The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Automatic Left Ventricle Segmentation by Edge Classification and Region Growing on Cardiac MRI

심장 자기공명영상의 에지 분류 및 영역 확장 기법을 통한 자동 좌심실 분할 알고리즘

  • 이해연 (국립금오공과대학교 컴퓨터공학부)
  • Published : 2008.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Cardiac disease is the leading cause of death in the world. Quantification of cardiac function is performed by manually calculating blood volume and ejection fraction in routine clinical practice, but it requires high computational costs. In this study, an automatic left ventricle (LV) segmentation algorithm using short-axis cine cardiac MRI is presented. We compensate coil sensitivity of magnitude images depending on coil location, classify edge information after extracting edges, and segment LV by applying region-growing segmentation. We design a weighting function for intensity signal and calculate a blood volume of LV considering partial voxel effects. Using cardiac cine SSFP of 38 subjects with Cornell University IRB approval, we compared our algorithm to manual contour tracing and MASS software. Without partial volume effects, we achieved segmentation accuracy of $3.3mL{\pm}5.8$ (standard deviation) and $3.2mL{\pm}4.3$ in diastolic and systolic phases, respectively. With partial volume effects, the accuracy was $19.1mL{\pm}8.8$ and $10.3mL{\pm}6.1$ in diastolic and systolic phases, respectively. Also in ejection fraction, the accuracy was $-1.3%{\pm}2.6$ and $-2.1%{\pm}2.4$ without and with partial volume effects, respectively. Results support that the proposed algorithm is exact and useful for clinical practice.

최근 연구 결과에 따르면 여러가지 질환 중에 심장 질환으로 인한 사망률이 가장 높은 것으로 나타났다. 임상 실습에서 심장 기능은 좌심실을 수동윤곽검출하여 혈류량이나 심박구출률을 계산하여 분석하지만, 많은 시간과 비용을 필요로 한다. 본 연구에서는 심장을 촬영한 단축 자기공명영상을 사용하여 자동 좌심실 분할 알고리즘을 제안한다. 코일 위치에 따른 왜곡을 보상하고, 에지 정보를 검출하고 특성에 따라 분류한후에, 영역 확장 기법을 사용하여 좌심실을 분할하였다. 또한 부분 복셀소(voxel)의 영향을 고려하였다. 코넬대학교 IRB의 승인하에 38 명의 심장 자기공명영상을 사용하여 제안한 알고리즘을 수동윤곽검출 및 GE MASS 소프트웨어와 비교하였다. 심장의 이완기와 수축기에 혈류량은 부분 복셀소 영향을 고려하지 않을 경우 각각 $3.3mL{\pm}5.8$(표준편차)와 $3.2mL{\pm}4.3$, 부분 복셀소 영향을 고려한 경우 각각 $19.1mL{\pm}8.8$와 $10.3mL{\pm}6.1$의 정확도를 보였다. 심박구출률은 부분 복셀소 영향을 고려하지 않은 경우와 고려한 경우에 대해서 각각 $-1.3%{\pm}2.6$ 와 $-2.1%{\pm}2.4$의 정확도를 보였다. 이를 통해 제안한 알고리즘이 정확하고 정기적인 임상 실습에 유용함을 확인할 수 있다.

Keywords

References

  1. L.P. Clarke, R.P. Velthuizen, M.A. Camacho, J.J. Heine, M. Vaidyanathan, L.O. Hall, R.W. Thatcher and M.L. Silbiger, “MRI segmentation: methods and applications,” Magnetic Resonance Imaging, Vol.13(3), pp.343-368, 1995 https://doi.org/10.1016/0730-725X(94)00124-L
  2. J.S. Suri, “Computer vision pattern recognition and image processing in left ventricle segmentation: the last 50 years,” Pattern Analysis and Applications, Vol.3, pp.209-242, 2000 https://doi.org/10.1007/s100440070008
  3. A.E.O. Boudraa, M. Arzi, J. Sau, J. Champier, S. Hadj-Moussa, J.-E. Besson, D. Sappey-Marinier, R. Itti and J.-J. Mallet, “Automated detection of the left ventricular region in gated nuclear cardiac imaging,” IEEE Trans. Biomedical Engineering, Vol.43(4), pp.430-437, 1996 https://doi.org/10.1109/10.486264
  4. A.E.O Boudraa, “Automated detection of the left ventricular region in magnetic resonance images by Fuzzy C-Means model,” The International Journal of Cardiac Imaging, Vol.13(4), pp.347-355, 1997 https://doi.org/10.1023/A:1005755819752
  5. G.D.Waiter, F.I. McKiddie, T.W. Redpath, S.I. Semple and R.J. Trent, “Determination of normal regional left ventricular function from cine-MR images using a semi-automated edge detection method,” Magnetic Resonance Imaging, Vol.17, pp.99-107, 1999 https://doi.org/10.1016/S0730-725X(98)00158-1
  6. A.S. Pednekar, R. Muthupillai, V.V. Lenge, I.A. Kakadiaris and S.D. Flamm, “Automatic identification of the left ventricle in cardiac cine-MR images: dual-contrast cluster analysis and scout-geometry approaches,” Journal of Magnetic Resonance Imaging, Vol.23(5), pp.641-651, 2006 https://doi.org/10.1002/jmri.20552
  7. M. Lynch, O. Ghita and P.F. Whelan, “Left-ventricle myocardium segmentation using a coupled level-set with a priori knowledge,” Computerized Medical Imaging and Graphics, Vol.30, pp.255-262, 2006 https://doi.org/10.1016/j.compmedimag.2006.03.009
  8. Z. Zhou, J. You, P.A. Heng and D. Xia, “Cardiac MR image segmentation and left ventricle surface reconstruction based on level set method,” Studies in health technology and informatics, Vol.111, pp.629-632, 2005
  9. R.J. van der Geest, V.G.M. Buller, E. Jansen, H.J. Lamb, L.H.B. Baur, E.E. van der Wall, A. de Roos and J.H.C. Reider, “Comparison between manual and semiautomated analysis of left ventricle volume parameters from short-axis MR images,” Journal of Computer Assisted Tomography, Vol. 21(5), pp.756-765, 1997 https://doi.org/10.1097/00004728-199709000-00019
  10. R.J. van Geuns, T. Baks, E.H. Gronenschild, J.P. Aben, P.A. Wielopolski, F. Cademartiri and P.J. de Feyter, “Automatic quantitative left ventricular analysis of cine MR images by using three-dimensional information for contour detection,” Radiology, Vol.240(1), pp.215-221, 2006 https://doi.org/10.1148/radiol.2401050471
  11. A. Pednekar, U. Kurkure, R. Muthupillari, S. Flamm and I.A. Kakadiaris, “Automated Left Ventricle Segmentation in Cardiac MRI,” IEEE Trans. Biomedical Engineering, Vol.53(7), pp.1425-1428, 2006 https://doi.org/10.1109/TBME.2006.873684
  12. M.F. Santarelli, V. Positano, C. Michelassi, M. Lombardi and L. Landini, “Automated cardiac MR image segmentation: theory and measurement evaluation,” Medical Engineering & Physics, Vol.25(2), pp.149-159, 2003 https://doi.org/10.1016/S1350-4533(02)00144-3
  13. M.R. Kaus, J. von Berg, J. Weese, W. Niessen and V. Pekar, “Automated segmentation of the left ventricle in cardiac MRI,” Medical Image Analysis, Vol. 8(3), pp.245-254, 2004 https://doi.org/10.1016/j.media.2004.06.015
  14. M.-P. Jolly, “Automatic Segmentation of the Left Ventricle in Cardiac MR and CT Images,” International Journal of Computer Vision, Vol.70(2), pp.151-163, 2006 https://doi.org/10.1007/s11263-006-7936-3
  15. R.J. van der Geest, B.P. Lelieveldt, E. Angelie, M. Danilouchkine, C. Swingen, M. Sonka and J.H. Reiber, “Evaluation of a new method for automated detection of left ventricular boundaries in time series of magnetic resonance images using an Active Appearance Motion Model,” Journal of Cardiovascular Magnetic Resonance, Vol.6(3), pp.609-617, 2004 https://doi.org/10.1081/JCMR-120038082
  16. Q. Chen, Z.M. Zhou, M. Tang, P.A. Heng and D.S. Xia, “Shape Statistics Variational Approach for the Outer Contour Segmentation of Left Ventricle MR Images,” IEEE Trans. Information Technology in Biomedicine, Vol.10(3), pp.588-597, 2006 https://doi.org/10.1109/TITB.2006.872051
  17. W.J. Niessen, B.M. ter H. Romeny and M.A. Viergever, “Geodesic deformable models for medical image analysis,” IEEE Trans. Medical Imaging, Vol.17(4), pp.634-641, 1998 https://doi.org/10.1109/42.730407
  18. N. Paragios, “A level set approach for shape-driven segmentation and tracking of the left ventricle,” IEEE Trans. Medical Imaging, Vol.22(6), pp.773-776, 2003 https://doi.org/10.1109/TMI.2003.814785
  19. C. Corsi, C. Lamberti, R. Battani, A. Maggioni, G. Discenza, P. MacEneaney, V. Mor-Avi, R.M. Lang and E.G. Caiani, “Computerized quantification of left ventricular volumes on cardiac magnetic resonance images by level set method,” Computer Assisted Radiology and Surgery, Vol.1268, pp. 1114-1119, 2004 https://doi.org/10.1016/j.ics.2004.03.117
  20. M. Lynch, O. Ghita and P.F. Whelan, “Automatic segmentation of the left ventricle cavity and myocardium in MRI data,” Computers in Biology and Medicine, Vol.36(4), pp.389-407, 2006 https://doi.org/10.1016/j.compbiomed.2005.01.005
  21. N. Codella, J.-W. Weinsaft, M.-D. Cham, M. Janik, M.-R. Prince and Y. Wang, “Automated Soft Segmentation of the Left Ventricle using Myocardial Effusing Threshold Reduction and Intravoxel Computation (LV-METRIC),” Radiology, 2008 (in printing)