The Role of 3D CT Imaging in the Accurate Diagnosis of Lung Function in Coronavirus Patients

Abstract

Early grading of coronavirus disease 2019 (COVID-19), as well as ventilator support machines, are prime ways to help the world fight this virus and reduce the mortality rate. To reduce the burden on physicians, we developed an automatic Computer-Aided Diagnostic (CAD) system to grade COVID-19 from Computed Tomography (CT) images. This system segments the lung region from chest CT scans using an unsupervised approach based on an appearance model, followed by 3D rotation invariant Markov-Gibbs Random Field (MGRF)-based morphological constraints. This system analyzes the segmented lung and generates precise, analytical imaging markers by estimating the MGRF-based analytical potentials. Three Gibbs energy markers were extracted from each CT scan by tuning the MGRF parameters on each lesion separately. The latter were healthy/mild, moderate, and severe lesions. To represent these markers more reliably, a Cumulative Distribution Function (CDF) was generated, then statistical markers were extracted from it, namely, 10th through 90th CDF percentiles with 10% increments. Subsequently, the three extracted markers were combined together and fed into a backpropagation neural network to make the diagnosis. The developed system was assessed on 76 COVID-19-infected patients using two metrics, namely, accuracy and Kappa. In this paper, the proposed system was trained and tested by three approaches. In the first approach, the MGRF model was trained and tested on the lungs. This approach achieved 95.83% accuracy and 93.39% kappa. In the second approach, we trained the MGRF model on the lesions and tested it on the lungs. This approach achieved 91.67% accuracy and 86.67% kappa. Finally, we trained and tested the MGRF model on lesions. It achieved 100% accuracy and 100% kappa. The results reported in this paper show the ability of the developed system to accurately grade COVID-19 lesions compared to other machine learning classifiers, such as k-Nearest Neighbor (KNN), decision tree, naïve Bayes, and random forest.

Keywords: COVID-19; Computer Assisted Diagnosis (CAD); Markov–Gibbs Random Field (MGRF); SARS-CoV-2; machine learning; neural network.

Figure 1

Illustrative examples of the three grades of COVID-19.

Figure 2

An illustrative framework for the proposed CAD system to detect the severity of COVID-19 through the CT images.

Figure 3

An illustrative example of the proposed segmentation approach for (a) healthy/mild, (b) moderate, and (c) severe COVID-19 infections. Note that the blue (green) border represents our segmentation (ground truth).

Figure 4

Fourth-order LBP structure, $g_0$ is the central pixel, $g_1$, $g_2$, $g_3$, and $g_4$ are the four neighbours, and r is the radius.

Figure 5

An illustrative example of the estimation of CDF percentile feature from CDF.

Figure 6

An illustrative color map example of Gibbs energies for (a) healthy/mild, (b) moderate, and (c) severe; tuned using healthy/mild, moderate, or severe COVID-19 lesions; applied to the lung ($2\mathrm{nd}–4$th rows), hybrid ($5\mathrm{th}–7$th rows), and lesion ($8\mathrm{th}–10$th rows) approaches.

Figure 7

Estimated error average of CDF percentiles for three grades when tuning MGRF parameters using (a) healthy/mild, (b) moderate, or (c) severe lesion infection, applied to lung (upper row), hybrid (middle row), and lesion (lower row) approaches.