Automatic Multi-organ Segmentation in Nonenhanced CT Datasets Using Hierarchical Shape Priors
2014 (English)In: Pattern Recognition (ICPR), 2014 22nd International Conference on, IEEE Computer Society, 2014, 3327-3332 p.Conference paper (Refereed)
An automatic multi-organ segmentation method using hierarchical-shape-prior guided level sets is proposed. The hierarchical shape priors are organized according to the anatomical hierarchy of the human body, so that major structures with less population variety are at the top and smaller structures with higher irregularities are linked at a lower level. The segmentation is performed in a top-down fashion, where major structures are first segmented with higher confidence, and their location information is then passed down to the lower level to initialize the segmentation, while boundary information from higher-level structures also provides extra cues to guide the segmentation of the lower-level structures. The proposed method was combined with a novel coherent propagating level set method, which is capable to detect local convergence and skip calculation in those parts, therefore significantly reducing computation time. Preliminary experiment results on a small number of clinical datasets are encouraging, the proposed method yielded a Dice coefficient above 90% for most major organs within a reasonable processing time without any user intervention.
Place, publisher, year, edition, pages
IEEE Computer Society, 2014. 3327-3332 p.
, International Conference on Pattern Recognition, ISSN 1051-4651
Radiology, Nuclear Medicine and Medical Imaging
IdentifiersURN: urn:nbn:se:liu:diva-115587DOI: 10.1109/ICPR.2014.574ScopusID: 10.1109/ICPR.2014.574OAI: oai:DiVA.org:liu-115587DiVA: diva2:795763
22nd International Conference on Pattern Recognition (ICPR) 2014, Stockholm Sweden