Proceedings of the KOSOMBE Conference (대한의용생체공학회:학술대회논문집)
- Volume 1990 Issue 05
- /
- Pages.33-37
- /
- 1990
Lung Area Segmentation in Chest Radiograph Using Neural Network
신경회로망을 이용한 흉부 X-선 영상에서의 폐 영역분할
- Kim, Jong-Hyo (Dept. of Biomed. Eng., college of Med., SNU.) ;
- Park, Kwang-Suk (Dept. of Biomed. Eng., college of Med., SNU.) ;
- Min, Byoung-Goo (Dept. of Biomed. Eng., college of Med., SNU.) ;
- Im, Jung-Gi (Dept. of Radiology, college of Med., SNU.) ;
- Han, Man-Cheong (Dept. of Radiology, college of Med., SNU.) ;
- Lee, Choong-Woong (Dept. of Elec. Eng., SNU.)
- 김종효 (서울의대 의공학교실) ;
- 박광석 (서울의대 의공학교실) ;
- 민병구 (서울의대 의공학교실) ;
- 임정기 (서울의대 방사선학 교실) ;
- 한만청 (서울의대 방사선학 교실) ;
- 이충웅 (서울 대학교 전자공학과)
- Published : 1990.05.23
Abstract
In this paper, a new method for lung area segmentation in chest radiographs has been presented. The movivation of this study is to include fuzzy informations about the relation between the image date structure and the area to be segmented in the segmentation process efficiently. The proposed method approached the segmentation problem in the perspective of pattern classification, using trainable pattern classifier, multi-layer perceptron. Having been trained with 10 samples, this method gives acceptable segmentation results, and also demonstrated the desirable property of giving better results as the training continues with more training samples.
Keywords