Skip to content

Disha4346/Lung_Cancer

Repository files navigation

# 🫁 Lung Cancer Detection using Machine Learning & Deep Learning

Early detection of lung cancer significantly improves treatment success and patient survival rates.  
This project leverages **Machine Learning** and **Deep Learning (CNNs)** to analyze clinical data and CT-scan images for automated lung cancer prediction.

---

## 🚀 Project Overview

This system provides two different approaches for diagnosis:

1️⃣ **Machine Learning model** using patient clinical parameters  
2️⃣ **CNN model** using CT-Scan images for direct cancer identification  

Both models serve as a decision-support system to assist healthcare professionals with faster and more accurate screening.

---

## 🌟 Key Features

✅ Multi-class lung cancer risk prediction (ML Model)  
✅ CT-Scan Tumor classification (CNN Model)  
✅ Streamlit Web Interface for real-time diagnosis  
✅ Simple & user-friendly UI  
✅ Accepts local image uploads for inference

---

## 🧠 Tech Stack

- **Python**
- **Streamlit**
- **TensorFlow / Keras**
- **NumPy, Pandas, Matplotlib**
- **Scikit-Learn**
- **OpenCV**

---

## 📌 Live Deployment

Try the live application here 👇  
🔗 **Streamlit Deployment:** [https://lungcancer-77.streamlit.app/](Link for deployed version)

---

## ⚙️ How to Run Locally

Clone the repository:

```bash
git clone https://github.com/Disha4346/Lung_Cancer.git
cd LungCancerDetection

Install requirements:

pip install -r requirements.txt

Run Streamlit App:

streamlit run app.py

🔹 Recommended: Use a separate Conda environment to avoid conflicts

conda create -n tf python=3.12
conda activate tf
pip install -r requirements.txt

🏗️ System Architecture


🎥 Project Demo

Watch the full working demo: 🔗 https://github.com/user-attachments/assets/944fa44c-27b1-4bce-9580-29c3e6c8e41e


📂 Datasets Used

📌 Machine Learning model dataset — Clinical patient data 📌 CNN model dataset — CT-scan images

Dataset source: 🔗 https://www.kaggle.com/datasets/mohamedhanyyy/chest-ctscan-images


📊 Model Performance (Optional Section)

Model Accuracy Technique
ML Model ~95% Logistic Regression / Random Forest
CNN Model ~92% Custom CNN with Data Augmentation

👩‍💻 Developed By

Disha Gupta B.Tech | GLA University, Mathura AI & Medical Imaging Enthusiast 🚀

📬 Email: imdisha4346@gmail.com 🔗 GitHub: https://github.com/Disha4346


🌈 Contributions

Contributions, improvements & feature requests are always welcome! Create an Issue or Pull Request 🤝


⭐ If you found this helpful, please consider starring this repo! ⭐

About

Internship project on Lung Cancer Detection focused on analyzing textual clinical data, with additional insights from medical images.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors