Premium
MR image segmentation using vector decomposition and probability techniques: A general model and its application to dual‐echo images
Author(s) -
Kao YiHsuan,
Sorenson James A.,
Winkler Stefan S.
Publication year - 1996
Publication title -
magnetic resonance in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.696
H-Index - 225
eISSN - 1522-2594
pISSN - 0740-3194
DOI - 10.1002/mrm.1910350115
Subject(s) - voxel , segmentation , artificial intelligence , pattern recognition (psychology) , partial volume , computer science , imaging phantom , noise (video) , mathematics , image (mathematics) , nuclear medicine , medicine
A general model is developed for segmenting magnetic resonance images using vector decomposition and probabilfty techniques. Each voxel is assigned fractional volumes of q tissues from p differently weighted images ( q ≤ p + 1) in the presence of partial‐volume mixing, random noise, and other tissues. Compared wtth the eigenimage method, fewer differently weighted images are needed for segmenting the q tissues, and the contrast‐to‐noise ratio in the calculated fractional volumes is improved. The model can produce com‐posrte tissue‐type images similar to that of the probability methods, by comparing the fractional volumes assigned to different tissues on each voxel. A three‐tissue ( p = 2, q = 3) model is illustrated for segmenting three tissues from dual‐echo images. M provides statistical analysis to the algebraic method. A three‐compartment phantom is segmented for validation. Two clinical examples are presented.