Radiomic Features From Diffusion-Weighted MRI of Retroperitoneal Soft-Tissue Sarcomas Are Repeatable and Exhibit Change After Radiotherapy.
DWI (diffusion weighted imaging)
Intraclass correlation coefficient (ICC)
apparent diffusion coefficient (ADC)
radiomics
radiotherapy
repeatability
soft-tissue sarcoma
Journal
Frontiers in oncology
ISSN: 2234-943X
Titre abrégé: Front Oncol
Pays: Switzerland
ID NLM: 101568867
Informations de publication
Date de publication:
2022
2022
Historique:
received:
18
03
2022
accepted:
17
06
2022
entrez:
4
8
2022
pubmed:
5
8
2022
medline:
5
8
2022
Statut:
epublish
Résumé
Size-based assessments are inaccurate indicators of tumor response in soft-tissue sarcoma (STS), motivating the requirement for new response imaging biomarkers for this rare and heterogeneous disease. In this study, we assess the test-retest repeatability of radiomic features from MR diffusion-weighted imaging (DWI) and derived maps of apparent diffusion coefficient (ADC) in retroperitoneal STS and compare baseline repeatability with changes in radiomic features following radiotherapy (RT). Thirty patients with retroperitoneal STS received an MR examination prior to treatment, of whom 23/30 were investigated in our repeatability analysis having received repeat baseline examinations and 14/30 patients were investigated in our post-treatment analysis having received an MR examination after completing pre-operative RT. One hundred and seven radiomic features were extracted from the full manually delineated tumor region using PyRadiomics. Test-retest repeatability was assessed using an intraclass correlation coefficient (baseline ICC), and post-radiotherapy variance analysis (post-RT-IMS) was used to compare the change in radiomic feature value to baseline repeatability. For the ADC maps and DWI images, 101 and 102 features demonstrated good baseline repeatability (baseline ICC > 0.85), respectively. Forty-three and 2 features demonstrated both good baseline repeatability and a high post-RT-IMS (>0.85), respectively. Pearson correlation between the baseline ICC and post-RT-IMS was weak (0.432 and 0.133, respectively). The ADC-based radiomic analysis shows better test-retest repeatability compared with features derived from DWI images in STS, and some of these features are sensitive to post-treatment change. However, good repeatability at baseline does not imply sensitivity to post-treatment change.
Sections du résumé
Background
UNASSIGNED
Size-based assessments are inaccurate indicators of tumor response in soft-tissue sarcoma (STS), motivating the requirement for new response imaging biomarkers for this rare and heterogeneous disease. In this study, we assess the test-retest repeatability of radiomic features from MR diffusion-weighted imaging (DWI) and derived maps of apparent diffusion coefficient (ADC) in retroperitoneal STS and compare baseline repeatability with changes in radiomic features following radiotherapy (RT).
Materials and Methods
UNASSIGNED
Thirty patients with retroperitoneal STS received an MR examination prior to treatment, of whom 23/30 were investigated in our repeatability analysis having received repeat baseline examinations and 14/30 patients were investigated in our post-treatment analysis having received an MR examination after completing pre-operative RT. One hundred and seven radiomic features were extracted from the full manually delineated tumor region using PyRadiomics. Test-retest repeatability was assessed using an intraclass correlation coefficient (baseline ICC), and post-radiotherapy variance analysis (post-RT-IMS) was used to compare the change in radiomic feature value to baseline repeatability.
Results
UNASSIGNED
For the ADC maps and DWI images, 101 and 102 features demonstrated good baseline repeatability (baseline ICC > 0.85), respectively. Forty-three and 2 features demonstrated both good baseline repeatability and a high post-RT-IMS (>0.85), respectively. Pearson correlation between the baseline ICC and post-RT-IMS was weak (0.432 and 0.133, respectively).
Conclusions
UNASSIGNED
The ADC-based radiomic analysis shows better test-retest repeatability compared with features derived from DWI images in STS, and some of these features are sensitive to post-treatment change. However, good repeatability at baseline does not imply sensitivity to post-treatment change.
Identifiants
pubmed: 35924167
doi: 10.3389/fonc.2022.899180
pmc: PMC9343063
doi:
Types de publication
Journal Article
Langues
eng
Pagination
899180Informations de copyright
Copyright © 2022 Thrussell, Winfield, Orton, Miah, Zaidi, Arthur, Thway, Strauss, Collins, Koh, Oelfke, Huang, O’Connor, Messiou and Blackledge.
Déclaration de conflit d'intérêts
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Références
Sci Rep. 2021 Jul 27;11(1):15276
pubmed: 34315971
Eur J Surg Oncol. 2010 Jul;36(7):678-83
pubmed: 20547446
Nat Rev Clin Oncol. 2017 Mar;14(3):169-186
pubmed: 27725679
Crit Rev Oncol Hematol. 2019 Jun;138:44-50
pubmed: 31092384
Phys Med. 2019 May;61:44-51
pubmed: 31151578
Tomography. 2016 Dec;2(4):361-365
pubmed: 30042967
Nat Methods. 2020 Mar;17(3):261-272
pubmed: 32015543
Eur J Cancer. 2016 Mar;56:37-44
pubmed: 26802529
Vis Comput Ind Biomed Art. 2019 Nov 20;2(1):19
pubmed: 32240418
Int J Radiat Oncol Biol Phys. 2018 Nov 15;102(4):1143-1158
pubmed: 30170872
Int J Hyperthermia. 2009 Jun;25(4):289-98
pubmed: 19670096
Sci Rep. 2019 Jul 1;9(1):9441
pubmed: 31263116
Semin Radiat Oncol. 2014 Jul;24(3):218-26
pubmed: 24931097
Radiology. 2009 May;251(2):447-56
pubmed: 19261927
Phys Med. 2018 Jun;50:26-36
pubmed: 29891091
N Engl J Med. 2005 Aug 18;353(7):701-11
pubmed: 16107623
J Digit Imaging. 2018 Jun;31(3):290-303
pubmed: 29181613
Eur J Cancer. 2009 Jan;45(2):228-47
pubmed: 19097774
Contrast Media Mol Imaging. 2018 Jul 30;2018:1729071
pubmed: 30154684
AJR Am J Roentgenol. 2007 Jun;188(6):1622-35
pubmed: 17515386
Front Oncol. 2019 Apr 25;9:280
pubmed: 31106141
Ann Surg Oncol. 2010 Oct;17(10):2578-84
pubmed: 20556523
Nature. 2020 Sep;585(7825):357-362
pubmed: 32939066
J Clin Epidemiol. 2008 Oct;61(10):978-82
pubmed: 18468854
Front Oncol. 2020 Sep 23;10:564852
pubmed: 33072594
Front Oncol. 2019 Oct 10;9:941
pubmed: 31649872
Comput Methods Programs Biomed. 2012 Jan;105(1):50-60
pubmed: 20864206
Phys Med Biol. 2016 Jul 7;61(13):R150-66
pubmed: 27269645
J Digit Imaging. 2018 Dec;31(6):879-894
pubmed: 29725965
Cancer Res. 2017 Nov 1;77(21):e104-e107
pubmed: 29092951
Radiother Oncol. 2010 Dec;97(3):404-7
pubmed: 21040989
J Magn Reson Imaging. 2018 Mar;47(3):829-840
pubmed: 28653477
Phys Med Biol. 2020 Aug 27;65(17):175006
pubmed: 32554891
Sci Rep. 2019 Mar 18;9(1):4800
pubmed: 30886309
Front Neuroinform. 2013 Dec 30;7:45
pubmed: 24416015