Year: 2025
Type: article
Abstract: Lung disorders like pneumonia, cancer, and COVID-19, a common and potentially deadly respiratory infection, are very challenging to identify accurately and promptly. Using advances in machine learning (ML) techniques, this research aims to produce a reliable and efficient pneumonia detection system. Chest CT images are used to build a convolutional neural network (CNN) model to differentiate between lung pictures with pneumonia and those that are healthy. Training and validation datasets are a diverse collection of chest CT images collected from multiple sources. With strong sensitivity and accuracy, the proposed approach detects pneumonia with promising results. COVID-19 can also cause long-term harm to the lungs and other organs. When an infected individual coughs, sneezes, or exhales, droplets are released that are the main way the COVID-19 virus is transmitted. Being too heavy to float in midair, these drops quickly land on floors or other objects. The corona virus disease 2019 (COVID-19) started to spread globally in early 2020, as everyone is aware. causing a global health crisis associated with existential issues. Thus, automating the diagnosis of lung infections from computed tomography (CT) images presents a significant possibility to improve the traditional healthcare approach to COVID-19. Nonetheless, there are several challenges in distinguishing infected regions from CT slices, including the broad variety of infection characteristics and the poor contrast between healthy tissues and infections. Moreover, collecting large amounts of data in a short period of time is impracticable, which hinders the training of a deep model. Our proposed technique would analyze the CT scan of the lung to determine the affected lung part and the infected region. The technology will assess the intensity of the inflection and help patients take the appropriate response
Authors: Yogita Kajabe, Brijendra Gupta
Language: English
Topic: COVID-19 diagnosis using AI
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W4409195265