Abstract
Background: For COVID-19 lung severity, segmentation of lungs on computed tomography (CT) is the first crucial step. Current deep learning (DL)-based Artificial Intelligence (AI) models have a bias in the training stage of segmentation because only one set of ground truth (GT) annotations are evaluated. We propose a robust and stable inter-variability analysis of CT lung segmentation in COVID-19 to avoid the effect of bias. Methodology: The proposed inter-variability study consists of two GT tracers for lung segmentation on chest CT. Three AI models, PSP Net, VGG-SegNet, and ResNet-SegNet, were trained using GT annotations. We hypothesized that if AI models are trained on the GT tracings from multiple experience levels, and if the AI performance on the test data between these AI models is within the 5% range, one can consider such an AI model robust and unbiased. The K5 protocol (training to testing: 80%:20%) was adapted. Ten kinds of metrics were used for performance evaluation. Results: The database consisted of 5000 CT chest images from 72 COVID-19-infected patients. By computing the coefficient of correlations (CC) between the output of the two AI models trained corresponding to the two GT tracers, computing their differences in their CC, and repeating the process for all three AI-models, we show the differences as 0%, 0.51%, and 2.04% (all < 5%), thereby validating the hypothesis. The performance was comparable; however, it had the following order: ResNet-SegNet > PSP Net > VGG-SegNet. Conclusions: The AI models were clinically robust and stable during the inter-variability analysis on the CT lung segmentation on COVID-19 patients.
Highlights
The WHO’s International Health Regulations and Emergency Committee (IHREC)proclaimed COVID-19 a “public health emergency of international significance” or “pandemic” on 30 January 2020
Section 4.2.1 presents the visual comparison of the results, which includes (i) boundary overlays against the ground truth boundary and (ii) lung long axis against the ground truth axis
Modeloverlays boundaries includes boundary against the groundand truthGT-boundary boundary and (ii)(red) lung corresponding to Observer
Summary
The WHO’s International Health Regulations and Emergency Committee (IHREC)proclaimed COVID-19 a “public health emergency of international significance” or “pandemic” on 30 January 2020. More than 231 million people have been infected worldwide, and nearly 4.7 million people have died due to COVID-19 [1] This “severe acute respiratory syndrome coronavirus 2” (SARS-CoV-2) virus targets the pulmonary and vascular system, it has the potential to travel through the body and lead to complications such as pulmonary embolism [2], myocardial infarction, stroke, or mesenteric ischemia [3,4,5]. Comorbidities such as diabetes mellitus, hypertension, and obesity substantially increase the severity and mortality of COVID-19 [6,7]. Chest radiographs and computed tomography (CT) [9,10,11] are used to determine disease severity in patients with moderate to severe disease or underlying comorbidities based on the extent of pulmonary opacities such as ground-glass (GGO), consolidation, and mixed opacities in CT scans [7,12,13,14]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
