An integrated dataset originating from multi-modal datasets can be used to target underlying causal biological actions that through a systems level process trigger the development of a disease. In this study, we use an integrated dataset related to cutaneous melanoma that comes from two separate sets (microarray and imaging) and the application of data imputation methods. Our goal is to associate low-level biological information, i.e. gene expression, to imaging features, that characterize disease at a macroscopic level. Using an average Spearman correlation measurement of a gene to a total of 31 imaging features, a set of 1701 genes were sorted based on their impact to imaging features. Top correlated genes, comprising a candidate set of gene biomarkers, were used to train an artificial feed forward neural network. Classification performance metrics reported here showed the proof of concept for our gene selection methodology which is to be further validated.