Spectral Clustering as a Diagnostic Tool in Cross-Sectional MR Studies: An Application to Mild Dementia

TY - CHAP

T1 - Spectral Clustering as a Diagnostic Tool in Cross-Sectional MR Studies: An Application to Mild Dementia

AU - Aljabar, Paul

AU - Rueckert, Daniel

AU - Crum, William

PY - 2008

Y1 - 2008

N2 - 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 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 used volumes alone.

AB - 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 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 used volumes alone.

U2 - 10.1007/978-3-540-85990-1_53

DO - 10.1007/978-3-540-85990-1_53

M3 - Conference paper

SN - 978-3-540-85989-5

VL - 5242 LNCS

SP - 442

EP - 449

BT - MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION - MICCAI 2008, PT II, PROCEEDINGS

A2 - Metaxas, D

A2 - Axel, L

A2 - Fichtinger, G

A2 - Szekely, G

PB - Springer

CY - BERLIN

T2 - 11th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI2008)

Y2 - 6 September 2008 through 10 September 2008

ER -