Determination of Tumor Boundaries on CT Images Using Unsupervised Clustering Algorithm

비교사적 군집화 알고리즘을 이용한 전산화 단층영상의 병소부위 결정에 관한 연구

  • Lee, Kyung-Hoo (Dept. of Radiation Oncology, Korea Cancer Center Hospital) ;
  • Ji, Young-Hoon (Dept. of Radiation Oncology, Korea Cancer Center Hospital) ;
  • Lee, Dong-Han (Dept. of Radiation Oncology, Korea Cancer Center Hospital) ;
  • Yoo, Seoung-Yul (Dept. of Radiation Oncology, Korea Cancer Center Hospital) ;
  • Cho, Chul-Koo (Dept. of Radiation Oncology, Korea Cancer Center Hospital) ;
  • Kim, Mi-Sook (Dept. of Radiation Oncology, Korea Cancer Center Hospital) ;
  • Yoo, Hyung-Jun (Dept. of Radiation Oncology, Korea Cancer Center Hospital) ;
  • Kwon, Soo-Il (Dept. of Medical Physics, Kyonggi University) ;
  • Chun, Jun-Chul (Dept. of Medical Physics, Kyonggi University)
  • 이경후 (원자력병원 방사선종양학과) ;
  • 지영훈 (원자력병원 방사선종양학과) ;
  • 이동한 (원자력병원 방사선종양학과) ;
  • 류성렬 (원자력병원 방사선종양학과) ;
  • 조철구 (원자력병원 방사선종양학과) ;
  • 김미숙 (원자력병원 방사선종양학과) ;
  • 유형준 (원자력병원 방사선종양학과) ;
  • 권수일 (경기대학교 의학물리학과) ;
  • 전준철 (경기대학교 의학물리학과)
  • Published : 2001.06.30

Abstract

It is a hot issue to determine the spatial location and shape of tumor boundary in fractionated stereotactic radiotherapy (FSRT). We could get consecutive transaxial plane images from the phantom (paraffin) and 4 patients with brain tumor using helical computed tomography(HCT). K-means classification algorithm was adjusted to change raw data pixel value in CT images into classified average pixel value. The classified images consists of 5 regions that ate tumor region (TR), normal region (NR), combination region (CR), uncommitted region (UR) and artifact region (AR). The major concern was how to separate the normal region from tumor region in the combination area. Relative average deviation analysis was adjusted to alter average pixel values of 5 regions into 2 regions of normal and tumor region to define maximum point among average deviation pixel values. And then we drawn gross tumor volume (GTV) boundary by connecting maximum points in images using semi-automatic contour method by IDL(Interactive Data Language) program. The error limit of the ROI boundary in homogeneous phantom is estimated within ${\pm}1%$. In case of 4 patients, we could confirm that the tumor lesions described by physician and the lesions described automatically by the K-mean classification algorithm and relative average deviation analyses were similar. These methods can make uncertain boundary between normal and tumor region into clear boundary. Therefore it will be useful in the CT images-based treatment planning especially to use above procedure apply prescribed method when CT images intermittently fail to visualize tumor volume comparing to MRI images.