In the context of Deep Learning applications and image processing, semantic segmentation consists of assigning a label to each pixel in the image, which returns a segmentation mask for each input image. In this chapter, the labels for the semantic segmentation task are “Lung” and “Background”.
Published in Chapter:
Deep Learning Applied to COVID-19 Detection in X-Ray Images
Harold Brayan Arteaga-Arteaga (Universidad Autónoma de Manizales, Colombia), Melissa delaPava (Universidad Nacional de Colombia, Colombia), Alejandro Mora-Rubio (Universidad Autónoma de Manizales, Colombia), Mario Alejandro Bravo-Ortíz (Universidad Autónoma de Manizales, Colombia), Jesus Alejandro Alzate-Grisales (Universidad Autónoma de Manizales, Colombia), Daniel Arias-Garzón (Universidad Autónoma de Manizales, Colombia), Luis Humberto López-Murillo (Universidad Nacional de Colombia, Colombia), Felipe Buitrago-Carmona (Universidad Autónoma de Manizales, Colombia), Juan Pablo Villa-Pulgarín (Universidad Autónoma de Manizales, Colombia), Esteban Mercado-Ruiz (Universidad Autónoma de Manizales, Colombia), Fernanda Martínez Rodríguez (Universidad de Guadalajara, Mexico), Maria Jose Palancares Sosa (Instituto Politécnico Nacional, Mexico), Sonia H. Contreras-Ortiz (Universidad Tecnológica de Bolívar, Colombia), Simon Orozco-Arias (Universidad Autónoma de Manizales, Colombia), Mahmoud Hassaballah (South Valley University, Egypt), María de la Iglesia Vayá (Fundación para el Fomento de la Investigación Sanitario y Biomédica de la Comunidad Valenciana, Spain), Oscar Cardona-Morales (Universidad Autónoma de Manizales, Colombia), and Reinel Tabares-Soto (Universidad Autonóma de Manizales, Colombia)
Copyright: © 2022
|Pages: 46
DOI: 10.4018/978-1-6684-2304-2.ch007
Abstract
COVID-19 caused by the SARS-CoV-2 virus has affected healthcare and people's lifestyles worldwide since 2019. Among the available diagnostic tools, reverse transcription-polymerase chain reaction has proven highly accurate. However, the need for a specialized laboratory makes these tests expensive and time-consuming between sample collection and results. Currently, there are initial steps for the diagnosis of COVID-19 through chest x-ray images. Additionally, artificial intelligence techniques like deep learning (DL) help identify abnormalities. Inspired by the reported success of DL, this chapter presents an introduction to state-of-the-art DL-based approaches applied to the detection of COVID-19 in chest x-ray images, which currently allows assessing disease severity. The results presented are obtained using well-known models and some novel networks designed for this task. In addition, the models were evaluated using the most used public datasets, applying preprocessing techniques to improve detection results. Finally, this chapter shows some possible future research directions.