Automated lung vessel segmentation reveals blood vessel volume redistribution in viral pneumonia. Issue 150 (May 2022)
- Record Type:
- Journal Article
- Title:
- Automated lung vessel segmentation reveals blood vessel volume redistribution in viral pneumonia. Issue 150 (May 2022)
- Main Title:
- Automated lung vessel segmentation reveals blood vessel volume redistribution in viral pneumonia
- Authors:
- Poletti, Julien
Bach, Michael
Yang, Shan
Sexauer, Raphael
Stieltjes, Bram
Rotzinger, David C.
Bremerich, Jens
Walter Sauter, Alexander
Weikert, Thomas - Abstract:
- Highlights: Lung vessel analysis provides meaningful imaging parameters for viral pneumonia. Blood vessel volume distribution differs between healthy and diseased patients. Vascular changes are more pronounced in COVID-19 than in Influenza. The suggested vascular imaging biomarkers correlate with disease severity. 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 mm 2 ), medium (BV5-10%, 5–10 mm 2 ) and large (BV10%, >10 mm 2 ). Results: Sensitivity of the LVSA was 84.6% (95 %CI: 73.9–95.3) for NECTs and 92.8%Highlights: Lung vessel analysis provides meaningful imaging parameters for viral pneumonia. Blood vessel volume distribution differs between healthy and diseased patients. Vascular changes are more pronounced in COVID-19 than in Influenza. The suggested vascular imaging biomarkers correlate with disease severity. 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 mm 2 ), medium (BV5-10%, 5–10 mm 2 ) and large (BV10%, >10 mm 2 ). 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. … (more)
- Is Part Of:
- European journal of radiology. Issue 150(2022)
- Journal:
- European journal of radiology
- Issue:
- Issue 150(2022)
- Issue Display:
- Volume 150, Issue 150 (2022)
- Year:
- 2022
- Volume:
- 150
- Issue:
- 150
- Issue Sort Value:
- 2022-0150-0150-0000
- Page Start:
- Page End:
- Publication Date:
- 2022-05
- Subjects:
- Algorithms -- Blood vessels -- Viral pneumonia -- COVID-19 -- Influenza
BV Blood Vessel Volume (ml) -- BV5 Blood Vessel Volume of vessels with cross-sectional area <5 mm2 -- BV5-10 Blood Vessel Volume of vessels with cross-sectional area between 5 and 10 mm2 -- BV10 Blood Vessel Volume of vessels with cross-sectional area >10 mm2 -- BV% Blood Vessel Volume percentage (%) (= the ratio BV/TBV) -- BV5% Ratio BV5/TBV, which is the Blood Vessel Volume percentage of vessels with a cross-sectional area <5 mm2 -- BV5-10% Ratio BV5-10/TBV, which is the Blood Vessel Volume percentage of vessels with a cross-sectional area between 5 and 10 mm2 -- BV10% Ratio BV5-10/TBV, which is the Blood Vessel Volume percentage of vessels with a cross-sectional area > 10 mm2 -- COPD Chronic Obstructive Pulmonary Disease -- COVID-19 Coronavirus Disease 2019 -- CT Computed Tomography -- CTPA Computed Tomography Pulmonary Angiogram -- HU Hounsfield Unit -- LVSA Lung Vessel Segmentation Algorithm -- NECT Non-Enhanced Computed Tomography -- PACS Picture Archiving and Communication System -- PGY Postgraduate Year -- POI Point of Interest -- RT-PCR Reverse Transcription Polymerase Chain Reaction -- SARS-CoV-2 Severe Acute Respiratory Syndrome Coronavirus 2 -- TBV Total Blood Vessel Volume in Lung -- TLV Total Lung Volume -- WHO World Health Organization
Medical radiology -- Periodicals
Radiology -- Periodicals
Radiologie médicale -- Périodiques
Medical radiology
Periodicals
616.075705 - Journal URLs:
- http://www.sciencedirect.com/science/journal/0720048X ↗
http://www.elsevier.com/homepage/elecserv.htt ↗
http://www.clinicalkey.com/dura/browse/journalIssue/0720048X ↗
http://www.clinicalkey.com.au/dura/browse/journalIssue/0720048X ↗
http://www.elsevier.com/journals ↗ - DOI:
- 10.1016/j.ejrad.2022.110259 ↗
- Languages:
- English
- ISSNs:
- 0720-048X
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 3829.738050
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 21222.xml