In medical imaging, it is widely accepted that image quality should be evaluated using a task-based approach in which one evaluates human... Show moreIn medical imaging, it is widely accepted that image quality should be evaluated using a task-based approach in which one evaluates human observer performance for a given diagnostic task. Unfortunately, human observer studies with expert readers are costly and time-demanding. To confront this problem, model observers (MO) have been used as surrogates for human observers. MOs typically can accurately predict human diagnostic performance but some types of MOs require sets of images and human observer scores for tuning (training). Current literature does not provide guidance on how to choose the training data set. Therefore, in this work we present two different approaches to the problem of selecting good MOs training data sets. One is based on an active learning methodology (AL) and the second uses Frechet and Bhattacharyya distances between image-feature distributions to select a small subset of images, previous to performing human study, which together are representative and will be subject to the next human observer study. The presented results indicate that the proposed data set selection approaches, together with a learning model observer based on the Relevance Vector Machine (RVM), has excellent performance in predicting human observer performance as measured by the area under the receiver operating curve (AUC). M.S. in Electrical Engineering, July 2014 Show less
