Cargando…

“Quo Vadis Diagnosis”: Application of Informatics in Early Detection of Pneumothorax

A pneumothorax is a condition that occurs in the lung region when air enters the pleural space—the area between the lung and chest wall—causing the lung to collapse and making it difficult to breathe. This can happen spontaneously or as a result of an injury. The symptoms of a pneumothorax may inclu...

Descripción completa

Detalles Bibliográficos
Autores principales: Kumar, V. Dhilip, Rajesh, P., Geman, Oana, Craciun, Maria Daniela, Arif, Muhammad, Filip, Roxana
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10093601/
https://www.ncbi.nlm.nih.gov/pubmed/37046523
http://dx.doi.org/10.3390/diagnostics13071305
_version_ 1785023625778167808
author Kumar, V. Dhilip
Rajesh, P.
Geman, Oana
Craciun, Maria Daniela
Arif, Muhammad
Filip, Roxana
author_facet Kumar, V. Dhilip
Rajesh, P.
Geman, Oana
Craciun, Maria Daniela
Arif, Muhammad
Filip, Roxana
author_sort Kumar, V. Dhilip
collection PubMed
description A pneumothorax is a condition that occurs in the lung region when air enters the pleural space—the area between the lung and chest wall—causing the lung to collapse and making it difficult to breathe. This can happen spontaneously or as a result of an injury. The symptoms of a pneumothorax may include chest pain, shortness of breath, and rapid breathing. Although chest X-rays are commonly used to detect a pneumothorax, locating the affected area visually in X-ray images can be time-consuming and prone to errors. Existing computer technology for detecting this disease from X-rays is limited by three major issues, including class disparity, which causes overfitting, difficulty in detecting dark portions of the images, and vanishing gradient. To address these issues, we propose an ensemble deep learning model called PneumoNet, which uses synthetic images from data augmentation to address the class disparity issue and a segmentation system to identify dark areas. Finally, the issue of the vanishing gradient, which becomes very small during back propagation, can be addressed by hyperparameter optimization techniques that prevent the model from slowly converging and poorly performing. Our model achieved an accuracy of 98.41% on the Society for Imaging Informatics in Medicine pneumothorax dataset, outperforming other deep learning models and reducing the computation complexities in detecting the disease.
format Online
Article
Text
id pubmed-10093601
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100936012023-04-13 “Quo Vadis Diagnosis”: Application of Informatics in Early Detection of Pneumothorax Kumar, V. Dhilip Rajesh, P. Geman, Oana Craciun, Maria Daniela Arif, Muhammad Filip, Roxana Diagnostics (Basel) Article A pneumothorax is a condition that occurs in the lung region when air enters the pleural space—the area between the lung and chest wall—causing the lung to collapse and making it difficult to breathe. This can happen spontaneously or as a result of an injury. The symptoms of a pneumothorax may include chest pain, shortness of breath, and rapid breathing. Although chest X-rays are commonly used to detect a pneumothorax, locating the affected area visually in X-ray images can be time-consuming and prone to errors. Existing computer technology for detecting this disease from X-rays is limited by three major issues, including class disparity, which causes overfitting, difficulty in detecting dark portions of the images, and vanishing gradient. To address these issues, we propose an ensemble deep learning model called PneumoNet, which uses synthetic images from data augmentation to address the class disparity issue and a segmentation system to identify dark areas. Finally, the issue of the vanishing gradient, which becomes very small during back propagation, can be addressed by hyperparameter optimization techniques that prevent the model from slowly converging and poorly performing. Our model achieved an accuracy of 98.41% on the Society for Imaging Informatics in Medicine pneumothorax dataset, outperforming other deep learning models and reducing the computation complexities in detecting the disease. MDPI 2023-03-30 /pmc/articles/PMC10093601/ /pubmed/37046523 http://dx.doi.org/10.3390/diagnostics13071305 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kumar, V. Dhilip
Rajesh, P.
Geman, Oana
Craciun, Maria Daniela
Arif, Muhammad
Filip, Roxana
“Quo Vadis Diagnosis”: Application of Informatics in Early Detection of Pneumothorax
title “Quo Vadis Diagnosis”: Application of Informatics in Early Detection of Pneumothorax
title_full “Quo Vadis Diagnosis”: Application of Informatics in Early Detection of Pneumothorax
title_fullStr “Quo Vadis Diagnosis”: Application of Informatics in Early Detection of Pneumothorax
title_full_unstemmed “Quo Vadis Diagnosis”: Application of Informatics in Early Detection of Pneumothorax
title_short “Quo Vadis Diagnosis”: Application of Informatics in Early Detection of Pneumothorax
title_sort “quo vadis diagnosis”: application of informatics in early detection of pneumothorax
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10093601/
https://www.ncbi.nlm.nih.gov/pubmed/37046523
http://dx.doi.org/10.3390/diagnostics13071305
work_keys_str_mv AT kumarvdhilip quovadisdiagnosisapplicationofinformaticsinearlydetectionofpneumothorax
AT rajeshp quovadisdiagnosisapplicationofinformaticsinearlydetectionofpneumothorax
AT gemanoana quovadisdiagnosisapplicationofinformaticsinearlydetectionofpneumothorax
AT craciunmariadaniela quovadisdiagnosisapplicationofinformaticsinearlydetectionofpneumothorax
AT arifmuhammad quovadisdiagnosisapplicationofinformaticsinearlydetectionofpneumothorax
AT filiproxana quovadisdiagnosisapplicationofinformaticsinearlydetectionofpneumothorax