Ultrasonic diagnosis of cirrhosis based on preprocessing using pyramid recurrent neural network

Jianming Lu, Jiang Liu, Xueqin Zhao, Takashi Yahagi

Research output: Contribution to journalArticle

Abstract

In this paper, a pyramid recurrent neural network is applied to characterize the hepatic parenchymal diseases in ultrasonic B-scan texture. The cirrhotic parenchymal diseases are classified into four types according to the size of hypoechoic nodular lesions. The B-mode patterns are wavelet transformed, and then the compressed data are fed into a pyramid neural network to diagnose the type of cirrhotic diseases. Compared with the three-layer neural networks, the performance of the proposed pyramid recurrent neural network is improved by a more efficient utilization of lower layers. Simulation results show that the proposed system is suitable for diagnosis of cirrhosis diseases.

Original languageEnglish
Pages (from-to)10-19
Number of pages10
JournalElectronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)
Volume91
Issue number7
DOIs
Publication statusPublished - 2008

Fingerprint

Recurrent neural networks
Pyramid
Recurrent Neural Networks
preprocessing
pyramids
Preprocessing
ultrasonics
Ultrasonics
Neural Networks
Neural networks
lesions
Texture
Wavelets
textures
Textures
Simulation
simulation

Keywords

  • Cirrhosis
  • Discrete wavelet transform
  • Pyramid recurrent neural network

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications
  • Physics and Astronomy(all)
  • Signal Processing
  • Applied Mathematics

Cite this

@article{06155e93848644c999578008b06a9b05,
title = "Ultrasonic diagnosis of cirrhosis based on preprocessing using pyramid recurrent neural network",
abstract = "In this paper, a pyramid recurrent neural network is applied to characterize the hepatic parenchymal diseases in ultrasonic B-scan texture. The cirrhotic parenchymal diseases are classified into four types according to the size of hypoechoic nodular lesions. The B-mode patterns are wavelet transformed, and then the compressed data are fed into a pyramid neural network to diagnose the type of cirrhotic diseases. Compared with the three-layer neural networks, the performance of the proposed pyramid recurrent neural network is improved by a more efficient utilization of lower layers. Simulation results show that the proposed system is suitable for diagnosis of cirrhosis diseases.",
keywords = "Cirrhosis, Discrete wavelet transform, Pyramid recurrent neural network",
author = "Jianming Lu and Jiang Liu and Xueqin Zhao and Takashi Yahagi",
year = "2008",
doi = "10.1002/ecj.10121",
language = "English",
volume = "91",
pages = "10--19",
journal = "Electronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)",
issn = "8756-663X",
publisher = "Scripta Technica",
number = "7",

}

TY - JOUR

T1 - Ultrasonic diagnosis of cirrhosis based on preprocessing using pyramid recurrent neural network

AU - Lu, Jianming

AU - Liu, Jiang

AU - Zhao, Xueqin

AU - Yahagi, Takashi

PY - 2008

Y1 - 2008

N2 - In this paper, a pyramid recurrent neural network is applied to characterize the hepatic parenchymal diseases in ultrasonic B-scan texture. The cirrhotic parenchymal diseases are classified into four types according to the size of hypoechoic nodular lesions. The B-mode patterns are wavelet transformed, and then the compressed data are fed into a pyramid neural network to diagnose the type of cirrhotic diseases. Compared with the three-layer neural networks, the performance of the proposed pyramid recurrent neural network is improved by a more efficient utilization of lower layers. Simulation results show that the proposed system is suitable for diagnosis of cirrhosis diseases.

AB - In this paper, a pyramid recurrent neural network is applied to characterize the hepatic parenchymal diseases in ultrasonic B-scan texture. The cirrhotic parenchymal diseases are classified into four types according to the size of hypoechoic nodular lesions. The B-mode patterns are wavelet transformed, and then the compressed data are fed into a pyramid neural network to diagnose the type of cirrhotic diseases. Compared with the three-layer neural networks, the performance of the proposed pyramid recurrent neural network is improved by a more efficient utilization of lower layers. Simulation results show that the proposed system is suitable for diagnosis of cirrhosis diseases.

KW - Cirrhosis

KW - Discrete wavelet transform

KW - Pyramid recurrent neural network

UR - http://www.scopus.com/inward/record.url?scp=62249184431&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=62249184431&partnerID=8YFLogxK

U2 - 10.1002/ecj.10121

DO - 10.1002/ecj.10121

M3 - Article

AN - SCOPUS:62249184431

VL - 91

SP - 10

EP - 19

JO - Electronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)

JF - Electronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)

SN - 8756-663X

IS - 7

ER -