Accurate diagnosis of respiratory conditions is crucial for effective treatment and patient care. This project leverages deep learning techniques to classify chest X-ray images into three categories:
- COVID-19
- Pneumonia
- Normal
The model combines the powerful feature extraction capabilities of ResNet50 with the sequence processing strengths of Gated Recurrent Units (GRUs). This hybrid architecture ensures high accuracy in distinguishing between different types of lung conditions.
To make this tool accessible to healthcare professionals and researchers, I have developed a user-friendly web application using Streamlit. This application allows users to upload X-ray images and receive instant classification results, aiding in quick and informed decision-making.
To run this project locally, follow these steps:
-
Clone the repository:
git clone https://github.com/nawaz0x1/X-Ray-Classification.git cd X-Ray-Classification
-
Install the required dependencies:
pip install -r requirements.txt
-
Download the
model.keras
file from the GDrive link and replace it withModel/model.keras
.
To run the Streamlit web app:
streamlit run App.py
The dataset was obtained from Kaggle.