한국콘텐츠학회논문지 (The Journal of the Korea Contents Association)

한국콘텐츠학회 (The Korea Contents Association)
권호 표지
DOI QR코드

DOI QR Code

의료 영상처리에서의 물리적 이론을 활용한 객체 유효 인식 방법

Effective Object Recognition based on Physical Theory in Medical Image Processing

  • 은성종 (가천대학교 전자계산학과) ;
  • 황보택근 (가천대학교 IT대학 인터랙티브미디어학과)
  • 투고 : 2012.11.01
  • 심사 : 2012.12.05
  • 발행 : 2012.12.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

의료 영상처리 분야에서의 일반적인 객체 인식 방법은 영역 분할 알고리즘을 기반으로 처리되어진다. 컴퓨팅 분야에서의 이러한 영역 분할 알고리즘은 대부분 밝기 정보, 형태 정보, 패턴 분석 등 다양한 입력정보의 컴퓨팅 처리를 통해 처리된다. 그러나 이러한 컴퓨팅 방법으로는 앞서 언급된 입력 정보들이 의미가 없을 경우, 영역 분할에 많은 제약이 따르게 된다. 따라서 본 논문은 이러한 컴퓨팅 처리의 근본적인 제약사항을 해결하고자, MR 이론의 R2-map 정보 기반의 효과적인 영역 분할 방법은 제안하였다. 본 방법은 간 영역이 포함된 영상에서 실험하였으며, R2-map의 특징점들을 2차원 영역성장법의 씨앗점으로 설정한 후, 검출된 영역의 최종 경계선 보정작업을 통해 경계가 모호하더라도 영역 분할이 가능하게끔 하였다. 해당 영상의 실험 결과, 평균 7.5%의 평균 영역 차이로 기존의 대표 영역 분할 알고리즘에 비해 높은 정확도가 산출되었다.

In medical image processing field, object recognition is usually processed based on region segmentation algorithm. Region segmentation in the computing field is carried out by computerized processing of various input information such as brightness, shape, and pattern analysis. If the information mentioned does not make sense, however, many limitations could occur with region segmentation during computer processing. Therefore, this paper suggests effective region segmentation method based on R2-map information within the magnetic resonance (MR) theory. In this study, the experiment had been conducted using images including the liver region and by setting up feature points of R2-map as seed points for 2D region growing and final boundary correction to enable region segmentation even when the border line was not clear. As a result, an average area difference of 7.5%, which was higher than the accuracy of conventional exist region segmentation algorithm, was obtained.

키워드

참고문헌

  1. Lih-Shyang Chen and R. Marc, Sontag, "Representation, Display, Manipulation of 3D Digital Scene and Their Medical Application," Computer Graphisc and Image Processing, Vol.48, pp.190-216, 1992.
  2. S. Hemachande, A. Verma, S. Arora, and Prasanta K. Panigrahi, Locally Adaptive Block Thresholding Method with Continuity Cons traint. Pattern Recognition Letters, Vol.28, pp.119-124, 2007. https://doi.org/10.1016/j.patrec.2006.06.005
  3. C. C. Kang and W. J. Wang, A Novel Edge Detection Method Based on Maximization of the Objective Function. Pattern Recognition, Vol.40, No.2, pp.609-618, 2007. https://doi.org/10.1016/j.patcog.2006.03.016
  4. R. C. Gonzalez and P. Wintz, Digital Image Processing, 3rd Ed., Addison-Wesley, 1993.
  5. Norio Baba, Norihiko Ichse, and Toshiyuki Tanaka, Image Area Extraction of Biological Objects from a Thin Section Image by Statistical Texture Analysis. Electron Microse, Vol.45, pp.298-306, 1996. https://doi.org/10.1093/oxfordjournals.jmicro.a023446
  6. R. I. Shrager, G. H. Weiss, and R. G. S. Spence, NMR Biomed., Vol.11, pp.297-305, 1998. https://doi.org/10.1002/(SICI)1099-1492(199810)11:6<297::AID-NBM531>3.0.CO;2-A
  7. R. V. Damadian, Science, Vol.171, pp.1151-1153, 1971. https://doi.org/10.1126/science.171.3976.1151
  8. R. A. de Graaf, P. B. Brown, S. McIntyre, T. W. Nixon, K. L. Behar, and D. L. Rothman, Magn, Reson.Med., Vol.56, pp.386-394, 2006. https://doi.org/10.1002/mrm.20946
  9. Pippa Storey, PhD, Alexis, A. Thompson, Christine L. Carqueville, BA, John C. Wood, R. Andrew de Freitas, and Cynthia K. Rigsby, R2${\ast}$ Imaging of Transfusional Iron Burden at 3T and Comparison with 1.5T, JOURNAL OF MAGNETIC RESONANCE IMAGING, Vol.25, pp.540-547, 2007 https://doi.org/10.1002/jmri.20816
  10. P. B. Kingsley, Concepts in Magn. Reson., Vol.11, pp.29-49, 1999. https://doi.org/10.1002/(SICI)1099-0534(1999)11:1<29::AID-CMR2>3.0.CO;2-M
  11. E. M. Haacke, R. W. Brown, M. R. Thompson, and R. Venkatesan, Magnetic Resonance Imaging:Physical Principles and Sequence Design, John Wiley & Sons Inc., USA., pp.129-133, 1999.
  12. E. M. Haacke, R. W. Brown, M. R. Thompson, and R. Venkatesan, Magnetic Resonance Imaging:Physical Principles and Sequence Design, John Wiley & Sons Inc., USA., pp.118-123, 1999.
  13. S. M. Pizer, R. E. Johnston, J. P. Ericksen, B. C. Yankaskas, and K. E. Muller, "Contrast-limited adaptive histogram equalization: speed and effectiveness," Visualization in Biomedical Computing, pp.337-345, 1990.
  14. B. Chande and D. Dutta Majumder, "A note on the graylevel co-occurrence matrix in threshold selection," Signal Processing, Vol.15, No.2, 1988(9).
  15. N. Otsu, "A Thresholding Selection Method from Gray-scale Histogram," In IEEE Transactions on System, Man, and Cybernetics, Vol.9, No.1, pp.62-66, 1979. https://doi.org/10.1109/TSMC.1979.4310076
  16. D. M. Gavrila, Daimler-Benz AG, "Multifeature Hierarchical Template Matching Using Distance Transforms", IEEE International Conference on Pattern Recognition, 1998.
  17. Umut Orguner, Fredrik Gustafsson, "Statistical Characteristics of Harris Corner Detector," IEEE/SP 14th Workshop, pp.571-575, 2007.
  18. E. Catmull, and R. Rom, "A class of local interpolating splines," Computer Aided Geome tric Design, pp.317-326, 1974
  19. J. L Muerle and D. C.Allen, Experimental Evaluation of a Technique for Automatic Seg mentation of Objects in Complex Scenes. IPPR, Thopmson, 1968.
  20. M. Kass and A. Witkin, Demetri Terzopoulos Active Contour Models. International Journal of Computer Vision, Vol.1, pp.321-331, 1988. https://doi.org/10.1007/BF00133570

피인용 문헌

  1. Edge Detection Method for Inspection of Nuclear Fuel Rods vol.13, pp.10, 2013, https://doi.org/10.5392/JKCA.2013.13.10.046