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

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

User-steered balloon: Application to Thigh Muscle Segmentation of Visible Human

사용자 조정 풍선 : Visible Human의 다리 근육 분할의 적용

  • 이정호 (숭실대학교 정보통신전자공학부) ;
  • 김동성 (숭실대학교 정보통신전자공학부) ;
  • 강흥식 (서울대학교 의과대학)
  • Published : 2000.03.15
Download PDF
⟨ Previous Next ⟩

Abstract

Medical image segmentation, which is essential in diagnosis and 3D reconstruction, is performed manually in most applications to produce accurate results. However, manual segmentation requires lots of time to segment, and is difficult even for the same operator to reproduce the same segmentation results for a region. To overcome such limitations, we propose a convenient and accurate semiautomatic segmentation method. The proposed method initially receives several control points of an ROI(Region of Interest Region) from a human operator, and then finds a boundary composed of a minimum cost path connecting the control points, which is the Live-wire method. Next, the boundary is modified to overcome limitations of the Live-wire, such as a zig-zag boundary and erosion of an ROI. Finally, the region is segmented by SRG(Seeded Region Growing), where the modified boundary acts as a blockage to prevent leakage. The proposed User-steered balloon method can overcome not only the limitations of the Live-wire but also the leakage problem of the SRG. Segmentation results of thigh muscles of the Visible Human are presented.

진단이나 인체 모델의 형성에 있어서 필수적인 의료 영상의 분할(Segmentation)은 정확성을 얻기 위해 대부분 수작업에 의해 수행되고 있다. 하지만 수작업은 많은 시간이 소비되며, 같은 영역을 재분할했을 때 동일한 결과를 얻기가 어렵다. 이를 해결하기 위해 본 논문에서는 사용하기 편리하면서 수작업의 정확성을 유지할 수 있는 반자동화된 영상 분할방법을 제안한다. 제안된 방법은 먼저 사용자로부터 분할하고자 하는 영역의 경계에 해당하는 제어점을 몇 개 입력받고 제어점들간의 최소 비용 경로를 연결하여 외곽선을 획득하는 Live-wire를 수행한다. 하지만 Live-wire는 톱날 모양의 외곽선을 형성하거나 영역의 침식을 발생시키므로, 이러한 문제점을 해결하기 위해서 획득된 분할 영역의 외곽선을 재설정시킨 후 이것을 장벽으로 사용하여 SRG(Seeded Region Growing)을 수행하였다. 제안된 User-steered balloon방법은 Live-wire의 문제점을 해결할 뿐만 아니라, SRG가 성장시 새어나가는(Leakage) 문제점도 해결할 수 있다. 본 논문에서는 제안된 방법을 가지고 Visible Human의 다리 근육에 대한 분할을 수행하여 제안된 방법을 검증하였다.

Keywords

References

  1. R.Adams and L.Bischof, 'Seeded Region Growing,' IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 16, No. 6, pp. 641-647, 1994 https://doi.org/10.1109/34.295913
  2. W.Lie, 'Automatic Target Segmentation by Locally Adaptive Image Thresholding,' IEEE Transaction on Image Processing, Vol. 4, No. 7, pp. 1036-1041, 1995 https://doi.org/10.1109/83.392347
  3. C.Li, D.Godlgof. and L.Hall, 'Knowledge-Based Classification and Tissue Labeling of MR Images of Human Brain,' IEEE Transaction on Medical Image, Vol. 12, No. 2, pp. 740-750, 1993 https://doi.org/10.1109/42.251125
  4. M.Kass, A.Witkin, and D.Terzopoulus. 'Snakes: Active Contour Models,' International Journal of Computer Vision, Vol. 1, pp. 312-331, 1988 https://doi.org/10.1007/BF00133570
  5. J.Snell, M.Merickel, J. M. Ortega, J. C. Goble, J. Brookeman, and N. Kassell, 'Segmentation of The Brain from 3-D MRI Using a Hierarchical Active Surface Templete,' Proceeding of SPIE: Medical Imaging, Vol. 2167. pp. 2-9, 1994 https://doi.org/10.1117/12.175044
  6. T.Kapur, W.Grimson, W.Wells III, and R.Kinis, 'Segmentation of Brain Tissue from Magnetic Resonance Images,' Medical Image Analysis, Vol 1. No. 2, pp. 109-127, 1996 https://doi.org/10.1016/S1361-8415(96)80008-9
  7. F.Lachrnann and C.Barillot, 'Brain Tissue Classification from MRI Data by Means of Texture Analysis,' Proceeding of SPIE: Medical Imaging VI: Image Processing, Vol. 1652, pp. 72-83, 1992 https://doi.org/10.1117/12.59413
  8. A.Chakraborty, L.H.Staib, and J,S.Duncan, 'An Integrated Approach to Boundary Finding in Medical Images,' Proceeding of IEEE Workshop on Biomedical Image Analysis. pp. 13-22, 1994 https://doi.org/10.1109/BIA.1994.315870
  9. Michale J. Ackerman, 'The Visible Human Project,' Procedings of the IEEE, Vol. 86, No. 3, pp. 504-514, 1998 https://doi.org/10.1109/5.662875
  10. George R. Thoma and L.Rodney Long, 'Compressing and Transmitting Visible Human Images', IEEE Multimedia , Vol. 4, No. 2, pp. 36-45, 1997 https://doi.org/10.1109/93.591160
  11. W.Barrett and E.Mortensen, 'Interactive Live-Wire Boundary Extraction,' Medical Image Analysis, Vol. 1, No. 4, pp. 331-341, 1997 https://doi.org/10.1016/S1361-8415(97)85005-0
  12. T.Schiemann, U.Tiede, and K.Hohne, 'Segmentation of the Visible Human for High-Quality Volume-Based Visualization,' Medical Image Analysis, Vol. 1, No. 4, pp. 263-270, 1997 https://doi.org/10.1016/S1361-8415(97)85001-3
  13. M.Gleicher, 'Image Snapping,' Proceeding of ACM SIGGRAPH 95: Computer Graphics and Interactive Techniques, pp. 183-190, 1995 https://doi.org/10.1145/218380.218441
  14. R.Gonzalez and R.Woods, Digital Image Processing, pp. 416-423, Addison Wesley, 1993
  15. Ramesh Jain, Rangachar Kasturi, and Brian G. Schunck, Machine Vision, pp. 134-136, McGraw- Hill, 1995
  16. 이정호, 김동성, 강흥식, 'Visible Human 영상분할을 위한 Live-Ribbon : 다리 근육 분할의 적용', 신호처리 합동 학술 대회, Vol. 11, No. 1, pp. 11-14, 1998