Extracting information from images for IGRT and ART usually involves segmentation and/or registration with a reference image. The purpose of this project is to develop and make freely available a software toolkit for research use that combines several registration and segmentation methods and is particularly applicable to problems involving multiple sequential images. Two automatic approaches will be integrated with standard interactive methods. One automatic approach solves PDEs describing visco-elastic flow to register a set of target images with a reference image. Segmentations can then be transferred from the reference image to target images via corresponding deformation fields. The second method segments images via Bayesian posterior optimization of m-reps. User efficiency will be improved by the ability to queue, view, work with, and compare multiple images and segmentations during a single session. Registered images and segmentations will be output in DICOM RT format.
Filed under: image-guided-RT