Abstract: A system and method for predicting an outcome specific signal (OSS) in test subject images. The method includes detecting the OSS in image data from outcome and control subjects; extracting a volumetric space containing the detected OSS and dividing the extracted volumetric space into a first set of sub-regions; determining a set of image features for the first set of sub-regions; determining a global feature set (GFS) by averaging the set of image features; utilizing a machine learning algorithm to select a subset of discriminant GFS to determine a best signal model (BSM) that distinguishes the outcome and control subjects; extracting volumetric space containing the target anatomy in test subject images and dividing the extracted volumetric space into a second set of sub-regions; and determining the subset of discriminant GFS at each of the second set of sub-regions, and using them in the BSM to generate the predicted OSS.