Beyond the tumor: Recurrence-prone radiomics for prognostication in negative PSMA PET/CT scans of prostate cancer
PURPOSE: Prostate-specific membrane antigen (PSMA) PET/CT is routinely used to restage prostate cancer (PCa) in patients with biochemical recurrence (BCR), yet negative scans may still harbor subclinical disease. This study investigated whether radiomics features extracted from recurrence-prone organs on negative [¹⁸F]DCFPyL PET/CT can predict clinical progression (CP) and clinical progression-free survival (CPFS).
Materials and Methods: We performed a post-hoc analysis of 132 patients with BCR (mean age, 74.5 years) who had negative [¹⁸F]DCFPyL PET/CT scans and received no further treatment after imaging. Recurrence-prone organs, defined as anatomical sites at highest risk for prostate cancer recurrence (prostate bed, lymph nodes, bones, liver, and lungs), were segmented using nnU-Net (TotalSegmentator), and radiomics features were extracted. Machine learning models (XGBoost) and Cox proportional hazards models were evaluated using nested cross-validation (5-fold outer, 3-fold inner). External validation across two independent centers was performed after ComBat harmonization. The effect of reader-assigned diagnostic certainty on predictive performance was also examined. Only recurrence-prone organs were analyzed, as prior studies have shown that more than 80% of PCa recurrences arise in these regions.
Results: Median PSA at imaging was 0.74 ng/mL. During a median follow-up of 25.5 months, 42 of 132 patients (31.8%) developed progression. The concordance index improved from 0.65 using clinical variables alone to 0.74 when PET, CT, and clinical features were combined (p < 0.05). Predictive performance was strongly influenced by diagnostic certainty, with moderate-certainty negative scans showing higher accuracy than high-certainty negative scans. Radiomics features derived from negative PSMA PET/CT reflected systemic recurrence risk and were associated with early lung metastases. External validation demonstrated less than 10% reduction in performance despite inter-center differences.
Conclusion: Radiomics signatures from recurrence-prone organs on negative PSMA PET/CT may reveal subclinical disease and provide complementary biomarkers for risk stratification in BCR patients.
Authors
- Elmira Yazdani (ORCID: https://orcid.org/0000-0001-8371-8832)
- Tahir Yusufaly (ORCID: https://orcid.org/0000-0002-8755-3614)
- Arman Rahmim (ORCID: https://orcid.org/0000-0002-9980-2403)
- Patrick Martineau
- Parham Geramifar (ORCID: https://orcid.org/0000-0002-7607-6859)
- François Bénard (ORCID: https://orcid.org/0000-0001-7995-3581)
- Monica Luo (ORCID: https://orcid.org/0000-0003-0204-1650)
- Fereshteh Yousefirizi (ORCID: https://orcid.org/0000-0001-5261-6163)
- Sara Harsini (ORCID: https://orcid.org/0000-0001-6196-6982)
- Mobin Mohebi (ORCID: https://orcid.org/0000-0003-4023-8753)
- Peyman Sheikhzadeh (ORCID: https://orcid.org/0000-0003-3053-2641)
- Carlos Uribe (ORCID: https://orcid.org/0000-0003-3127-7478)
- Maziar Sabouri (ORCID: https://orcid.org/0000-0001-7525-8952)
- Hamid Abdollahi (ORCID: https://orcid.org/0000-0003-0761-1309)
- Seyyede Mirabedian
- Don Wilson
- Ian Alberts
Institutions
- BC Cancer Agency (CA)
- University of British Columbia (CA)
- Iran University of Medical Sciences (IR)
- University of Toronto (CA)
- University of California San Diego (US)
- Institut de Biologie Valrose (FR)
- Tehran University of Medical Sciences (IR)
Publication Details
- Journal
- Biomedical Physics & Engineering Express
- Published
- 2026-06-30
- DOI
- https://doi.org/10.1088/2057-1976/ae8450
- Primary Topic
- Prostate Cancer Treatment and Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- BC Cancer Foundation
- Canadian Institutes of Health Research