The diagnostic performance of deep-learning-based CT severity score to identify COVID-19 pneumonia

Quantitative Computed Tomography Lung COVID Scores with Laboratory Markers: Utilization to Predict Rapid Progression and Monitor Longitudinal Changes in Patients with Coronavirus 2019 (COVID-19) Pneumonia

Coronavirus disease 2019 (COVID-19), is an ongoing issue in certain populations, presenting rapidly worsening pneumonia and persistent symptoms. This study aimed to test the predictability of rapid progression using radiographic scores and laboratory markers and present longitudinal changes. This retrospective study included 218 COVID-19 pneumonia patients admitted at the Chungnam National University Hospital. Rapid progression was defined as respiratory failure requiring mechanical ventilation within one week of hospitalization. Quantitative COVID (QCOVID) scores were derived from high-resolution computed tomography (CT) analyses: (1) ground glass opacity (QGGO), (2) mixed diseases (QMD), and (3) consolidation (QCON), and the sum, quantitative total lung diseases (QTLD). Laboratory data, including inflammatory markers, were obtained from electronic medical records. Rapid progression was observed in 9.6% of patients. All QCOVID scores predicted rapid progression, with QMD showing the best predictability (AUC = 0.813). In multivariate analyses, the QMD score and interleukin(IL)-6 level were important predictors for rapid progression (AUC = 0.864). With >2 months follow-up CT, remained lung lesions were observed in 21 subjects, even after several weeks of negative reverse transcription polymerase chain reaction test. AI-driven quantitative CT scores in conjugation with laboratory markers can be useful in predicting the rapid progression and monitoring of COVID-19.

Unveiling COVID-19 Secrets: Harnessing Cytokines as Powerful Biomarkers for Diagnosis and Predicting Severity

Introduction

In coronavirus disease (COVID-19), inflammation takes center stage, with a cascade of cytokines released, contributing to both inflammation and lung damage. The objective of this study is to identify biomarkers for diagnosing and predicting the severity of COVID-19.

Materials and Methods

Cytokine levels were determined in the serum from venous blood samples collected from 100 patients with COVID-19 and 50 healthy controls. COVID-19 patients classified based on the Modified Early Warning (MEWS) score. Cytokine concentrations were determined with a multiplex ELISA kit (Bio-Plex Pro™ Human Cytokine Screening Panel).

Results

The concentrations of all analyzed cytokines were elevated in the serum of COVID-19 patients relative to the control group, but no significant differences were observed in interleukin-9 (IL-9) and IL-12 p70 levels. In addition, the concentrations of IL-1α, IL-1β, IL-1ra, IL-2Rα, IL-6, IL-12 p40, IL-18, and tumor necrosis factor alpha (TNFα) were significantly higher in symptomatic patients with accompanying pneumonia without respiratory failure (stage 2) than in asymptomatic/mildly symptomatic patients (stage 1).

Conclusion

The study revealed that IL-1ra, IL-2Rα, IL-6, IL-8, IL-12 p40, IL-16, and IL-18 levels serve as potential diagnostic biomarkers in COVID-19 patients. Furthermore, elevated IL-1α levels proved to be valuable in assessing the severity of COVID-19.

The Diagnostic Utility of Artificial Intelligence-Guided Computed Tomography-Based Severity Scores for Predicting Short-Term Clinical Outcomes in Adults with COVID-19 Pneumonia

Chest computed tomography (CT) imaging with the use of an artificial intelligence (AI) analysis program has been helpful for the rapid evaluation of large numbers of patients during the COVID-19 pandemic. We have previously demonstrated that adults with COVID-19 infection with high-risk obstructive sleep apnea (OSA) have poorer clinical outcomes than COVID-19 patients with low-risk OSA. In the current secondary analysis, we evaluated the association of AI-guided CT-based severity scores (SSs) with short-term outcomes in the same cohort. In total, 221 patients (mean age of 52.6 ± 15.6 years, 59% men) with eligible chest CT images from March to May 2020 were included. The AI program scanned the CT images in 3D, and the algorithm measured volumes of lobes and lungs as well as high-opacity areas, including ground glass and consolidation. An SS was defined as the ratio of the volume of high-opacity areas to that of the total lung volume. The primary outcome was the need for supplemental oxygen and hospitalization over 28 days. A receiver operating characteristic (ROC) curve analysis of the association between an SS and the need for supplemental oxygen revealed a cut-off score of 2.65 on the CT images, with a sensitivity of 81% and a specificity of 56%. In a multivariate logistic regression model, an SS > 2.65 predicted the need for supplemental oxygen, with an odds ratio (OR) of 3.98 (95% confidence interval (CI) 1.80-8.79; p < 0.001), and hospitalization, with an OR of 2.40 (95% CI 1.23-4.71; p = 0.011), adjusted for age, sex, body mass index, diabetes, hypertension, and coronary artery disease. We conclude that AI-guided CT-based SSs can be used for predicting the need for supplemental oxygen and hospitalization in patients with COVID-19 pneumonia.

Are the thorax Computed Tomography findings of ICU patients diagnosed with COVID-19 pneumonia related to the duration of hospital stay and mortality?

INTRODUCTION

Quantitative thorax Computed Tomography (CT) is used to determine the severity of COVID-19 pneumonia. With a new approach, quantitative thoracic CT is to contribute to the triage of patients with severe COVID-19 pneumonia in the ICU and to evaluate its relation with mortality by taking into account the vaccination status.

METHODS

Fifty-six patients who had a diagnosis of COVID-19 pneumonia confirmed in the adult ICU were evaluated retrospectively. To evaluate the degree of parenchymal involvement, the quantitative CT "craniocaudal diameter of the thorax/craniocaudal largest lesion diameter (CCDT/CCDL)" ratio and semi-quantitative total CT severity scores (TCTSS) (0:0%; 1:1-25%; 2:26-50%; 3:51-75% and 4:76-100%) were calculated. Both methods were analyzed with comparative ROC curves for predicting mortality. The effects of vaccines on thorax CT findings and laboratory parameters were also investigated.

RESULTS

The sensitivities and specificities were found to be 72.5%, 75.61%, and 80%, 73.33% when CCDT/CCDL and TCTSS cutoff value was taken <1.4, and >9, respectively, to predict mortality in COVID-19 pneumonia (Area Under the Curve = AUC = 0.797 and 0.752). Both methods predicted mortality well and no statistical differences were detected between them (p = 0.3618). In vaccinated patients, CRP was higher (p = 0.045), and LDH and ferritin were lower (p = 0.049, p = 0.004). The number of lobes involved was lower in the vaccinated group (p = 0.001).

CONCLUSIONS

The quantitative CT score (CCDT/CCDL) may play as important a role as TCTSS in diagnosing COVID-19 pneumonia, determining the severity of the disease, and predicting the related mortality. COVID-19 vaccines may affect laboratory parameters and cause less pneumonia on thoracic CT than in unvaccinated individuals.

Automatized lung disease quantification in patients with COVID-19 as a predictive tool to assess hospitalization severity

The pandemic of COVID-19 led to a dramatic situation in hospitals, where staff had to deal with a huge number of patients in respiratory distress. To alleviate the workload of radiologists, we implemented an artificial intelligence (AI) - based analysis named CACOVID-CT, to automatically assess disease severity on chest CT scans obtained from those patients. We retrospectively studied CT scans obtained from 476 patients admitted at the University Hospital of Liege with a COVID-19 disease. We quantified the percentage of COVID-19 affected lung area (% AA) and the CT severity score (total CT-SS). These quantitative measurements were used to investigate the overall prognosis and patient outcome: hospital length of stay (LOS), ICU admission, ICU LOS, mechanical ventilation, and in-hospital death. Both CT-SS and % AA were highly correlated with the hospital LOS, the risk of ICU admission, the risk of mechanical ventilation and the risk of in-hospital death. Thus, CAD4COVID-CT analysis proved to be a useful tool in detecting patients with higher hospitalization severity risk. It will help for management of the patients flow. The software measured the extent of lung damage with great efficiency, thus relieving the workload of radiologists.

Disease Localization and Severity Assessment in Chest X-Ray Images using Multi-Stage Superpixels Classification

BACKGROUND AND OBJECTIVES

Chest X-ray (CXR) is a non-invasive imaging modality used in the prognosis and management of chronic lung disorders like tuberculosis (TB), pneumonia, coronavirus disease (COVID-19), etc. The radiomic features associated with different disease manifestations assist in detection, localization, and grading the severity of infected lung regions. The majority of the existing computer-aided diagnosis (CAD) system used these features for the classification task, and only a few works have been dedicated to disease-localization and severity scoring. Moreover, the existing deep learning approaches use class activation map and Saliency map, which generate a rough localization. This study aims to generate a compact disease boundary, infection map, and grade the infection severity using proposed multistage superpixel classification-based disease localization and severity assessment framework.

METHODS

The proposed method uses a simple linear iterative clustering (SLIC) technique to subdivide the lung field into small superpixels. Initially, the different radiomic texture and proposed shape features are extracted and combined to train different benchmark classifiers in a multistage framework. Subsequently, the predicted class labels are used to generate an infection map, mark disease boundary, and grade the infection severity. The performance is evaluated using a publicly available Montgomery dataset and validated using Friedman average ranking and Holm and Nemenyi post-hoc procedures.

RESULTS

The proposed multistage classification approach achieved accuracy (ACC)= 95.52%, F-Measure (FM)= 95.48%, area under the curve (AUC)= 0.955 for Stage-I and ACC=85.35%, FM=85.20%, AUC=0.853 for Stage-II using calibration dataset and ACC = 93.41%, FM = 95.32%, AUC = 0.936 for Stage-I and ACC = 84.02%, FM = 71.01%, AUC = 0.795 for Stage-II using validation dataset. Also, the model has demonstrated the average Jaccard Index (JI) of 0.82 and Pearson's correlation coefficient (r) of 0.9589.

CONCLUSIONS

The obtained classification results using calibration and validation dataset confirms the promising performance of the proposed framework. Also, the average JI shows promising potential to localize the disease, and better agreement between radiologist score and predicted severity score (r) confirms the robustness of the method. Finally, the statistical test justified the significance of the obtained results.

Automated System for Identifying COVID-19 Infections in Computed Tomography Images Using Deep Learning Models

Coronavirus disease 2019 (COVID-19) is a novel disease that affects healthcare on a global scale and cannot be ignored because of its high fatality rate. Computed tomography (CT) images are presently being employed to assist doctors in detecting COVID-19 in its early stages. In several scenarios, a combination of epidemiological criteria (contact during the incubation period), the existence of clinical symptoms, laboratory tests (nucleic acid amplification tests), and clinical imaging-based tests are used to diagnose COVID-19. This method can miss patients and cause more complications. Deep learning is one of the techniques that has been proven to be prominent and reliable in several diagnostic domains involving medical imaging. This study utilizes a convolutional neural network (CNN), stacked autoencoder, and deep neural network to develop a COVID-19 diagnostic system. In this system, classification undergoes some modification before applying the three CT image techniques to determine normal and COVID-19 cases. A large-scale and challenging CT image dataset was used in the training process of the employed deep learning model and reporting their final performance. Experimental outcomes show that the highest accuracy rate was achieved using the CNN model with an accuracy of 88.30%, a sensitivity of 87.65%, and a specificity of 87.97%. Furthermore, the proposed system has outperformed the current existing state-of-the-art models in detecting the COVID-19 virus using CT images.