The STOIC study (ThOracIque Scanner for the diagnosis of pneumonia linked to Coronavirus 19) coordinated by Pr Marie-Pierre Revel, head of department at Cochin AP-HP hospital, University of Paris, was the subject of a publication in Radiology on June 29, 2021.

This study, promoted by Assistance Publique – Hôpitaux de Paris, involved 20 university hospitals, mainly in Paris but also Strasbourg, Lyon, Rennes and Montpellier and 10,735 patients suspected of Covid-19 during the first wave of the pandemic in France.

Its objective was to evaluate the diagnostic performance and the prognostic role of the thoracic scanner, by collecting the outcome at 1 month of patients with a positive PCR and respiratory signs.

The images were annotated by experts from the Thoracic Imaging Society, who assessed the extent of pneumonia and signs reflecting pre-existing comorbidities, such as chest wall fat, the presence of pulmonary emphysema, and severity of coronary calcifications.

An internet annotation tool has been specifically developed by General Electric Healthcare, allowing remote annotation.

The study shows good diagnostic performance of the scanner using predefined criteria and the need to repeat the PCR if it is initially negative in a patient with a positive CT scan. It also shows that the initial extent of pneumonia is the strongest predictor of unfavorable outcome.

The database, unique by its size and the richness of the annotations, will allow the development of artificial intelligence algorithms to better fight against the pandemic.

The authors would like to thank all the clinical research technicians involved in the project, as well as Orange Healthcare for hosting the data, the Guerbet company, the Innothéra company, the CentraleSupélec foundation and the AP-HP Foundation for their financial support.

Reference: Study of Thoracic CT in COVID-19: The STOIC Project : Marie-Pierre Revel, Samia Boussouar, Constance de Margerie-Mellon, Inès Saab, Thibaut Lapotre, Dominique Mompoint, Guillaume Chassagnon, Audrey Milon, Mathieu Lederlin, Souhail Bennani, Sébastien Molière, Marie-Pierre Debray, Florian Bompard, Severine Dangeard, Chahinez Hani, Mickaël Ohana, Sébastien Bommart, Carole Jalaber, Mostafa El Hajjam, Isabelle Petit, Laure Fournier, Antoine Khali, Pierre-Yves Brillet, Marie-France Bellin, Alban Redheui, Laurence Rocher, Valérie Bousson, Pascal Rousset, Jules Grégory, Jean-François Deux, Elisabeth Dion, Dominique Valeyre, Raphael Porcher, Léa Jilet, Hendy Abdou, Radiology .

DOI: https://doi.org/10.1148/radiol.2021210384