The identification of lesions is critical for the diagnostic evaluation of prostate cancer. 68 Ga-PSMA-11 PET/CT is a specific imaging for prostate cancer. However, this is extremely challenging considering the large number of lesions of varying size and uptake that may be distributed in various anatomical settings with different backgrounds throughout the body. In this paper, we propose a deep learning approach for automatic detection of whole-body prostate cancer lesions on PSMA imaging. We established and evaluated our model on the 68 Ga-PSMA-11 PET/CT image dataset of 107 patients with metastatic prostate cancer, and finally obtained Precision, Recall and F1-score of 82.9%, 100% and 90.6%, respectively, on the independent test set. Preliminary tests confirmed the potential of our method for disease detection on a systemic scale. Increasing the amount of training data can further improve the performance of the proposed deep learning method.