Segmentation of large brain lesions

This paper describes a region-growing algorithm for the segmentation of large lesions in T/sub 1/-weighted magnetic resonance (MR) images of the head. The algorithm involves a gray level similarity criterion to expand the region and a size criterion to prevent from over-growing outside the lesion. T...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on medical imaging 2001-07, Vol.20 (7), p.666-669
Main Authors: Hojjatoleslami, S.A., Kruggel, F.
Format: Article
Language:English
Subjects:
Algorithms
Biological and medical sciences
Brain
Brain - pathology
Brain Diseases - pathology
Computer aided software engineering
Criteria
Fourier Analysis
Hemorrhaging
Image Processing, Computer-Assisted
Image segmentation
Imaging, Three-Dimensional
Inspection
Investigative techniques, diagnostic techniques (general aspects)
Lesions
Magnetic heads
Magnetic resonance
Magnetic resonance imaging
Magnetic Resonance Imaging - methods
Medical imaging
Medical sciences
Miscellaneous. Technology
Multiple sclerosis
Neuroscience
Pathology
Protocols
Radiodiagnosis. Nmr imagery. Nmr spectrometry
Segmentation
Sensitivity and Specificity
Similarity
Statistical methods
Three dimensional
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper describes a region-growing algorithm for the segmentation of large lesions in T/sub 1/-weighted magnetic resonance (MR) images of the head. The algorithm involves a gray level similarity criterion to expand the region and a size criterion to prevent from over-growing outside the lesion. The performance of tile algorithm is evaluated and validated on a series of pathologic three-dimensional MR images of the head.
ISSN:0278-0062
1558-254X
DOI:10.1109/42.932750