Ensemble deep learning for the detection of COVID-19 in unbalanced chest X-ray dataset
| dc.contributor.author | Win, Khin Yadanar | |
| dc.contributor.author | Maneerat, Noppadol | |
| dc.contributor.author | Sreng, Syna | |
| dc.contributor.author | Hamamoto, Kazuhiko | |
| dc.date.accessioned | 2026-08-06T10:33:53Z | |
| dc.date.available | 2026-08-06T10:33:53Z | |
| dc.date.issued | 2021-11-01 | |
| dc.description.abstract | The ongoing COVID-19 pandemic has caused devastating effects on humanity worldwide. With practical advantages and wide accessibility, chest X-rays (CXRs) play vital roles in the diagnosis of COVID-19 and the evaluation of the extent of lung damages incurred by the virus. This study aimed to leverage deep-learning-based methods toward the automated classification of COVID-19 from normal and viral pneumonia on CXRs, and the identification of indicative regions of COVID-19 biomarkers. Initially, we preprocessed and segmented the lung regions usingDeepLabV3+ method, and subsequently cropped the lung regions. The cropped lung regions were used as inputs to several deep convolutional neural networks (CNNs) for the prediction of COVID-19. The dataset was highly unbalanced; the vast majority were normal images, with a small number of COVID-19 and pneumonia images. To remedy the unbalanced distribution and to avoid biased classification results, we applied five different approaches: (i) balancing the class using weighted loss; (ii) image augmentation to add more images to minority cases; (iii) the undersampling of majority classes; (iv) the oversampling of minority classes; and (v) a hybrid resampling approach of oversampling and undersampling. The best-performing methods from each approach were combined as the ensemble classifier using two voting strategies. Finally, we used the saliency map of CNNs to identify the indicative regions of COVID-19 biomarkers which are deemed useful for interpretability. The algorithms were evaluated using the largest publicly available COVID-19 dataset. An ensemble of the top five CNNs with image augmentation achieved the highest accuracy of 99.23% and area under curve (AUC) of 99.97%, surpassing the results of previous studies. | |
| dc.identifier.citation | Applied Sciences Switzerland, 11(22), 2021 | |
| dc.identifier.doi | 10.3390/app112210528 | |
| dc.identifier.issn | 20763417 | |
| dc.identifier.other | 2-s2.0-85119300906 | |
| dc.identifier.uri | https://dspace.kmitl.ac.th/handle/123456789/12372 | |
| dc.source | Applied Sciences Switzerland | |
| dc.subject | Chest X-rays | |
| dc.subject | COVID-19 | |
| dc.subject | Deep learning | |
| dc.subject | Ensemble learning | |
| dc.subject | Image augmentation | |
| dc.subject | Oversampling | |
| dc.subject | Undersampling | |
| dc.subject | Weighted loss | |
| dc.title | Ensemble deep learning for the detection of COVID-19 in unbalanced chest X-ray dataset | |
| dc.type | Article |