Pneumonia is a deadly lung infection which impacts millions of people around the world. According to a report by the American Thoracic Society in 2015, it was the world’s leading cause of death among children under 5 years of age. This project deals with classification of pneumonia based on chest X-ray images using Machine Learning based techniques. With this project, we hope to make the diagnostic process easier by providing quick and accurate results.
For training our models, we used the Labeled Optical Coherence Tomography (OCT) and Chest X-Ray Images for Classification hosted publicly under the Creative Commons License at https://data.mendeley.com/datasets/rscbjbr9sj/2.
| Dataset Examples | Dataset Distribution |
|---|---|
 |
 |
- Accuracy
- Confusion matrix
- F1- Score (data is imbalanced)
- Baseline: HOG Features + SVM model
- HOG Features + ANN
- Vanilla CNN
- Transfer Learning using VGG-16
Please refer the notebooks at https://github.com/adityasaini70/Pneumonia-classification-using-chest-X-ray-Images/tree/main/Models for more information about the training workflow.
(Equal contribution by all)