Linked Life Data

18003276

Source:http://linkedlifedata.com/resource/pubmed/id/18003276

Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:dateCreated
2007-11-16
pubmed:abstractText
In this paper, we present an automatic, robust and reliable process to quantify liver steatosis. The degree of steatosis is a useful marker of steatohepatitis. This degree is routinely assessed visually by an expert and then lacks of accuracy and robustness. The process that we have developed is divided in two steps. A fuzzy classification first merges into classes pixels according to their intensity. We use a generalized objective function that allows to detect micro and blurredness vacuoles of steatosis. Then, regions with inhomogeneous texture and irregular shape were eliminated with compactness and standard deviation parameters. The obtained results are good correlated with expert graduation (in five levels). A better correlation is obtained with a more precise grading.
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
IM
pubmed:status
MEDLINE
pubmed:issn
1557-170X
pubmed:author
pubmed:issnType
Print
pubmed:volume
2007
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
5575-8
pubmed:meshHeading
pubmed:year
2007
pubmed:articleTitle
Fuzzy algorithms to extract vacuoles of steatosis on liver histological color images.
pubmed:affiliation
LISA UPRES-EA 4014, 62, Avenue Notre Dame du Lac, 49000 Angers, France. vincent.roullier@etud.univ-angers.fr
pubmed:publicationType
Journal Article, Research Support, Non-U.S. Gov't