Machine learning approaches for COVID-19 detection from chest X-ray imaging: A Systematic Review
It helps researchers navigate the crowded field of ML-based COVID-19 diagnostic tools, offering a consolidated reference for future work, though it is incremental as a review paper.
This systematic review addresses the challenge of identifying effective machine learning approaches for COVID-19 detection from chest X-ray images by analyzing existing research to provide a baseline on methods, architectures, databases, and limitations.
There is a necessity to develop affordable, and reliable diagnostic tools, which allow containing the COVID-19 spreading. Machine Learning (ML) algorithms have been proposed to design support decision-making systems to assess chest X-ray images, which have proven to be useful to detect and evaluate disease progression. Many research articles are published around this subject, which makes it difficult to identify the best approaches for future work. This paper presents a systematic review of ML applied to COVID-19 detection using chest X-ray images, aiming to offer a baseline for researchers in terms of methods, architectures, databases, and current limitations.