Parameters Influencing PET Imaging Features: A Phantom Study with Irregular and Heterogeneous Synthetic Lesions

Aim. To evaluate reproducibility and stability of radiomic features as effects of the use of different volume segmentation methods and reconstruction settings. The potential of radiomics in really capturing the presence of heterogeneous tumor uptake and irregular shape was also investigated. Materia...

Full description

Bibliographic Details
Main Authors: Francesca Gallivanone, Matteo Interlenghi, Daniela D’Ambrosio, Giuseppe Trifirò, Isabella Castiglioni
Format: Article
Language:English
Published: Hindawi-Wiley 2018-01-01
Series:Contrast Media & Molecular Imaging
Online Access:http://dx.doi.org/10.1155/2018/5324517
id doaj-8358d49e800c454482f1a307b6c80696
record_format Article
spelling doaj-8358d49e800c454482f1a307b6c806962020-11-24T21:35:58ZengHindawi-WileyContrast Media & Molecular Imaging1555-43091555-43172018-01-01201810.1155/2018/53245175324517Parameters Influencing PET Imaging Features: A Phantom Study with Irregular and Heterogeneous Synthetic LesionsFrancesca Gallivanone0Matteo Interlenghi1Daniela D’Ambrosio2Giuseppe Trifirò3Isabella Castiglioni4Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), Milan, ItalyInstitute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), Milan, ItalyMedical Physics Unit, IRCCS Fondazione S. Maugeri, Pavia, ItalyNuclear Medicine Unit, IRCCS Fondazione S. Maugeri, Pavia, ItalyInstitute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), Milan, ItalyAim. To evaluate reproducibility and stability of radiomic features as effects of the use of different volume segmentation methods and reconstruction settings. The potential of radiomics in really capturing the presence of heterogeneous tumor uptake and irregular shape was also investigated. Materials and Methods. An anthropomorphic phantom miming real clinical situations including synthetic lesions with irregular shape and nonuniform radiotracer uptake was used. 18F-FDG PET/CT measurements of the phantom were performed including 38 lesions of different shape, size, lesion-to-background ratio, and radiotracer uptake distribution. Different reconstruction parameters and segmentation methods were considered. COVs were calculated to quantify feature variations over the different reconstruction settings. Friedman test was applied to the values of the radiomic features obtained for the considered segmentation approaches. Two sets of test-retest measurement were acquired and the pairwise intraclass correlation coefficient was calculated. Fifty-eight morphological and statistical features were extracted from the segmented lesion volumes. A Mann–Whitney test was used to evaluate significant differences among each feature when calculated from heterogeneous versus homogeneous uptake. The significance of each radiomic feature in terms of capturing heterogeneity was evaluated also by testing correlation with gold standard indexes of heterogeneity and sphericity. Results. The choice of the segmentation method has a strong impact on the stability of radiomic features (less than 20% can be considered stable features). Reconstruction affects the estimate of radiomic features (only 26% are stable). Thirty-one radiomic features (53%) resulted to be reproducible, 11 of them are able to discriminate heterogeneity. Among these, we found a subset of 3 radiomic features strongly correlated with GS heterogeneity index that can be suggested as good features for retrospective evaluations.http://dx.doi.org/10.1155/2018/5324517
collection DOAJ
language English
format Article
sources DOAJ
author Francesca Gallivanone
Matteo Interlenghi
Daniela D’Ambrosio
Giuseppe Trifirò
Isabella Castiglioni
spellingShingle Francesca Gallivanone
Matteo Interlenghi
Daniela D’Ambrosio
Giuseppe Trifirò
Isabella Castiglioni
Parameters Influencing PET Imaging Features: A Phantom Study with Irregular and Heterogeneous Synthetic Lesions
Contrast Media & Molecular Imaging
author_facet Francesca Gallivanone
Matteo Interlenghi
Daniela D’Ambrosio
Giuseppe Trifirò
Isabella Castiglioni
author_sort Francesca Gallivanone
title Parameters Influencing PET Imaging Features: A Phantom Study with Irregular and Heterogeneous Synthetic Lesions
title_short Parameters Influencing PET Imaging Features: A Phantom Study with Irregular and Heterogeneous Synthetic Lesions
title_full Parameters Influencing PET Imaging Features: A Phantom Study with Irregular and Heterogeneous Synthetic Lesions
title_fullStr Parameters Influencing PET Imaging Features: A Phantom Study with Irregular and Heterogeneous Synthetic Lesions
title_full_unstemmed Parameters Influencing PET Imaging Features: A Phantom Study with Irregular and Heterogeneous Synthetic Lesions
title_sort parameters influencing pet imaging features: a phantom study with irregular and heterogeneous synthetic lesions
publisher Hindawi-Wiley
series Contrast Media & Molecular Imaging
issn 1555-4309
1555-4317
publishDate 2018-01-01
description Aim. To evaluate reproducibility and stability of radiomic features as effects of the use of different volume segmentation methods and reconstruction settings. The potential of radiomics in really capturing the presence of heterogeneous tumor uptake and irregular shape was also investigated. Materials and Methods. An anthropomorphic phantom miming real clinical situations including synthetic lesions with irregular shape and nonuniform radiotracer uptake was used. 18F-FDG PET/CT measurements of the phantom were performed including 38 lesions of different shape, size, lesion-to-background ratio, and radiotracer uptake distribution. Different reconstruction parameters and segmentation methods were considered. COVs were calculated to quantify feature variations over the different reconstruction settings. Friedman test was applied to the values of the radiomic features obtained for the considered segmentation approaches. Two sets of test-retest measurement were acquired and the pairwise intraclass correlation coefficient was calculated. Fifty-eight morphological and statistical features were extracted from the segmented lesion volumes. A Mann–Whitney test was used to evaluate significant differences among each feature when calculated from heterogeneous versus homogeneous uptake. The significance of each radiomic feature in terms of capturing heterogeneity was evaluated also by testing correlation with gold standard indexes of heterogeneity and sphericity. Results. The choice of the segmentation method has a strong impact on the stability of radiomic features (less than 20% can be considered stable features). Reconstruction affects the estimate of radiomic features (only 26% are stable). Thirty-one radiomic features (53%) resulted to be reproducible, 11 of them are able to discriminate heterogeneity. Among these, we found a subset of 3 radiomic features strongly correlated with GS heterogeneity index that can be suggested as good features for retrospective evaluations.
url http://dx.doi.org/10.1155/2018/5324517
work_keys_str_mv AT francescagallivanone parametersinfluencingpetimagingfeaturesaphantomstudywithirregularandheterogeneoussyntheticlesions
AT matteointerlenghi parametersinfluencingpetimagingfeaturesaphantomstudywithirregularandheterogeneoussyntheticlesions
AT danieladambrosio parametersinfluencingpetimagingfeaturesaphantomstudywithirregularandheterogeneoussyntheticlesions
AT giuseppetrifiro parametersinfluencingpetimagingfeaturesaphantomstudywithirregularandheterogeneoussyntheticlesions
AT isabellacastiglioni parametersinfluencingpetimagingfeaturesaphantomstudywithirregularandheterogeneoussyntheticlesions
_version_ 1725943070731534336