Usefulness of Hospital Admission Chest X-ray Score for Predicting Mortality and ICU Admission in COVID-19 Patients.

We aimed to investigate the performance of a chest X-ray (CXR) scoring scale of lung injury in prediction of death and ICU admission among patients with COVID-19 during the 2021 peak pandemic in HCM City, Vietnam. CXR and clinical data were collected from Vinmec Central Park-hospitalized patients from July to September 2021. Three radiologists independently assessed the day-one CXR score consisting of both severity and extent of lung lesions (maximum score = 24). Among 219 included patients, 28 died and 34 were admitted to the ICU. There was a high consensus for CXR scoring among radiologists (κ = 0.90; CI95%: 0.89-0.92). CXR score was the strongest predictor of mortality (tdAUC 0.85 CI95% 0.69-1) within the first 3 weeks after admission. A multivariate model confirmed a significant effect of an increased CXR score on mortality risk (HR = 1.33, CI95%: 1.10 to 1.62). At a threshold of 16 points, the CXR score allowed for predicting in-hospital mortality and ICU admission with good sensitivity (0.82 (CI95%: 0.78 to 0.87) and 0.86 (CI95%: 0.81 to 0.90)) and specificity (0.89 (CI95%: 0.88 to 0.90) and 0.87 (CI95%: 0.86 to 0.89)), respectively, and can be used to identify high-risk patients in needy countries such as Vietnam.

Deep learning for lung disease segmentation on CT: Which reconstruction kernel should be used?

PURPOSE: The purpose of this study was to determine whether a single reconstruction kernel or both high and low frequency kernels should be used for training deep learning models for the segmentation of diffuse lung disease on chest computed tomography (CT). MATERIALS AND METHODS: Two annotated datasets of COVID-19 pneumonia (323,960 slices) and interstitial lung disease (ILD) (4,284 slices) were used. Annotated CT images were used to train a U-Net architecture to segment disease. All CT slices were reconstructed using both a lung kernel (LK) and a mediastinal kernel (MK). Three different trainings, resulting in three different models were compared for each disease: training on LK only, MK only or LK+MK images. Dice similarity scores (DSC) were compared using the Wilcoxon signed-rank test. RESULTS: Models only trained on LK images performed better on LK images than on MK images (median DSC = 0.62 [interquartile range (IQR): 0.54, 0.69] vs. 0.60 [IQR: 0.50, 0.70], P < 0.001 for COVID-19 and median DSC = 0.62 [IQR: 0.56, 0.69] vs. 0.50 [IQR 0.43, 0.57], P < 0.001 for ILD). Similarly, models only trained on MK images performed better on MK images (median DSC = 0.62 [IQR: 0.53, 0.68] vs. 0.54 [IQR: 0.47, 0.63], P < 0.001 for COVID-19 and 0.69 [IQR: 0.61, 0.73] vs. 0.63 [IQR: 0.53, 0.70], P < 0.001 for ILD). Models trained on both kernels performed better or similarly than those trained on only one kernel. For COVID-19, median DSC was 0.67 (IQR: =0.59, 0.73) when applied on LK images and 0.67 (IQR: 0.60, 0.74) when applied on MK images (P < 0.001 for both). For ILD, median DSC was 0.69 (IQR: 0.63, 0.73) when applied on LK images (P = 0.006) and 0.68 (IQR: 0.62, 0.72) when applied on MK images (P > 0.99). CONCLUSION: Reconstruction kernels impact the performance of deep learning-based models for lung disease segmentation. Training on both LK and MK images improves the performance.

AI-driven quantification, staging and outcome prediction of COVID-19 pneumonia.

Coronavirus disease 2019 (COVID-19) emerged in 2019 and disseminated around the world rapidly. Computed tomography (CT) imaging has been proven to be an important tool for screening, disease quantification and staging. The latter is of extreme importance for organizational anticipation (availability of intensive care unit beds, patient management planning) as well as to accelerate drug development through rapid, reproducible and quantified assessment of treatment response. Even if currently there are no specific guidelines for the staging of the patients, CT together with some clinical and biological biomarkers are used. In this study, we collected a multi-center cohort and we investigated the use of medical imaging and artificial intelligence for disease quantification, staging and outcome prediction. Our approach relies on automatic deep learning-based disease quantification using an ensemble of architectures, and a data-driven consensus for the staging and outcome prediction of the patients fusing imaging biomarkers with clinical and biological attributes. Highly promising results on multiple external/independent evaluation cohorts as well as comparisons with expert human readers demonstrate the potentials of our approach.