The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping - Inserm - Institut national de la santé et de la recherche médicale Accéder directement au contenu
Article Dans Une Revue Radiology Année : 2020

The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping

Alex Zwanenburg (1, 2, 3) , Martin Vallières (4) , Mahmoud A. Abdalah (5) , Hugo J.W. Aerts (6, 7) , Vincent Andrearczyk (8) , Aditya Apte (9) , Saeed Ashrafinia (10) , Spyridon Bakas (11) , Roelof J. Beukinga (12) , Ronald Boellaard (12) , Marta Bogowicz (13) , Luca Boldrini (14) , Irene Buvat (15) , Gary J. R. Cook (16) , Christos Davatzikos (11) , Adrien Depeursinge (8, 17) , Marie-Charlotte Desseroit (18) , Nicola Dinapoli (14) , Cuong Viet Dinh (19) , Sebastian Echegaray (20) , Issam El Naqa (4, 21) , Andriy y Fedorov (6) , Roberto Gatta (14) , Robert J Gillies (5) , Vicky Goh (16) , Michael Götz (3) , Matthias Guckenberger (13) , Sung Min Ha (11) , Mathieu Hatt (18) , Fabian Isensee (3) , Philippe Lambin (22) , Stefan Leger (1, 2, 3) , Ralph T.H. Leijenaar (22) , Jacopo Lenkowicz (14) , Fiona Lippert (23) , Are Losnegård (24) , Klaus H Maier-Hein (3) , Olivier Morin (25) , Henning Muller (8, 26) , Sandy Napel (20) , Christophe Nioche (15) , Fanny Orlhac (15) , Sarthak Pati (11) , Elisabeth A.G. Pfaehler (12) , Arman Rahmim (10, 27) , Arvind U.K. Rao (21) , Jonas Scherer (3) , Muhammad Musib Siddique (16) , Nanna M. Sijtsema (12) , Jairo Socarras Fernandez (23) , Emiliano Spezi (28, 29) , Roel J.H.M. Steenbakkers (12) , Stephanie Tanadini-Lang (13) , Daniela Thorwarth (23) , Esther G.C Troost (1, 2, 3) , Taman Upadhaya (18, 30) , Vincenzo Valentini (14) , Lisanne V. van Dijk (12) , Joost van Griethuysen (19, 22, 7, 6) , Floris H.P. van Velden (31) , Philip Whybra (28) , Christian Richter (1, 2, 3) , Steffen Löck (1, 2, 3)
Philippe Lambin
Philip Whybra
  • Fonction : Auteur

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 Online supplemental material is available for this article. See also the editorial by Kuhl and Truhn in this issue.

Domaines

Imagerie
Fichier principal
Vignette du fichier
Radiology_IBSI_Accepted_Version_IB.pdf (2.14 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

inserm-02954737 , version 1 (28-12-2020)

Identifiants

Citer

Alex Zwanenburg, Martin Vallières, Mahmoud A. Abdalah, Hugo J.W. Aerts, Vincent Andrearczyk, et al.. The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. Radiology, 2020, 295 (2), pp.328-338. ⟨10.1148/radiol.2020191145⟩. ⟨inserm-02954737⟩
371 Consultations
298 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More