Convolutional Neural Network Model to Detect Coronavirus Disease 2019 (COVID-19) Pneumonia in Chest Radiographs — RedNeumon  

COVID-19 Pneumonia Clinical Trial

Official title: The Predictive Capacity of a Convolutional Neural Network (CNN) Model to Detect Viral Pneumonia in Adult Patients With Coronavirus Disease 2019 (COVID-19) in Cali, Colombia

Status Completed

Clinical Trial Summary

This study aims to design a Convolutional Neural Network (CNN) and apply an attention model to help differentiate pneumonia due to Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), pneumonia due to other viruses/bacteria, and normal chest x-ray (CXR) in clinical practice. A bank of digital chest images from a high-complexity health facility in Cali, Colombia, was used.

Clinical Trial Description

To differentiate coronavirus disease 2019 (COVID-19) pneumonia from other types of pneumonia, expert radiologists must analyze the chest x-ray (CXR) to identify visual, radiographic patterns associated with Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. It is challenging because the findings are similar for different types of pneumonia.

Since the manual diagnosis of COVID-19 from CXR is a difficult and time-consuming process, applying deep learning (DL) models to medical image analysis is a current hot research topic. This work will develop a new Convolutional Neural Network (CNN) to detect COVID-19 radiographs. It will use a large dataset of chest radiographs classified into three classes: viral/bacterial pneumonia, COVID-19 pneumonia, and normal images. The study aims to incorporate a new attention module that applies CNNs to the linear projection operation to help differentiate COVID-19 pneumonia from other pneumonia and normal chest radiographs in clinical practice. ;

Related Conditions & MeSH terms

• Coronavirus Infections
• COVID-19
• COVID-19 Pneumonia
• Pneumonia

• NCT number: NCT05722665
• Study type: Observational
• Source: Fundacion Clinica Valle del Lili
• Status: Completed
• Start date: August 26, 2021
• Completion date: November 30, 2022