Lung lesion detectability on images obtained from decimated and CNN-based denoised [18F]-FDG PET/CT scan: an observer-based study for lung-cancer screening
European Journal of Nuclear Medicine and Molecular Imaging · 2025
DOI: 10.1007/s00259-025-07259-2 ↗Kurz gefasst
Evaluationsstudie in der Zeitschrift European Journal of Nuclear Medicine and Molecular Imaging, 2025. Verfasst von Daphné Faist und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Nuclear Medicine and Molecular Imaging, Lausanne University Hospital and University of Lausanne, Rue du Bugnon 21, CH- 1011, Lausanne, …. Hauptthemen laut MEDLINE: Lung Neoplasms, Early Detection of Cancer, Positron Emission Tomography Computed Tomography, Convolutional Neural Networks. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Foundations Solis and CHUV, University of Lausanne.
Abstract (Originalsprache)
Purpose
To assess feasibility of lung cancer screening, we analysed lung lesion detectability simulating low-dose and convolutional neural network (CNN) denoised [ 18 F]-FDG PET/CT reconstructions.
Methods
Retrospectively, we analysed lung lesions on full statistics and decimated [ 18 F]-FDG PET/CT. Reduced count PET data were emulated according to various percentage levels of total. Full and reduced statistics datasets were denoised using a CNN algorithm trained to recreate full statistics PET. Two readers assessed a detectability score from 3 to 0 for each lesion. The resulting detectability score and quantitative measurements were compared between full statistics and the different decimation levels (100%, 30%, 5%, 2%, 1%) with and without denoising.
Results
We analysed 141 lung lesions from 49 patients across 588 reconstructions. The dichotomised lung lesion malignancy score was significantly different from 10% decimation without denoising ( p < 0.029) and from 5% decimation with denoising ( p < 0.001). Compared to full statistics, detectability score distribution differed significantly from 2% decimation without denoising ( p < 0.001) and from 5% decimation with denoising ( p < 0.001). Detectability scores at same decimation levels with or without denoising differed significantly at 10%, 2%, and 1% decimation ( p < 0.019); dichotomised scores did not differ significantly. Denoising significantly increased the proportion of lung lesion scores with a high diagnostic confidence (3 and 0) ( p < 0.038).
Conclusion
Lung lesion detectability was preserved down to 30% of injected activity without denoising and to 10% with denoising. These results support the feasibility of reduced-activity [ 18 F]-FDG PET/CT as a potential tool for lung lesion detection. Further studies are warranted to compare this approach with low-dose CT in screening settings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Nuclear Medicine and Molecular Imaging, Lausanne University Hospital and University of Lausanne, Rue du Bugnon 21, CH- 1011, Lausanne, Switzerland.
- Institute of Radiation Physics, Lausanne University Hospital and University of Lausanne, Rue du Bugnon 21, CH- 1011, Lausanne, Switzerland.
- Institute of Informatics, School of Management, HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland, Rue du Technopôle 3, CH-3960, Sierre, Switzerland.
- Siemens Medical Solutions USA, Inc. 810 Innovation Drive, Knoxville, TN, 37932, USA.
- Department of Nuclear Medicine and Molecular Imaging, Lausanne University Hospital and University of Lausanne, Rue du Bugnon 21, CH- 1011, Lausanne, Switzerland. John.Prior@chuv.ch.
ORCID-Profile: Daphné Faist, Silvano Gnesin, Siria Medici, Marie Nicod Lalonde, Niklaus Schaefer, Adrien Depeursinge, Joshua Schaefferkoetter, John O Prior, Mario Jreige
Förderung
- Foundations Solis and CHUV
- University of Lausanne
Zitieren
APA
Faist, D., Gnesin, S., Medici, S., Khan, A., Nicod Lalonde, M., Schaefer, N., Depeursinge, A., Conti, M., Schaefferkoetter, J., Prior, J. O., & Jreige, M. (2025). Lung lesion detectability on images obtained from decimated and CNN-based denoised [18F]-FDG PET/CT scan: an observer-based study for lung-cancer screening. European Journal of Nuclear Medicine and Molecular Imaging. https://doi.org/10.1007/s00259-025-07259-2
Vancouver
Faist D, Gnesin S, Medici S, Khan A, Nicod Lalonde M, Schaefer N, et al. Lung lesion detectability on images obtained from decimated and CNN-based denoised [18F]-FDG PET/CT scan: an observer-based study for lung-cancer screening. European Journal of Nuclear Medicine and Molecular Imaging. 2025. doi:10.1007/s00259-025-07259-2
BibTeX
@article{Faist2025,
author = {Faist, Daphné and Gnesin, Silvano and Medici, Siria and Khan, Alysée and Nicod Lalonde, Marie and Schaefer, Niklaus and Depeursinge, Adrien and Conti, Maurizio and Schaefferkoetter, Joshua and Prior, John O and Jreige, Mario},
title = {Lung lesion detectability on images obtained from decimated and CNN-based denoised [18F]-FDG PET/CT scan: an observer-based study for lung-cancer screening},
journal = {European Journal of Nuclear Medicine and Molecular Imaging},
year = {2025},
doi = {10.1007/s00259-025-07259-2}
}
EUVIMED