| Literature DB >> 32154773 |
Alex Zwanenburg1, Martin Vallières1, Mahmoud A Abdalah1, Hugo J W L Aerts1, Vincent Andrearczyk1, Aditya Apte1, Saeed Ashrafinia1, Spyridon Bakas1, Roelof J Beukinga1, Ronald Boellaard1, Marta Bogowicz1, Luca Boldrini1, Irène Buvat1, Gary J R Cook1, Christos Davatzikos1, Adrien Depeursinge1, Marie-Charlotte Desseroit1, Nicola Dinapoli1, Cuong Viet Dinh1, Sebastian Echegaray1, Issam El Naqa1, Andriy Y Fedorov1, Roberto Gatta1, Robert J Gillies1, Vicky Goh1, Michael Götz1, Matthias Guckenberger1, Sung Min Ha1, Mathieu Hatt1, Fabian Isensee1, Philippe Lambin1, Stefan Leger1, Ralph T H Leijenaar1, Jacopo Lenkowicz1, Fiona Lippert1, Are Losnegård1, Klaus H Maier-Hein1, Olivier Morin1, Henning Müller1, Sandy Napel1, Christophe Nioche1, Fanny Orlhac1, Sarthak Pati1, Elisabeth A G Pfaehler1, Arman Rahmim1, Arvind U K Rao1, Jonas Scherer1, Muhammad Musib Siddique1, Nanna M Sijtsema1, Jairo Socarras Fernandez1, Emiliano Spezi1, Roel J H M Steenbakkers1, Stephanie Tanadini-Lang1, Daniela Thorwarth1, Esther G C Troost1, Taman Upadhaya1, Vincenzo Valentini1, Lisanne V van Dijk1, Joost van Griethuysen1, Floris H P van Velden1, Philip Whybra1, Christian Richter1, Steffen Löck1.
Abstract
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 Online supplemental material is available for this article. See also the editorial by Kuhl and Truhn in this issue.Entities:
Mesh：
Substances：
Year: 2020 PMID： 32154773 PMCID： PMC7193906 DOI： 10.1148/radiol.2020191145
Source DB: PubMed Journal: Radiology ISSN： 0033-8419 Impact factor: 29.146