Journal Article

DKFZ-2023-00549

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Development of PSMA-PET-guided CT-based radiomic signature to predict biochemical recurrence after salvage radiotherapy.

Spohn, S. K. B.DKFZ* ; Schmidt-Hegemann, N.-S. ; Ruf, J. ; Mix, M.DKFZ* ; Benndorf, M. ; Bamberg, F. ; Makowski, M. R. ; Kirste, S.DKFZ* ; Rühle, A.DKFZ* ; Nouvel, J.DKFZ* ; Sprave, T.DKFZ* ; Vogel, M. M. E.DKFZ* ; Galitsnaya, P.DKFZ* ; Gschwend, J. E. ; Gratzke, C. ; Stief, C. ; Löck, S. ; Zwanenburg, A.DKFZ* ; Trapp, C. ; Bernhardt, D.DKFZ* ; Nekolla, S. G. ; Li, M. ; Belka, C. ; Combs, S. E.DKFZ* ; Eiber, M. ; Unterrainer, L. ; Unterrainer, M. ; Bartenstein, P. ; Grosu, A.-L. ; Zamboglou, C.DKFZ* ; Peeken, J. C.DKFZ*

2023
Springer-Verl. Heidelberg [u.a.]

Abstract: To develop a CT-based radiomic signature to predict biochemical recurrence (BCR) in prostate cancer patients after sRT guided by positron-emission tomography targeting prostate-specific membrane antigen (PSMA-PET).Consecutive patients, who underwent 68Ga-PSMA11-PET/CT-guided sRT from three high-volume centers in Germany, were included in this retrospective multicenter study. Patients had PET-positive local recurrences and were treated with intensity-modulated sRT. Radiomic features were extracted from volumes of interests on CT guided by focal PSMA-PET uptakes. After preprocessing, clinical, radiomics, and combined clinical-radiomic models were developed combining different feature reduction techniques and Cox proportional hazard models within a nested cross validation approach.Among 99 patients, median interval until BCR was the radiomic models outperformed clinical models and combined clinical-radiomic models for prediction of BCR with a C-index of 0.71 compared to 0.53 and 0.63 in the test sets, respectively. In contrast to the other models, the radiomic model achieved significantly improved patient stratification in Kaplan-Meier analysis. The radiomic and clinical-radiomic model achieved a significantly better time-dependent net reclassification improvement index (0.392 and 0.762, respectively) compared to the clinical model. Decision curve analysis demonstrated a clinical net benefit for both models. Mean intensity was the most predictive radiomic feature.This is the first study to develop a PSMA-PET-guided CT-based radiomic model to predict BCR after sRT. The radiomic models outperformed clinical models and might contribute to guide personalized treatment decisions.

Keyword(s): Outcome prediction ; PSMA-PET/CT ; Personalization ; Prostate cancer ; Radiomics ; Salvage radiotherapy

Note: 2023 Jul;50(8):2537-2547

---

Contributing Institute(s):

1. DKTK FR zentral (FR01)
2. DKTK MU LMU zentral (MU01)
3. DKTK DD zentral (DD01)

Research Program(s):

1. 899 - ohne Topic (POF4-899) (POF4-899)

Appears in the scientific report 2023

---

Database coverage:
; Clarivate Analytics Master Journal List ; Current Contents - Clinical Medicine ; Current Contents - Life Sciences ; DEAL Springer ; DEAL Springer ; Ebsco Academic Search ; Essential Science Indicators ; IF >= 5 ; JCR ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection

---