Automated deep learning-based segmentation of COVID-19 lesions from chest computed tomography images

Abstract

Purpose: The novel coronavirus COVID-19, which spread globally in late December 2019, is a global health crisis. Chest computed tomography (CT) has played a pivotal role in providing useful information for clinicians to detect COVID-19. However, segmenting COVID-19-infected regions from chest CT results is challenging. Therefore, it is desirable to develop an efficient tool for automated segmentation of COVID-19 lesions using chest CT. Hence, we aimed to propose 2D deep-learning algorithms to automatically segment COVID-19-infected regions from chest CT slices and evaluate their performance.

Material and methods: Herein, 3 known deep learning networks: U-Net, U-Net++, and Res-Unet, were trained from scratch for automated segmenting of COVID-19 lesions using chest CT images. The dataset consists of 20 labelled COVID-19 chest CT volumes. A total of 2112 images were used. The dataset was split into 80% for training and validation and 20% for testing the proposed models. Segmentation performance was assessed using Dice similarity coefficient, average symmetric surface distance (ASSD), mean absolute error (MAE), sensitivity, specificity, and precision.

Results: All proposed models achieved good performance for COVID-19 lesion segmentation. Compared with Res-Unet, the U-Net and U-Net++ models provided better results, with a mean Dice value of 85.0%. Compared with all models, U-Net gained the highest segmentation performance, with 86.0% sensitivity and 2.22 mm ASSD. The U-Net model obtained 1%, 2%, and 0.66 mm improvement over the Res-Unet model in the Dice, sensitivity, and ASSD, respectively. Compared with Res-Unet, U-Net++ achieved 1%, 2%, 0.1 mm, and 0.23 mm improvement in the Dice, sensitivity, ASSD, and MAE, respectively.

Conclusions: Our data indicated that the proposed models achieve an average Dice value greater than 84.0%. Two-dimensional deep learning models were able to accurately segment COVID-19 lesions from chest CT images, assisting the radiologists in faster screening and quantification of the lesion regions for further treatment. Nevertheless, further studies will be required to evaluate the clinical performance and robustness of the proposed models for COVID-19 semantic segmentation.

Keywords: COVID-19; computed tomography; deep learning; image segmentation; infection segmentation.

Figure 1

Examples of computed tomography images along with corresponding mask from the COVID-19-CT-Seg-Datase

Figure 2

An illustration of the workflow used for COVID-19 lesion segmentation

Figure 3

Sample computed tomography image before (A) and after (B) applying contrast limited adaptive histogram equalization (CLAHE) technique

Figure 4

Cropped computed tomography image (A) along with corresponding binary mask (B)

Figure 5

Boxplots of quantitative metrics for U-Net and U-Net++, and Res-Unet models for COVID-19 lesion segmentation, including (A) Dice similarity coefficient (%), (B) ASSD (mm), and (C) MAE (mm). In each panel, the bold line represents the median, the boxes represent the 25^th and 75^th percentiles, and whiskers represent ranges not including outliers. The individual point is considered as an outlier

Figure 6

Representative manual and automated segmentation of COVID-19 lesions for 4 different cases from the COVID-19-CT-Seg-Dataset using U-Net, U-Net++, and Res-Unet