Pneumonia-Detection-using-Deep-Learning

KO | EN

gitlite — search

#python #java #python3 #arduino #golang #machine-learning #rust #html #flask #javascript #seismology #nodejs

Pneumonia-Detection-using-Deep-Learning

★ 6 Open GitHub ↗

This project utilizes deep learning techniques to detect pneumonia from chest X-ray images. It employs the VGG16 convolutional neural network, pre-trained on ImageNet, and fine-tuned for binary classification (normal vs. pneumonia). The model is trained on a dataset of chest X-ray images and achieves high accuracy in distinguishing pneumonia cases.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Pneumonia Detection using Deep Learning

## Overview
This project utilizes deep learning techniques, specifically the VGG16 convolutional neural network, to detect pneumonia from chest X-ray images. The model is trained on a dataset consisting of images labeled as either "normal" or "pneumonia".

## Dataset
The dataset used in this project is sourced from Kaggle [https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia]. It consists of two main classes:
- Normal: Chest X-ray images of patients without pneumonia.
- Pneumonia: Chest X-ray images of patients diagnosed with pneumonia.

The dataset is split into training and testing sets, with appropriate preprocessing applied using Keras' `ImageDataGenerator`.

## Model Architecture
The VGG16 model, pre-trained on ImageNet, is employed as the base model. The top layers of VGG16 are adapted to fit the binary classification task of pneumonia detection. The model is fine-tuned by freezing the convolutional base and training only the custom classifier layers.

## Training
The model is compiled with:
- **Loss Function**: Categorical Cross-Entropy, suitable for multi-class classification.
- **Optimizer**: Adam optimizer for efficient weight updates.
- **Metrics**: Accuracy metric to monitor model performance during training.

The training process involves iterating through batches of augmented images generated by `ImageDataGenerator`, optimizing the model parameters to minimize the loss function.

## Evaluation
Model performance is evaluated on a separate test set to assess its ability to generalize to unseen data. Evaluation metrics include accuracy and loss on both training and validation sets across epochs.

## Prediction
Once trained, the model can make predictions on new chest X-ray images to classify them as either normal or indicating pneumonia. The predictions are based on the highest probability output from the softmax layer of the model.

## File Structure
- **Pneumonia.py**: Python script containing model definition, training, and saving.
- **Test.py**: Python script for loading the trained model and making predictions on new images.
- **Requirements.txt**: List of Python packages required to run the project.
- **LossVal_loss.png**: Plot showing training and validation loss during model training.
- **AccVal_acc.png**: Plot showing training and validation accuracy during model training.
- **pneumonia_model.keras**: Saved model file containing trained weights and architecture.

## Usage
To use the project:
1. Install the necessary dependencies listed in `requirements.txt`.
2. Train the model using `Pneumonia.py`.
3. Evaluate model performance and visualize training history using the generated plots.
4. Make predictions on new images using `Test.py`.

## Dependencies
Ensure you have the following dependencies installed:
- Keras
- TensorFlow
- Matplotlib
- NumPy

## Future Improvements
- Incorporate more advanced architectures like ResNet or DenseNet for potentially improved performance.
- Experiment with different augmentation techniques to further enhance model generalization.

## Authors
- [Khalid Md Ashik](https://github.com/K-Ashik)

## License
This project is licensed under the [MIT License](https://opensource.org/licenses/MIT).

Pneumonia-Detection-using-Deep-Learning

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README