Inter-Variability Study of COVLIAS 1.0: Hybrid Deep Learning Models for COVID-19 Lung Segmentation in Computed Tomography

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.

Lung Disease Classification in CXR Images Using Hybrid Inception-ResNet-v2 Model and Edge Computing

“…It has applications in disease diagnosis, classification, and prognosis. Computed tomography (CT) scan and CXR imaging are two very commonly used diagnostic techniques used for the detection of lung diseases [ 1 – 4 ]. The detection of lung diseases has gained a lot of popularity due to the prevailing COVID-19 spread.…”

COVLIAS 1.0 vs. MedSeg: Artificial Intelligence-Based Comparative Study for Automated COVID-19 Computed Tomography Lung Segmentation in Italian and Croatian Cohorts

“…However, most of the studies lack in individual lung area estimation, transparency overlay generation, and usage of HDL. Table 3 depicts the benchmarking table, which includes studies from Paluru et al (2020) [ 76 ], Saood et al (2021) [ 77 ], Cai et al (2020) [ 78 ], Suri et al (2021) [ 1 ], and Suri et al (2021) [ 3 ], where [ 76 , 77 , 78 ] have used solo DL models to segment the lungs, compared to [ 1 , 3 ], where both solo DL and HDL model were used. This proposed study by Suri et al consisted of two kinds of MD which are benchmarked against a web-based lung segmentation tool, MedSeg.…”

“…COVID-19 lung segmentation in computed tomography (CT) scans is critical for determining lung severity [ 1 , 2 , 3 ]. According to the World Health Organization (WHO), as of 4 November 2021, more than 247 million individuals have been infected with the acute respiratory syndrome coronavirus 2 (SAR-COV-2).…”

“…These methods are time-consuming and subjective for the examination of pulmonary opacities [ 18 , 19 , 20 , 21 ]. As part of the pipeline for COVID-19 diagnosis, CT lung segmentation is crucial [ 1 , 2 , 3 ]. Here is where artificial intelligence (AI) comes into play in automating this time-consuming process and providing a faster diagnosis of the disease [ 22 , 23 , 24 , 25 ].…”

“…This robust AI system (from here on will be called COVLIAS) is designed to keep in mind its clinical acceptability for the segmentation of COVID-19 affected CT lungs. The proposed study presents a comparison of COVLIAS [ 1 , 2 , 3 ] and the previously offered AI integrated web-based CT image segmentation tool MedSeg [ 26 ]. The working of COVLIAS and MedSeg is discussed briefly in the methodology section.…”