Proceedings of the KIEE Conference (대한전기학회:학술대회논문집)

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지

Detection of Abnormal Regions Neural-Network In Chest Photofluorography

신경회로망을 이용한 흉부 X-선 간접촬영에서의 병변검출

  • Lee, Hoo-Min (Department of Radiotechnology Dongnam Health College) ;
  • Yun, Kwang-Ho (Department of Electrical Engineering Kon-Kuk University) ;
  • Kim, Sang-Hoon (Department of Electrical Engineering Kon-Kuk University) ;
  • Nam, Moon-Hyun (Department of Electrical Engineering Kon-Kuk University)
  • 이후민 (동남보건대학 방사선과) ;
  • 윤광호 (건국대학교 전기공학과) ;
  • 김상훈 (건국대학교 전기공학과) ;
  • 남문현 (건국대학교 전기공학과)
  • Published : 2000.07.17
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we have developed an automated computer aided diagnostic (CAD) scheme by using artificial neural networks(ANN) on guantitative analysis of chest photofluorography. The first ANN performs the detection of suspicious regions in a low resolution image. This was trained specifically on the problem of detecting abnormal regions digitized chest photofluorography. The second space matching method was used to distinguish between normal and abnormal regions of interest(ROI). If the ratio of the number of abnormal ROI to the total number of all ROI in a chest image was greater than a specified threshold level, the image was classified as abnormal.

Keywords