Segmentation Evaluation Tool

This software has a user interface that enables medical experts to load and view local images and multiple experts¨ segmentations. The software is based on Bayesian Decision Rule.

It allows users to submit the segmentations to the server with the initial associated specificity and sensibility. The server computes and sends back to the users with 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.

We developed the software in Java. This software is a tool as part of study of the evolution of lesions related to cervical cancer conducted by NCI together with the National Library of Medicine (NLM).


To Run:


Update History:





 Java Version



More Information

 JNI Technology
 Web Start

Related Links

 National Library of Medicine
 Lehigh University
 J2EE web application




The web site is maintained by Yaoyao Zhu and Megan Vasta