“…The practice of image synthesis has been gaining attention recently (Rousseau, 2008; Roy et al, 2010a,b; Rousseau, 2010; Roy et al, 2011; Roohi et al, 2012; Jog et al, 2013a; Rousseau and Studholme, 2013; Konukoglu et al, 2013; Ye et al, 2013; Iglesias et al, 2013; Roy et al, 2013a,b; Jog et al, 2014a; Roy et al, 2014; Burgos et al, 2014; van Tulder and de Bruijne, 2015; Jog et al, 2015a; Cardoso et al, 2015; Van Nguyen et al, 2015; Bahrami, Khosro and Shi, Feng and Zong, Xiaopeng and Shin, Hae Won and An, Hongyu and Shen, Dinggang, 2015; Zikic et al, 2014) and the number of applications where image synthesis methods are being used is also growing. Synthesis of modalities differs from the data imputation literature (Hor and Moradi, 2015) in that the main goal is synthesis of the missing modality as opposed to classification in the absence of it.…”