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

Completed

• Conditions: COVID-19 Pneumonia; COVID-19 (Coronavirus Disease 2019)
• Interventions: Other: Categorization of chest xrays images

• Registration Number: NCT05722665
• Lead Sponsor: Fundacion Clinica Valle del Lili

Brief 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.

Detailed 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.

Study Timeline

• Study Start: 2021-08-26
• Primary Completion: 2022-11-30
• Study Completion: 2022-11-30
• Status Verified: 2023-02
• Study First Submitted: 2023-02-08
• Study First Submitted QC: 2023-02-08
• Study First Posted: 2023-02-10
• Last Update Submitted: 2023-02-20
• Last Update Posted: 2023-02-23

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 3599

Inclusion Criteria

• Chest radiographs from patients without COVID-19 or other pneumonia took before the pandemic start date (January 2020)
• Chest radiographs from patients with COVID-19 confirmed by positive Reverse Transcriptase polymerase chain reaction (RT-PCR) and/or presence of antibodies to COVID-19 and/or positive COVID-19 viral antigen.
• Chest radiographs from patients without COVID-19 confirmed by a negative Reverse Transcriptase polymerase chain reaction (RT-PCR) and other pneumonia diagnoses taken before the pandemic start date (January 2020)

Exclusion Criteria

• N/A

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
COVID-19 chest radiographs	Categorization of chest xrays images	X-rays belonging to patients with a diagnosis of COVID-19 confirmed by positive Reverse Transcriptase polymerase chain reaction (RT-PCR) and/or presence of antibodies to COVID-19 and/or positive COVID-19 viral antigen.
Normal chest radiographs	Categorization of chest xrays images	X-rays without alterations in the lung parenchyma
Other pneumonia chest radiographs	Categorization of chest xrays images	X-rays belonging to patients with a diagnosis of pneumonia other than COVID-19

Primary Outcome Measures

Name	Time	Method
COVID-19 (coronavirus disease 2019) pneumonia chest radiograph identified	month 8	Development and determination of the predictive capacity of a Convolutional Neural Network model to detect viral pneumonia in chest radiographs of adult patients with acute respiratory disease secondary to SARS-COV-2 infection.

Trial Locations

Locations (1)

Fundacion Valle del Lili; 🇨🇴 Cali, Valle Del Cauca, Colombia