Back to all papers

Deep learning-based PSMA PET segmentation repeatability: A post-hoc analysis of a single-center, prospective, test-retest trial.

October 30, 2025pubmed logopapers

Authors

Kendrick J,Francis RJ,Hassan GM,Ong JSL,Jeraj R,Barry N,Ebert MA

Affiliations (13)

  • School of Physics, Mathematics and Computing, The University of Western Australia, 35 Stirling Highway, Mailbag M013, Crawley, Perth, WA, 6009, Australia. [email protected].
  • Centre for Advanced Technologies in Cancer Research, Perth, WA, Australia. [email protected].
  • Australian Centre for Quantitative Imaging, University of Western Australia, Crawley, WA, Australia. [email protected].
  • Australian Centre for Quantitative Imaging, University of Western Australia, Crawley, WA, Australia.
  • Medical School, University of Western Australia, Crawley, WA, Australia.
  • Department of Nuclear Medicine, Royal Brisbane and Women's Hospital, Herston, QLD, Australia.
  • Department of Nuclear Medicine, Sir Charles Gairdner Hospital, Perth, WA, Australia.
  • School of Physics, Mathematics and Computing, The University of Western Australia, 35 Stirling Highway, Mailbag M013, Crawley, Perth, WA, 6009, Australia.
  • Department of Nuclear Medicine, Fiona Stanley Hospital, Murdoch, WA, Australia.
  • Department of Medical Physics and Human Oncology, University of Wisconsin, Madison, WI, USA.
  • Department of Physics, University of Ljubljana, Ljubljana, Slovenia.
  • Centre for Advanced Technologies in Cancer Research, Perth, WA, Australia.
  • Department of Radiation Oncology, Sir Charles Gairdner Hospital, Perth, WA, Australia.

Abstract

The primary aim of this study was to quantify the subject-level test-retest repeatability of artificial intelligence (AI)-derived PSMA PET imaging biomarkers using a previously developed model. The secondary aim was to assess the performance of this segmentation model, which was trained on [<sup>68</sup> Ga]Ga-PSMA-11 PET scans, on [<sup>18</sup>F]F-PSMA-1007 PET scans. This was a post-hoc analysis of a prospective, single-center, test-retest trial. Seventeen patients with metastatic prostate cancer (mPCa) were randomised into groups, either receiving the same tracer ([<sup>68</sup> Ga]Ga-PSMA-11 or [<sup>18</sup>F]F-PSMA-1007) for both scans (intra-tracer group, n = 9) or a different tracer (inter-tracer group, n = 8). Scans were delineated using a fully automated AI method and semi-automatically. The subject-level repeatability of four imaging biomarkers, including PSMA-positive tumour volume, was quantified. Repeatability analysis demonstrated poorer repeatability for all biomarkers in the inter-tracer group. In the intra-tracer group, the AI-derived PSMA-positive tumour volume had a repeatability coefficient of 13.8% for higher volume disease patients (≥ median tumour volume). There was no significant difference in the per-scan lesion-level positive predictive value of the AI model between [<sup>68</sup> Ga]Ga-PSMA-11 and [<sup>18</sup>F]F-PSMA-1007 PET scans (0.88, IQR 0.69-1.00 vs. 0.78, IQR 0.54-1.00, p = 0.60). AI-based PSMA-positive tumour volume calculations have repeatability limits that are consistent with the use of the Response Evaluation Criteria in PSMA PET/CT (RECIP 1.0) criteria for higher volume disease patients when the same tracer is used. Substantially wider repeatability limits in the inter-tracer group provide evidence that response assessment should be conducted using the same radiotracer.

Topics

Journal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.