Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Manually segmented template library for 8-year-old pediatric brain MRI data with 16 subcortical structures

Manually segmented template library for 8-year-old pediatric brain MRI data with 16 subcortical... Abstract. Manual segmentation of anatomy in brain MRI data taken to be the closest to the “gold standard” in quality is often used in automated registration-based segmentation paradigms for transfer of template labels onto the unlabeled MRI images. This study presents a library of template data with 16 subcortical structures in the central brain area which were manually labeled for MRI data from 22 children (8 male, mean age = 8 ± 0.6 years ). The lateral ventricle, thalamus, caudate, putamen, hippocampus, cerebellum, third vevntricle, fourth ventricle, brainstem, and corpuscallosum were segmented by two expert raters. Cross-validation experiments with randomized template subset selection were conducted to test for their ability to accurately segment MRI data under an automated segmentation pipeline. A high value of the dice similarity coefficient ( 0.86 ± 0.06 , min = 0.74 , max = 0.96 ) and small Hausdorff distance ( 3.33 ± 4.24 , min = 0.63 , max = 25.24 ) of the automated segmentation against the manual labels was obtained on this template library data. Additionally, comparison with segmentation obtained from adult templates showed significant improvement in accuracy with the use of an age-matched library in this cohort. A manually delineated pediatric template library such as the one described here could provide a useful benchmark for testing segmentation algorithms. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Medical Imaging SPIE

Manually segmented template library for 8-year-old pediatric brain MRI data with 16 subcortical structures

Download PDF
11 pages

Loading next page...
 
/lp/spie/manually-segmented-template-library-for-8-year-old-pediatric-brain-mri-ZxT0qns0DQ
Publisher
SPIE
Copyright
© 2014 Society of Photo-Optical Instrumentation Engineers (SPIE)
Subject
Computer-Aided Diagnosis; Paper
ISSN
2329-4302
eISSN
2329-4310
DOI
10.1117/1.JMI.1.3.034502
pmid
26158067
Publisher site
See Article on Publisher Site

Abstract

Abstract. Manual segmentation of anatomy in brain MRI data taken to be the closest to the “gold standard” in quality is often used in automated registration-based segmentation paradigms for transfer of template labels onto the unlabeled MRI images. This study presents a library of template data with 16 subcortical structures in the central brain area which were manually labeled for MRI data from 22 children (8 male, mean age = 8 ± 0.6 years ). The lateral ventricle, thalamus, caudate, putamen, hippocampus, cerebellum, third vevntricle, fourth ventricle, brainstem, and corpuscallosum were segmented by two expert raters. Cross-validation experiments with randomized template subset selection were conducted to test for their ability to accurately segment MRI data under an automated segmentation pipeline. A high value of the dice similarity coefficient ( 0.86 ± 0.06 , min = 0.74 , max = 0.96 ) and small Hausdorff distance ( 3.33 ± 4.24 , min = 0.63 , max = 25.24 ) of the automated segmentation against the manual labels was obtained on this template library data. Additionally, comparison with segmentation obtained from adult templates showed significant improvement in accuracy with the use of an age-matched library in this cohort. A manually delineated pediatric template library such as the one described here could provide a useful benchmark for testing segmentation algorithms.

Journal

Journal of Medical Imaging – SPIE

Published: Oct 1, 2014

There are no references for this article.