LUNG SEGMENTATION

点击翻译按钮获取中文摘要

This subproject is one of many research subprojects utilizing the resources provided by a Center grant funded by NIH/NCRR. Primary support for the subproject and the subproject's principal investigator may have been provided by other sources, including other NIH sources. The Total Cost listed for the subproject likely represents the estimated amount of Center infrastructure utilized by the subproject, not direct funding provided by the NCRR grant to the subproject or subproject staff. Keywords: Volume data analysis, visualization and distribution collaboration Abstract: Spitzer's group recently finished a torso on the order of 100 micron isotropic resolution. The volumetric dataset starts just above the ball and socket joint in the shoulder to just below the diaphram (3199 slices, 1 slice is missing) resulting in a 110 GByte dataset. During the preparation of the torso, the arteries were filled with red latex paint, veins were filled with blue latex paint, and the respiratory system was filled with yellow latex paint. Spitzer's group has completed some segmentation on the lungs, identifying three to four different levels of branching. Our goal is to initially load their data plus all segmentation masks that they have completed to provide them with a private server that will allow them to continue segmenting the lungs. The lungs are especially problematic in that there are three different systems: arteries and veins forming the capilaries around the air sacs. Thus, although the region appears to be empty, it will be difficult to get a complete and accurate segmentation.