README.md

metadata

title: Chest Cancer Detection
emoji: 🚀
colorFrom: blue
colorTo: red
sdk: gradio
sdk_version: 5.27.0
app_file: app.py
pinned: false
license: mit

Chest CT Scan Cancer Detection

This application uses a deep learning model to detect cancer in chest CT scan images. The model is based on a DenseNet121 architecture and trained on the Chest CT-Scan Images dataset from Kaggle.

How to Use

1. Upload a chest CT scan image using the interface
2. Click "Analyze Image" to get results
3. View the prediction (Normal or Cancer) and visualization

About the Model

• Architecture: Modified DenseNet121
• Task: Binary Classification (Normal vs. Cancer)
• Input: Chest CT scan images (resized to 256x256)
• Performance: ~90% accuracy on test set

Limitations

• The model works best with chest CT scans similar to those in the training data
• This is a research tool and should not be used for clinical diagnosis without professional medical oversight

Citation

If you use this model in your research, please cite: @misc{samadov2025chestcancer, author = {Ismat Samadov}, title = {Chest Cancer Detection Using Deep Learning}, year = {2025}, publisher = {GitHub}, journal = {GitHub repository}, howpublished = {\url{https://github.com/Ismat-Samadov/chest_cancer_detection}} }