Variational segmentation and PCA applied to dynamic PET analysis

Authors:
Brian Parker;David Dagan Feng
Affiliations:
Biomedical & Multimedia Information Technology (BMIT) Group, School of Information Technologies, University of Sydney, Australia;Biomedical & Multimedia Information Technology (BMIT) Group, School of Information Technologies, University of Sydney, Australia
Venue:
VIP '02 Selected papers from the 2002 Pan-Sydney workshop on Visualisation - Volume 22
Year:
2003

Citing 3
Cited 2

A multiscale algorithm for image segmentation by variational method

SIAM Journal on Numerical Analysis
Variational methods in image segmentation

Variational methods in image segmentation
Three-dimensional medical image segmentation using a graph-theoretic energy-minimisation approach

VIP '01 Proceedings of the Pan-Sydney area workshop on Visual information processing - Volume 11

Certain investigation on MRI segmentation for the implementation of CAD system

WSEAS Transactions on Computers
Segmentation of dynamic emission tomography data in projection space

CVAMIA'06 Proceedings of the Second ECCV international conference on Computer Vision Approaches to Medical Image Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

A graph-theoretic variational segmentation algorithm is applied to 22-frame dynamic positron emission tomography (PET) data sets after dimension reduction along the time axis using principal component analysis. Initial results indicate that the PCA is a very useful initial preprocessing step for segmentation and is effective in minimising the artifacts present in the PET data sets, allowing accurate delineation of pathological and anatomical features by the variational segmentation algorithm.