Paper Info
Title
Quantifying Small Changes in Brain Ventricular Volume Using Non-rigid Registration
Abstract
Non-rigid registration can automatically quantify small changes in volume of anatomical structures over time by means of segmentation propagation. Here we use a non-rigid registration algorithm based on optimising normalised mutual information to quantify small changes in brain ventricular volume in MR images of a group of five patients treated with growth hormone replacement therapy and a control group of six volunteers. The lateral ventricles are segmented from each subject image by registering the brainweb image [1] which has this structure delineated. The mean (standard deviation) volume change measurements are 1.09cc (0.73cc) for the patient group and 0.08cc (0.62cc) for the volunteer group, this difference is statistically significant at the 1% level. We validate our volume change measurements by comparing them to previously published results obtained by visual inspection of difference images, and demonstrate high rank correlation coefficient (p = 0.7, n=11).
Year
DOI
Venue
2001
10.1007/3-540-45468-3_7
MICCAI
Keywords
Field
DocType
volunteer group,brain ventricular volume,non-rigid registration,small change,patient group,small changes,mr image,volume change measurement,control group,brainweb image,difference image,rank correlation,standard deviation,mutual information,statistical significance,visual inspection
Lateral ventricles,Rank correlation,Computer vision,Growth hormone,Segmentation,Mutual information,Artificial intelligence,Anatomical structures,Standard deviation,Mathematics
Conference
ISBN
Citations 
PageRank 
3-540-42697-3
6
1.05
References 
Authors
7
3
Name
Order
Citations
PageRank
Mark Holden11386.75
Julia A Schnabel21978151.49
Derek L G Hill32823441.79