EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY 4.0

Multicenter PET image harmonization using generative adversarial networks

David Haberl, Clemens P Spielvogel, Zewen Jiang, Fanny Orlhac, David Iommi, Ignasi Carrió, Irène Buvat, Alexander R Haug, Laszlo Papp iD

European Journal of Nuclear Medicine and Molecular Imaging · 2024

DOI: 10.1007/s00259-024-06708-8 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift European Journal of Nuclear Medicine and Molecular Imaging, 2024. Verfasst von David Haberl und 8 weiteren Autor:innen. Beteiligte Einrichtung: Division of Nuclear Medicine, Medical University of Vienna, Währinger Gürtel 18-20/E4L, A-1090, Vienna, Austria. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Positron-Emission Tomography. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: ERACoSysMed, Medical University of Vienna.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To improve reproducibility and predictive performance of PET radiomic features in multicentric studies by cycle-consistent generative adversarial network (GAN) harmonization approaches.

Methods

GAN-harmonization was developed to harmonize whole-body PET scans to perform image style and texture translation between different centers and scanners. GAN-harmonization was evaluated by application to two retrospectively collected open datasets and different tasks. First, GAN-harmonization was performed on a dual-center lung cancer cohort (127 female, 138 male) where the reproducibility of radiomic features in healthy liver tissue was evaluated. Second, GAN-harmonization was applied to a head and neck cancer cohort (43 female, 154 male) acquired from three centers. Here, the clinical impact of GAN-harmonization was analyzed by predicting the development of distant metastases using a logistic regression model incorporating first-order statistics and texture features from baseline 18 F-FDG PET before and after harmonization.

Results

Image quality remained high (structural similarity: left kidney $$\ge$$ ≥ 0.800, right kidney $$\ge$$ ≥ 0.806, liver $$\ge$$ ≥ 0.780, lung $$\ge$$ ≥ 0.838, spleen $$\ge$$ ≥ 0.793, whole-body $$\ge$$ ≥ 0.832) after image harmonization across all utilized datasets. Using GAN-harmonization, inter-site reproducibility of radiomic features in healthy liver tissue increased at least by $$\ge$$ ≥ 5 ± 14% (first-order), $$\ge$$ ≥ 16 ± 7% (GLCM), $$\ge$$ ≥ 19 ± 5% (GLRLM), $$\ge$$ ≥ 16 ± 8% (GLSZM), $$\ge$$ ≥ 17 ± 6% (GLDM), and $$\ge$$ ≥ 23 ± 14% (NGTDM). In the head and neck cancer cohort, the outcome prediction improved from AUC 0.68 (95% CI 0.66–0.71) to AUC 0.73 (0.71–0.75) by application of GAN-harmonization.

Conclusions

GANs are capable of performing image harmonization and increase reproducibility and predictive performance of radiomic features derived from different centers and scanners.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedPositron-Emission TomographyHumansFemaleMaleLung NeoplasmsMiddle AgedReproducibility of ResultsHead and Neck NeoplasmsRetrospective StudiesFluorodeoxyglucose F18Aged

Stichwörter der Autor:innen

Deep learningGenerative adversarial networksHarmonizationMulticenterQuantitative PET

Substanzen

Fluorodeoxyglucose F18

Autor:innen und Institutionen

  • Division of Nuclear Medicine, Medical University of Vienna, Währinger Gürtel 18-20/E4L, A-1090, Vienna, Austria.
  • Christian Doppler Laboratory for Applied Metabolomics, Medical University of Vienna, Vienna, Austria.
  • LITO Laboratory, U1288 Inserm, Institut Curie, University Paris-Saclay, Orsay, France.
  • Department of Nuclear Medicine, Hospital Sant Pau and Autonomous University of Barcelona, Barcelona, Spain.
  • Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria. laszlo.papp@meduniwien.ac.at.

ORCID-Profile: Laszlo Papp

Förderung

  • ERACoSysMed
  • Medical University of Vienna

Zitieren

APA

Haberl, D., Spielvogel, C. P., Jiang, Z., Orlhac, F., Iommi, D., Carrió, I., Buvat, I., Haug, A. R., & Papp, L. (2024). Multicenter PET image harmonization using generative adversarial networks. European Journal of Nuclear Medicine and Molecular Imaging. https://doi.org/10.1007/s00259-024-06708-8

Vancouver

Haberl D, Spielvogel CP, Jiang Z, Orlhac F, Iommi D, Carrió I, et al. Multicenter PET image harmonization using generative adversarial networks. European Journal of Nuclear Medicine and Molecular Imaging. 2024. doi:10.1007/s00259-024-06708-8

BibTeX
@article{Haberl2024,
  author = {Haberl, David and Spielvogel, Clemens P and Jiang, Zewen and Orlhac, Fanny and Iommi, David and Carrió, Ignasi and Buvat, Irène and Haug, Alexander R and Papp, Laszlo},
  title = {Multicenter PET image harmonization using generative adversarial networks},
  journal = {European Journal of Nuclear Medicine and Molecular Imaging},
  year = {2024},
  doi = {10.1007/s00259-024-06708-8}
}
Kostenlos starten →