Brain tumor segmentation and characterization by pattern analysis of multispectral NMR images

Autor: Tom Mikkelsen, Donald J. Peck, Joe P. Windham, Hamid Soltanian-Zadeh
Rok vydání: 1998
Předmět:
Zdroj: NMR in Biomedicine. 11:201-208
ISSN: 1099-1492
0952-3480
DOI: 10.1002/(sici)1099-1492(199806/08)11:4/5<201::aid-nbm508>3.0.co;2-6
Popis: A major problem in tumor treatment planning and evaluation is determination of the tumor extent. Thispaper presents a pattern analysis methodology for segmentation and characterization of brain tumors frommultispectral NMR images. The proposed approach has been used in 15 clinical studies of cerebral tumor patientswho have been scheduled for surgical biopsy and resection. The tissue biopsy results, obtained at specific spatialcoordinates determined in the analysis, have been utilized to validate the methodology. It was found that in all casesthe lesion had extended into normal tissue, at least to the location where the sample was taken. In most cases, theproposed method suggested that the lesion had extended several millimetres beyond the point from where the biopsysample was taken. In some cases, the extent of the lesion into normal tissue was well beyond the boundary seen on T 1 -or T 2 -weighted images. It is concluded that the proposed approach indicates brain tumor infiltration more preciselythan what is visualized in the original NMR images and therefore its utilization facilitates proper treatment planningfor the cerebral tumor patients. 1998 John Wiley & Sons, Ltd.KEYWORDS: pattern recognition; pattern analysis; magnetic resonance imaging; image processing
Databáze: OpenAIRE
Externí odkaz: