Comparison of deep learning, radiomics and subjective assessment of chest CT findings in SARS-CoV-2 pneumonia

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

  • Chiara Arru, Harvard University
  • ,
  • Shadi Ebrahimian, Harvard University
  • ,
  • Zeno Falaschi, Ospedale Maggiore
  • ,
  • Jacob Valentin Hansen
  • Alessio Pasche, Ospedale Maggiore
  • ,
  • Mads Dam Lyhne
  • Mathis Zimmermann, Siemens
  • ,
  • Felix Durlak, Siemens
  • ,
  • Matthias Mitschke, Siemens
  • ,
  • Alessandro Carriero, Ospedale Maggiore
  • ,
  • Jens Erik Nielsen-Kudsk
  • Mannudeep K. Kalra, Harvard University
  • ,
  • Luca Saba, University Hospital of Cagliari

Purpose: Comparison of deep learning algorithm, radiomics and subjective assessment of chest CT for predicting outcome (death or recovery) and intensive care unit (ICU) admission in patients with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. Methods: The multicenter, ethical committee-approved, retrospective study included non-contrast-enhanced chest CT of 221 SARS-CoV-2 positive patients from Italy (n = 196 patients; mean age 64 ± 16 years) and Denmark (n = 25; mean age 69 ± 13 years). A thoracic radiologist graded presence, type and extent of pulmonary opacities and severity of motion artifacts in each lung lobe on all chest CTs. Thin-section CT images were processed with CT Pneumonia Analysis Prototype (Siemens Healthineers) which yielded segmentation masks from a deep learning (DL) algorithm to derive features of lung abnormalities such as opacity scores, mean HU, as well as volume and percentage of all-attenuation and high-attenuation (opacities >−200 HU) opacities. Separately, whole lung radiomics were obtained for all CT exams. Analysis of variance and multiple logistic regression were performed for data analysis. Results: Moderate to severe respiratory motion artifacts affected nearly one-quarter of chest CTs in patients. Subjective severity assessment, DL-based features and radiomics predicted patient outcome (AUC 0.76 vs AUC 0.88 vs AUC 0.83) and need for ICU admission (AUC 0.77 vs AUC 0.0.80 vs 0.82). Excluding chest CT with motion artifacts, the performance of DL-based and radiomics features improve for predicting ICU admission. Conclusion: DL-based and radiomics features of pulmonary opacities from chest CT were superior to subjective assessment for differentiating patients with favorable and adverse outcomes.

Original languageEnglish
JournalClinical Imaging
Pages (from-to)58-66
Number of pages9
Publication statusPublished - Dec 2021

Bibliographical note

Publisher Copyright:
© 2021

    Research areas

  • Chest CT, Deep learning, Pneumonia, Radiomics, SARS-CoV-2

See relations at Aarhus University Citationformats

ID: 219709432