Journal of KIISE (정보과학회 논문지)

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

DOI QR Code

Anterior Cruciate Ligament Segmentation in Knee MRI with Locally-aligned Probabilistic Atlas and Iterative Graph Cuts

무릎 자기공명영상에서 지역적 확률 아틀라스 정렬 및 반복적 그래프 컷을 이용한 전방십자인대 분할

  • 이한상 (한국과학기술원 전기 및 전자공학과) ;
  • 홍헬렌 (서울여자대학교 멀티미디어학과)
  • Received : 2015.06.02
  • Accepted : 2015.08.10
  • Published : 2015.10.15
⟨ Previous Next ⟩

Abstract

Segmentation of the anterior cruciate ligament (ACL) in knee MRI remains a challenging task due to its inhomogeneous signal intensity and low contrast with surrounding soft tissues. In this paper, we propose a multi-atlas-based segmentation of the ACL in knee MRI with locally-aligned probabilistic atlas (PA) in an iterative graph cuts framework. First, a novel PA generation method is proposed with global and local multi-atlas alignment by means of rigid registration. Second, with the generated PA, segmentation of the ACL is performed by maximum-aposteriori (MAP) estimation and then by graph cuts. Third, refinement of ACL segmentation is performed by improving shape prior through mask-based PA generation and iterative graph cuts. Experiments were performed with a Dice similarity coefficients of 75.0%, an average surface distance of 1.7 pixels, and a root mean squared distance of 2.7 pixels, which increased accuracy by 12.8%, 22.7%, and 22.9%, respectively, from the graph cuts with patient-specific shape constraints.

무릎 자기공명영상에서 전방십자인대의 분할은 밝기값의 불균일성 및 주변 조직들과의 유사 밝기값 특성으로 인해 기존 분할기법의 적용에 한계가 있다. 본 논문에서는 지역적 정렬을 통한 확률아틀라스 생성 및 반복적 그래프 컷을 통한 다중아틀라스 기반 전방십자인대 분할기법을 제안한다. 첫째, 전역 및 지역적 다중아틀라스 강체정합을 통해 전방십자인대의 확률아틀라스를 생성한다. 둘째, 생성된 확률아틀라스를 이용하여 최대사후추정 및 그래프 컷을 통하여 전방십자인대 초기 분할을 수행한다. 셋째, 마스크 기반 강체정합을 통한 형상정보 개선 및 반복적 그래프 컷을 통해 전방십자인대 분할 개선을 수행한다. 제안방법의 성능평가를 위하여 육안평가 및 정확성평가를 수행하였으며, 평가 결과 제안방법의 Dice 유사도는 75.0%, 평균표면거리는 1.7화소, 제곱근표면거리는 2.7화소로서 기존 그래프 컷 방법에 비하여 전방 십자인대의 분할정확도가 각각 12.8%, 22.7%, 및 22.9% 향상된 것으로 나타났다.

Keywords

Acknowledgement

Supported by : 서울여자대학교 컴퓨터과학연구소

References

  1. C. Arden, K. Webster, N. Taylor and J. Feller, "Return to Sport Following Anterior Cruciate Ligament Reconstruction Surgery: A Systematic Review and Meta-analysis of the State of Play," Br. J. Sports Med., Vol. 45, pp. 596-606, 2011. https://doi.org/10.1136/bjsm.2010.076364
  2. G. Limbert, J. Middleton and M. Taylor, "Finite Element Analysis of the Human ACL Subjected to Passive Anterior Tibial Loads," Comput. Methods Biomech. Biomed. Eng., Vol. 7, No. 1, pp. 1-8, 2004. https://doi.org/10.1080/10255840410001658839
  3. J. Gardiner and J. Weiss, "Subject-specific Finite Element Analysis of the Human Medial Collateral Ligament During Valgus Knee Loading," J. Orthop. Res., Vol. 21, pp. 1098-1106, 2003. https://doi.org/10.1016/S0736-0266(03)00113-X
  4. A. Chaudhari, E. Zelman, D. Flanigan, C. Kaeding and H. Nagaraja, "Anterior Cruciate Ligamentinjured Subjects Have Smaller Anterior Cruciate Ligaments Than Matched Controls: A Magnetic Resonance Imaging Study," Am. J. Sports Med., Vol. 37, No. 7, pp. 1282-1287, 2009. https://doi.org/10.1177/0363546509332256
  5. J. Ho, W. Lung, C. Seah, C. Poh, K. Sheah, D. Lie and K. Yew, "Anterior Cruciate Ligament Segmentation: Using Morphological Operations with Active Contour," Proc. of the 4th Int. Conf. on Bioinfo. Biomed. Eng., 2010.
  6. T. Chan and L. Vese, "Active Contours without Edges," IEEE Trans. Image Process., Vol. 10, No. 2, pp. 266-277, 2001. https://doi.org/10.1109/83.902291
  7. H. Lee, H. Hong and J. Kim, "Anterior Cruciate Ligament Segmentation from Knee MR Images Using Graph Cuts with Geometric and Probabilistic Shape Constraints," Proc. of the Asian Conf. Comput. Vis., 2012.
  8. H. Lee, H. Hong and J. Kim, "Anterior Cruciate Ligament Segmentation from Knee MR Images Using Graph Cuts with Shape Priors," Journal of KIISE: Software and Applications, Vol. 41, No. 1, pp. 36-45, 2014.
  9. H. Lee, H. Hong and J. Kim, "Segmentation of Anterior Cruciate Ligament in Knee MR Images Using Graph Cuts with Patient-specific Shape Constraints and Label Refinement," Comput. Bio. Med., Vol. 55, pp. 1-10, 2014. https://doi.org/10.1016/j.compbiomed.2014.09.004
  10. Y. Boykov and G. Funka-Lea, "Graph Cuts and Efficient N-D Image Segmentation," Int. J. Comput. Vis., Vol. 70, No. 2, pp. 109-131, 2006. https://doi.org/10.1007/s11263-006-7934-5
  11. M. Linguraru, J. Pura, V. Pamulapati and R. Summers, "Statistical 4D Graphs Form Multi-organ Abdominal Segmentation from Multiphase CT," Med. Image Anal., Vol. 16, pp. 904-914, 2012. https://doi.org/10.1016/j.media.2012.02.001
  12. M. Oda, T. Nakaoka, T. Kitasaka, K. Furukawa, K. Misawa, M. Fujiwara and K. Mori, "Organ Segmentation from 3D Abdominal CT Images Based on Atlas Selection and Graph Cut," Abdominal imaging, 2012.
  13. R. Wolz, C. Chu, K. Misawa, K. Mori and D. Rueckert, "Multi-organ Abdominal CT Segmentation Using Hierarchically Weighted Subject-specific Atlases," Int. Conf. Med. Image Comp. Comput. Aided Interv., 2012.
  14. V. Kolmogorov and R. Zabih, "What Energy Functions Can Be Minimized via Graph Cuts?," IEEE Trans. Pattern Anal. Mach. Intell., Vol. 26, No. 2, pp. 147-159, 2004. https://doi.org/10.1109/TPAMI.2004.1262177