This extension assesses synthetic CT conversion accuracy. Mean Absolute Error (MAE) and Mean Error (ME) are computed bewteen genearated image and ground truth. Spatial error distrubution map and evaluation based on automatic bone segmentation are available as well.
The implemented workflow is described in: Spadea MF, Pileggi G, Zaffino P, Salome P, Catana C, Izquierdo-Garcia D, Amato F, Seco J. Deep Convolution Neural Network (DCNN) Multiplane Approach to Synthetic CT Generation From MR images—Application in Brain Proton Therapy. International Journal of Radiation Oncology* Biology* Physics. 2019 Nov 1;105(3):495-503.
The license used is APACHE 2.0.