1 About
This project aims to detect pneumonia from chest X-ray images using deep learning. The model is trained on 5,863 chest X-ray images and achieved an accuracy of 93.5% on the test set. We have achieved a maximum accuracy of around 70% with Logistic Regression when we used solver as liblinear and in case of Decision Trees, we could achieve an accuracy of 62.5% with a Decision Tree of maximum depth 3.
2 Source
Here, I provide an overview of the project. To delve into the methodology and explore the critical findings, I encourage you to review the accompanying slides and detailed report (above links).
3 Data Overview
Dataset is available in Mendeley dataset website (https://data.mendeley.com/datasets/rscbjbr9sj/3) Dataset contains thousands of validated OCT and Chest X-Ray images. The images are split into a training set and a testing set of independent patients. Images are labelled as (disease)- (randomized patient ID)-(image number by this patient) and split into 4 directories: CNV, DME, DRUSEN, and NORMAL.