You are here
Inactive Project: Multiple Observer Segmentation Evaluation System
LHNCBC is no longer conducting active research on this project. Information is presented here for historical purposes.
CEB has carried out technical work with students and faculty from Lehigh University to develop a web-based software for automatic performance evaluation of multiple image segmentations as a tool for study of lesions related to uterine cervical cancer.
The Multiple Observer Segmentation Evaluation System (MOSES) is based on the Bayesian Decision framework. It computes a probabilistic estimate of the true segmentation (ground truth map) and performance measures for the individual segmentations (sensitivity and specificity). The strength of the tool is that it integrates the two kinds of prior knowledge of segmentations: the truth prior (the prior probability) and the observer prior (the performance measures of observers). It can handle four different scenarios with differing application purposes: (1) with known truth prior; (2) with observer prior; (3) with neither truth prior nor observer prior; and (4) with both truth prior and observer prior.
The tool is presently available to a restricted set of users. NLM/CEB is currently generalizing the tool to a larger set of image formats and developing a standard data description format for a future release of the tool to the general community.