Hyperparameter Optimization for COVID-19 Chest X-Ray Classification
This work addresses the need for cheaper and faster COVID-19 testing methods, though it is incremental as it applies existing optimization techniques to a specific medical imaging task.
The paper tackled the problem of detecting COVID-19 from chest X-rays by optimizing hyperparameters and augmentations, achieving 83% accuracy in binary classification and 64% in multi-class classification.
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.