A sustainable deep learning based framework for automated segmentation of COVID-19 infected regions: Using U-Net with an attention mechanism and boundary loss function

Ahmed, Imran, Chehri, Abdellah and Jeon, Gwanggil (2022) A sustainable deep learning based framework for automated segmentation of COVID-19 infected regions: Using U-Net with an attention mechanism and boundary loss function. Electronics, 11 (15). p. 2296. ISSN 2079-9292

[img]
Preview
Text
Published Version
Available under the following license: Creative Commons Attribution Non-commercial No Derivatives.

Download (1MB) | Preview
[img] Text
Accepted Version
Restricted to Repository staff only
Available under the following license: Creative Commons Attribution Non-commercial No Derivatives.

Download (1MB) | Request a copy
Official URL: https://www.mdpi.com/2079-9292/11/15/2296

Abstract

COVID-19 has been spreading rapidly, affecting billions of people globally, with significant public health impacts. Biomedical imaging, such as computed tomography (CT), has significant potential as a possible substitute for the screening process. Because of this, automatic segmentation of images is highly desirable as clinical decision support for an extensive evaluation of disease control and monitoring. It is a dynamic tool and performs a central role in precise or accurate segmentation of infected areas or regions in CT scans, thus helping in screening, diagnosing, and disease monitoring. For this purpose, we introduced a deep learning framework for automated segmentation of COVID-19 infected lesions/regions in lung CT scan images. Specifically, we adopted a segmentation model, i.e., U-Net, and utilized an attention mechanism to enhance the framework’s ability for the segmentation of virus-infected regions. Since all of the features extracted or obtained from the encoders are not valuable for segmentation; thus, we applied the U-Net architecture with a mechanism of attention for a better representation of the features. Moreover, we applied a boundary loss function to deal with small and unbalanced lesion segmentation’s. Using different public CT scan image data sets, we validated the framework’s effectiveness in contrast with other segmentation techniques. The experimental outcomes showed the improved performance of the presented framework for the automated segmentation of lungs and infected areas in CT scan images. We also considered both boundary loss and weighted binary cross-entropy dice loss function. The overall dice accuracies of the framework are 0.93 and 0.76 for lungs and COVID-19 infected areas/regions.

Item Type: Journal Article
Keywords: Sustainability,, Artificial Intelligence,, Biomedical Images,, Deep Learning,, COVID-19.
Faculty: COVID-19 Research Collection
Faculty of Science & Engineering
SWORD Depositor: Symplectic User
Depositing User: Symplectic User
Date Deposited: 21 Jul 2022 20:26
Last Modified: 04 Aug 2022 16:02
URI: https://arro.anglia.ac.uk/id/eprint/707769

Actions (login required)

Edit Item Edit Item