The purpose of this work is to validate the application of a deep learning-based method for pelvic synthetic CT (sCT) generation that can be used for prostate proton beam therapy treatment planning. We propose to integrate dense block minimization into 3D cycle-consistent generative adversarial networks (cycle GAN) framework to effectively learn the nonlinear mapping between MRI and CT pairs. A cohort of 17 patients with co-registered CT and MR pairs were used to test the deep learning-based sCT generation method by leave-one-out cross-validation. Image quality between the sCT and CT images, gamma analysis passing rate, dose-volume metrics, distal range displacement, and the individual pencil beam Bragg peak shift between sCT- and CT-based proton plans were evaluated. The average mean absolute error (MAE) was 51.32±16.91 HU. The relative differences of the statistics of the PTV dose volume histogram (DVH) metrics in between sCT and CT were generally less than 1%. Mean values of dose difference, absolute dose difference (in percent of prescribed dose) were -0.07±0.07% and 0.23±0.08%. Mean gamma analysis pass rate of 1mm/1%, 2mm/2%, 3mm/3% criteria with 10% dose threshold were 92.39±5.97%, 97.95±2.95% and 98.97±1.62% respectively. The median, mean and standard deviation of absolute maximum range differences were 0.09 cm and 0.23±0.25 cm. The median and mean Bragg peak shifts among the 17 patients were 0.09 cm and 0.18±0.07 cm. The image similarity, dosimetric and distal range agreement between sCT and original CT suggests the feasibility of further development of an MRI-only workflow for prostate proton radiotherapy.