├── .gitattributes ├── Model └── FrameWork.png └── README.md /.gitattributes: -------------------------------------------------------------------------------- 1 | # Auto detect text files and perform LF normalization 2 | * text=auto 3 | -------------------------------------------------------------------------------- /Model/FrameWork.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hazrat-Ali9/Skin-Cancer-Classification/HEAD/Model/FrameWork.png -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # An Efficient CNN Architecture for Classifying Skin Cancer on an Imbalanced Dataset 2 | 3 | ✨ Key Features 4 | 5 | 🖼️ Dermatology Image Preprocessing – Normalization, augmentation, and resizing 6 | 7 | 🤖 Deep Learning Models – CNNs, Transfer Learning (ResNet, VGG, EfficientNet, Inception) 8 | 9 | 📊 Performance Evaluation – Accuracy, Precision, Recall, F1-score, ROC curve, and Confusion Matrix 10 | 11 | 🔍 Multi-Class Classification – Different types of skin lesions (benign vs malignant) 12 | 13 | 📈 Visualization Tools – Training curves, misclassified samples, Grad-CAM heatmaps 14 | 15 | ⚡ Scalable Deployment (Optional) – Streamlit/Flask app for real-time image classification 16 | 17 | 🧰 Tech Stack 18 | 19 | Programming: Python 🐍 20 | 21 | Libraries & Frameworks: TensorFlow / Keras, PyTorch, OpenCV, scikit-learn, NumPy, Pandas, Matplotlib, Seaborn 22 | 23 | Environment: Jupyter Notebook / Google Colab 24 | 25 | Deployment (Optional): Flask / FastAPI / Streamlit / Django 26 | 27 | 📁 Project Structure 28 | 📁 data/ # Skin lesion datasets (train/test/validation) 29 | 📁 notebooks/ # Jupyter notebooks for model experiments 30 | 📁 models/ # Trained CNN & transfer learning models 31 | 📁 src/ # Scripts for preprocessing, training, evaluation 32 | 📁 results/ # Metrics, graphs, confusion matrices 33 | 📁 app/ # Web app or API for deployment 34 | 35 | 🚀 Getting Started 36 | git clone https://github.com/yourusername/Skin-Cancer-Classification.git 37 | cd Skin-Cancer-Classification 38 | pip install -r requirements.txt 39 | jupyter notebook 40 | 41 | 📌 Use Cases 42 | 43 | 🏥 Medical Diagnosis Assistance – Helps dermatologists with skin lesion classification 44 | 45 | 📊 Research & Healthcare AI – Academic projects in computer vision & medical AI 46 | 47 | 🎓 Educational Resource – Learn deep learning applications in healthcare 48 | 49 | 🌍 Telemedicine Solutions – Deploy as a web/mobile app for remote skin screening 50 | 51 | 🤝 Contributing 52 | 53 | Contributions are welcome! Add datasets, improve CNN architectures, or extend deployment by submitting a PR. 54 | 55 | 📜 License 56 | 57 | MIT License – Free for research, education, and healthcare innovation. 58 | 59 | ⭐ Support 60 | 61 | If this project inspires you, please star ⭐ the repo and share it with the AI + Healthcare community! 62 | 63 | 📚 This repository contains the original implementation of SkinNet-8: An Efficient CNN Architecture for Classifying Skin Cancer on an Imbalanced Dataset. 64 | 65 | 📧 **Contact**: For inquiries, you can reach out to us at rhslion34@gmail.com. 66 | 67 | ## Dataset Availability 68 | 69 | This project uses the following dataset for Skin Cancer Images: 70 | 71 | ## Code 72 | 73 | You can find the implementation of SkinNet-8 in the following file: 74 | 75 | - [SkinNet-8 Skin Cancer Classification.ipynb](Model/SkinNet-8%20Skin%20Cancer%20Classification.ipynb) 76 | 77 | ## Paper Framework 78 | 79 | 🖼️ **PIPELINE**: 80 | 81 | ![PIPELINE](Model/FrameWork.png) 82 | 83 | ## Copying 84 | 85 | This code is shared for research use only. If you encounter any issues or find inappropriate content in this code, please feel free to contact us. 86 | 87 | --------------------------------------------------------------------------------