Determination of disease severity in COVID-19 patients using deep learning in chest X-ray images.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read More Add to Saved list
  • Additional Information
    • Source:
      Publisher: Galenos Publishing House Country of Publication: Turkey NLM ID: 101241152 Publication Model: Print Cited Medium: Internet ISSN: 1305-3612 (Electronic) Linking ISSN: 13053825 NLM ISO Abbreviation: Diagn Interv Radiol Subsets: MEDLINE
    • Publication Information:
      Publication: Istanbul : Galenos Publishing House
      Original Publication: Ankara, Turkey : Turkish Society of Radiology, [2005]-
    • Subject Terms:
      COVID-19/*diagnosis ; Deep Learning/*statistics & numerical data ; Radiography, Thoracic/*methods ; SARS-CoV-2/*genetics ; Thorax/*diagnostic imaging; Adult ; Age Factors ; Aged ; COVID-19/epidemiology ; COVID-19/therapy ; COVID-19/virology ; Comorbidity ; Feasibility Studies ; Female ; Humans ; Italy/epidemiology ; Male ; Middle Aged ; Radiography, Thoracic/classification ; Radiologists ; Retrospective Studies ; Severity of Illness Index ; Thorax/pathology
    • Abstract:
      Purpose: Chest X-ray plays a key role in diagnosis and management of COVID-19 patients and imaging features associated with clinical elements may assist with the development or validation of automated image analysis tools. We aimed to identify associations between clinical and radiographic features as well as to assess the feasibility of deep learning applied to chest X-rays in the setting of an acute COVID-19 outbreak.
      Methods: A retrospective study of X-rays, clinical, and laboratory data was performed from 48 SARS-CoV-2 RT-PCR positive patients (age 60±17 years, 15 women) between February 22 and March 6, 2020 from a tertiary care hospital in Milan, Italy. Sixty-five chest X-rays were reviewed by two radiologists for alveolar and interstitial opacities and classified by severity on a scale from 0 to 3. Clinical factors (age, symptoms, comorbidities) were investigated for association with opacity severity and also with placement of central line or endotracheal tube. Deep learning models were then trained for two tasks: lung segmentation and opacity detection. Imaging characteristics were compared to clinical datapoints using the unpaired student's t-test or Mann-Whitney U test. Cohen's kappa analysis was used to evaluate the concordance of deep learning to conventional radiologist interpretation.
      Results: Fifty-six percent of patients presented with alveolar opacities, 73% had interstitial opacities, and 23% had normal X-rays. The presence of alveolar or interstitial opacities was statistically correlated with age (P = 0.008) and comorbidities (P = 0.005). The extent of alveolar or interstitial opacities on baseline X-ray was significantly associated with the presence of endotracheal tube (P = 0.0008 and P = 0.049) or central line (P = 0.003 and P = 0.007). In comparison to human interpretation, the deep learning model achieved a kappa concordance of 0.51 for alveolar opacities and 0.71 for interstitial opacities.
      Conclusion: Chest X-ray analysis in an acute COVID-19 outbreak showed that the severity of opacities was associated with advanced age, comorbidities, as well as acuity of care. Artificial intelligence tools based upon deep learning of COVID-19 chest X-rays are feasible in the acute outbreak setting.
    • References:
      JAMA. 2020 Apr 7;323(13):1239-1242. (PMID: 32091533)
      Eur J Nucl Med Mol Imaging. 2020 May;47(5):1275-1280. (PMID: 32107577)
      Radiology. 2020 Apr;295(1):202-207. (PMID: 32017661)
      Lancet. 2020 Mar 28;395(10229):1054-1062. (PMID: 32171076)
      Radiology. 2020 Aug;296(2):E65-E71. (PMID: 32191588)
      Radiology. 2020 Apr;295(1):16-17. (PMID: 32017662)
      Radiology. 2020 Jun;295(3):200463. (PMID: 32077789)
      AJR Am J Roentgenol. 2020 Jun;214(6):1280-1286. (PMID: 32130038)
      J Am Coll Radiol. 2020 Apr;17(4):447-451. (PMID: 32092296)
      Quant Imaging Med Surg. 2014 Dec;4(6):475-7. (PMID: 25525580)
      JAMA. 2020 Apr 28;323(16):1612-1614. (PMID: 32191259)
      Lancet Infect Dis. 2020 Jul;20(7):773. (PMID: 32171390)
      Radiology. 2020 Aug;296(2):E46-E54. (PMID: 32155105)
      Invest Radiol. 2020 Jun;55(6):327-331. (PMID: 32118615)
      AJR Am J Roentgenol. 2000 Jan;174(1):71-4. (PMID: 10628457)
      Travel Med Infect Dis. 2020 Mar - Apr;34:101627. (PMID: 32179123)
      Eur Radiol. 2020 Aug;30(8):4381-4389. (PMID: 32193638)
      Radiol Cardiothorac Imaging. 2020 Feb 13;2(1):e200034. (PMID: 33778547)
      Eur J Radiol. 2020 May;126:108972. (PMID: 32240913)
      Eur Radiol. 2020 Aug;30(8):4407-4416. (PMID: 32215691)
      Clin Imaging. 2020 Jul;63:7-9. (PMID: 32120312)
      Korean J Radiol. 2020 Apr;21(4):505-508. (PMID: 32174053)
      AJR Am J Roentgenol. 2020 May;214(5):1072-1077. (PMID: 32125873)
      Radiology. 2020 Apr;295(1):22-23. (PMID: 32049600)
      Radiology. 2020 Aug;296(2):E32-E40. (PMID: 32101510)
      JAMA Intern Med. 2020 Jul 1;180(7):934-943. (PMID: 32167524)
      Cytometry A. 2020 Mar;97(3):215-216. (PMID: 32142596)
      AJR Am J Roentgenol. 2020 Jun;214(6):1287-1294. (PMID: 32134681)
      Eur Radiol. 2020 Jun;30(6):3306-3309. (PMID: 32055945)
      Radiology. 2020 Aug;296(2):E55-E64. (PMID: 32191587)
      Radiology. 2020 Aug;296(2):E115-E117. (PMID: 32073353)
      Radiology. 2020 Apr;295(1):210-217. (PMID: 32027573)
      Korean J Radiol. 2020 Apr;21(4):494-500. (PMID: 32100485)
      Eur J Radiol. 2020 May;126:108941. (PMID: 32193037)
      Radiology. 2020 Jun;295(3):715-721. (PMID: 32053470)
      Radiology. 2020 Aug;296(2):E41-E45. (PMID: 32049601)
    • Grant Information:
      75N91019D00024 United States CA NCI NIH HHS
    • Publication Date:
      Date Created: 20200821 Date Completed: 20210201 Latest Revision: 20240401
    • Publication Date:
      20240401
    • Accession Number:
      PMC7837735
    • Accession Number:
      10.5152/dir.2020.20205
    • Accession Number:
      32815519