Nickols NG, Anand A, Sjöstrand K, et al. - Given that [F18]DCFPyL (PyL) is a PSMA targeted imaging agent for prostate cancer, researchers sought to analyze the performance of a deep learning algorithm on PyL images of the primary tumor to anticipate co-existing distant metastases. Seventy-four veterans with high risk primary prostate cancer tumors were imaged with both PyL PSMA PET/CT and conventional imaging. According to findings, the logistical regression model using clinicopathologic features had an AUC of 0.71, whereas the PyL-AI model based on intra-prostatic PyL Images alone had an AUC of 0.81 for the anticipation of metastatic disease as defined by conventional imaging. Using classical clinicopathologic features, the PyL-AI deep learning model based on image demonstrates a higher predictive precision over the logistic model. The study is a hypothesis generating observation in an independent data set that needs prospective validation.