Segmentation of liver vessels as seen in MR and CT images

Autor:	Ole Christian Eidheim, Tom Mala, Lars Aurdal, Bjørn Edwin, T. Omholt-Jensen
Rok vydání:	2004
Předmět:	Computer science business.industry Matched filter Graph based ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Graph (abstract data type) Computer vision Segmentation General Medicine Artificial intelligence business Thresholding Vessel structure
Zdroj:	CARS
ISSN:	0531-5131
DOI:	10.1016/j.ics.2004.03.184
Popis:	Deriving liver vessel structure from CT and MR scans manually is time consuming and error prone. An automatic procedure that could help the radiologist in her analysis is therefore needed. We use matched filters to emphasise blood vessels and entropy-based thresholding to segment the vessels. Vessel interconnections are next extracted and exported to a graph structure. At the end, genetic algorithms are used to search globally for the most likely graph based on a set of fitness functions. Results show that the methods presented are promising and can eventually be used clinically.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::e9cdc83bc3ae62fa4cc1c54033e5d373 https://doi.org/10.1016/j.ics.2004.03.184 Zobrazit plný text záznamu Full Text from ScienceDirect