The following is a summary of “Prognostic utility of RECIP 1.0 with manual and AI-based segmentations in biochemically recurrent prostate cancer from [68Ga]Ga-PSMA-11 PET images,” published in the August 2023 issue of Oncology by Kendrick et al.

Researchers performed a retrospective study to validate RECIP 1.0 criteria in biochemically recurrent (BCR) prostate cancer patients (PCa) and explore automated applications through artificial intelligence (AI).

The study imaged 199 patients with [⁶⁸Ga] Ga-PSMA-11 PET/CT once at the time of biochemical recurrence and then a second time a median of 6.0 months later to assess disease progression. Standard-of-care treatments were administered to patients in the interim. Whole-body tumor volume was quantified semi-automatically (TTV_man) in all patients and using a novel AI method (TTV_AI) in a subset (n = 74, the remainder were used in the training process of the model). Patients were classified as having a progressive disease (RECIP-PD) or non-progressive disease (non-RECIP-PD). RECIP classifications and overall survival (OS) were assessed using Kaplan-Meier, Cox regression, and Cohen’s kappa.

Results demonstrated that in the patients (26/199 = 13.1%), RECIP-PD was identified using semi-automated delineation, which correlated with significantly lower survival probability (log-rank P< 0.005) and higher risk of death (HR = 3.78 [1.96-7.28], P< 0.005). With AI-based segmentation, (12/74 = 16.2%) showed RECIP-PD, also associated with significantly lower survival (log-rank P= 0.013) and higher risk of death (HR = 3.75 [1.23-11.47], P= 0.02). Semi-automated and AI-based RECIP classifications demonstrated fair agreement (Cohen’s k = 0.31).

The study concluded that RECIP 1.0 is a reliable and valuable tool for assessing disease progression in PCa patients.

Source: pubmed.ncbi.nlm.nih.gov/37550494/