MR 영상에서 중간형상정보 생성을 통한 활성형상모델 기반 반월상 연골 자동 분할

Automatic Segmentation of the meniscus based on Active Shape Model in MR Images through Interpolated Shape Information

  • 김민정 (서울여자대학교 미디어학부) ;
  • 유지현 (서울여자대학교 미디어학부) ;
  • 홍헬렌 (서울여자대학교 미디어학부)
  • 투고 : 2010.08.11
  • 심사 : 2010.10.06
  • 발행 : 2010.11.15

초록

본 논문에서는 MR 영상에서 중간형상정보를 이용한 활성형상모델 기반의 반월상 연골 자동 분할 기법을 제안한다. 첫째, 훈련집합 내의 형상 변형을 반영하기 위해 반월상 연골 통계형상모델을 생성한다. 둘째, 큰 변형을 갖는 반월상 연골의 견고한 분할을 위해 유사도에 따른 가중치 기법을 이용하여 중간형상정보 생성 기법을 제안한다. 마지막으로 활성형상모탤 적합을 통해 반월상 연골 자동 분할을 수행한다. 제안 방법의 평가를 위하여 육안평가와 정확성 평가 그리고 수행시간을 측정하였다. 정확성 평가는 자동 분할과 반자동 분할 결과간의 평균거리차이를 측정하였고 이를 컬러맵으로 표현하였다. 실험 결과 평균거리차이는 내측 반월상 연골은 $0.54{\pm}0.16mm$, 외측 반월상 연골은 $0.73{\pm}0.39mm$으로 측정되었고, 수행시간은 평균 4.87초로 측정되었다.

In this paper, we propose an automatic segmentation of the meniscus based on active shape model using interpolated shape information in MR images. First, the statistical shape model of meniscus is constructed to reflect the shape variation in the training set. Second, the generation technique of interpolated shape information by using the weight according to shape similarity is proposed to robustly segment the meniscus with large variation. Finally, the automatic meniscus segmentation is performed through the active shape model fitting. For the evaluation of our method, we performed the visual inspection, accuracy measure and processing time. For accuracy evaluation, the average distance difference between automatic segmentation and semi-automatic segmentation are calculated and visualized by color-coded mapping. Experimental results show that the average distance difference was $0.54{\pm}0.16mm$ in medial meniscus and $0.73{\pm}0.39mm$ in lateral meniscus. The total processing time was 4.87 seconds on average.

키워드

참고문헌

  1. Cemal Kose, Okyay Gencalioglu, Ugur Sevik, "An automatic diagnosis method for the knee meniscus tears in MR images," Expert Systems with Applications, vol.36, no.2, pp.1208-1216, Mar. 2009. https://doi.org/10.1016/j.eswa.2007.11.036
  2. M. S. Swanson, J. W. Prescott, T. M. Best, K. Powell, R. D. Jackson, F. Haq and M. N. Gurcan, "Semi-automated segmentation to assess the lateral meniscus in normal and osteoarthritic knees," Osteoarthritis Cartilage, vol.18, no.3, pp.344-353, Mar. 2010. https://doi.org/10.1016/j.joca.2009.10.004
  3. Ioannis Boniatis, George Panayiotakis, Elias Panagiotopoulos, "A Computer-Based System for the Discrimination Between Normal and Degenerated Menisci From Magnetic Resonance Images," Proc. of IEEE International Workshop on Imaging Systems and Techniques, pp.335-339, Sep. 2008.
  4. Jurgen Fripp, Pierrick Bourgeat, Craig Engstrom, S´ebastien Ourselin, Stuart Crozier, Olivier Salvado, "AUTOMATED SEGMENTATION OF THE MENISCI FROM MR IMAGES," Proc. of IEEE International Conference on Symposium on Biomedical Imaging, pp.510-513, Jun. 2009.
  5. T. Sasaki, Y. Hata, Y. Ando, M. Ishikawa, and H. Ishikawa, "Fuzzy rule-based approach to segment the menisci regions from MR images," Proc. of SPIE Medical Imaging, vol.3661, pp.258-265, Feb. 1999.
  6. Y. Hata, S. Kobashi, Y. Tokimoto, M. Ishikawa, and H. Ishikawa, "Computer Aided Diagnosis System of Meniscal Tears with T1 and T2 Weighted MR Images Based on Fuzzy Inference," Proc. of Conference on Computational Intelligence, vol.2206, pp.55-58, Oct. 2001.
  7. Helen Hong, Joo Hwi Lee, Hyun Hee Jo, Ji Hyun Yoo, "Automatic Generation of the Mandible Bones using Statistical Shape Model in CT Dataset," Proc. of CARS, vol.2, pp.522-526, Jun. 2007.
  8. Ji Hyun Yoo, Helen Hong, "Building a Robust 3D Statistical Shape Model of the Mandible," Journal of KIISE : Software and Applications, vol.35, no.2, pp.118-127, Feb. 2008. (in korea)
  9. M. B. Stegmann, D. D. Gomez, "A Brief Introduction to Statistical Shape Analysis," Image Analysis and Computer Graphics, Mar. 2002.