Proceedings of the KOSOMBE Conference (대한의용생체공학회:학술대회논문집)

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

Automatic Multi-threshold Detection Algorithm for the Segmentation of Echocardiographic Images

심초음파 영상의 영역 분류를 위한 다중 문턱치 자동 검출 알고리듬

  • Choi, Chang-Hou (Dept. of Electronics, Kyungpook National University) ;
  • Koo, Sung-Mo (Dept. of Electronics, Kyungpook National University) ;
  • Kim, Myoung-Nam (Dept. of Electronics, Kyungpook National University) ;
  • Cho, Sung-Mok (Dept. of Electronics, Kyungpook National University) ;
  • Cho, Jin-Ho (Dept. of Electronics, Kyungpook National University and Dept. of Biomedical Eng., Kyungpook National University Hospital)
  • 최창효 (경북대학교 전자공학과) ;
  • 구성모 (경북대학교 전자공학과) ;
  • 김명남 (경북대학교 전자공학과) ;
  • 조성목 (경북대학교 전자공학과) ;
  • 조진호 (경북대학교 전자공학과 및 경북대학교병원 의공학과)
  • Published : 1994.12.03
Download PDF
⟨ Previous Next ⟩

Abstract

An automatic multi-threshold algorithm for segmentation of 2D ultrasound images based on average filtering and the characteristics of speckle noise in 2D ultrasound image is proposed. To do this, we investigate the histogram of difference between $7{\times}7$ averaging histogram and $3{\times}3$ averaging histogram. And, we find zero crossing points in the positive portion of the differenced histogram and select middle points of the zero crossing points. We assign these selected points to characteristic points. The thresholds are the center of two characteristic points. Then we segment 2D ultrasound image by using these thresholds and extract edges from applying edge operator to optimal segmented image. Experimental results show that the segmented regions are devided accurately around the homogeneous region.

Keywords