Presentation 2008-12-18
Segmentation of Brain MR Images Using Unsupervised Hybrid Learning
Toshimitsu OTANI, Kazuhito SATO, Hirokazu MADOKORO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents a segmentation method using unsupervised hybrid learning of SOM (Self-Organizing Maps) and ART (Adaptive Resonance Theory) for brain MR (Magnetic Resonance) images only used in brightness characteristics and its distribution. This method consists of two steps. The first step is fine segmentation of brain tissues using SOM. The second step is to integrate categories using ART. We evaluated the method comparing with our former method only using SOM. The proposed method can extract according to the brain structures especially in CSF regions. Moreover we applied the method to clinical MR images. Objective classification results are obtained for diagnosis support for quantification of atrophy of the brain.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) MR images / SOM / FuzzyART / Segmentation / Quantification of atrophy of the brain
Paper # PRMU2008-154
Date of Issue

Conference Information
Committee PRMU
Conference Date 2008/12/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Segmentation of Brain MR Images Using Unsupervised Hybrid Learning
Sub Title (in English)
Keyword(1) MR images
Keyword(2) SOM
Keyword(3) FuzzyART
Keyword(4) Segmentation
Keyword(5) Quantification of atrophy of the brain
1st Author's Name Toshimitsu OTANI
1st Author's Affiliation Faculty of Systems Science and Technology, Akita Prefectural University()
2nd Author's Name Kazuhito SATO
2nd Author's Affiliation Faculty of Systems Science and Technology, Akita Prefectural University
3rd Author's Name Hirokazu MADOKORO
3rd Author's Affiliation Faculty of Systems Science and Technology, Akita Prefectural University
Date 2008-12-18
Paper # PRMU2008-154
Volume (vol) vol.108
Number (no) 363
Page pp.pp.-
#Pages 6
Date of Issue