Ultrasonic image analysis for liver diagnosis

Yung-Nien Sun, M. H. Horng, Xi-Zhang Lin, J. Y. Wang

Research output: Contribution to journalReview article

43 Citations (Scopus)

Abstract

Ultrasonic image analysis provides a reliable and noninvasive method for measuring liver histology. This method enables the classification of liver states as normal, hepatitis, or liver cirrhosis. This method involves the definition of suitable settings for the ultrasonic device. Inhomogeneous structures from the area of interest in the image are removed and useful texture parameters are searched from the co-occurrence matrix, statistical feature matrix, texture spectrum, and fractal dimension descriptors, using the forward sequential search method. The selected parameters are then fed into a probabilistic neural network for the classification of liver disease.

Original languageEnglish
Pages (from-to)93-101
Number of pages9
JournalIEEE Engineering in Medicine and Biology Magazine
Volume15
Issue number6
DOIs
Publication statusPublished - 1996 Nov 1

Fingerprint

Ultrasonics
Liver
Image analysis
Textures
Ultrasonic devices
Fractals
Histology
Fractal dimension
Liver Cirrhosis
Hepatitis
Liver Diseases
Neural networks
Equipment and Supplies

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

@article{fc7065e9d09440b9bdae083190f2ec0e,
title = "Ultrasonic image analysis for liver diagnosis",
abstract = "Ultrasonic image analysis provides a reliable and noninvasive method for measuring liver histology. This method enables the classification of liver states as normal, hepatitis, or liver cirrhosis. This method involves the definition of suitable settings for the ultrasonic device. Inhomogeneous structures from the area of interest in the image are removed and useful texture parameters are searched from the co-occurrence matrix, statistical feature matrix, texture spectrum, and fractal dimension descriptors, using the forward sequential search method. The selected parameters are then fed into a probabilistic neural network for the classification of liver disease.",
author = "Yung-Nien Sun and Horng, {M. H.} and Xi-Zhang Lin and Wang, {J. Y.}",
year = "1996",
month = "11",
day = "1",
doi = "10.1109/51.544516",
language = "English",
volume = "15",
pages = "93--101",
journal = "IEEE Pulse",
issn = "2154-2287",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

Ultrasonic image analysis for liver diagnosis. / Sun, Yung-Nien; Horng, M. H.; Lin, Xi-Zhang; Wang, J. Y.

In: IEEE Engineering in Medicine and Biology Magazine, Vol. 15, No. 6, 01.11.1996, p. 93-101.

Research output: Contribution to journalReview article

TY - JOUR

T1 - Ultrasonic image analysis for liver diagnosis

AU - Sun, Yung-Nien

AU - Horng, M. H.

AU - Lin, Xi-Zhang

AU - Wang, J. Y.

PY - 1996/11/1

Y1 - 1996/11/1

N2 - Ultrasonic image analysis provides a reliable and noninvasive method for measuring liver histology. This method enables the classification of liver states as normal, hepatitis, or liver cirrhosis. This method involves the definition of suitable settings for the ultrasonic device. Inhomogeneous structures from the area of interest in the image are removed and useful texture parameters are searched from the co-occurrence matrix, statistical feature matrix, texture spectrum, and fractal dimension descriptors, using the forward sequential search method. The selected parameters are then fed into a probabilistic neural network for the classification of liver disease.

AB - Ultrasonic image analysis provides a reliable and noninvasive method for measuring liver histology. This method enables the classification of liver states as normal, hepatitis, or liver cirrhosis. This method involves the definition of suitable settings for the ultrasonic device. Inhomogeneous structures from the area of interest in the image are removed and useful texture parameters are searched from the co-occurrence matrix, statistical feature matrix, texture spectrum, and fractal dimension descriptors, using the forward sequential search method. The selected parameters are then fed into a probabilistic neural network for the classification of liver disease.

UR - http://www.scopus.com/inward/record.url?scp=0030297488&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030297488&partnerID=8YFLogxK

U2 - 10.1109/51.544516

DO - 10.1109/51.544516

M3 - Review article

AN - SCOPUS:0030297488

VL - 15

SP - 93

EP - 101

JO - IEEE Pulse

JF - IEEE Pulse

SN - 2154-2287

IS - 6

ER -