Proceedings of the KOSOMBE Conference (대한의용생체공학회:학술대회논문집)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지

Ultrasonic image diagnosis using pattern recognition

패턴인식을 이용한 초음파 화상의 진단

  • Choi, K.C. (Dept. of Electronic Eng., Hanyang University) ;
  • Kim, S.I. (Dept of Mesuring Eng., Hanyang University) ;
  • Lee, D.S. (Dept. of Electronic Eng., Hanyang University)
  • 최광철 (한양대학교 전자공학과) ;
  • 김선일 (한양대학교 의과대학 계량의학 교실) ;
  • 이두수 (한양대학교 전자공학과)
  • Published : 1991.11.15
Download PDF
⟨ Previous Next ⟩

Abstract

A new approach to texture classification for ultrasound liver diagnosis using run difference matrix was developed. The run difference matrix consists of the gray level difference along with distance. From this run difference matrix, we defined several parameters such as LDE, LDEL, NUF, SMO, SMG, SHP etc. and three vectors namely DOD, DGD and DAD. Each parameter value calculated in fatty cirrhotic, chronic hepatitic and normal liver mage was plotted in two dimensional plane. We compared our results with run length method. There are several advantages of run difference matrix method over the run lengths. 1) It is more sensitive to small difference of gray level distribution. 2) The parameters provide more statistically significant value. Images were classified with the extracted parameters to each diseases using neural networks. In preliminary clinical exprements, this approach showed satisfying results.

Keywords