifier}
}

Contact

For questions or issues, contact the DermaIntel team.