dc.contributor.author
Michallek, Florian
dc.contributor.author
Genske, Ulrich
dc.contributor.author
Niehues, Stefan Markus
dc.contributor.author
Hamm, Bernd
dc.contributor.author
Jahnke, Paul
dc.date.accessioned
2024-08-20T09:15:48Z
dc.date.available
2024-08-20T09:15:48Z
dc.identifier.uri
https://refubium.fu-berlin.de/handle/fub188/44664
dc.identifier.uri
http://dx.doi.org/10.17169/refubium-44375
dc.description.abstract
Objectives: To compare image quality of deep learning reconstruction (AiCE) for radiomics feature extraction with filtered back projection (FBP), hybrid iterative reconstruction (AIDR 3D), and model-based iterative reconstruction (FIRST).
Methods: Effects of image reconstruction on radiomics features were investigated using a phantom that realistically mimicked a 65-year-old patient's abdomen with hepatic metastases. The phantom was scanned at 18 doses from 0.2 to 4 mGy, with 20 repeated scans per dose. Images were reconstructed with FBP, AIDR 3D, FIRST, and AiCE. Ninety-three radiomics features were extracted from 24 regions of interest, which were evenly distributed across three tissue classes: normal liver, metastatic core, and metastatic rim. Features were analyzed in terms of their consistent characterization of tissues within the same image (intraclass correlation coefficient >= 0.75), discriminative power (Kruskal-Wallis test p value < 0.05), and repeatability (overall concordance correlation coefficient >= 0.75).
Results: The median fraction of consistent features across all doses was 6%, 8%, 6%, and 22% with FBP, AIDR 3D, FIRST, and AiCE, respectively. Adequate discriminative power was achieved by 48%, 82%, 84%, and 92% of features, and 52%, 20%, 17%, and 39% of features were repeatable, respectively. Only 5% of features combined consistency, discriminative power, and repeatability with FBP, AIDR 3D, and FIRST versus 13% with AiCE at doses above 1 mGy and 17% at doses >= 3 mGy. AiCE was the only reconstruction technique that enabled extraction of higher-order features.
Conclusions: AiCE more than doubled the yield of radiomics features at doses typically used clinically. Inconsistent tissue characterization within CT images contributes significantly to the poor stability of radiomics features.
en
dc.rights.uri
https://creativecommons.org/licenses/by/4.0/
dc.subject
X-ray computed
en
dc.subject
Phantoms, imaging
en
dc.subject
Liver neoplasms
en
dc.subject
Reproducibility of results
en
dc.subject.ddc
600 Technik, Medizin, angewandte Wissenschaften::610 Medizin und Gesundheit::610 Medizin und Gesundheit
dc.title
Deep learning reconstruction improves radiomics feature stability and discriminative power in abdominal CT imaging: a phantom study
dc.type
Wissenschaftlicher Artikel
dcterms.bibliographicCitation.doi
10.1007/s00330-022-08592-y
dcterms.bibliographicCitation.journaltitle
European Radiology
dcterms.bibliographicCitation.number
7
dcterms.bibliographicCitation.originalpublishername
Springer Nature
dcterms.bibliographicCitation.pagestart
4587
dcterms.bibliographicCitation.pageend
4595
dcterms.bibliographicCitation.volume
32
refubium.affiliation
Charité - Universitätsmedizin Berlin
refubium.funding
Springer Nature DEAL
refubium.resourceType.isindependentpub
no
dcterms.accessRights.openaire
open access
dcterms.bibliographicCitation.pmid
35174400
dcterms.isPartOf.eissn
1432-1084