This project is an implementation of a deep learning model to detect pneumonia in X-ray images of patients. The model uses a Convolutional Neural Network (CNN) architecture with three convolution layers to extract relevant features from the images and classify them as "Normal" or "Pneumonia."
Early detection of pneumonia is crucial for effective treatment and patient recovery. This project utilizes deep learning techniques to automate the analysis of X-ray images and identify the presence of pneumonia.
The CNN model used in this project consists of three convolution layers, followed by pooling layers and dense layers. The architecture is as follows:
- Convolutional Layer with 32 filters, 3x3 kernel size, ReLU activation function.
- Max Pooling Layer with a 2x2 pool size.
- Convolutional Layer with 64 filters, 3x3 kernel size, ReLU activation function.
- Max Pooling Layer with a 2x2 pool size.
- Convolutional Layer with 128 filters, 3x3 kernel size, ReLU activation function.
- Max Pooling Layer with a 2x2 pool size.
- Dense layers followed by an output layer with sigmoid activation.
Obs.: On the 'pneumonia' and 'normal' folders are the data of test set. If you want to see all archives go to the link below. The project can also be found at: link to the Kaggle dataset