Performance of Radiomics Features in the Quantification of Idiopathic Pulmonary Fibrosis from HRCT.
High resolution computed tomography
Idiopathic pulmonary fibrosis
Radiomics
Journal
Diagnostics (Basel, Switzerland)
ISSN: 2075-4418
Titre abrégé: Diagnostics (Basel)
Pays: Switzerland
ID NLM: 101658402
Informations de publication
Date de publication:
15 May 2020
15 May 2020
Historique:
received:
09
04
2020
revised:
10
05
2020
accepted:
13
05
2020
entrez:
21
5
2020
pubmed:
21
5
2020
medline:
21
5
2020
Statut:
epublish
Résumé
Our study assesses the diagnostic value of different features extracted from high resolution computed tomography (HRCT) images of patients with idiopathic pulmonary fibrosis. These features are investigated over a range of HRCT lung volume measurements (in Hounsfield Units) for which no prior study has yet been published. In particular, we provide a comparison of their diagnostic value at different Hounsfield Unit (HU) thresholds, including corresponding pulmonary functional tests. We consider thirty-two patients retrospectively for whom both HRCT examinations and spirometry tests were available. First, we analyse the HRCT histogram to extract quantitative lung fibrosis features. Next, we evaluate the relationship between pulmonary function and the HRCT features at selected HU thresholds, namely -200 HU, 0 HU, and +200 HU. We model the relationship using a Poisson approximation to identify the measure with the highest log-likelihood. Our Poisson models reveal no difference at the -200 and 0 HU thresholds. However, inferential conclusions change at the +200 HU threshold. Among the HRCT features considered, the percentage of normally attenuated lung at -200 HU shows the most significant diagnostic utility. The percentage of normally attenuated lung can be used together with qualitative HRCT assessment and pulmonary function tests to enhance the idiopathic pulmonary fibrosis (IPF) diagnostic process.
Sections du résumé
BACKGROUND
BACKGROUND
Our study assesses the diagnostic value of different features extracted from high resolution computed tomography (HRCT) images of patients with idiopathic pulmonary fibrosis. These features are investigated over a range of HRCT lung volume measurements (in Hounsfield Units) for which no prior study has yet been published. In particular, we provide a comparison of their diagnostic value at different Hounsfield Unit (HU) thresholds, including corresponding pulmonary functional tests.
METHODS
METHODS
We consider thirty-two patients retrospectively for whom both HRCT examinations and spirometry tests were available. First, we analyse the HRCT histogram to extract quantitative lung fibrosis features. Next, we evaluate the relationship between pulmonary function and the HRCT features at selected HU thresholds, namely -200 HU, 0 HU, and +200 HU. We model the relationship using a Poisson approximation to identify the measure with the highest log-likelihood.
RESULTS
RESULTS
Our Poisson models reveal no difference at the -200 and 0 HU thresholds. However, inferential conclusions change at the +200 HU threshold. Among the HRCT features considered, the percentage of normally attenuated lung at -200 HU shows the most significant diagnostic utility.
CONCLUSIONS
CONCLUSIONS
The percentage of normally attenuated lung can be used together with qualitative HRCT assessment and pulmonary function tests to enhance the idiopathic pulmonary fibrosis (IPF) diagnostic process.
Identifiants
pubmed: 32429182
pii: diagnostics10050306
doi: 10.3390/diagnostics10050306
pmc: PMC7277964
pii:
doi:
Types de publication
Journal Article
Langues
eng
Déclaration de conflit d'intérêts
The authors declare no conflict of interest.
Références
Semin Respir Crit Care Med. 2016 Jun;37(3):358-67
pubmed: 27231860
Am J Respir Crit Care Med. 2000 Feb;161(2 Pt 1):646-64
pubmed: 10673212
Comput Biol Med. 2018 Nov 1;102:1-15
pubmed: 30219733
Multidiscip Respir Med. 2018 Dec 1;13:43
pubmed: 30519466
Artif Intell Med. 2019 Mar;94:67-78
pubmed: 30871684
Lancet Respir Med. 2018 Feb;6(2):86-88
pubmed: 29241977
Ann Intern Med. 2012 May 15;156(10):684-91
pubmed: 22586007
Med Phys. 2009 Oct;36(10):4592-9
pubmed: 19928090
Clin Transl Imaging. 2018;6(5):411-413
pubmed: 30416989
Acad Radiol. 2015 Jan;22(1):70-80
pubmed: 25262954
Respir Res. 2017 Mar 7;18(1):45
pubmed: 28264721
Radiology. 2016 Feb;278(2):563-77
pubmed: 26579733
PLoS One. 2016 Mar 01;11(3):e0149240
pubmed: 26930658
J Thorac Imaging. 2020 Mar;35(2):115-122
pubmed: 31913257
Eur J Radiol. 2019 Jul;116:144-149
pubmed: 31153556
Comput Methods Programs Biomed. 2013 Mar;109(3):260-8
pubmed: 23146420
Am J Respir Crit Care Med. 2011 Mar 15;183(6):788-824
pubmed: 21471066
PLoS One. 2016 Mar 31;11(3):e0152505
pubmed: 27031615
BMC Pulm Med. 2015 Jul 24;15:74
pubmed: 26202767
Respir Res. 2013;14 Suppl 1:S3
pubmed: 23734841
Eur J Radiol. 2017 Jan;86:297-307
pubmed: 27638103
Radiother Oncol. 2011 Jan;98(1):117-25
pubmed: 21074882
Curr Probl Diagn Radiol. 2019 Oct 31;:
pubmed: 31761413