The following is a summary of “[68Ga]Ga‑PSMA‑617 PET-based radiomics model to identify candidates for active surveillance amongst patients with GGG 1–2 prostate cancer at biopsy,” published in the July 2024 issue of Oncology by Yang et al.
The objective of this study was to develop a radiomics-based model utilizing [68Ga]Ga-PSMA PET/CT to predict postoperative adverse pathology (AP) in patients with biopsy Gleason Grade Group (GGG) 1–2 prostate cancer (PCa), thereby assisting in the selection of candidates for active surveillance (AS).
A cohort of 75 men diagnosed with biopsy GGG 1–2 PCa who subsequently underwent radical prostatectomy (RP) was enrolled in this study. The patients were randomly assigned to either a training group (70%) or a testing group (30%). Radiomics features were extracted from [68Ga]Ga-PSMA PET scans of the entire prostate. These features were then selected using the minimum redundancy maximum relevance algorithm and the least absolute shrinkage and selection operator regression model. Prediction models were constructed through logistic regression analyses. These models’ diagnostic value, clinical utility, and predictive accuracy were assessed using receiver operating characteristic (ROC) curves, decision curve analysis (DCA), and calibration curves, respectively.
Of the 75 patients, 30 were confirmed to have AP through RP. The clinical model demonstrated an area under the curve (AUC) of 0.821 (95% CI: 0.695–0.947) in the training set and 0.795 (95% CI: 0.603–0.987) in the testing set. The radiomics model achieved AUC values of 0.830 (95% CI: 0.720–0.941) in the training set and 0.829 (95% CI: 0.624–1.000) in the testing set. Notably, the combined model, which integrated the Radiomics score (Radscore) and the ratio of free prostate-specific antigen (FPSA) to total prostate-specific antigen (TPSA), exhibited superior diagnostic efficacy, with AUC values of 0.875 (95% CI: 0.780–0.970) in the training set and 0.872 (95% CI: 0.678–1.000) in the testing set. Decision curve analysis revealed that the net benefits of the combined and radiomics models were higher than those of the clinical model alone.
In conclusion, incorporating radiomics and clinical features, the combined model demonstrates significant potential in stratifying men with biopsy GGG 1–2 PCa based on the likelihood of AP at final pathology. This model outperforms models based solely on clinical or radiomics features and may aid urologists in more accurately selecting suitable patients for active surveillance, potentially improving patient outcomes and resource allocation.
Source: cancerimagingjournal.biomedcentral.com/articles/10.1186/s40644-024-00735-2