Next Article in Journal
Effect of Cardiac Phase on Cardiac Output Index Derived from Dynamic CT Myocardial Perfusion Imaging
Next Article in Special Issue
Effect of Inter-Reader Variability on Diffusion-Weighted MRI Apparent Diffusion Coefficient Measurements and Prediction of Pathologic Complete Response for Breast Cancer
Previous Article in Journal
Implications of the Harmonization of [18F]FDG-PET/CT Imaging for Response Assessment of Treatment in Radiotherapy Planning
Previous Article in Special Issue
An Anthropomorphic Digital Reference Object (DRO) for Simulation and Analysis of Breast DCE MRI Techniques
Article

Noise-Based Image Harmonization Significantly Increases Repeatability and Reproducibility of Radiomics Features in PET Images: A Phantom Study

1
Department of Radiation Oncology, University of Toronto, Toronto, ON M5T 1P5, Canada
2
Techna Institute, University Health Network, Toronto, ON M5G 2C4, Canada
3
Department of Radiology, Weill Cornell Medical College, New York, NY 10021, USA
4
Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
5
Department of Cancer Physiology, H.L. Moffitt Cancer Center, Tampa, FL 33612, USA
6
Department of Radiology, The University of Iowa, Iowa City, IA 52242, USA
7
Department of Electrical and Computer Engineering, The University of Iowa, Iowa City, IA 52242, USA
8
Functional Imaging, BC Cancer Agency, Vancouver, BC V5Z 4E6, Canada
9
Department of Radiology, The University of British Columbia, Vancouver, BC V5Z 1M9, Canada
10
Lawson Health Research Institute, London, ON N6A 4V2, Canada
11
Department of Medical Biophysics, University of Western Ontario, London, ON N6A 5C1, Canada
*
Author to whom correspondence should be addressed.
Academic Editors: Robert J. Nordstrom, Lubomir Hadjiiski, Chad Quarles and Jasper Nijkamp
Tomography 2022, 8(2), 1113-1128; https://doi.org/10.3390/tomography8020091
Received: 14 January 2022 / Revised: 4 April 2022 / Accepted: 8 April 2022 / Published: 13 April 2022
(This article belongs to the Special Issue Quantitative Imaging Network)
For multicenter clinical studies, characterizing the robustness of image-derived radiomics features is essential. Features calculated on PET images have been shown to be very sensitive to image noise. The purpose of this work was to investigate the efficacy of a relatively simple harmonization strategy on feature robustness and agreement. A purpose-built texture pattern phantom was scanned on 10 different PET scanners in 7 institutions with various different image acquisition and reconstruction protocols. An image harmonization technique based on equalizing a contrast-to-noise ratio was employed to generate a “harmonized” alongside a “standard” dataset for a reproducibility study. In addition, a repeatability study was performed with images from a single PET scanner of variable image noise, varying the binning time of the reconstruction. Feature agreement was measured using the intraclass correlation coefficient (ICC). In the repeatability study, 81/93 features had a lower ICC on the images with the highest image noise as compared to the images with the lowest image noise. Using the harmonized dataset significantly improved the feature agreement for five of the six investigated feature classes over the standard dataset. For three feature classes, high feature agreement corresponded with higher sensitivity to the different patterns, suggesting a way to select suitable features for predictive models. View Full-Text
Keywords: PET radiomics features; feature agreement; image harmonization; repeatability; reproducibility PET radiomics features; feature agreement; image harmonization; repeatability; reproducibility
Show Figures

Figure 1

MDPI and ACS Style

Keller, H.; Shek, T.; Driscoll, B.; Xu, Y.; Nghiem, B.; Nehmeh, S.; Grkovski, M.; Schmidtlein, C.R.; Budzevich, M.; Balagurunathan, Y.; Sunderland, J.J.; Beichel, R.R.; Uribe, C.; Lee, T.-Y.; Li, F.; Jaffray, D.A.; Yeung, I. Noise-Based Image Harmonization Significantly Increases Repeatability and Reproducibility of Radiomics Features in PET Images: A Phantom Study. Tomography 2022, 8, 1113-1128. https://doi.org/10.3390/tomography8020091

AMA Style

Keller H, Shek T, Driscoll B, Xu Y, Nghiem B, Nehmeh S, Grkovski M, Schmidtlein CR, Budzevich M, Balagurunathan Y, Sunderland JJ, Beichel RR, Uribe C, Lee T-Y, Li F, Jaffray DA, Yeung I. Noise-Based Image Harmonization Significantly Increases Repeatability and Reproducibility of Radiomics Features in PET Images: A Phantom Study. Tomography. 2022; 8(2):1113-1128. https://doi.org/10.3390/tomography8020091

Chicago/Turabian Style

Keller, Harald, Tina Shek, Brandon Driscoll, Yiwen Xu, Brian Nghiem, Sadek Nehmeh, Milan Grkovski, Charles R. Schmidtlein, Mikalai Budzevich, Yoganand Balagurunathan, John J. Sunderland, Reinhard R. Beichel, Carlos Uribe, Ting-Yim Lee, Fiona Li, David A. Jaffray, and Ivan Yeung. 2022. "Noise-Based Image Harmonization Significantly Increases Repeatability and Reproducibility of Radiomics Features in PET Images: A Phantom Study" Tomography 8, no. 2: 1113-1128. https://doi.org/10.3390/tomography8020091

Find Other Styles

Article Access Map by Country/Region

1
Back to TopTop