DC-GAN-based synthetic X-ray images augmentation for increasing the performance of EfficientNet for COVID-19 detection

Pir Masoom Shah and Hamid Ullah and Rahim Ullah and Dilawar Shah and Yulin Wang and Saif ul Islam and Abdullah Gani and Rodrigues, Joel J. P. C. (2021) DC-GAN-based synthetic X-ray images augmentation for increasing the performance of EfficientNet for COVID-19 detection. Expert Systems, 39. pp. 1-13.

[img] Text
DC-GAN-based synthetic X-ray images augmentation for increasing the performance of EfficientNet for COVID-19 detection.pdf
Restricted to Registered users only

Download (299kB) | Request a copy
[img] Text
DC-GAN-based synthetic X-ray images augmentation for increasing the performance of EfficientNet for COVID-19 detection _ABSTRACT.pdf

Download (85kB)

Abstract

Currently, many deep learning models are being used to classify COVID‐19 and normal cases from chest X‐rays. However, the available data (X‐rays) for COVID‐19 is limited to train a robust deep‐learning model. Researchers have used data augmentation techniques to tackle this issue by increasing the numbers of samples through flipping, translation, and rotation. However, by adopting this strategy, the model compromises for the learning of high‐dimensional features for a given problem. Hence, there are high chances of overfitting. In this paper, we used deep‐convolutional generative adversarial networks algorithm to address this issue, which generates synthetic images for all the classes (Normal, Pneumonia, and COVID‐19). To validate whether the generated images are accurate, we used the k‐mean clustering technique with three clusters (Normal, Pneumonia, and COVID‐19). We only selected the X‐ray images classified in the correct clusters for training. In this way, we formed a synthetic dataset with three classes. The generated dataset was then fed to The EfficientNetB4 for training. The experiments achieved promising results of 95% in terms of area under the curve (AUC). To validate that our network has learned discriminated features associated with lung in the X‐rays, we used the Grad‐CAM technique to visualize the underlying pattern, which leads the network to its final decision.

Item Type: Article
Keyword: Convolutional neural networks , Covid-19 , Deep-convolutional generative adversarial networks , Synthetic images , X-rays
Subjects: R Medicine > RC Internal medicine > RC31-1245 Internal medicine > RC581-951 Specialties of internal medicine
Department: FACULTY > Faculty of Computing and Informatics
Depositing User: SAFRUDIN BIN DARUN -
Date Deposited: 16 Jun 2022 15:33
Last Modified: 16 Jun 2022 15:33
URI: https://eprints.ums.edu.my/id/eprint/32820

Actions (login required)

View Item View Item