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

Autor: Keller H; Department of Radiation Oncology, University of Toronto, Toronto, ON M5T 1P5, Canada.; Techna Institute, University Health Network, Toronto, ON M5G 2C4, Canada., Shek T; Techna Institute, University Health Network, Toronto, ON M5G 2C4, Canada., Driscoll B; Techna Institute, University Health Network, Toronto, ON M5G 2C4, Canada., Xu Y; Department of Radiation Oncology, University of Toronto, Toronto, ON M5T 1P5, Canada., Nghiem B; Techna Institute, University Health Network, Toronto, ON M5G 2C4, Canada., Nehmeh S; Department of Radiology, Weill Cornell Medical College, New York, NY 10021, USA., Grkovski M; Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA., Schmidtlein CR; Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA., Budzevich M; Department of Cancer Physiology, H.L. Moffitt Cancer Center, Tampa, FL 33612, USA., Balagurunathan Y; Department of Cancer Physiology, H.L. Moffitt Cancer Center, Tampa, FL 33612, USA., Sunderland JJ; Department of Radiology, The University of Iowa, Iowa City, IA 52242, USA., Beichel RR; Department of Electrical and Computer Engineering, The University of Iowa, Iowa City, IA 52242, USA., Uribe C; Functional Imaging, BC Cancer Agency, Vancouver, BC V5Z 4E6, Canada.; Department of Radiology, The University of British Columbia, Vancouver, BC V5Z 1M9, Canada., Lee TY; Lawson Health Research Institute, London, ON N6A 4V2, Canada., Li F; Department of Medical Biophysics, University of Western Ontario, London, ON N6A 5C1, Canada., Jaffray DA; Department of Radiation Oncology, University of Toronto, Toronto, ON M5T 1P5, Canada.; Techna Institute, University Health Network, Toronto, ON M5G 2C4, Canada., Yeung I; Department of Radiation Oncology, University of Toronto, Toronto, ON M5T 1P5, Canada.; Techna Institute, University Health Network, Toronto, ON M5G 2C4, Canada.
Jazyk: angličtina
Zdroj: Tomography (Ann Arbor, Mich.) [Tomography] 2022 Apr 13; Vol. 8 (2), pp. 1113-1128. Date of Electronic Publication: 2022 Apr 13.
DOI: 10.3390/tomography8020091
Abstrakt: 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.
Databáze: MEDLINE