Presentation | 2006-12-01 The Speckle Reduction and Boundary Emphasis on Medical Ultrasonic Images using the Neural Network Kenjiro MARUYAMA, Masakuni OSHIRO, Ken YOKAWA, Toshihiro NISHIMURA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | An Ultrasound equipment has been widely used in medical scenes. Ultrasound propagates with safety wave and is also non-invasive. In spite of the benefits, however, Ultrasonic Images have contained speckle noise. Speckle is complex phenomenon. Speckle appears interference of back-scattered wave from many microscopic diffused reflection which passing through internal organs. A Neural Network can perform a nonlinear processing and construct input and output system of demanding by learning. In this study, we present the Neural Network architecture that is used for a reduction of speckle noise having nonlinear property. The Neural Network architecture consists of 3 layers. In input and hidden layer, each unit was arranged two dimension. The layers to which two dimensions were arranged perform image processing as nonlinear filter. A Processed image was made by simulated speckle noise model. The Network was trained with the backpropagation algorithm using ultrasonic image model for the reduction noise. After training, an effect of noise reduction was simulated using the network. In consequence of simulation, the network processed the image included few noise and keeping edges very well. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Ultrasonic image / Neural Network / Speckle / Boundary Emphasis |
Paper # | IE2006-105 |
Date of Issue |
Conference Information | |
Committee | IE |
---|---|
Conference Date | 2006/11/24(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 | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | The Speckle Reduction and Boundary Emphasis on Medical Ultrasonic Images using the Neural Network |
Sub Title (in English) | |
Keyword(1) | Ultrasonic image |
Keyword(2) | Neural Network |
Keyword(3) | Speckle |
Keyword(4) | Boundary Emphasis |
1st Author's Name | Kenjiro MARUYAMA |
1st Author's Affiliation | Graduate School of Information, Production and Systems, Waseda University() |
2nd Author's Name | Masakuni OSHIRO |
2nd Author's Affiliation | Graduate School of Information, Production and Systems, Waseda University |
3rd Author's Name | Ken YOKAWA |
3rd Author's Affiliation | Graduate School of Information, Production and Systems, Waseda University |
4th Author's Name | Toshihiro NISHIMURA |
4th Author's Affiliation | Graduate School of Information, Production and Systems, Waseda University |
Date | 2006-12-01 |
Paper # | IE2006-105 |
Volume (vol) | vol.106 |
Number (no) | 398 |
Page | pp.pp.- |
#Pages | 4 |
Date of Issue |