Selected article for: "mean age and negative correlation"
Author: Mergen, Victor; Kobe, Adrian; Blüthgen, Christian; Euler, André; Flohr, Thomas; Frauenfelder, Thomas; Alkadhi, Hatem; Eberhard, Matthias
Title: Deep learning for automatic quantification of lung abnormalities in COVID-19 patients: first experience and correlation with clinical parameters
  • Cord-id: zh3h4597
  • Document date: 2020_10_6
    • ID: zh3h4597
    Snippet: RATIONALE AND OBJECTIVES: To demonstrate the first experience of a deep learning-based algorithm for automatic quantification of lung parenchymal abnormalities in chest CT of COVID-19 patients and to correlate quantitative results with clinical and laboratory parameters. MATERIALS AND METHODS: We retrospectively included 60 consecutive patients (mean age, 61 ± 12 years; 18 females) with proven COVID-19 infection undergoing chest CT between March and May 2020. Clinical and laboratory data (withi
    Document: RATIONALE AND OBJECTIVES: To demonstrate the first experience of a deep learning-based algorithm for automatic quantification of lung parenchymal abnormalities in chest CT of COVID-19 patients and to correlate quantitative results with clinical and laboratory parameters. MATERIALS AND METHODS: We retrospectively included 60 consecutive patients (mean age, 61 ± 12 years; 18 females) with proven COVID-19 infection undergoing chest CT between March and May 2020. Clinical and laboratory data (within 24 hours before/after chest CT) were recorded. Prototype software using a deep learning algorithm was applied for automatic segmentation and quantification of lung opacities. Percentage of opacity (PO, ground-glass and consolidations) and percentage of high opacity (PHO, consolidations), were defined as 100 times the volume of segmented abnormalities divided by the volume of the lung mask. RESULTS: Automatic CT analysis of the lung was feasible in all patients (n = 60). The median time to accomplish automatic evaluation was 120 s (IQR: 118–128 s). In four cases (7%), manual corrections were necessary. Patients with need for mechanical ventilation had a significantly higher PO (median 44%, IQR: 23-58% versus 13%, IQR: 10-24%; p = 0.001) and PHO (median: 11%, IQR: 6-21% versus 3%, IQR: 2-7%, p = 0.002) compared to those without. The PO and PHO moderately correlated with c-reactive protein (r = 0.49-0.60, both p < 0.001) and leucocyte count (r = 0.30-0.40, both p = 0.05). PO had a negative correlation with SO(2) (r=-0.50, p = 0.001). CONCLUSION: Preliminary experience indicates the feasibility of a rapid, automatic quantification tool of lung parenchymal abnormalities in COVID-19 patients using deep learning, with results correlating with laboratory and clinical parameters.

    Search related documents:
    Co phrase search for related documents
    • accurate segmentation and lung parenchyma: 1, 2
    • accurate segmentation and machine learning: 1, 2, 3
    • local ethics committee and lung parenchyma: 1, 2
    • local ethics committee and machine learning: 1, 2
    • lung ct analysis and machine learning: 1, 2, 3
    • lung evaluation and machine learning: 1, 2
    • lung opacity and machine learning: 1, 2, 3, 4, 5, 6
    • lung parenchyma and machine learning: 1, 2, 3, 4, 5, 6, 7