Automated quantification of COVID-19 pneumonia severity in chest CT using histogram-based multi-level thresholding segmentation

Abstract

Background Chest computed tomography (CT) has proven its critical importance in detection, grading, and follow-up of lung affection in COVID-19 pneumonia. There is a close relationship between clinical severity and the extent of lung CT findings in this potentially fatal disease. The extent of lung lesions in CT is an important indicator of risk stratification in COVID-19 pneumonia patients. This study aims to explore automated histogram-based quantification of lung affection in COVID-19 pneumonia in volumetric computed tomography (CT) images in comparison to conventional semi-quantitative severity scoring. This retrospective study enrolled 153 patients with proven COVID-19 pneumonia. Based on the severity of clinical presentation, the patients were divided into three groups: mild, moderate and severe. Based upon the need for oxygenation support, two groups were identified as follows: common group that incorporated mild and moderate severity patients who did not need intubation, and severe illness group that included patients who were intubated. An automated multi-level thresholding histogram-based quantitative analysis technique was used for evaluation of lung affection in CT scans together with the conventional semi-quantitative severity scoring performed by two expert radiologists. The quantitative assessment included volumes, percentages and densities of ground-glass opacities (GGOs) and consolidation in both lungs. The results of the two evaluation methods were compared, and the quantification metrics were correlated. Results The Spearman’s correlation coefficient between the semi-quantitative severity scoring and automated quantification methods was 0.934 (p < 0.0001). Conclusions The automated histogram-based quantification of COVID-19 pneumonia shows good correlation with conventional severity scoring. The quantitative imaging metrics show high correlation with the clinical severity of the disease.

Image quality assessment in low-dose COVID-19 chest CT examinations

“…Although the Catphan analysis of CNR showed a significant difference between low-dose protocols and standard acquisitions on both CT scans A and B in the inserts that are closest in HU units to emphysema (Air) or semi-consolidation or consolidation (PMP, LDPE, Polystyrene) as defined by Yousef at al., the clinical relevance of these significant differences was not demonstrated ( 29 ). In fact, the Catphan analysis of CNR is a quick and straightforward measurement that has its limitations and may not be as comprehensive to assess image quality in clinical conditions, which could be brought by other additional metrics such as noise power spectrum, task-based transfer function, or detectability index ( 30 ).…”

Steroids Therapy in Patients With Severe COVID-19: Association With Decreasing of Pneumonia Fibrotic Tissue Volume

“…However, semi-quantitative visual assessment highly relies on the experience of the observer. It is time-consuming, lacks reproducibility, and has interobserver and even intraobserver variability ( 15 ). For the longitudinal study in this work, semi-quantitative methods may significantly affect the accuracy and feasibility of the results.…”

“…Therefore, CT has been proposed as an ancillary approach for screening individuals with suspected COVID-19 pneumonia during the epidemic period and monitoring treatment response according to the dynamic radiological changes (12)(13)(14). Traditional CT image analysis methods such as manual or semiquantitative assessments rely on the previous experience of radiologists, and these methods are subjective, time-consuming, and lack interobserver consistency (15,16). As a fast, accurate and reproducible analytical tool, quantitative CT image analysis has been increasingly implemented in pulmonary diseases to extract objective data that can aid in lesion characterization and quantification (17,18).…”

Automated assessment of chest CT severity scores in patients suspected of COVID-19 infection

“…The American College of Radiology (ACR) recommends the use of computed tomography for suspected COVID-19 infection (21). However, visual assessment of COVID-19 lesions from chest CT scans is time-consuming, suffers from inter-and intra-reader variability, and lacks reproducibility (22) Neither of these two studies reported the MAE for their algorithms. In a deep learning task with numerical outcomes, MAE provides a notion of how much the results will vary in clinical settings.…”