Development of deep learning-based classification models for opacity differentiation in pediatric chest radiography

Opacities of non-interstitial origin in a pediatric patient's chest radiograph may indicate either consolidations and/or atelectasis, based on the appropriate clinical context. However, the overlapping and complex symptomatology of respiratory tract diseases in pediatric patients can make it di...

Full description

Saved in:
Bibliographic Details
Main Authors: Germán Enrique Galvis Ruiz, Johana Benavides-Cruz, Daniela Muñoz Corredor, Esteban Morales-Mendoza, Héctor Daniel Alejandro Cotrino Palma, Andrés Cely-Jiménez
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Informatics in Medicine Unlocked
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S235291482400162X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850175220629897216
author Germán Enrique Galvis Ruiz
Johana Benavides-Cruz
Daniela Muñoz Corredor
Esteban Morales-Mendoza
Héctor Daniel Alejandro Cotrino Palma
Andrés Cely-Jiménez
author_facet Germán Enrique Galvis Ruiz
Johana Benavides-Cruz
Daniela Muñoz Corredor
Esteban Morales-Mendoza
Héctor Daniel Alejandro Cotrino Palma
Andrés Cely-Jiménez
author_sort Germán Enrique Galvis Ruiz
collection DOAJ
description Opacities of non-interstitial origin in a pediatric patient's chest radiograph may indicate either consolidations and/or atelectasis, based on the appropriate clinical context. However, the overlapping and complex symptomatology of respiratory tract diseases in pediatric patients can make it difficult for physicians to interpret opacities. Artificial intelligence models are frequently employed by physicians for diagnostic support in healthcare, especially to evaluate aspects of radiographs that are not visible with the naked eye. In this study, a prediction model based on deep learning was used to differentiate between atelectasis and consolidations in pediatric chest radiographs from a clinical perspective. The radiologist can assist pediatricians in diagnosing respiratory pathologies based on the type of opacities using the machine learning model. We used 1297 chest X-ray images of pediatric patients with opacities including consolidations (n=500), atelectasis (n=499); and images without opacities (n=298). The images were preprocessed, and various deep learning models were applied to determine the model with the best metrics. The InceptionV3 model demonstrated a significant improvement over its initial results.
format Article
id doaj-art-7eff5f5c020b4cbfbe0bd4ac487c066b
institution OA Journals
issn 2352-9148
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Informatics in Medicine Unlocked
spelling doaj-art-7eff5f5c020b4cbfbe0bd4ac487c066b2025-08-20T02:19:30ZengElsevierInformatics in Medicine Unlocked2352-91482025-01-015210160510.1016/j.imu.2024.101605Development of deep learning-based classification models for opacity differentiation in pediatric chest radiographyGermán Enrique Galvis Ruiz0Johana Benavides-Cruz1Daniela Muñoz Corredor2Esteban Morales-Mendoza3Héctor Daniel Alejandro Cotrino Palma4Andrés Cely-Jiménez5Radiology and Diagnostic Imaging Program, Fundación Universitaria Sanitas, Street 170 #8-41, 110151, Bogotá D.C., ColombiaResearch Unit, Fundación Universitaria Sanitas, Street 170 #8-41, 110151, Bogotá D.C., Colombia; Corresponding author. Street 170 8-41, 110151, Bogotá D.C, Colombia.Healthcare Management Institute, Fundación Universitaria Sanitas, Street 170 #8-41, 110151, Bogotá D.C., ColombiaHealthcare Management Institute, Fundación Universitaria Sanitas, Street 170 #8-41, 110151, Bogotá D.C., ColombiaRadiology and Diagnostic Imaging Program, Fundación Universitaria Sanitas, Street 170 #8-41, 110151, Bogotá D.C., ColombiaDepartment of Data Management, Keralty, Street 100 #11b – 67, 110221, Bogotá D.C., ColombiaOpacities of non-interstitial origin in a pediatric patient's chest radiograph may indicate either consolidations and/or atelectasis, based on the appropriate clinical context. However, the overlapping and complex symptomatology of respiratory tract diseases in pediatric patients can make it difficult for physicians to interpret opacities. Artificial intelligence models are frequently employed by physicians for diagnostic support in healthcare, especially to evaluate aspects of radiographs that are not visible with the naked eye. In this study, a prediction model based on deep learning was used to differentiate between atelectasis and consolidations in pediatric chest radiographs from a clinical perspective. The radiologist can assist pediatricians in diagnosing respiratory pathologies based on the type of opacities using the machine learning model. We used 1297 chest X-ray images of pediatric patients with opacities including consolidations (n=500), atelectasis (n=499); and images without opacities (n=298). The images were preprocessed, and various deep learning models were applied to determine the model with the best metrics. The InceptionV3 model demonstrated a significant improvement over its initial results.http://www.sciencedirect.com/science/article/pii/S235291482400162XArtificial intelligenceDeep learningRadiographyPulmonary atelectasisChildrenLung diseases
spellingShingle Germán Enrique Galvis Ruiz
Johana Benavides-Cruz
Daniela Muñoz Corredor
Esteban Morales-Mendoza
Héctor Daniel Alejandro Cotrino Palma
Andrés Cely-Jiménez
Development of deep learning-based classification models for opacity differentiation in pediatric chest radiography
Informatics in Medicine Unlocked
Artificial intelligence
Deep learning
Radiography
Pulmonary atelectasis
Children
Lung diseases
title Development of deep learning-based classification models for opacity differentiation in pediatric chest radiography
title_full Development of deep learning-based classification models for opacity differentiation in pediatric chest radiography
title_fullStr Development of deep learning-based classification models for opacity differentiation in pediatric chest radiography
title_full_unstemmed Development of deep learning-based classification models for opacity differentiation in pediatric chest radiography
title_short Development of deep learning-based classification models for opacity differentiation in pediatric chest radiography
title_sort development of deep learning based classification models for opacity differentiation in pediatric chest radiography
topic Artificial intelligence
Deep learning
Radiography
Pulmonary atelectasis
Children
Lung diseases
url http://www.sciencedirect.com/science/article/pii/S235291482400162X
work_keys_str_mv AT germanenriquegalvisruiz developmentofdeeplearningbasedclassificationmodelsforopacitydifferentiationinpediatricchestradiography
AT johanabenavidescruz developmentofdeeplearningbasedclassificationmodelsforopacitydifferentiationinpediatricchestradiography
AT danielamunozcorredor developmentofdeeplearningbasedclassificationmodelsforopacitydifferentiationinpediatricchestradiography
AT estebanmoralesmendoza developmentofdeeplearningbasedclassificationmodelsforopacitydifferentiationinpediatricchestradiography
AT hectordanielalejandrocotrinopalma developmentofdeeplearningbasedclassificationmodelsforopacitydifferentiationinpediatricchestradiography
AT andrescelyjimenez developmentofdeeplearningbasedclassificationmodelsforopacitydifferentiationinpediatricchestradiography