S2419
Physics - Radiomics, functional and biological imaging, and outcome prediction
ESTRO 2026
derived RFs in the prediction of local recurrence (LCR) of PCa after radiotherapy (RT). Material/Methods: This single-center study retrospectively included 30 PCa patients who had undergone RT – 12 patients with histologically confirmed LCR, 18 patients without recurrence – at least one PET-CT scan with either [68Ga]Ga-PSMA-11 or [18F]PSMA-1007 and a median follow-up of about 3 years. All previously reported PSMA PET radiomic features predictive of LCR after RT with available details on extraction procedures, were extracted using the same methodology as described in the original studies. Wilcoxon test with correction for multiple testing followed by ROC analysis were applied to evaluate the predictive power of these RFs for LCR after RT in our patient cohorts. Results: The six texture features from (1) and tumor volume in PSMA PET (PSMA-TV) previously reported in (2) correlated highly significant to LCR and outperformed the clinical risk parameters in LCR prediction with the only significant clinical LCR predictor being initial PSA in our cohorts. PSMA-TV performed best with a sensitivity and specificity of 0.92 and 0.89 for a cutoff of 2.3 ml. Conclusion: We successfully validated a selection of external Radiomic Features (RFs) from PET with [68Ga]Ga- PSMA-11 or [18F]PSMA-1007 for the prediction of local recurrence of PCa after radiotherapy. Clinical trials are warranted to investigate appropriate treatment adjustments based on these RFs. References: 1. Dutta A, Chan J, Haworth A, Dubowitz DJ, Kneebone A, Reynolds HM. Robustness of magnetic resonance imaging and positron emission tomography radiomic features in prostate cancer: Impact on recurrence prediction after radiation therapy. Phys Imaging Radiat Oncol. Januar 2024;29:100530. 2. Bela Andela S, Amthauer H, Furth C, Rogasch JM, Beck M, Mehrhof F, u. a. Quantitative PSMA-PET parameters in localized prostate cancer: prognostic and potential predictive value. Radiat Oncol. 29. Juli 2024;19(1):97. Keywords: local recurrence, prostate cancer, radiomics
Conclusion: Baseline ALC correlated with estimated radiosensitivity, suggesting that pre-treatment immune status reflects differential lymphocyte vulnerability to radiation. Estimating patient-specific α from baseline ALC modestly improved prediction accuracy for radiation-induced lymphocyte depletion compared with a fixed cohort-median α , although the difference did not reach statistical significance. These findings suggest that personalized radiosensitivity modeling may help optimize RT with respect to immune preservation. References: [1] Jin JY et al. A framework for modeling radiation- induced lymphopenia in radiotherapy. Radiother Oncol. 2020; 144: 105– 113. https://doi.org/10.1016/j.radonc.2019.11.014 Keywords: Lymphopenia, NSCLC, radiotherapy Can PSMA PET Predict Local Recurrence After Radiotherapy of Prostate Cancer? A Validation Study of External PET-derived Radiomic Features Philipp M. A. Waibel 1 , Tobias Fechter 2 , Ioana M. Marinescu 1 , Sophia L. Bürkle 1 , Martin T. Freitag 3 , Constantinos Zamboglou 1,4 , Anca-Ligia Grosu 1 , Simon K. B. Spohn 1 1 Radiation Oncology, University Medical Center Freiburg, Freiburg, Germany. 2 Radiation Oncology - Division of Medical Physics, University Medical Center Freiburg, Freiburg, Germany. 3 Nuclear Medicine, University Medical Center Freiburg, Freiburg, Germany. 4 German Oncology Center, European University of Cyprus, Limassol, Cyprus Purpose/Objective: PSMA-PET holds great potential for individual non- invasive risk stratification of prostate cancer (PCa). This study evaluated several external PSMA-PET Digital Poster 899
Digital Poster 988
Image-driven metrics of overall survival following surgery and chemo-radiation of glioblastoma patients Jacob Snäll 1,2 , Klara Stefansson 1 , André Haraldsson 1,2 , Mikael Nilsson 3 , Henrietta Nittby Redebrandt 4 , Crister Ceberg 2 , Pia C Sundgren 5,6 , Per Munck af Rosenschöld 1,2
Made with FlippingBook - Share PDF online