Our project aims to develop a Pneumonia Detection System using AI. The system will be trained on a dataset of labelled lung X-Ray images, consisting of three categories - Normal, Bacterial Pneumonia, and Viral Pneumonia. We will be using the FastAI Python library to build and train the deep learning model for classification.
To use this project, follow these steps:
1) Clone the repository: git clone https://github.com/karantiet/Pneumonia-Detection_AI/
2) Install the necessary dependencies: pip install fastbook
3) Download the Chest X-ray dataset from Kaggle and extract it to the appropriate directory.
Open the pneumonia-detection.ipynb notebook and follow the instructions to train and evaluate the model.
Note: You will need to have FastAI installed to run this project
The Chest X-Ray Images (Pneumonia Detection) dataset on Kaggle will be used for training and testing our model. This dataset consists of 5,856 chest X-ray images with three categories - Normal, Bacterial Pneumonia, and Viral Pneumonia.
The pre-trained ResNet50 model from FastAI will be used as the base model for training the classifier. This model allows us to train deep neural networks with over 150 layers, which will help us achieve better accuracy in detecting pneumonia from X-Ray images.
We will use FastAI to preprocess the images and create data loaders for the training and testing data. We will then train the classifier on the preprocessed data and evaluate its performance using various metrics such as accuracy and F1 score.
Contributions and feedback are welcome. Please open an issue or a pull request if you have any suggestions or improvements.
- Karan Chhabra
- Taanisha Agarwal
- Divyam Malik
- Arshiya Sethi
By building a Pneumonia Detection System using AI, we can help doctors and medical professionals make faster and more accurate diagnoses of pneumonia, which can lead to better patient outcomes.
This project is licensed under the MIT License. See the LICENSE file for details.