EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI lesion tracking in PET/CT imaging: a proposal for a Siamese-based CNN pipeline applied to PSMA PET/CT scans

Stefan P Hein iD, Manuel Schultheiss, Andrei Gafita, Raphael Zaum, Farid Yagubbayli, Robert Tauber, Isabel Rauscher, Matthias Eiber, Franz Pfeiffer, Wolfgang A Weber

European Journal of Nuclear Medicine and Molecular Imaging · 2025

DOI: 10.1007/s00259-025-07426-5 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Nuclear Medicine and Molecular Imaging, 2025. Verfasst von Stefan P Hein und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Nuclear Medicine, School of Medicine and Health, TUM Klinikum, Technical University of Munich, Munich, 81675, Germany. stefan.hein@tum.…. Hauptthemen laut MEDLINE: Positron Emission Tomography Computed Tomography, Image Processing, Computer-Assisted, Convolutional Neural Networks. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Technische Universität München.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Assessing tumor response to systemic therapies is one of the main applications of PET/CT. Routinely, only a small subset of index lesions out of multiple lesions is analyzed. However, this operator dependent selection may bias the results due to possible significant inter-metastatic heterogeneity of response to therapy. Automated, AI-based approaches for lesion tracking hold promise in enabling the analysis of many more lesions and thus providing a better assessment of tumor response. This work introduces a Siamese CNN approach for lesion tracking between PET/CT scans.

Methods

Our approach is applied on the laborious task of tracking a high number of bone lesions in full-body baseline and follow-up [ 68 Ga]Ga- or [ 18 F]F-PSMA PET/CT scans after two cycles of [ 177 Lu]Lu-PSMA therapy of metastatic castration resistant prostate cancer patients. Data preparation includes lesion segmentation and affine registration. Our algorithm extracts suitable lesion patches and forwards them into a Siamese CNN trained to classify the lesion patch pairs as corresponding or non-corresponding lesions.

Results

Experiments have been performed with different input patch types and a Siamese network in 2D and 3D. The CNN model successfully learned to classify lesion assignments, reaching an accuracy of 83 % in its best configuration with an AUC = 0.91. For corresponding lesions the pipeline accomplished lesion tracking accuracy of even 89 %.

Conclusion

We proved that a CNN may facilitate the tracking of multiple lesions in PSMA PET/CT scans. Future clinical studies are necessary if this improves the prediction of the outcome of therapies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Positron Emission Tomography Computed TomographyImage Processing, Computer-AssistedConvolutional Neural NetworksArtificial IntelligenceGallium IsotopesGallium RadioisotopesComputer SimulationProstatic Neoplasms, Castration-ResistantBone NeoplasmsImage Interpretation, Computer-AssistedHumansImaging, Three-DimensionalWorkflowAlgorithmsMale

Stichwörter der Autor:innen

AICNNLesion trackingMetastatic castration resistant prostate cancerPET/CTPSMA

Substanzen

gallium 68 PSMA-11Gallium IsotopesGallium Radioisotopes

Autor:innen und Institutionen

  • Department of Nuclear Medicine, School of Medicine and Health, TUM Klinikum, Technical University of Munich, Munich, 81675, Germany. stefan.hein@tum.de.
  • Chair of Biomedical Physics, Department of Physics, TUM School of Natural Sciences, Technical University of Munich, Garching, 85748, Germany. stefan.hein@tum.de.
  • Chair of Biomedical Physics, Department of Physics, TUM School of Natural Sciences, Technical University of Munich, Garching, 85748, Germany.
  • Institute for Diagnostic and Interventional Radiology, School of Medicine and Health, TUM Klinikum, Technical University of Munich, Munich, 81675, Germany.
  • Division of Nuclear Medicine and Molecular Imaging, The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, 21205, MD, USA.
  • Department of Nuclear Medicine, School of Medicine and Health, TUM Klinikum, Technical University of Munich, Munich, 81675, Germany.

ORCID-Profile: Stefan P Hein

Förderung

  • Technische Universität München

Zitieren

APA

Hein, S. P., Schultheiss, M., Gafita, A., Zaum, R., Yagubbayli, F., Tauber, R., Rauscher, I., Eiber, M., Pfeiffer, F., & Weber, W. A. (2025). AI lesion tracking in PET/CT imaging: a proposal for a Siamese-based CNN pipeline applied to PSMA PET/CT scans. European Journal of Nuclear Medicine and Molecular Imaging. https://doi.org/10.1007/s00259-025-07426-5

Vancouver

Hein SP, Schultheiss M, Gafita A, Zaum R, Yagubbayli F, Tauber R, et al. AI lesion tracking in PET/CT imaging: a proposal for a Siamese-based CNN pipeline applied to PSMA PET/CT scans. European Journal of Nuclear Medicine and Molecular Imaging. 2025. doi:10.1007/s00259-025-07426-5

BibTeX
@article{Hein2025,
  author = {Hein, Stefan P and Schultheiss, Manuel and Gafita, Andrei and Zaum, Raphael and Yagubbayli, Farid and Tauber, Robert and Rauscher, Isabel and Eiber, Matthias and Pfeiffer, Franz and Weber, Wolfgang A},
  title = {AI lesion tracking in PET/CT imaging: a proposal for a Siamese-based CNN pipeline applied to PSMA PET/CT scans},
  journal = {European Journal of Nuclear Medicine and Molecular Imaging},
  year = {2025},
  doi = {10.1007/s00259-025-07426-5}
}
Kostenlos starten →