Medical Imaging Technology Detection for Machine Learning Classification Approach

Abstract

Impressive technological advancements continue to develop, impacting all aspects of life, especially the medical field. Medical technology allows us to solve many sophisticated problems improving our day-to-day health. Chest X-ray (CXR) technology is one of the essential developments in effective medical diagnosis. Usually, doctors manually analyze X-ray images to decide the severity and the type of medical problem. The recent respiratory pandemic, COVID-19, has affected millions of people globally. To tackle problems like COVID-19 more quickly and efficiently, we need to find solutions and mechanisms that quickly and efficiently detect respiratory diseases. The most pressing concern is classifying the difference between common pneumonia and COVID-19. The primary purpose of this study is to examine technological processes to find quicker CXR analysis possibilities for future usage. After completing the research, I found that machine-learning models demonstrated strong evidence for improved CXR image interpretation. Doctors and other frontline medical workers could use machine learning (ML) to improve the speed and reliability of CXR diagnoses. The summary report on the model showed its complete trustworthiness and usability. The research clarified the layering process to measure data accuracy, including layer type, shape, and parameters. Based on the model structure and training, testing data, the ML of the CNN algorithm proved that the ML method was more reliable and took less time to diagnose COVID-19 symptoms than manual image reading methods.