Evaluation of (68)Ga-PSMA-11 PET-MRI in Patients with Advanced Prostate Cancer Receiving (177)Lu-PSMA-617 Therapy: A Radiomics Analysis

SIMPLE SUMMARY: PSMA Therapy has recently become an additional therapeutic option in advanced prostate cancer. In the present study, the predictive and prognostic value of radiomic features from pretherapeutic PSMA PET-MRI are analyzed. Twenty-one patients with advanced prostate cancer underwent PSMA-therapy, including pretherapeutic PSMA PET-MRI. Radiomic features from PET- and MRI-sequences were extracted and processed to select the features differentiating responders and non-responders. Out of ten independent radiomic features differentiating between these two groups, the feature interquartile range from the T2 weighted images revealed the highest accuracy. PSA response and higher T2 interquartile range values might have impact on survival. This proof-of-concept study applies radiomic analysis to pretherapeutic PSMA PET-MRI before PSMA therapy, providing new parameters with potential predictive and prognostic value. ABSTRACT: (177)Lutetium PSMA-617 (Lu-PSMA) therapy in patients with metastatic castration resistant prostate cancer (mCRPC) has gained visibility through the ongoing phase III trial. The data on prediction of therapy outcome and survival out of pretherapeutic imaging parameters is still sparse. In this study, the predictive and prognostic value of radiomic features from (68)Ga-PSMA-11 PET-MRI are analyzed. In total, 21 patients with mCRPC underwent (68)Ga-PSMA-11 PET-MRI before Lu-PSMA therapy. The PET-positive tumor volume was defined and transferred to whole-body T2-, T1- and contrast-enhanced T1-weighted MRI-sequences. The radiomic features from PET and MRI sequences were extracted by using a freely available software package. For selecting features that allow differentiation of biochemical response (PSA decrease > 50%), a stepwise dimension reduction was performed. Logistic regression models were fitted, and selected features were tested for their prognostic value (overall survival) in all patients. Eight patients achieved biochemical response after Lu-PSMA therapy. Ten independent radiomic features differentiated well between responders and non-responders. The logistic regression model, including the feature interquartile range from T2-weighted images, revealed the highest accuracy (AUC = 0.83) for the prediction of biochemical response after Lu-PSMA therapy. Within the final model, patients with a biochemical response (p = 0.003) and higher T2 interquartile range values in pre-therapeutic imaging (p = 0.038) survived significantly longer. This proof-of-concept study provides first evidence on a potential predictive and prognostic value of radiomic analysis of pretherapeutic (68)Ga-PSMA-11 PET-MRI before Lu-PSMA therapy.