Skip to content

Latest commit

 

History

History
73 lines (48 loc) · 2.72 KB

File metadata and controls

73 lines (48 loc) · 2.72 KB

Chest Cancer Detection With Chest CT-Scan 🩺💻📈

Chest cancer is a leading cause of death worldwide. Early detection of chest cancer is crucial for successful treatment and better patient outcomes. Chest CT-scans are an important tool for diagnosing chest cancer, but the process of analyzing CT-scans can be time-consuming and require specialized medical expertise.

To address this challenge, I have developed a deep learning-based system for detecting chest cancer using chest CT-scans. The system uses state-of-the-art machine learning algorithms to analyze medical images and identify potential cancerous lesions in the chest. By automating the analysis process, our system can help healthcare professionals make faster and more accurate diagnoses, potentially saving lives. 💪🔬💊

Dataset 📊

I used the Chest CT-Scan Images dataset from Kaggle, which contains 1000 CT-scans of the chest, labeled as either normal or 3 type of cancerous lesions. The images in the dataset have varying resolutions, so I preprocessed them to ensure they were all the same size. 📈📉📊

Technologies Used 💻

The project was developed using the following technologies:

  • Python 🐍
  • PyTorch 🔥
  • Timm 🚀
  • OpenCV 📷
  • NumPy 🔢
  • Matplotlib 📈
  • Pillow 🛏️

System Requirements 🛠️

The following system requirements must be met in order to run the project:

  • Python 3.6 or higher
  • PyTorch 1.12.1+cu113
  • Timm 0.6.11
  • NumPy 1.21.6
  • Torchvision 0.13.1+cu113
  • OpenCV-Python 4.6.0
  • Matplotlib 3.2.2
  • Pillow 7.1.2
  • Json 2.0.9

Train Model 🚂

To train the model, run the Train.py script. I used the ResNet50 architecture for the model. 🏋️‍♂️🤖

Results 📊

After training the model on the Chest CT-Scan dataset, we achieved the following results:

Results Results Results Results

ToDo 📝

Here are some ideas for future development:

  • Improve model accuracy by training on larger datasets or using more advanced architectures.
  • Develop a user-friendly interface for the system to make it more accessible to healthcare professionals.
  • Add Notebook vesion (Done!)

Contributing 🤝

I welcome contributions to this project! If you would like to contribute, please follow these steps:

  1. Fork the repository.
  2. Create a new branch with a descriptive name.
  3. Make your changes.
  4. Test your changes.
  5. Submit a pull request.

I will review your pull request and provide feedback as soon as possible.

License 📄

This project is licensed under the MIT License - see the LICENSE.md file for details. 📜👨‍💻