A multicenter evaluation of a deep learning software (LungQuant) for lung parenchyma characterization in COVID-19 pneumonia.

BACKGROUND: The role of computed tomography (CT) in the diagnosis and characterization of coronavirus disease 2019 (COVID-19) pneumonia has been widely recognized. We evaluated the performance of a software for quantitative analysis of chest CT, the LungQuant system, by comparing its results with independent visual evaluations by a group of 14 clinical experts. The aim of this work is to evaluate the ability of the automated tool to extract quantitative information from lung CT, relevant for the design of a diagnosis support model. METHODS: LungQuant segments both the lungs and lesions associated with COVID-19 pneumonia (ground-glass opacities and consolidations) and computes derived quantities corresponding to qualitative characteristics used to clinically assess COVID-19 lesions. The comparison was carried out on 120 publicly available CT scans of patients affected by COVID-19 pneumonia. Scans were scored for four qualitative metrics: percentage of lung involvement, type of lesion, and two disease distribution scores. We evaluated the agreement between the LungQuant output and the visual assessments through receiver operating characteristics area under the curve (AUC) analysis and by fitting a nonlinear regression model. RESULTS: Despite the rather large heterogeneity in the qualitative labels assigned by the clinical experts for each metric, we found good agreement on the metrics compared to the LungQuant output. The AUC values obtained for the four qualitative metrics were 0.98, 0.85, 0.90, and 0.81. CONCLUSIONS: Visual clinical evaluation could be complemented and supported by computer-aided quantification, whose values match the average evaluation of several independent clinical experts. KEY POINTS: We conducted a multicenter evaluation of the deep learning-based LungQuant automated software. We translated qualitative assessments into quantifiable metrics to characterize coronavirus disease 2019 (COVID-19) pneumonia lesions. Comparing the software output to the clinical evaluations, results were satisfactory despite heterogeneity of the clinical evaluations. An automatic quantification tool may contribute to improve the clinical workflow of COVID-19 pneumonia.

Chest radiography findings of COVID-19 pneumonia: a specific pattern for a confident differential diagnosis.

BACKGROUND: Chest radiography (CR) patterns for the diagnosis of COVID-19 have been established. However, they were not ideated comparing CR features with those of other pulmonary diseases. PURPOSE: To create the most accurate COVID-19 pneumonia pattern comparing CR findings of COVID-19 and non-COVID-19 pulmonary diseases and to test the model against the British Society of Thoracic Imaging (BSTI) criteria. MATERIAL AND METHODS: CR of COVID-19 and non-COVID-19 pulmonary diseases, admitted to the emergency department, were evaluated. Assessed features were interstitial opacities, ground glass opacities, and/or consolidations and the predominant lung alteration. We also assessed uni-/bilaterality, location (upper/middle/lower), and distribution (peripheral/perihilar), as well as pleural effusion and perihilar vessels blurring. A binary logistic regression was adopted to obtain the most accurate CR COVID-19 pattern, and sensitivity and specificity were computed. The newly defined pattern was compared to BSTI criteria. RESULTS: CR of 274 patients were evaluated (146 COVID-19, 128 non-COVID-19). The most accurate COVID-19 pneumonia pattern consisted of four features: bilateral alterations (Expß=2.8, P=0.002), peripheral distribution of the predominant (Expß=2.3, P=0.013), no pleural effusion (Expß=0.4, P=0.009), and perihilar vessels' contour not blurred (Expß=0.3, P=0.002). The pattern showed 49% sensitivity, 81% specificity, and 64% accuracy, while BSTI criteria showed 51%, 77%, and 63%, respectively. CONCLUSION: Bilaterality, peripheral distribution of the predominant lung alteration, no pleural effusion, and perihilar vessels contour not blurred determine the most accurate COVID-19 pneumonia pattern. Lower field involvement, proposed by BSTI criteria, was not a distinctive finding. The BSTI criteria has lower specificity.

The role of chest CT in deciphering interstitial lung involvement: systemic sclerosis versus COVID-19.

OBJECTIVE: The aim of this study was to identify the main CT features that may help in distinguishing a progression of interstitial lung disease (ILD) secondary to SSc from COVID-19 pneumonia. METHODS: This multicentric study included 22 international readers grouped into a radiologist group (RADs) and a non-radiologist group (nRADs). A total of 99 patients, 52 with COVID-19 and 47 with SSc-ILD, were included in the study. RESULTS: Fibrosis inside focal ground-glass opacities (GGOs) in the upper lobes; fibrosis in the lower lobe GGOs; reticulations in lower lobes (especially if bilateral and symmetrical or associated with signs of fibrosis) were the CT features most frequently associated with SSc-ILD. The CT features most frequently associated with COVID- 19 pneumonia were: consolidation (CONS) in the lower lobes, CONS with peripheral (both central/peripheral or patchy distributions), anterior and posterior CONS and rounded-shaped GGOs in the lower lobes. After multivariate analysis, the presence of CONs in the lower lobes (P < 0.0001) and signs of fibrosis in GGOs in the lower lobes (P < 0.0001) remained independently associated with COVID-19 pneumonia and SSc-ILD, respectively. A predictive score was created that was positively associated with COVID-19 diagnosis (96.1% sensitivity and 83.3% specificity). CONCLUSION: CT diagnosis differentiating between COVID-19 pneumonia and SSc-ILD is possible through a combination of the proposed score and radiologic expertise. The presence of consolidation in the lower lobes may suggest COVID-19 pneumonia, while the presence of fibrosis inside GGOs may indicate SSc-ILD.

Knowledge Graphs for COVID-19: An Exploratory Review of the Current Landscape.

BACKGROUND: Searching through the COVID-19 research literature to gain actionable clinical insight is a formidable task, even for experts. The usefulness of this corpus in terms of improving patient care is tied to the ability to see the big picture that emerges when the studies are seen in conjunction rather than in isolation. When the answer to a search query requires linking together multiple pieces of information across documents, simple keyword searches are insufficient. To answer such complex information needs, an innovative artificial intelligence (AI) technology named a knowledge graph (KG) could prove to be effective. METHODS: We conducted an exploratory literature review of KG applications in the context of COVID-19. The search term used was "covid-19 knowledge graph". In addition to PubMed, the first five pages of search results for Google Scholar and Google were considered for inclusion. Google Scholar was used to include non-peer-reviewed or non-indexed articles such as pre-prints and conference proceedings. Google was used to identify companies or consortiums active in this domain that have not published any literature, peer-reviewed or otherwise. RESULTS: Our search yielded 34 results on PubMed and 50 results each on Google and Google Scholar. We found KGs being used for facilitating literature search, drug repurposing, clinical trial mapping, and risk factor analysis. CONCLUSIONS: Our synopses of these works make a compelling case for the utility of this nascent field of research.