Add RadImageNet option to Perceptual loss

[Warvito]

Add the option to select between LPIPS based implementation of the perceptual loss (based on model pretrained on ImageNet) or the RadImageNet option (based on a network pretrained no the RadImageNet dataset) (https://github.com/BMEII-AI/RadImageNet).

The use of this network in a similar approach was already implemented for a FID metric in https://github.com/RichardObi/medigan which might be interesting to use too.

[Warvito]

For now, I created this repo to access the pytorch models from radimagenet, but I am talking with Zelong and @xmei123 to possibly have some official repo and weights to share the pytorch models.