한국정보과학회논문지:소프트웨어및응용 (Journal of KIISE:Software and Applications)

한국정보과학회 (Korean Institute of Information Scientists and Engineers)
권호 표지

복부 CT 영상에서 신장암의 자동추출

Automatic Detection of Kidney Tumor from Abdominal CT Scans

  • 김도연 (충남대학교 컴퓨터공학과) ;
  • 노승무 (충남대학교 일반외과) ;
  • 조준식 (충남대학교 진단방사선과) ;
  • 김종철 (충남대학교 진단방사선과) ;
  • 박종원 (충남대학교 정보통신공학과)
  • 발행 : 2002.12.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문은 복부 컴퓨터단층촬영(CT) 영상에서의 자동화된 신장 및 신장암 추출에 관한 연구를 수행하였다. 필름으로 보관된 복부 CT 영상을 디지털화하여 영상분석을 수행하였으며, 명암값에 의한 임계값(Gray-Level Thresholding) 처리 기법을 사용하여 신장만을 분리하였다. 신장암의 샘플영상에 대한 텍스쳐(Texture)분석 결과를 토대로, 대표적인 통계적 모멘트 값인 평균 및 표준 편차값을 동질성 시험 기준으로 삼아 신장암의 SEED를 선택하였다. 선택된 SEED의 중앙 픽셀을 시작점으로 하여, 명암값을 동질성 시험기준으로 사용한 영역확장(Region Growing) 방법을 적용하여 신장암을 추출하였다. GE사의 Hispeed Advantage CT 스캐너를 사용하여 촬영된 9개의 예, 총 113매 영상을 Lumisys LS-40 필름 디지타이저로 디지털화 하여 적용한 결과, 85%의 신장암 추출 민감도를 가진다.

This paper describes automatic methods for detection of kidney and kidney tumor on abdominal CT scans. The abdominal CT images were digitalized using a film digitizer and a gray-level threshold method was used to segment the kidney. Based on texture analysis results, which were perform on sample images of kidney tumors, SEED region of kidney tumor was selected as result of homogeneity test. The average and standard deviation, which are representative statistical moments, were used to as an acceptance criteria for homogeneous test. Region growing method was used to segment the kidney tumor from the center pixel of selected SEED region using a gray-level value as an acceptance criteria for homogeneity test. These method were applied to 113 images of 9 cases, which were scanned by GE Hispeed Advantage CT scanner and digitalized by Lumisvs LS-40 film digitizer. The sensitivity was 85% and there was no false-positive results.

키워드

참고문헌

  1. Jayaram K. Udupa and Gabor T. Hermen, 3D Imaging in Medicine, p. 3-5, CRC Press, 1991
  2. John Bradley, XV : Interactive Image Display for the X Window System, p. 2-65, version 3.10a, 1994
  3. Lumisys, Inc., LSDT Software Functions Library Reference Guide, P/N 0066-022, Rev. 10, 1999
  4. M.J. Calotto, 'Histogram Analysis Using a Scale-Space Approach', IEEE Transaction on PAMI, pp. 121-129, 1987
  5. Scott E. Umbaugh, Computer Vision and Image Processing, p. 197-215, Prentice-Hall, Inc, 1998
  6. Dana H. Ballard and Christopher M. Brown, Computer Vision, p. 181-184, Prentice-Hall, Inc, 1982
  7. J.R.Parker, Algorithms for Image Processing and Computer Vision, p. 69-108, John-Wiley & Sons, Inc, 1997
  8. R.C. Gonzalez, R.E. Woods, Digital Image Processing, p. 458-465, 503-518, Addison-Wesley, 1992
  9. NEMA Draft Standards, Digital Imaging and Communications in Medicine (DICOM), Part 1-14
  10. D.Y. Kim, J.H. Kim, S.M. Noh, J.W. Park, 'Automated Detection and Volume Calculation of Nodular Lung Cancer on CT Scans', Journal of KISS :Computing Practices, Volume 7, Number 5, pp. 451-457, 2001, 10
  11. Giger ML, Bae KT, MacMahon H, 'Computerized Detection of Pulmonary Nodules in Computed Tomography Images', Investigate Radiology, Volume 29, Number 4, pp. 459-465, 1994 https://doi.org/10.1097/00004424-199404000-00013
  12. Okumura T, Miwa T, Kako j, et al, 'Computer aided diagnosis system for lung cancer based on helical CT images', Proceedings of Medical Imaging by SPIE, Volume 3034, pp. 975-984, 1997 https://doi.org/10.1117/12.274186
  13. Armato SG HI, Giger ML, Moran CJ, MacMahon H, Blackburn JT, Doi K, 'Computerized Detection of Pulmonary Nodules on CT Scans', RadioGraphic, Volume 19, pp. 1303-1311, 1999