Deep convolution neural networks to differentiate between COVID-19 and other pulmonary abnormalities on chest radiographs Evaluation using internal and external datasets

Deep convolution neural networks to differentiate between COVID-19 and other pulmonary abnormalities on chest radiographs : Evaluation using internal and external datasets

© 2021 Wiley Periodicals LLC.

Bibliographische Detailangaben
Veröffentlicht in:International journal of imaging systems and technology. - 1990. - 31(2021), 3 vom: 28. Sept., Seite 1087-1104
1. Verfasser: Cho, Yongwon (VerfasserIn)
Weitere Verfasser: Hwang, Sung Ho, Oh, Yu-Whan, Ham, Byung-Joo, Kim, Min Ju, Park, Beom Jin
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2021
Zugriff auf das übergeordnete Werk:International journal of imaging systems and technology
Schlagworte:Journal Article COVID‐19 chest radiography computer‐aided diagnosis (CAD) deep learning lung diseases
Beschreibung
Zusammenfassung:© 2021 Wiley Periodicals LLC.
We aimed to evaluate the performance of convolutional neural networks (CNNs) in the classification of coronavirus disease 2019 (COVID-19) disease using normal, pneumonia, and COVID-19 chest radiographs (CXRs). First, we collected 9194 CXRs from open datasets and 58 from the Korea University Anam Hospital (KUAH). The number of normal, pneumonia, and COVID-19 CXRs were 4580, 3884, and 730, respectively. The CXRs obtained from the open dataset were randomly assigned to the training, tuning, and test sets in a 70:10:20 ratio. For external validation, the KUAH (20 normal, 20 pneumonia, and 18 COVID-19) dataset, verified by radiologists using computed tomography, was used. Subsequently, transfer learning was conducted using DenseNet169, InceptionResNetV2, and Xception to identify COVID-19 using open datasets (internal) and the KUAH dataset (external) with histogram matching. Gradient-weighted class activation mapping was used for the visualization of abnormal patterns in CXRs. The average AUC and accuracy of the multiscale and mixed-COVID-19Net using three CNNs over five folds were (0.99 ± 0.01 and 92.94% ± 0.45%), (0.99 ± 0.01 and 93.12% ± 0.23%), and (0.99 ± 0.01 and 93.57% ± 0.29%), respectively, using the open datasets (internal). Furthermore, these values were (0.75 and 74.14%), (0.72 and 68.97%), and (0.77 and 68.97%), respectively, for the best model among the fivefold cross-validation with the KUAH dataset (external) using domain adaptation. The various state-of-the-art models trained on open datasets show satisfactory performance for clinical interpretation. Furthermore, the domain adaptation for external datasets was found to be important for detecting COVID-19 as well as other diseases
Beschreibung:Date Revised 29.08.2024
published: Print-Electronic
Citation Status PubMed-not-MEDLINE
ISSN:0899-9457
DOI:10.1002/ima.22595