Automated lung vessel segmentation reveals blood vessel volume redistribution in viral pneumonia

Julien Poletti; Michael Bach; Shan Yang; Raphael Sexauer; Bram Stieltjes; David C Rotzinger; Jens Bremerich; Alexander Walter Sauter; Thomas Weikert

doi:10.1016/j.ejrad.2022.110259

Automated lung vessel segmentation reveals blood vessel volume redistribution in viral pneumonia

Eur J Radiol. 2022 May:150:110259. doi: 10.1016/j.ejrad.2022.110259. Epub 2022 Mar 17.

Authors

Julien Poletti¹, Michael Bach², Shan Yang³, Raphael Sexauer⁴, Bram Stieltjes⁵, David C Rotzinger⁶, Jens Bremerich⁷, Alexander Walter Sauter⁸, Thomas Weikert⁹

Affiliations

¹ Department of Radiology, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland. Electronic address: julien.poletti@unibas.ch.
² Department of Research and Analysis, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland. Electronic address: michael.bach@usb.ch.
³ Department of Research and Analysis, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland. Electronic address: shan.yang@usb.ch.
⁴ Department of Radiology, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland. Electronic address: raphael.sexauer@usb.ch.
⁵ Department of Research and Analysis, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland. Electronic address: bram.stieltjes@usb.ch.
⁶ Cardiothoracic and Vascular Division, Department of Diagnostic and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Rue du Bugnon 46, 1011 Lausanne, Switzerland. Electronic address: david.rotzinger@chuv.ch.
⁷ Department of Radiology, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland. Electronic address: jens.bremerich@usb.ch.
⁸ Department of Radiology, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland; Department of Research and Analysis, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland. Electronic address: alexander.sauter@usb.ch.
⁹ Department of Radiology, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland; Department of Research and Analysis, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland. Electronic address: thomas.weikert@usb.ch.

PMID: 35334245
DOI: 10.1016/j.ejrad.2022.110259

Abstract

Purpose: It is known from histology studies that lung vessels are affected in viral pneumonia. However, their diagnostic potential as a chest CT imaging parameter has only rarely been exploited. The purpose of this study is to develop a robust method for automated lung vessel segmentation and morphology analysis and apply it to a large chest CT dataset.

Methods: In total, 509 non-enhanced chest CTs (NECTs) and 563 CT pulmonary angiograms (CTPAs) were included. Sub-groups were patients with healthy lungs (group_NORM, n = 634) and those RT-PCR-positive for Influenza A/B (group_INF, n = 159) and SARS-CoV-2 (group_COV, n = 279). A lung vessel segmentation algorithm (LVSA) based on traditional image processing was developed, validated with a point-of-interest approach, and applied to a large clinical dataset. Total blood vessel volume in lung (TBV) and the blood vessel volume percentage (BV%) of three blood vessel size types were calculated and compared between groups: small (BV5%, cross-sectional area < 5 mm²), medium (BV5-10%, 5-10 mm²) and large (BV10%, >10 mm²).

Results: Sensitivity of the LVSA was 84.6% (95 %CI: 73.9-95.3) for NECTs and 92.8% (95 %CI: 90.8-94.7) for CTPAs. In viral pneumonia, besides an increased TBV, the main finding was a significantly decreased BV5% in group_COV (n = 14%) and group_INF (n = 15%) compared to group_NORM (n = 18%) [p < 0.001]. At the same time, BV10% was increased (group_COV n = 15% and group_INF n = 14% vs. group_NORM n = 11%; p < 0.001).

Conclusion: In COVID-19 and Influenza, the blood vessel volume is redistributed from small to large vessels in the lung. Automated LSVA allows researchers and clinicians to derive imaging parameters for large amounts of CTs. This can enhance the understanding of vascular changes, particularly in infectious lung diseases.

Keywords: Algorithms; Blood vessels; COVID-19; Influenza; Viral pneumonia.

MeSH terms

COVID-19*
Humans
Influenza, Human* / diagnostic imaging
Lung / blood supply
Lung / diagnostic imaging
Pneumonia, Viral* / diagnostic imaging
Retrospective Studies
SARS-CoV-2