Deep learning methods for Registering Images with ERC

MRI images of same subject at different times are used for image registration to diagnose the prostate cancer .It is very difficult to diagnose when the image has Endorectal coil (ERC).For this we have to use iterative methods .so we are going to use deep learning methods. In this paper for forward/backward registration we are using cyclic constraint loss. Inverse constraint loss is used for diffeomorphic registration. In addition, an adaptive anatomical constraint aiming for regularizing the registration network with the use of anatomical labels is introduced. Compared with other existing methods, our approach works more efficiently with average running time less than a second and is able to obtain more visually realistic results.