The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping.
Biomarkers
/ analysis
Calibration
Fluorodeoxyglucose F18
Humans
Image Processing, Computer-Assisted
/ standards
Lung Neoplasms
/ diagnostic imaging
Magnetic Resonance Imaging
Phantoms, Imaging
Phenotype
Positron-Emission Tomography
Radiopharmaceuticals
Reproducibility of Results
Sarcoma
/ diagnostic imaging
Software
Tomography, X-Ray Computed
Journal
Radiology
ISSN: 1527-1315
Titre abrégé: Radiology
Pays: United States
ID NLM: 0401260
Informations de publication
Date de publication:
05 2020
05 2020
Historique:
pubmed:
11
3
2020
medline:
28
7
2020
entrez:
11
3
2020
Statut:
ppublish
Résumé
Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020
Identifiants
pubmed: 32154773
doi: 10.1148/radiol.2020191145
pmc: PMC7193906
doi:
Substances chimiques
Biomarkers
0
Radiopharmaceuticals
0
Fluorodeoxyglucose F18
0Z5B2CJX4D
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
328-338Subventions
Organisme : NCI NIH HHS
ID : U24 CA180918
Pays : United States
Organisme : Department of Health
ID : 09/22/49
Pays : United Kingdom
Organisme : NCI NIH HHS
ID : U01 CA187947
Pays : United States
Organisme : NCI NIH HHS
ID : P30 CA008748
Pays : United States
Organisme : Wellcome Trust
ID : WT203148/Z/16/Z
Pays : United Kingdom
Organisme : NIH HHS
ID : S10 OD023495
Pays : United States
Organisme : NINDS NIH HHS
ID : R01 NS042645
Pays : United States
Organisme : NCI NIH HHS
ID : U24 CA189523
Pays : United States
Commentaires et corrections
Type : CommentIn
Références
Radiology. 2019 Dec;293(3):583-591
pubmed: 31573400
Radiology. 2016 Feb;278(2):563-77
pubmed: 26579733
Tomography. 2016 Dec;2(4):361-365
pubmed: 30042967
Nat Rev Clin Oncol. 2011 Aug 23;8(10):587-96
pubmed: 21862978
Eur J Nucl Med Mol Imaging. 2017 Jan;44(1):151-165
pubmed: 27271051
J Nucl Med. 2014 Mar;55(3):414-22
pubmed: 24549286
Int J Radiat Oncol Biol Phys. 2018 Nov 15;102(4):1074-1082
pubmed: 30170101
Nat Commun. 2019 Feb 15;10(1):764
pubmed: 30770825
Radiology. 2019 Aug;292(2):365-373
pubmed: 31210613
Eur J Nucl Med Mol Imaging. 2019 Dec;46(13):2638-2655
pubmed: 31240330
J Clin Epidemiol. 2014 Apr;67(4):401-9
pubmed: 24581294
Sci Rep. 2017 Mar 31;7:45639
pubmed: 28361913
Nat Rev Clin Oncol. 2017 Dec;14(12):749-762
pubmed: 28975929
J Digit Imaging. 2013 Dec;26(6):1045-57
pubmed: 23884657
J Med Imaging (Bellingham). 2018 Oct;5(4):044505
pubmed: 30840747
Radiology. 2018 Aug;288(2):407-415
pubmed: 29688159
Br J Surg. 2015 Feb;102(3):148-58
pubmed: 25627261
Radiother Oncol. 2017 Dec;125(3):385-391
pubmed: 29122358
Nat Rev Clin Oncol. 2017 Mar;14(3):169-186
pubmed: 27725679
Abdom Radiol (NY). 2019 Jun;44(6):1960-1984
pubmed: 31049614
J Chiropr Med. 2016 Jun;15(2):155-63
pubmed: 27330520
Radiology. 2019 Apr;291(1):53-59
pubmed: 30694160
Lancet Oncol. 2018 Sep;19(9):1180-1191
pubmed: 30120041
Psychol Bull. 1979 Mar;86(2):420-8
pubmed: 18839484
IEEE Rev Biomed Eng. 2018;11:97-111
pubmed: 29994606
Eur J Nucl Med Mol Imaging. 2019 Dec;46(13):2656-2672
pubmed: 31214791
Phys Med Biol. 2015 Jul 21;60(14):5471-96
pubmed: 26119045
Int J Radiat Oncol Biol Phys. 2018 Nov 15;102(4):1143-1158
pubmed: 30170872
Nat Commun. 2014 Jun 03;5:4006
pubmed: 24892406
Radiother Oncol. 2019 Jan;130:2-9
pubmed: 30416044
Med Image Anal. 2014 Jan;18(1):176-96
pubmed: 24231667
Tomography. 2016 Dec;2(4):430-437
pubmed: 28149958