Premium
A template‐based automatic skull‐stripping approach for mouse brain MR microscopy
Author(s) -
Lin Lan,
Wu Shuicai,
Yang Chunlan
Publication year - 2013
Publication title -
microscopy research and technique
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.536
H-Index - 118
eISSN - 1097-0029
pISSN - 1059-910X
DOI - 10.1002/jemt.22128
Subject(s) - jaccard index , neuroimaging , neuroanatomy , computer science , artificial intelligence , contouring , pattern recognition (psychology) , neuroscience , biology , computer graphics (images)
Small animal magnetic resonance microscopy (MRM) has been widely used today in computational neuroanatomy. Accurate identification of brain tissue in a mouse MRM is a critical fundamental step in neuroimaging processing, which is given less attention. This study presents an automatic skull‐stripping technique based on template models and histogram analysis. Results were evaluated by calculating the Jaccard similarity index (JSI) and boundary concordance ratio (BCR) between the automatically segmented and manually traced brain volumes. Results demonstrate that this technique accurately extracts the brain volume (mean JSI = 97.1%, BC = 94.4%). The brain extraction method presented in this study will greatly facilitate analysis of neuroimaging studies of rodent animals in neurodegenerative diseases. Microsc. Res. Tech. 2013. © 2012 Wiley Periodicals, Inc.