Segmentation of lung lobes and lesions in chest CT for the classification of COVID-19 severity

Abstract

To precisely determine the severity of COVID-19-related pneumonia, computed tomography (CT) is an imaging modality beneficial for patient monitoring and therapy planning. Thus, we aimed to develop a deep learning-based image segmentation model to automatically assess lung lesions related to COVID-19 infection and calculate the total severity score (TSS). The entire dataset consisted of 124 COVID-19 patients acquired from Chulabhorn Hospital, divided into 28 cases without lung lesions and 96 cases with lung lesions categorized severity by radiologists regarding TSS. The model used a 3D-UNet along with DenseNet and ResNet models that had already been trained to separate the lobes of the lungs and figure out the percentage of lung involvement due to COVID-19 infection. It also used the Dice similarity coefficient (DSC) to measure TSS. Our final model, consisting of 3D-UNet integrated with DenseNet169, achieved segmentation of lung lobes and lesions with the Dice similarity coefficients of 91.52% and 76.89%, respectively. The calculated TSS values were similar to those evaluated by radiologists, with an R2 of 0.842. The correlation between the ground-truth TSS and model prediction was greater than that of the radiologist, which was 0.890 and 0.709, respectively.

Figure 1

Overall pipeline of the data preprocessing.

Figure 2

Segmentation Model Workflow and Total Severity Score Calculation Protocol for Lung CT Scans.

Figure 3

Examples lung lobe segmentation results for each severity level obtained by the 3D-UNet + the DenseNet169 model trained on the original images and images processed by CLAHE. Each lobe of the lung, right upper lobe (RUL), right lower lobe (RLL), right middle lobe (RML), left upper lobe (LUL), and left lower lobe (LLL), is indicated by the colors red, blue, green, yellow, and pink, respectively.

Figure 4

Example of segmentation results obtained by models trained on the original images and images processed by the contrast-limited adaptive histogram equalization (CLAHE) at each level of severity. The red pixels indicate the lesion areas.

Figure 5

Distribution of TSS values obtained by our model prediction and a radiologist for test set 2 (n = 72). (A) Bland–Altman plot illustrating the comparison of TSS values between the radiologist and prediction. (B) Regression plot depicting the correlation between TSS calculated from the radiologist and prediction.

Figure 6

Distribution of TSS values for method comparison with ground truth using Test Set 1. (A) Bland–Altman plot illustrating the comparison of TSS values between the ground truth and prediction. (B) Regression plot depicting the correlation between TSS calculated from the ground truth and TSS predicted. (C) Bland–Altman plot demonstrating the comparison of TSS values between the ground truth and radiologist. (D) Regression plot analysis showcasing the correlation between TSS values calculated from the ground truth and those provided by the radiologist.