Document Detail


Handcrafted fuzzy rules for tissue classification.
MedLine Citation:
PMID:  18479879     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
This article proposes a handcrafted fuzzy rule-based system for segmentation and identification of different tissue types in magnetic resonance (MR) brain images. The proposed fuzzy system uses a combination of histogram and spatial neighborhood-based features. The intensity variation from one type of tissue to another is gradual at the boundaries due to the inherent nature of the MR signal (MR physics). A fuzzy rule-based approach is expected to better handle these variations and variability in features corresponding to different types of tissues. The proposed segmentation is tested to classify the pixels of the T2-weighted axial MR images of the brain into three primary tissue types: white matter, gray matter and cerebral-spinal fluid. The results are compared with those from manual segmentation by an expert, demonstrating good agreement between them.
Authors:
Shashi Bhushan Mehta; Santanu Chaudhury; Asok Bhattacharyya; Amarnath Jena
Related Documents :
4034959 - Wilson disease of the brain: mr imaging.
15987979 - Intracortical lesions in multiple sclerosis: improved detection with 3d double inversio...
7726069 - Magnetization transfer imaging of periventricular hyperintense white matter in the elde...
2014309 - Osteogenic sarcoma: mr signal abnormalities of the brain in asymptomatic patients treat...
740209 - Leukoencephalopathy following high-dose intravenous methotrexate chemotherapy: quantita...
15856249 - 1h chemical shift imaging of the brain in guanidino methyltransferase deficiency, a cre...
19328379 - Disparities in use of computed tomography for patients presenting with headache.
8485299 - Linear dichroism demonstrates that the bases in poly[d(ac)].poly[d (gt)] and poly[d(ag)...
16279069 - Chord-based versus voxel-based methods of electron transport in the skeletal tissues.
Publication Detail:
Type:  Journal Article     Date:  2008-05-13
Journal Detail:
Title:  Magnetic resonance imaging     Volume:  26     ISSN:  0730-725X     ISO Abbreviation:  Magn Reson Imaging     Publication Date:  2008 Jul 
Date Detail:
Created Date:  2008-07-01     Completed Date:  2008-12-03     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  8214883     Medline TA:  Magn Reson Imaging     Country:  United States    
Other Details:
Languages:  eng     Pagination:  815-23     Citation Subset:  IM    
Affiliation:
Philips Innovation Campus, Nagavara, Bangalore 560045, India. sbm20@yahoo.com
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Brain / anatomy & histology*
Fuzzy Logic
Humans
Image Processing, Computer-Assisted
Magnetic Resonance Imaging*
Pattern Recognition, Automated

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Feasibility of using hyperpolarized [1-13C]lactate as a substrate for in vivo metabolic 13C MRSI stu...
Next Document:  Pharmacokinetic study of matrine, oxymatrine and oxysophocarpine in rat plasma after oral administra...