Accuracy of deep learning for automated detection of pneumonia using chest X-Ray images: A systematic review and meta-analysis.
Artificial intelligence
CXR
Deep learning
Meta-analysis
Pneumonia
Journal
Computers in biology and medicine
ISSN: 1879-0534
Titre abrégé: Comput Biol Med
Pays: United States
ID NLM: 1250250
Informations de publication
Date de publication:
08 2020
08 2020
Historique:
received:
23
05
2020
revised:
21
06
2020
accepted:
27
06
2020
entrez:
10
8
2020
pubmed:
10
8
2020
medline:
22
6
2021
Statut:
ppublish
Résumé
Recently, deep learning (DL) algorithms have received widespread popularity in various medical diagnostics. This study aimed to evaluate the diagnostic performance of DL models in the detection and classifying of pneumonia using chest X-ray (CXR) images. PubMed, Embase, Scopus, Web of Science, and Google Scholar were searched in order to retrieve all studies that implemented a DL algorithm for discriminating pneumonia patients from healthy controls using CXR images. We used bivariate linear mixed models to pool diagnostic estimates including sensitivity (SE), specificity (SP), positive likelihood ratio (PLR), negative likelihood ratio (NLR), and diagnostic odds ratio (DOR). Also, the area under receiver operating characteristics curves (AUC) of the included studies was used to estimate the diagnostic value. The pooled SE, SP, PLR, NLR, DOR and AUC for DL in discriminating pneumonia CXRs from controls were 0.98 (95% confidence interval (CI): 0.96-0.99), 0.94 (95% CI: 0.90-0.96), 15.35 (95% CI: 10.04-23.48), 0.02 (95% CI: 0.01-0.04), 718.13 (95% CI: 288.45-1787.93), and 0.99 (95% CI: 0.98-100), respectively. The pooled SE, SP, PLR, NLR, DOR and AUC for DL in discriminating bacterial from viral pneumonia using CXR radiographs were 0.89 (95% CI: 0.79-0.94), 0.89 (95% CI: 0.78-0.95), 8.34 (95% CI: 3.75-18.55), 0.13 (95% CI: 0.06-0.26), 66.14 (95% CI: 17.34-252.37), and 0.95 (0.93-0.97). DL indicated high accuracy performance in classifying pneumonia from normal CXR radiographs and also in distinguishing bacterial from viral pneumonia. However, major methodological concerns should be addressed in future studies for translating to the clinic.
Sections du résumé
BACKGROUND
Recently, deep learning (DL) algorithms have received widespread popularity in various medical diagnostics. This study aimed to evaluate the diagnostic performance of DL models in the detection and classifying of pneumonia using chest X-ray (CXR) images.
METHODS
PubMed, Embase, Scopus, Web of Science, and Google Scholar were searched in order to retrieve all studies that implemented a DL algorithm for discriminating pneumonia patients from healthy controls using CXR images. We used bivariate linear mixed models to pool diagnostic estimates including sensitivity (SE), specificity (SP), positive likelihood ratio (PLR), negative likelihood ratio (NLR), and diagnostic odds ratio (DOR). Also, the area under receiver operating characteristics curves (AUC) of the included studies was used to estimate the diagnostic value.
RESULTS
The pooled SE, SP, PLR, NLR, DOR and AUC for DL in discriminating pneumonia CXRs from controls were 0.98 (95% confidence interval (CI): 0.96-0.99), 0.94 (95% CI: 0.90-0.96), 15.35 (95% CI: 10.04-23.48), 0.02 (95% CI: 0.01-0.04), 718.13 (95% CI: 288.45-1787.93), and 0.99 (95% CI: 0.98-100), respectively. The pooled SE, SP, PLR, NLR, DOR and AUC for DL in discriminating bacterial from viral pneumonia using CXR radiographs were 0.89 (95% CI: 0.79-0.94), 0.89 (95% CI: 0.78-0.95), 8.34 (95% CI: 3.75-18.55), 0.13 (95% CI: 0.06-0.26), 66.14 (95% CI: 17.34-252.37), and 0.95 (0.93-0.97).
CONCLUSION
DL indicated high accuracy performance in classifying pneumonia from normal CXR radiographs and also in distinguishing bacterial from viral pneumonia. However, major methodological concerns should be addressed in future studies for translating to the clinic.
Identifiants
pubmed: 32768045
pii: S0010-4825(20)30247-X
doi: 10.1016/j.compbiomed.2020.103898
pii:
doi:
Types de publication
Journal Article
Meta-Analysis
Review
Systematic Review
Langues
eng
Sous-ensembles de citation
IM
Pagination
103898Informations de copyright
Copyright © 2020 Elsevier Ltd. All rights reserved.