Title :
Multispectral analysis of the brain in magnetic resonance imaging
Author :
Taxt, Torfinn ; Lundervold, Arvid
Author_Institution :
Section for Med. Image Anal. & Pattern Recognition, Bergen Univ., Norway
Abstract :
The authors demonstrate an improved differentiation of the most common tissue types in the human brain and surrounding structures by quantitative validation using multispectral analysis of magnetic resonance images. This is made possible by a combination of a special training technique and an increase in the number of magnetic resonance channel images with different pulse acquisition parameters. A description of the tissue-specific multivariate statistical distributions of the pixel intensity values and a statistical method to estimate the tissue-specific longitudinal and transverse relaxation times are given. It is concluded that multispectral analysis of magnetic resonance images is a valuable tool to recognize the most common normal tissue types in the brain and surrounding structures
Keywords :
biomedical NMR; brain; medical image processing; nuclear magnetic resonance imaging; nuclear magnetic resonance spectroscopy; brain magnetic resonance imaging; magnetic resonance channel images; medical diagnostic imaging; multispectral analysis; pixel intensity values; pulse acquisition parameters; quantitative validation; statistical method; tissue types differentiation; tissue-specific longitudinal relaxation time; tissue-specific multivariate statistical distributions; transverse relaxation time; Biomedical imaging; Humans; Image analysis; Image recognition; Magnetic analysis; Magnetic resonance; Magnetic resonance imaging; Neoplasms; Pathology; Pixel;
Conference_Titel :
Biomedical Image Analysis, 1994., Proceedings of the IEEE Workshop on
Conference_Location :
Seattle, WA
Print_ISBN :
0-8186-5802-9
DOI :
10.1109/BIA.1994.315868
