Radiomic features as biomarkers of soft tissue paediatric sarcomas: preliminary results of a PET/MR study.
PET/MR
oncology
pediatric soft tissue sarcomas
radiomics
Journal
Radiology and oncology
ISSN: 1581-3207
Titre abrégé: Radiol Oncol
Pays: Poland
ID NLM: 9317213
Informations de publication
Date de publication:
28 03 2022
28 03 2022
Historique:
received:
19
11
2021
accepted:
04
03
2022
pubmed:
29
3
2022
medline:
20
5
2022
entrez:
28
3
2022
Statut:
epublish
Résumé
Pediatric soft tissue sarcomas are rare tumors with rhabdomyosarcoma being the most frequent histotype. Diagnostic imaging plays a significant role in the evaluation of this type of tumors. Thus, aim of this study was to assess the prognostic and diagnostic value of radiomic features extracted from axial T2w images of the primary lesion in children with soft tissue sarcomas examined by PET/MR for staging. Using an open source software, each lesion was segmented and 33 radiomic features then extracted. Factor and logistic regression analyses were applied to select highly correlating features and evaluate their prognostic role, respectively. Differences in radiomic, demographics, metabolic, and laboratory variables according to tumor grade and histotype were investigated by the Students' and Chi-square tests. In case of differences the diagnostic value of the variable/s was assessed by receiver operating curves. Eighteen children (11 female; mean age 7.8 ± 4.6-year-old) matched the inclusion criteria. The factor analysis allowed the selection of five highly correlating features which, according to regression analysis, did not influence the outcome (p > 0.05, each). The feature lmc1 was significantly higher in low grade lesions (p = 0.045) and showed 70.4% accuracy in classifying high grade tumors while the feature variance was significantly lower in rhabdomyosarcomas (p = 0.008) and showed 83.3% accuracy for this histotype. In conclusion, our preliminary results suggest that specific radiomic features may act as biomarkers of pediatric soft tissue sarcoma grade and histotype.
Sections du résumé
BACKGROUND
Pediatric soft tissue sarcomas are rare tumors with rhabdomyosarcoma being the most frequent histotype. Diagnostic imaging plays a significant role in the evaluation of this type of tumors. Thus, aim of this study was to assess the prognostic and diagnostic value of radiomic features extracted from axial T2w images of the primary lesion in children with soft tissue sarcomas examined by PET/MR for staging.
METHODS
Using an open source software, each lesion was segmented and 33 radiomic features then extracted. Factor and logistic regression analyses were applied to select highly correlating features and evaluate their prognostic role, respectively. Differences in radiomic, demographics, metabolic, and laboratory variables according to tumor grade and histotype were investigated by the Students' and Chi-square tests. In case of differences the diagnostic value of the variable/s was assessed by receiver operating curves.
RESULTS
Eighteen children (11 female; mean age 7.8 ± 4.6-year-old) matched the inclusion criteria. The factor analysis allowed the selection of five highly correlating features which, according to regression analysis, did not influence the outcome (p > 0.05, each). The feature lmc1 was significantly higher in low grade lesions (p = 0.045) and showed 70.4% accuracy in classifying high grade tumors while the feature variance was significantly lower in rhabdomyosarcomas (p = 0.008) and showed 83.3% accuracy for this histotype.
CONCLUSIONS
In conclusion, our preliminary results suggest that specific radiomic features may act as biomarkers of pediatric soft tissue sarcoma grade and histotype.
Identifiants
pubmed: 35344641
pii: raon-2022-0013
doi: 10.2478/raon-2022-0013
pmc: PMC9122292
doi:
Substances chimiques
Biomarkers
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
138-141Informations de copyright
© 2022 Chiara Giraudo, Giulia Fichera, Roberto Stramare, Gianni Bisogno, Raffaella Motta, Laura Evangelista, Diego Cecchin, Pietro Zucchetta, published by Sciendo.
Références
Van Ewijk R, Schoot RA, Sparber-Sauer M, Ter Horst SAJ, Jehanno N, Borgwardt L, et al. European guideline for imaging in paediatric and adolescent rhabdomyosarcoma - joint statement by the European Paediatric Soft Tissue Sarcoma Study Group, the Cooperative Weichteilsarkom Studiengruppe and the Oncology Task Force of the European Society of Paediatric Radiology. Pediatr Radiol 2021; 51: 1940-51. doi: 10.1007/s00247-021-05081-0
doi: 10.1007/s00247-021-05081-0
Ferrari A, van Noesel MM, Brennan B, Zanetti I, Corradini N, Casanova M, et al. Paediatric non-rhabdomyosarcoma soft tissue sarcomas: the prospective NRSTS 2005 study by the European Pediatric Soft Tissue Sarcoma Study Group (EpSSG). Lancet Child Adolesc Health 2021; 8: 546-58. doi: 10.1016/S2352-4642(21)00159-0
doi: 10.1016/S2352-4642(21)00159-0
Orsatti G, Zucchetta P, Varotto A, Crimì F, Weber M, Cecchin D, et al. Volumetric histograms-based analysis of apparent diffusion coefficients and standard uptake values for the assessment of pediatric sarcoma at staging: preliminary results of a PET/MRI study. Radiol Med 2021; 126: 878-85. doi: 10.1007/s11547-021-01340-0
doi: 10.1007/s11547-021-01340-0
Corino V, Montin E, Messina A, Casali PG, Gronchi A, Marchianò A, et al. Radiomic analysis of soft tissues sarcomas can distinguish intermediate from high-grade lesions. J Magn Reson Imaging 2018; 47: 829-40. doi: 10.1002/jmri.25791
doi: 10.1002/jmri.25791
Crombé A, Fadli D, Buy X, Italiano A, Saut O, Kind M. High-grade soft-tissue sarcomas: Can optimizing dynamic contrast-enhanced MRI postprocessing improve prognostic radiomics models? J Magn Reson Imaging 2020; 52: 282-97. doi: 10.1002/jmri.27040
doi: 10.1002/jmri.27040
Cassarino G, Evangelista L, Giraudo C, Capizzi A, Carretta G, Zucchetta P, et al. 18F-FDG PET/MRI in adult sarcomas. Clin Translational Imag 2020; 8: 405-12. doi: 10.1007/s40336-020-00395-9
doi: 10.1007/s40336-020-00395-9
Cicchetti DV. Guidelines, criteria, and rules of thumb for evaluating normed and standardized assessment instruments in psychology. Psychol Assess 1994; 6: 284-90. doi: 10.1037/1040-3590.6.4.284
doi: 10.1037/1040-3590.6.4.284
Giraudo C, Karanikas G, Weber M, Raderer M, Jaeger U, Simonitsch-Klupp I, et al. Correlation between glycolytic activity on [18F]-FDG-PET and cell density on diffusion-weighted MRI in lymphoma at staging. J Magn Reson Imaging 2018; 47: 1217-26. doi: 10.1002/jmri.25884
doi: 10.1002/jmri.25884
Spraker MB, Wootton LS, Hippe DS, Ball KC, Peeken JC, Macomber MW, et al. MRI Radiomic features are independently associated with overall survival in soft tissue sarcoma. Adv Radiat Oncol 2019; 4: 413-21. doi: 10.1016/j.adro.2019.02.003
doi: 10.1016/j.adro.2019.02.003
Cook GJR, Azad G, Owczarczyk K, Siddique M, Goh V. Challenges and promises of PET radiomics. Int J Radiat Oncol Biol Phys 2018; 102: 1083-89. doi: 10.1016/j.ijrobp.2017.12.268
doi: 10.1016/j.ijrobp.2017.12.268