This project aims to automate the screening and identification of tuberculosis (TB) from chest X-ray images using deep learning techniques, with a focus on different Convolutional Neural Networks (CNN) architecture i.e. Resnet, VGG19, and Inception. We explore these various CNN architectures to improve the accuracy and efficiency of TB detection, comparing our results to traditional radiologist interpretations.
- Python 3.x
- TensorFlow 2.x
- OpenCV for image processing
- Various CNN architectures (ResNet, Inception, VGG)
To get started with this project, clone this repository https://github.com/mirugwe1/TB_AI_screening.git
and install the required dependencies listed in requirements.txt
.