Texture Classification for Liver Tissues from Ultrasonic B-Scan Images Using Testified PNN
Summary :
Visual criteria for diagnosing liver diseases, such as cirrhosis, from ultrasound images can be assisted by computerized texture classification. This paper proposes a system applying a PNN (Pyramid Neural Network) for classifying the hepatic parenchymal diseases in ultrasonic B-scan texture. In this study, we propose a multifractal-dimensions method to select the patterns for the training set and the validation sets. A modified box-counting algorithm is used to calculate the dimensions of the B-scan images. FDWT (Fast Discrete Wavelet Transform) is applied for feature extraction during the preprocessing. The structure of the proposed neural network is testified by training and validation sets by cross-validation method. The performance of the proposed system and a system based on the conventional multilayer network architecture is compared. The results show that, compared with the conventional 3-layer neural network, the performance of the proposed pyramid neural network is improved by efficiently utilizing the lower layer of the neural network.
- Publication
- IEICE TRANSACTIONS on Information Vol.E89-D No.8 pp.2420-2428
- Publication Date
- 2006/08/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1093/ietisy/e89-d.8.2420
- Type of Manuscript
- PAPER
- Category
- Pattern Recognition
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Yan SUN, Jianming LU, Takashi YAHAGI, "Texture Classification for Liver Tissues from Ultrasonic B-Scan Images Using Testified PNN" in IEICE TRANSACTIONS on Information,
vol. E89-D, no. 8, pp. 2420-2428, August 2006, doi: 10.1093/ietisy/e89-d.8.2420.
Abstract: Visual criteria for diagnosing liver diseases, such as cirrhosis, from ultrasound images can be assisted by computerized texture classification. This paper proposes a system applying a PNN (Pyramid Neural Network) for classifying the hepatic parenchymal diseases in ultrasonic B-scan texture. In this study, we propose a multifractal-dimensions method to select the patterns for the training set and the validation sets. A modified box-counting algorithm is used to calculate the dimensions of the B-scan images. FDWT (Fast Discrete Wavelet Transform) is applied for feature extraction during the preprocessing. The structure of the proposed neural network is testified by training and validation sets by cross-validation method. The performance of the proposed system and a system based on the conventional multilayer network architecture is compared. The results show that, compared with the conventional 3-layer neural network, the performance of the proposed pyramid neural network is improved by efficiently utilizing the lower layer of the neural network.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.8.2420/_p
Copy
@ARTICLE{e89-d_8_2420,
author={Yan SUN, Jianming LU, Takashi YAHAGI, },
journal={IEICE TRANSACTIONS on Information},
title={Texture Classification for Liver Tissues from Ultrasonic B-Scan Images Using Testified PNN},
year={2006},
volume={E89-D},
number={8},
pages={2420-2428},
abstract={Visual criteria for diagnosing liver diseases, such as cirrhosis, from ultrasound images can be assisted by computerized texture classification. This paper proposes a system applying a PNN (Pyramid Neural Network) for classifying the hepatic parenchymal diseases in ultrasonic B-scan texture. In this study, we propose a multifractal-dimensions method to select the patterns for the training set and the validation sets. A modified box-counting algorithm is used to calculate the dimensions of the B-scan images. FDWT (Fast Discrete Wavelet Transform) is applied for feature extraction during the preprocessing. The structure of the proposed neural network is testified by training and validation sets by cross-validation method. The performance of the proposed system and a system based on the conventional multilayer network architecture is compared. The results show that, compared with the conventional 3-layer neural network, the performance of the proposed pyramid neural network is improved by efficiently utilizing the lower layer of the neural network.},
keywords={},
doi={10.1093/ietisy/e89-d.8.2420},
ISSN={1745-1361},
month={August},}
Copy
TY - JOUR
TI - Texture Classification for Liver Tissues from Ultrasonic B-Scan Images Using Testified PNN
T2 - IEICE TRANSACTIONS on Information
SP - 2420
EP - 2428
AU - Yan SUN
AU - Jianming LU
AU - Takashi YAHAGI
PY - 2006
DO - 10.1093/ietisy/e89-d.8.2420
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2006
AB - Visual criteria for diagnosing liver diseases, such as cirrhosis, from ultrasound images can be assisted by computerized texture classification. This paper proposes a system applying a PNN (Pyramid Neural Network) for classifying the hepatic parenchymal diseases in ultrasonic B-scan texture. In this study, we propose a multifractal-dimensions method to select the patterns for the training set and the validation sets. A modified box-counting algorithm is used to calculate the dimensions of the B-scan images. FDWT (Fast Discrete Wavelet Transform) is applied for feature extraction during the preprocessing. The structure of the proposed neural network is testified by training and validation sets by cross-validation method. The performance of the proposed system and a system based on the conventional multilayer network architecture is compared. The results show that, compared with the conventional 3-layer neural network, the performance of the proposed pyramid neural network is improved by efficiently utilizing the lower layer of the neural network.
ER -
English
