Hyperparameter Optimization for COVID-19 Chest X-Ray Classification

TL;DR

This paper explores hyperparameter optimization techniques to improve COVID-19 detection accuracy from chest X-ray images, achieving up to 83% in binary classification and 64% in multi-class scenarios.

Contribution

It introduces a hyperparameter tuning approach that enhances model performance for COVID-19 chest X-ray classification.

Findings

Achieved 83% accuracy in binary classification

Achieved 64% accuracy in multi-class classification

Demonstrated effectiveness of hyperparameter optimization

Abstract

Despite the introduction of vaccines, Coronavirus disease (COVID-19) remains a worldwide dilemma, continuously developing new variants such as Delta and the recent Omicron. The current standard for testing is through polymerase chain reaction (PCR). However, PCRs can be expensive, slow, and/or inaccessible to many people. X-rays on the other hand have been readily used since the early 20th century and are relatively cheaper, quicker to obtain, and typically covered by health insurance. With a careful selection of model, hyperparameters, and augmentations, we show that it is possible to develop models with 83% accuracy in binary classification and 64% in multi-class for detecting COVID-19 infections from chest x-rays.