1. The Image Biomarker Standardization Initiative: standardized quantitative radiomics for highthroughput image-based phenotyping
- Author
-
Zwanenburg, A., Vallières, M., Abdalah, M. A., Aerts, H. J. W. L., Andrearczyk, V., Apte, A., Ashrafinia, S., Bakas, S., Beukinga, R. J., Boellaard, R., Bogowicz, M., Boldrini, L., Buvat, I., Cook, G. J. R., Davatzikos, C., Depeursinge, A., Desseroit, M.-C., Dinapoli, N., Viet Dinh, C., Echegaray, S., El Naqa, I., Fedorov, A. Y., Gatta, R., Gillies, R. J., Goh, V., Guckenberger, M., Götz, M., Min Ha, S., Hatt, M., Isensee, F., Lambin, P., Leger, S., Leijenaar, R. T. H., Lenkowicz, J., Lippert, F., Losnegård, A., Maier-Hein, K. H., Morin, O., Müller, H., Napel, S., Nioche, C., Orlhac, F., Pati, S., Pfaehler, E. A. G., Rahmim, A., Rao, A. U. K., Scherer, J., Musib Siddique, M., Sijtsema, N. M., Socarras Fernandez, J., Spezi, E., Steenbakkers, R. J. H. M., Tanadini-Lang, S., Thorwarth, D., (0000-0001-9550-9050) Troost, E. G. C., Upadhaya, T., Valentini, V., V. Van Dijk, L., Griethuysen, J., Velden, F. H. P., Whybra, P., (0000-0003-4261-4214) Richter, C., Löck, S., Zwanenburg, A., Vallières, M., Abdalah, M. A., Aerts, H. J. W. L., Andrearczyk, V., Apte, A., Ashrafinia, S., Bakas, S., Beukinga, R. J., Boellaard, R., Bogowicz, M., Boldrini, L., Buvat, I., Cook, G. J. R., Davatzikos, C., Depeursinge, A., Desseroit, M.-C., Dinapoli, N., Viet Dinh, C., Echegaray, S., El Naqa, I., Fedorov, A. Y., Gatta, R., Gillies, R. J., Goh, V., Guckenberger, M., Götz, M., Min Ha, S., Hatt, M., Isensee, F., Lambin, P., Leger, S., Leijenaar, R. T. H., Lenkowicz, J., Lippert, F., Losnegård, A., Maier-Hein, K. H., Morin, O., Müller, H., Napel, S., Nioche, C., Orlhac, F., Pati, S., Pfaehler, E. A. G., Rahmim, A., Rao, A. U. K., Scherer, J., Musib Siddique, M., Sijtsema, N. M., Socarras Fernandez, J., Spezi, E., Steenbakkers, R. J. H. M., Tanadini-Lang, S., Thorwarth, D., (0000-0001-9550-9050) Troost, E. G. C., Upadhaya, T., Valentini, V., V. Van Dijk, L., Griethuysen, J., Velden, F. H. P., Whybra, P., (0000-0003-4261-4214) Richter, C., and Löck, S.
- Abstract
Background: Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical usage. 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, fifteen 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: <3 matches: weak; 3-5: moderate; 6-9: strong; ≥10 very strong. In the final phase (III), a public dataset of multi-modality imaging (CT, 18F-FDG-PET and T1-weighted MR) 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 232/302 (76.8%; phase I) and 703/1075 (65.4%; phase II) features. At the final iteration, weak consensus remained for only 2/487 (0.4%; phase I) and 19/1347 (1.4%; phase II) features, and strong or better consensus was achieved for 463/487 (95.1%; phase I) and 1220/1347 (90.6%; phase II). Overall, 169/174 features were standardized in the first two phases. In the final validation phase (III), almost all standardized features could be excellently reproduced: CT:166/169 features; PET:164/169 and MRI: 164/169. Conclusion: A set of 169 radiomics features was standardized, which enables verification and calibration of different radiomics software.
- Published
- 2020