A new approach to ultrasonic liver image classification

Jiann Shu Lee, Yung-Nien Sun, Xi-Zhang Lin

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In this paper, we have proposed a new method for diffuse liver disease classification with sonogram, including the normal liver, hepatitis and cirrhosis, from a new point of view "scale." The new system utilizes a multiscale analysis tool, called wavelet transforms, to analyze the ultrasonic liver images. A new set of features consisting of second order statistics derived from the wavelet transformed images is employed. From these features, we have found that the third scale is the representative scale for the classification of the considered liver diseases, and the horizontal wavelet transform can improve the representation of the corresponding features. Experimental results show that our method can achieve about 88% correct classification rate which is superior to other measures such as the co-occurrence matrices [1], the Fourier power spectrum [2], and the texture spectrum [3]-[5]. This implies that our feature set can access the granularity from sonogram more effectively. It should be pointed out that our features are powerful for discriminating the normal livers from the cirrhosis because there is no misclassification samples between the normal liver and the cirrhosis sets. In addition, the experimental results also verify the usefulness of "scale" because our multiscale feature set can gain eighteen percent advantage over the direct use of the statistical features. This means that the wavelet transform at proper scales can effectively increase the distances among the statistical feature clusters of different liver diseases.

Original languageEnglish
Pages (from-to)1301-1308
Number of pages8
JournalIEICE Transactions on Information and Systems
VolumeE83-D
Issue number6
Publication statusPublished - 2000 Jan 1

Fingerprint

Image classification
Liver
Ultrasonics
Wavelet transforms
Power spectrum
Textures
Statistics

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Cite this

@article{9d81746a4ed74774ab547b9aa2bc145d,
title = "A new approach to ultrasonic liver image classification",
abstract = "In this paper, we have proposed a new method for diffuse liver disease classification with sonogram, including the normal liver, hepatitis and cirrhosis, from a new point of view {"}scale.{"} The new system utilizes a multiscale analysis tool, called wavelet transforms, to analyze the ultrasonic liver images. A new set of features consisting of second order statistics derived from the wavelet transformed images is employed. From these features, we have found that the third scale is the representative scale for the classification of the considered liver diseases, and the horizontal wavelet transform can improve the representation of the corresponding features. Experimental results show that our method can achieve about 88{\%} correct classification rate which is superior to other measures such as the co-occurrence matrices [1], the Fourier power spectrum [2], and the texture spectrum [3]-[5]. This implies that our feature set can access the granularity from sonogram more effectively. It should be pointed out that our features are powerful for discriminating the normal livers from the cirrhosis because there is no misclassification samples between the normal liver and the cirrhosis sets. In addition, the experimental results also verify the usefulness of {"}scale{"} because our multiscale feature set can gain eighteen percent advantage over the direct use of the statistical features. This means that the wavelet transform at proper scales can effectively increase the distances among the statistical feature clusters of different liver diseases.",
author = "Lee, {Jiann Shu} and Yung-Nien Sun and Xi-Zhang Lin",
year = "2000",
month = "1",
day = "1",
language = "English",
volume = "E83-D",
pages = "1301--1308",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "6",

}

A new approach to ultrasonic liver image classification. / Lee, Jiann Shu; Sun, Yung-Nien; Lin, Xi-Zhang.

In: IEICE Transactions on Information and Systems, Vol. E83-D, No. 6, 01.01.2000, p. 1301-1308.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A new approach to ultrasonic liver image classification

AU - Lee, Jiann Shu

AU - Sun, Yung-Nien

AU - Lin, Xi-Zhang

PY - 2000/1/1

Y1 - 2000/1/1

N2 - In this paper, we have proposed a new method for diffuse liver disease classification with sonogram, including the normal liver, hepatitis and cirrhosis, from a new point of view "scale." The new system utilizes a multiscale analysis tool, called wavelet transforms, to analyze the ultrasonic liver images. A new set of features consisting of second order statistics derived from the wavelet transformed images is employed. From these features, we have found that the third scale is the representative scale for the classification of the considered liver diseases, and the horizontal wavelet transform can improve the representation of the corresponding features. Experimental results show that our method can achieve about 88% correct classification rate which is superior to other measures such as the co-occurrence matrices [1], the Fourier power spectrum [2], and the texture spectrum [3]-[5]. This implies that our feature set can access the granularity from sonogram more effectively. It should be pointed out that our features are powerful for discriminating the normal livers from the cirrhosis because there is no misclassification samples between the normal liver and the cirrhosis sets. In addition, the experimental results also verify the usefulness of "scale" because our multiscale feature set can gain eighteen percent advantage over the direct use of the statistical features. This means that the wavelet transform at proper scales can effectively increase the distances among the statistical feature clusters of different liver diseases.

AB - In this paper, we have proposed a new method for diffuse liver disease classification with sonogram, including the normal liver, hepatitis and cirrhosis, from a new point of view "scale." The new system utilizes a multiscale analysis tool, called wavelet transforms, to analyze the ultrasonic liver images. A new set of features consisting of second order statistics derived from the wavelet transformed images is employed. From these features, we have found that the third scale is the representative scale for the classification of the considered liver diseases, and the horizontal wavelet transform can improve the representation of the corresponding features. Experimental results show that our method can achieve about 88% correct classification rate which is superior to other measures such as the co-occurrence matrices [1], the Fourier power spectrum [2], and the texture spectrum [3]-[5]. This implies that our feature set can access the granularity from sonogram more effectively. It should be pointed out that our features are powerful for discriminating the normal livers from the cirrhosis because there is no misclassification samples between the normal liver and the cirrhosis sets. In addition, the experimental results also verify the usefulness of "scale" because our multiscale feature set can gain eighteen percent advantage over the direct use of the statistical features. This means that the wavelet transform at proper scales can effectively increase the distances among the statistical feature clusters of different liver diseases.

UR - http://www.scopus.com/inward/record.url?scp=0033682947&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033682947&partnerID=8YFLogxK

M3 - Article

VL - E83-D

SP - 1301

EP - 1308

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 6

ER -