Cargando…

Automated CT Lung Density Analysis of Viral Pneumonia and Healthy Lungs Using Deep Learning-Based Segmentation, Histograms and HU Thresholds

CT patterns of viral pneumonia are usually only qualitatively described in radiology reports. Artificial intelligence enables automated and reliable segmentation of lungs with chest CT. Based on this, the purpose of this study was to derive meaningful imaging biomarkers reflecting CT patterns of vir...

Descripción completa

Detalles Bibliográficos
Autores principales: Romanov, Andrej, Bach, Michael, Yang, Shan, Franzeck, Fabian C., Sommer, Gregor, Anastasopoulos, Constantin, Bremerich, Jens, Stieltjes, Bram, Weikert, Thomas, Sauter, Alexander Walter
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8143124/
https://www.ncbi.nlm.nih.gov/pubmed/33919094
http://dx.doi.org/10.3390/diagnostics11050738
_version_ 1783696693464662016
author Romanov, Andrej
Bach, Michael
Yang, Shan
Franzeck, Fabian C.
Sommer, Gregor
Anastasopoulos, Constantin
Bremerich, Jens
Stieltjes, Bram
Weikert, Thomas
Sauter, Alexander Walter
author_facet Romanov, Andrej
Bach, Michael
Yang, Shan
Franzeck, Fabian C.
Sommer, Gregor
Anastasopoulos, Constantin
Bremerich, Jens
Stieltjes, Bram
Weikert, Thomas
Sauter, Alexander Walter
author_sort Romanov, Andrej
collection PubMed
description CT patterns of viral pneumonia are usually only qualitatively described in radiology reports. Artificial intelligence enables automated and reliable segmentation of lungs with chest CT. Based on this, the purpose of this study was to derive meaningful imaging biomarkers reflecting CT patterns of viral pneumonia and assess their potential to discriminate between healthy lungs and lungs with viral pneumonia. This study used non-enhanced and CT pulmonary angiograms (CTPAs) of healthy lungs and viral pneumonia (SARS-CoV-2, influenza A/B) identified by radiology reports and RT-PCR results. After deep learning segmentation of the lungs, histogram-based and threshold-based analyses of lung attenuation were performed and compared. The derived imaging biomarkers were correlated with parameters of clinical and biochemical severity (modified WHO severity scale; c-reactive protein). For non-enhanced CTs (n = 526), all imaging biomarkers significantly differed between healthy lungs and lungs with viral pneumonia (all p < 0.001), a finding that was not reproduced for CTPAs (n = 504). Standard deviation (histogram-derived) and relative high attenuation area [600–0 HU] (HU-thresholding) differed most. The strongest correlation with disease severity was found for absolute high attenuation area [600–0 HU] (r = 0.56, 95% CI = 0.46–0.64). Deep-learning segmentation-based histogram and HU threshold analysis could be deployed in chest CT evaluation for the differentiating of healthy lungs from AP lungs.
format Online
Article
Text
id pubmed-8143124
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-81431242021-05-25 Automated CT Lung Density Analysis of Viral Pneumonia and Healthy Lungs Using Deep Learning-Based Segmentation, Histograms and HU Thresholds Romanov, Andrej Bach, Michael Yang, Shan Franzeck, Fabian C. Sommer, Gregor Anastasopoulos, Constantin Bremerich, Jens Stieltjes, Bram Weikert, Thomas Sauter, Alexander Walter Diagnostics (Basel) Article CT patterns of viral pneumonia are usually only qualitatively described in radiology reports. Artificial intelligence enables automated and reliable segmentation of lungs with chest CT. Based on this, the purpose of this study was to derive meaningful imaging biomarkers reflecting CT patterns of viral pneumonia and assess their potential to discriminate between healthy lungs and lungs with viral pneumonia. This study used non-enhanced and CT pulmonary angiograms (CTPAs) of healthy lungs and viral pneumonia (SARS-CoV-2, influenza A/B) identified by radiology reports and RT-PCR results. After deep learning segmentation of the lungs, histogram-based and threshold-based analyses of lung attenuation were performed and compared. The derived imaging biomarkers were correlated with parameters of clinical and biochemical severity (modified WHO severity scale; c-reactive protein). For non-enhanced CTs (n = 526), all imaging biomarkers significantly differed between healthy lungs and lungs with viral pneumonia (all p < 0.001), a finding that was not reproduced for CTPAs (n = 504). Standard deviation (histogram-derived) and relative high attenuation area [600–0 HU] (HU-thresholding) differed most. The strongest correlation with disease severity was found for absolute high attenuation area [600–0 HU] (r = 0.56, 95% CI = 0.46–0.64). Deep-learning segmentation-based histogram and HU threshold analysis could be deployed in chest CT evaluation for the differentiating of healthy lungs from AP lungs. MDPI 2021-04-21 /pmc/articles/PMC8143124/ /pubmed/33919094 http://dx.doi.org/10.3390/diagnostics11050738 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Romanov, Andrej
Bach, Michael
Yang, Shan
Franzeck, Fabian C.
Sommer, Gregor
Anastasopoulos, Constantin
Bremerich, Jens
Stieltjes, Bram
Weikert, Thomas
Sauter, Alexander Walter
Automated CT Lung Density Analysis of Viral Pneumonia and Healthy Lungs Using Deep Learning-Based Segmentation, Histograms and HU Thresholds
title Automated CT Lung Density Analysis of Viral Pneumonia and Healthy Lungs Using Deep Learning-Based Segmentation, Histograms and HU Thresholds
title_full Automated CT Lung Density Analysis of Viral Pneumonia and Healthy Lungs Using Deep Learning-Based Segmentation, Histograms and HU Thresholds
title_fullStr Automated CT Lung Density Analysis of Viral Pneumonia and Healthy Lungs Using Deep Learning-Based Segmentation, Histograms and HU Thresholds
title_full_unstemmed Automated CT Lung Density Analysis of Viral Pneumonia and Healthy Lungs Using Deep Learning-Based Segmentation, Histograms and HU Thresholds
title_short Automated CT Lung Density Analysis of Viral Pneumonia and Healthy Lungs Using Deep Learning-Based Segmentation, Histograms and HU Thresholds
title_sort automated ct lung density analysis of viral pneumonia and healthy lungs using deep learning-based segmentation, histograms and hu thresholds
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8143124/
https://www.ncbi.nlm.nih.gov/pubmed/33919094
http://dx.doi.org/10.3390/diagnostics11050738
work_keys_str_mv AT romanovandrej automatedctlungdensityanalysisofviralpneumoniaandhealthylungsusingdeeplearningbasedsegmentationhistogramsandhuthresholds
AT bachmichael automatedctlungdensityanalysisofviralpneumoniaandhealthylungsusingdeeplearningbasedsegmentationhistogramsandhuthresholds
AT yangshan automatedctlungdensityanalysisofviralpneumoniaandhealthylungsusingdeeplearningbasedsegmentationhistogramsandhuthresholds
AT franzeckfabianc automatedctlungdensityanalysisofviralpneumoniaandhealthylungsusingdeeplearningbasedsegmentationhistogramsandhuthresholds
AT sommergregor automatedctlungdensityanalysisofviralpneumoniaandhealthylungsusingdeeplearningbasedsegmentationhistogramsandhuthresholds
AT anastasopoulosconstantin automatedctlungdensityanalysisofviralpneumoniaandhealthylungsusingdeeplearningbasedsegmentationhistogramsandhuthresholds
AT bremerichjens automatedctlungdensityanalysisofviralpneumoniaandhealthylungsusingdeeplearningbasedsegmentationhistogramsandhuthresholds
AT stieltjesbram automatedctlungdensityanalysisofviralpneumoniaandhealthylungsusingdeeplearningbasedsegmentationhistogramsandhuthresholds
AT weikertthomas automatedctlungdensityanalysisofviralpneumoniaandhealthylungsusingdeeplearningbasedsegmentationhistogramsandhuthresholds
AT sauteralexanderwalter automatedctlungdensityanalysisofviralpneumoniaandhealthylungsusingdeeplearningbasedsegmentationhistogramsandhuthresholds