COVID-19 detection and disease progression visualization: Deep learning on chest X-rays for classification and coarse localization
Article
Zebin, T. and Rezvy, S. 2021. COVID-19 detection and disease progression visualization: Deep learning on chest X-rays for classification and coarse localization. Applied Intelligence. 51 (2), pp. 1010-1021. https://doi.org/10.1007/s10489-020-01867-1
Type | Article |
---|---|
Title | COVID-19 detection and disease progression visualization: Deep learning on chest X-rays for classification and coarse localization |
Authors | Zebin, T. and Rezvy, S. |
Abstract | Chest X-rays are playing an important role in the testing and diagnosis of COVID-19 disease in the recent pandemic. However, due to the limited amount of labelled medical images, automated classification of these images for positive and negative cases remains the biggest challenge in their reliable use in diagnosis and disease progression. We implemented a transfer learning pipeline for classifying COVID-19 chest X-ray images from two publicly available chest X-ray datasets1,2. The classifier effectively distinguishes inflammation in lungs due to COVID-19 and Pneumonia from the ones with no infection (normal). We have used multiple pre-trained convolutional backbones as the feature extractor and achieved an overall detection accuracy of 90%, 94.3%, and 96.8% for the VGG16, ResNet50, and EfficientNetB0 backbones respectively. Additionally, we trained a generative adversarial framework (a CycleGAN) to generate and augment the minority COVID-19 class in our approach. For visual explanations and interpretation purposes, we implemented a gradient class activation mapping technique to highlight the regions of the input image that are important for predictions. Additionally, these visualizations can be used to monitor the affected lung regions during disease progression and severity stages. |
Keywords | Article, Artificial Intelligence Applications for COVID-19, Detection, Control, Prediction, and Diagnosis, Activation maps, COVID-19, Deep neural networks, Transfer learning |
Publisher | Springer US |
Journal | Applied Intelligence |
ISSN | 0924-669X |
Electronic | 1573-7497 |
Publication dates | |
Online | 12 Sep 2020 |
01 Feb 2021 | |
Publication process dates | |
Deposited | 13 Jan 2021 |
Output status | Published |
Publisher's version | License |
Copyright Statement | © The Author(s) |
Digital Object Identifier (DOI) | https://doi.org/10.1007/s10489-020-01867-1 |
Language | English |
https://repository.mdx.ac.uk/item/893w5
Download files
28
total views10
total downloads0
views this month0
downloads this month