Presentation 2007-11-30
The active artificial neural network by a neuro-fuzzy classification for speckle noise removal in medical ultrasound image
Hyungseok OH, Toshihiro NISHIMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Medical ultrasound image is one of the major diagnostic tool in medical image. However, ultrasound images are degraded by the random granular texture called speckle noise. Therefore, the speckle noise is considered dominant source of noise in ultrasound image. In this paper, we propose the active artificial neural network by a neuro-fuzzy classification for speckle noise removal in medical ultrasound image. The proposed method is based on the artificial neural network by back-propagation and utilized the neuro-fuzzy model to select one neural network among three artificial neural networks. Then, auto-threshold method is adopted to control the threshold value in neuro-fuzzy method. The proposed method is compared to other methods and evaluated the performance by prewitt edge detection. Finally, we verify the performance improvement in utilizing the new strategy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Ultrasound image / Speckle noise / Artificial Neural Network / Neuro-fuzzy Model / Auto-threshold method
Paper # IE2007-104
Date of Issue

Conference Information
Committee IE
Conference Date 2007/11/22(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 Image Engineering (IE)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) The active artificial neural network by a neuro-fuzzy classification for speckle noise removal in medical ultrasound image
Sub Title (in English)
Keyword(1) Ultrasound image
Keyword(2) Speckle noise
Keyword(3) Artificial Neural Network
Keyword(4) Neuro-fuzzy Model
Keyword(5) Auto-threshold method
1st Author's Name Hyungseok OH
1st Author's Affiliation Graduate school of Information, Production and Systems, Waseda University()
2nd Author's Name Toshihiro NISHIMURA
2nd Author's Affiliation Graduate school of Information, Production and Systems, Waseda University
Date 2007-11-30
Paper # IE2007-104
Volume (vol) vol.107
Number (no) 358
Page pp.pp.-
#Pages 4
Date of Issue