Spectral clustering as a diagnostic tool in cross-sectional MR studies: an application to mild dementia

Structural imaging investigations commonly apply a segmentation step followed by the extraction of feature data that can be used to compare or discriminate groups. We present a framework for such a study based on automated multi-atlas segmentation followed by the extraction of low-level morphologica...

Full description

Saved in:
Bibliographic Details
Published inMedical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Vol. 11; no. Pt 2; p. 442
Main Authors Aljabar, Paul, Rueckert, Daniel, Crum, William R
Format Journal Article
LanguageEnglish
Published Germany 2008
Subjects
Aged
Algorithms
Artificial Intelligence
Brain - pathology
Cluster Analysis
Cross-Sectional Studies
Dementia - diagnosis
Female
Humans
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Imaging, Three-Dimensional - methods
Magnetic Resonance Imaging - methods
Male
Pattern Recognition, Automated - methods
Reproducibility of Results
Sensitivity and Specificity
Subtraction Technique
Online AccessGet more information

Cover

More Information
Summary:Structural imaging investigations commonly apply a segmentation step followed by the extraction of feature data that can be used to compare or discriminate groups. We present a framework for such a study based on automated multi-atlas segmentation followed by the extraction of low-level morphological features, volumes and overlaps, for classification. A spectral analysis step is used to transform pairwise overlap information into feature data that relate to individual subjects. Applying the framework to a group of controls and patients with mild dementia, we compare the volume- and overlap-based classification performance using both supervised and unsupervised classifiers. The results indicate that unsupervised classification following a spectral analysis of label overlaps performs very well, outperforming classifiers that use volumes alone.