Add a CycleGAN with mutual information as a consistency loss

Is your feature request related to a problem? Please describe.
Provide an style transfer model to learn to generate synthetic CT from MRI, or T2 from T1, or e.g. T1 from on scanner to T1 from a different scanner/site without loosing anatomical/geometric information.

Describe the solution you'd like
Add a CycleGAN with mutual information as a consistency loss, e.g. implementing https://arxiv.org/abs/1912.08061

Modanwal, Gourav, Adithya Vellal, and Maciej A. Mazurowski. "Normalization of breast MRIs using Cycle-Consistent Generative Adversarial Networks." Computer Methods and Programs in Biomedicine (2021): 106225.

Describe alternatives you've considered
It would be nice to have a tutorial illustrating different losses.

Additional context

• predict CT without inducing radiation in patients
• segment bones from MRI as if you had segmented used CT
• adapt data from different site to look similar to data used to train a unet

Start by reading the linked CycleGAN mutual-information paper and the issue's cited breast MRI reference. The payload names no target files, tests, or entry point, so repository structure and existing model, loss, and tutorial conventions must be identified first. Done means a CycleGAN with mutual-information consistency loss is added for the described image-translation use cases, with an illustrative loss tutorial if included.