A research team recently carried out a study to determine the effectiveness of Fluorine-18 (18F)-prostate-specific membrane antigen (PSMA)-1007 positron emission tomography/computed tomography (PET/CT) radiomics to determine tumor malignancy and risk stratification in primary prostate cancer (PCa).
Wang Z et al analyzed 161 patients with PCa and extracted radiomics features from PCa 18F-PSMA-1007-PET/CT imaging. Prostate-specific antigen (PSA), Gleason score (GS), and PET/CT indexes (SUVmin, SUVmax, and SUVmean) were compared in the patients based on risk stratification.
A binary logistic regression and nomogram classifier were created from the radiomics score that integrated clinicopathologic characteristics and specific parameters from the patients.
The radiomics signature comprised 30 individual features and was associated with PSA level and GS (P<.001 for both primary and validation cohorts). The individualized prediction nomogram was created using radiomics score, PSA level, and metastasis status. Predictors in the nomogram included radiomics score, PSA level, and metastasis status.
The combined clinical-radiomic score nomogram showed a similar benefit to using PET/CT radiomic features alone for GS discrimination. The 18F-PSMA-1007-PET/CT radiomics signature was determined to be useful for facilitating preoperative individualized prediction of GS.
