Lack of repeatability of radiomic features derived from PET scans: Results from a 18 F‐DCFPyL test–retest cohort
The Prostate · 2023
DOI: 10.1002/pros.24483 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Prostate, 2023. Verfasst von Rudolf A Werner und 18 weiteren Autor:innen. Beteiligte Einrichtung: Department of Nuclear Medicine, University Hospital Würzburg, Würzburg, Germany. Hauptthemen laut MEDLINE: Positron Emission Tomography Computed Tomography, Prostatic Neoplasms. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Objectives
PET‐based radiomic metrics are increasingly utilized as predictive image biomarkers. However, the repeatability of radiomic features on PET has not been assessed in a test–retest setting. The prostate‐specific membrane antigen‐targeted compound 18 F‐DCFPyL is a high‐affinity, high‐contrast PET agent that we utilized in a test‐retest cohort of men with metastatic prostate cancer (PC).
Methods
Data of 21 patients enrolled in a prospective clinical trial with histologically proven PC underwent two 18 F‐DCFPyL PET scans within 7 days, using identical acquisition and reconstruction parameters. Sites of disease were segmented and a set of 29 different radiomic parameters were assessed on both scans. We determined repeatability of quantification by using Pearson's correlations, within‐subject coefficient of variation (wCOV), and Bland–Altman analysis.
Results
In total, 230 lesions (177 bone, 38 lymph nodes, 15 others) were assessed on both scans. For all investigated radiomic features, a broad range of inter‐scan correlation was found ( r , 0.07–0.95), with acceptable reproducibility for entropy and homogeneity (wCOV, 16.0% and 12.7%, respectively). On Bland–Altman analysis, no systematic increase or decrease between the scans was observed for either parameter (±1.96 SD: 1.07/−1.30, 0.23/−0.18, respectively). The remaining 27 tested radiomic metrics, however, achieved unacceptable high wCOV (≥21.7%).
Conclusion
Many common radiomic features derived from a test–retest PET study had poor repeatability. Only Entropy and homogeneity achieved good repeatability, supporting the notion that those image biomarkers may be incorporated in future clinical trials. Those radiomic features based on high frequency aspects of images appear to lack the repeatability on PET to justify further study.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Nuclear Medicine, University Hospital Würzburg, Würzburg, Germany.
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
- Department of Nuclear Medicine, University Hospital Bonn, Bonn, Germany.
- Nuclear Medicine, Medical Faculty, University of Augsburg, Augsburg, Germany.
- Department of Nuclear Medicine, Hannover Medical School, Hannover, Germany.
- Department of Urology, The James Buchanan Brady Urological Institute, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
ORCID-Profile: Thorsten Derlin, Mark C Markowski, Steven P Rowe, Ralph A Bundschuh
Zitieren
APA
Werner, R. A., Habacha, B., Lütje, S., Bundschuh, L., Kosmala, A., Essler, M., Derlin, T., Higuchi, T., Lapa, C., Buck, A. K., Pienta, K. J., Lodge, M. A., Eisenberger, M. A., Markowski, M. C., Pomper, M. G., Gorin, M. A., Frey, E. C., Rowe, S. P., & Bundschuh, R. A. (2023). Lack of repeatability of radiomic features derived from PET scans: Results from a 18 F‐DCFPyL test–retest cohort. The Prostate. https://doi.org/10.1002/pros.24483
Vancouver
Werner RA, Habacha B, Lütje S, Bundschuh L, Kosmala A, Essler M, et al. Lack of repeatability of radiomic features derived from PET scans: Results from a 18 F‐DCFPyL test–retest cohort. The Prostate. 2023. doi:10.1002/pros.24483
BibTeX
@article{Werner2023,
author = {Werner, Rudolf A and Habacha, Bilêl and Lütje, Susanne and Bundschuh, Lena and Kosmala, Alekandser and Essler, Markus and Derlin, Thorsten and Higuchi, Takahiro and Lapa, Constantin and Buck, Andreas K and Pienta, Kenneth J and Lodge, Martin A and Eisenberger, Mario A and Markowski, Mark C and Pomper, Martin G and Gorin, Michael A and Frey, Eric C and Rowe, Steven P and Bundschuh, Ralph A},
title = {Lack of repeatability of radiomic features derived from PET scans: Results from a 18 F‐DCFPyL test–retest cohort},
journal = {The Prostate},
year = {2023},
doi = {10.1002/pros.24483}
}
EUVIMED