Observer agreement and clinical significance of chest CT reporting in patients suspected of COVID-19 (preprint)

Objectives: To assess inter-observer agreement and clinical significance of chest CT reporting in patients suspected of COVID-19. Methods: From 16th to 24th March 2020, 241 consecutive patients addressed to hospital for COVID-19 suspicion had both chest CT and SARS-CoV-2 RT-PCR. Eight observers (2 thoracic and 2 general senior radiologists, 2 junior radiologists and 2 emergency physicians) retrospectively categorized each CT into one out of 3 categories (evocative, compatible for COVID-19 pneumonia, and not evocative or normal). Observer agreement for categorization between all readers and pairs of readers with similar experience was evaluated with the Kappa coefficient. The results of a consensus categorization were correlated to RT-PCR. Results: Observer agreement across the 3 categories was good between all readers (kappa value 0.68 95%CI 0.67-0.70) and good to very good between pairs of readers (0.64-0.85). It was very good (0.81 95%CI 0.79-0.83), fair (0.32 95%CI 0.29-0.34) and good (0.74 95%CI 0.71-0.76) for the categories evocative, compatible and not evocative or normal, respectively. RT-PCR was positive in 97%, 50% and 27% of cases classified in the respective categories. Observer agreement was lower (p=0.045) and RT-PCR positive cases were less frequently categorized evocative in presence of an underlying pulmonary disease (p<0.001). Conclusion: Inter-observer agreement for chest CT reporting using categorization of findings is good in patients suspected of COVID-19. Among patients considered for hospitalization in an epidemic context, CT categorized evocative is highly predictive of COVID-19, whereas the predictive value of CT decreases between the categories compatible and not evocative.

AI-Driven CT-based quantification, staging and short-term outcome prediction of COVID-19 pneumonia (preprint)

Improving screening, discovering therapies, developing a vaccine and performing staging and prognosis are decisive steps in addressing the COVID-19 pandemic. Staging and prognosis are especially crucial for organizational anticipation (intensive-care bed availability, patient management planning) and accelerating drug development; through rapid, reproducible and quantified response-to-treatment assessment. In this letter, we report on an artificial intelligence solution for performing automatic staging and prognosis based on imaging, clinical, comorbidities and biological data. This approach relies on automatic computed tomography (CT)-based disease quantification using deep learning, robust data-driven identification of physiologically-inspired COVID-19 holistic patient profiling, and strong, reproducible staging/outcome prediction with good generalization properties using an ensemble of consensus methods. Highly promising results on multiple independent external evaluation cohorts along with comparisons with expert human readers demonstrate the potentials of our approach. The developed solution offers perspectives for optimal patient management, given the shortage of intensive care beds and ventilators1, 2, along with means to assess patient response to treatment.

AI-Driven CT-based quantification, staging and short-term outcome prediction of COVID-19 pneumonia (preprint)

Chest computed tomography (CT) is widely used for the management of Coronavirus disease 2019 (COVID-19) pneumonia because of its availability and rapidity. The standard of reference for confirming COVID-19 relies on microbiological tests but these tests might not be available in an emergency setting and their results are not immediately available, contrary to CT. In addition to its role for early diagnosis, CT has a prognostic role by allowing visually evaluating the extent of COVID-19 lung abnormalities. The objective of this study is to address prediction of short-term outcomes, especially need for mechanical ventilation. In this multi-centric study, we propose an end-to-end artificial intelligence solution for automatic quantification and prognosis assessment by combining automatic CT delineation of lung disease meeting performance of experts and data-driven identification of biomarkers for its prognosis. AI-driven combination of variables with CT-based biomarkers offers perspectives for optimal patient management given the shortage of intensive care beds and ventilators.