ABSTRACT
Background: The aim of the study was to analyze the relationship between patient characteristics, including anagraphic and laboratoristic data and amount of adipose tissue measured in computed tomography (CT) scans in coronavirus disease 2019 (COVID-19) patients, and incidence of soft tissue bleeding requiring medical and/or interventional radiology management. Methods: A total of 132 patients hospitalized for COVID-19 pathology from October 2020 to May 2021 were included in the study and divided into two groups: a bleeding group of 70 cases with soft tissue bleeding occurring during hospitalization, and a control group of 62 hospitalized COVID-19 patients without bleeding events. In the bleeding group, two subgroups were considered: an embolization group including soft tissue bleeding cases requiring interventional radiology with transarterial embolization (TAE) (16/70; 22.9%) and a non-embolization group, clinically managed without TAE (54/70; 77.1%). Demographics and clinical data, visceral adipose tissue (VAT) area and subcutaneous adipose tissue (SAT) area measured on CT images and VAT/SAT ratio were compared between bleeding and control groups and between embolization and non-embolization subgroups. Results: Bleeding and control groups did not significantly differ for sex distribution, COVID-19, platelet (PLT) count, international normalized ratio (INR), SAT area, VAT area, and VAT/SAT ratio. Embolization and non-embolization groups did not significantly differ for age, COVID-19, PLT count, INR, SAT area, and VAT/SAT ratio. Bleeding group had lower body mass index (BMI) than control group as well as embolization group compared to non-embolization group. A statistically significant difference was observed between embolization and non-embolization groups for VAT area, with smaller values in embolization group (mean difference: 64.2 cm2, 95% confidence interval: 8.3 - 120.1; P < 0.05). Conclusion: Soft tissue bleeding in COVID-19 is more frequent and severe in patients with low amount of VAT, demonstrating that fat mass may have a containing function on bleeding, limiting its progression in surrounding structures. There are some other factors that influence the risk of bleeding, such as age, thromboprophylaxis therapy and BMI.
ABSTRACT
BACKGROUND: Coronavirus disease 2019 (COVID-19) pneumonia and immune checkpoint inhibitor (ICI) therapy-related pneumonitis share common features. The aim of this study was to determine on chest computed tomography (CT) images whether a deep convolutional neural network algorithm is able to solve the challenge of differential diagnosis between COVID-19 pneumonia and ICI therapy-related pneumonitis. METHODS: We enrolled three groups: a pneumonia-free group (n = 30), a COVID-19 group (n = 34), and a group of patients with ICI therapy-related pneumonitis (n = 21). Computed tomography images were analyzed with an artificial intelligence (AI) algorithm based on a deep convolutional neural network structure. Statistical analysis included the Mann-Whitney U test (significance threshold at p < 0.05) and the receiver operating characteristic curve (ROC curve). RESULTS: The algorithm showed low specificity in distinguishing COVID-19 from ICI therapy-related pneumonitis (sensitivity 97.1%, specificity 14.3%, area under the curve (AUC) = 0.62). ICI therapy-related pneumonitis was identified by the AI when compared to pneumonia-free controls (sensitivity = 85.7%, specificity 100%, AUC = 0.97). CONCLUSIONS: The deep learning algorithm is not able to distinguish between COVID-19 pneumonia and ICI therapy-related pneumonitis. Awareness must be increased among clinicians about imaging similarities between COVID-19 and ICI therapy-related pneumonitis. ICI therapy-related pneumonitis can be applied as a challenge population for cross-validation to test the robustness of AI models used to analyze interstitial pneumonias of variable etiology.