Skin Diseases Detection Model (DermaDL)

Overview

This repository hosts a deep learning–based skin disease detection model trained on dermoscopic images.
The model classifies multiple skin conditions using a Convolutional Neural Network (CNN) and is designed to support early screening and awareness.

⚠️ This model is intended for research and educational purposes only and should not be used as a replacement for professional medical diagnosis.

Model Details

• Architecture: CNN (Transfer Learning)
• Framework: PyTorch
• Task: Image Classification
• Domain: Medical Imaging (Dermatology)
• Accuracy: ~91% on validation data

Supported Classes

• Melanoma
• Basal Cell Carcinoma
• Squamous Cell Carcinoma
• Benign Keratosis
• Actinic Keratosis
• Dermatofibroma
• Vascular Lesions
• Nevus

(Class labels may vary depending on dataset version)

Training Details

• Dataset: Dermoscopic skin lesion images
• Image Size: 224 × 224
• Loss Function: Cross-Entropy Loss
• Optimizer: Adam
• Evaluation Metric: Accuracy

How to Use

1️⃣ Install Dependencies

pip install torch torchvision pillow