Endo- and Epi-cardial Boundary Detection of the Left Ventricle Using Intensity Distribution and Adaptive Gradient Profile in Cardiac CT Images

심장 CT 영상에서 밝기값 분포와 적응적 기울기 프로파일을 이용한 좌심실 내외벽 경계 검출

  • 이민진 (서울여자대학교 컴퓨터학과) ;
  • 홍헬렌 (서울여자대학교 미디어학부)
  • Received : 2009.06.25
  • Accepted : 2010.01.12
  • Published : 2010.04.15

Abstract

In this paper, we propose an automatic segmentation method of the endo- and epicardial boundary by using ray-casting profile based on intensity distribution and gradient information in CT images. First, endo-cardial boundary points are detected by using adaptive thresholding and seeded region growing. To include papillary muscles inside the boundary, the endo-cardial boundary points are refined by using ray-casting based profile. Second, epi-cardial boundary points which have both a myocardial intensity value and a maximum gradient are detected by using ray-casting based adaptive gradient profile. Finally, to preserve an elliptical or circular shape, the endo- and epi-cardial boundary points are refined by using elliptical interpolation and B-spline curve fitting. Then, curvature-based contour fitting is performed to overcome problems associated with heterogeneity of the myocardium intensity and lack of clear delineation between myocardium and adjacent anatomic structures. To evaluate our method, we performed visual inspection, accuracy and processing time. For accuracy evaluation, average distance difference and overalpping region ratio between automatic segmentation and manual segmentation are calculated. Experimental results show that the average distnace difference was $0.56{\pm}0.24mm$. The overlapping region ratio was $82{\pm}4.2%$ on average. In all experimental datasets, the whole process of our method was finished within 1 second.

본 논문에서는 CT 영상에서 밝기값 분포와 기울기 정보를 고려한 방사선 추적 기반의 좌심실 내외벽 자동 분할 기법을 제안한다. 첫째, 심근 내벽 경계는 임계값 기법과 영역확장법으로 분할하고, 꼭지근을 포함하는 위하여 방사형의 방사선 추적 기법을 이용하여 분할한다. 둘째, 심근 외벽 경계는 적응적 기울기 프로파일 내에 심근의 밝기값과 최대 기울기를 갖는 점을 추출한다. 마지막으로, 타원이나 원의 형태를 유지하기 위하여 내외벽의 잘못된 경계점들을 타원방정식으로 선형 보간하고 B-스플라인을 적용하여 최종 분할된 결과를 추출한다. 제안방법의 평가를 위해 육안평가와 정확성 평가, 수행시간을 측정하였다. 정확성 평가를 위하여 임상의의 수동 분할 결과와 제안 방법 분할 결과 간의 평균거리차이와 중복영역비율을 측정하였다. 실험 결과 평균거리차이는 $0.56{\pm}0.24mm$로 측정되었고, 평균 중복영역비율은 평균 $82{\pm}4.2%$로 측정되었다. 제안 방법을 적용한 수행 시간은 평균 1초로 수행을 완료하였다.

Keywords

References

  1. Juergens KU, Fischbach R., "Left ventricluar function studied with MDCT," Eur Radiology, vol.16, pp.342-35, 2006. https://doi.org/10.1007/s00330-005-2888-5
  2. Schlosser T., Pagonidis K., Herborn CU, Hunold P. et al., "Assessment of left ventricular parameters using 16-MDCT and new software for endocardial and epicardial border delineation," An J Roentgenol, vol.184 pp.765-773.
  3. G. Mujlenbruch, M. Das, C. Hohl, J. Wildberger et al., "Global left ventricular function in cardiac CT. Evaluation of an automated 3D region-growing segmentation algorithm," Eur Radiology, vol.16, pp.1117-1123 2006. https://doi.org/10.1007/s00330-005-0079-z
  4. J. Fleureau, M. Garreau, D. Boulmier, A. Hernandez, "A new 3D Multi-Object Segmentation Method in Cardiac MSCT Imaging using a Multi- Agent Approach," CLAIB2007, IFMBE Proceedings, vol.18, pp.249-253, 2007.
  5. Urschler M., Mayer H., Bolter R., Leberl F., "The LiveWire Approach for the Segmentation of Left Ventricle Electron-Beam CT Images," Proc. of 26th Workshop of the Austrian Association for Pattern Recognition: Vision with Non-traditional Sensors, vol.160, pp.319-326, 2002.
  6. Neubaure A., Wegenkittl R., "Skeleton-Based Myocardium Segmentation," Proc. of SPIE, vol.5009 pp.56-67, 2003.
  7. Neubaure A., Wegenkittl R., "Analysis of Four- Dimensional Cardiac Data Sets using Skeleton- Based Segmentation," Journal of WSCG, vol.11, no.1, pp.1213-6972, 2003.
  8. Mikhail G., Faiza A., Rob J., Boudewijn P., Johan H., "Automated Quantification of Cardiac Short- Axis Multi-Slice CT Images for Assessment of Left Ventricular Global Function," Proc. of SPIE, vol.5747, pp.463-474, 2005.
  9. Marie-Pierre Jolly, "Automatic Segmentation of the Left Ventricle in Cardiac MR and CT Images," International Journal of Computer vision, vol.70, no.2, pp.151-163, 2006. https://doi.org/10.1007/s11263-006-7936-3
  10. Muller-Karger C., Wong S., Cruz A., et al., "A Level-set Segmentation Approach for 4-D Cardiac Images," IFMBE proceedings, vol.18, pp.286-289, 2007.
  11. M. Lee, H. Hong, "Epi- and Endocardial Segmentation of the Left Ventricle using Adaptive Gradient Profile in CT Cardiac Dataset," Proc. of the 35th KIISE Spring Conference, vol.35, pp. 291-292, 2008. (in Korean)
  12. Liang J., Gangyi D., Yuwei W., "Segmentation of the Left Ventricle from Cardiac MR Images Based on Radial GVF Snake," 2008 International Conference on BioMedical Engineering and Informatics, vol.2, pp.238-242, 2008.
  13. Robert M. Lapp, Lorenzo-Valdes M., Rueckert D., "3D/4D Cardiac Segmentation Using Active Appearance Models, Non-rigid Registration, and the Insight Toolkit," in Proc. Medical Image Computing and Computer-Assisted Intervention, vol.3216, pp.419-426, 2004.
  14. H.C. Assen, R.J. Geest, M.G. Danilouchkine, et al., "3D Active shape Model Matching for Left Ventricle Segmentation in Cardiac CT," Proc. of SPIE, vol.5032, pp.384-393, 2003.
  15. H.C. van Assen, M.G. Danilouchkine, et al,, "Cardiac LV segmentation using a 3D active shape model driven by fuzzy inference," in Proc. Medical Image Computing and Computer-Assisted Intervention, vol.2878, pp.533-540, 2003.
  16. Fritz D., Kroll J.,, Dillmann R., Scheuering M. "Automatic 4D-Segmentation of the Left Vetnricle in Cardiac-CT-Data," in Proc. International Society for Optical Engineering SPIE, vol.6512, Mar 2007.
  17. M. Unser, "Splines - a perfect fit for signal/image processing," IEEE Signal Processing Magazine, vol.16, no.6, pp.22-38, 1999. https://doi.org/10.1109/79.799930