Lee DK, Sung DJ, Kim CS, et al. - This study was attempted to evaluate the performance of a 3D convolutional neural network (CNN) for automatic segmentation of prostates on MR images and to compare the volume estimates from the 3D CNN with those of the ellipsoid formula. Researchers recruited a total of 330 MR image sets that were classified into 260 training sets and 70 test sets for automated segmentation of the entire prostate. Among these, for transition zone segmentation, 162 training sets and 50 test sets were applied. Results indicates that fully automated network studied gives reliable volume calculates of the entire prostate in comparison with those obtained with the ellipsoid formula. Via use of the 3D CNN, fast and accurate volume measurement may guide clinicians to evaluate prostate disease.