Shape and appearance priors for level set-based left ventricle segmentation
- Author(s): Ronghua Yang 1 ; Majid Mirmehdi 1 ; Xianghua Xie 2 ; David Hall 3
-
-
View affiliations
-
Affiliations:
1:
Department of Computer Science, University of Bristol, Bristol BS8 1TH, UK;
2: Department of Computer Science, University of Swansea, Swansea SA2 8PP, UK;
3: Department of Medical Physics and Bioengineering, University Hospitals Bristol NHS Foundation Trust, UK
-
Affiliations:
1:
Department of Computer Science, University of Bristol, Bristol BS8 1TH, UK;
- Source:
Volume 7, Issue 3,
June 2013,
p.
170 – 183
DOI: 10.1049/iet-cvi.2012.0081 , Print ISSN 1751-9632, Online ISSN 1751-9640
The authors propose a novel spatiotemporal constraint based on shape and appearance and combine it with a level-set deformable model for left ventricle (LV) segmentation in four-dimensional gated cardiac SPECT, particularly in the presence of perfusion defects. The model incorporates appearance and shape information into a ‘soft-to-hard’ probabilistic constraint, and utilises spatiotemporal regularisation via a maximum a posteriori framework. This constraint force allows more flexibility than the rigid forces of shape constraint-only schemes, as well as other state of the art joint shape and appearance constraints. The combined model can hypothesise defective LV borders based on prior knowledge. The authors present comparative results to illustrate the improvement gain. A brief defect detection example is finally presented as an application of the proposed method.
Inspec keywords: medical image processing; image segmentation; cardiology; single photon emission computed tomography
Other keywords: 4D gated cardiac SPECT; spatiotemporal constraint; level set based left ventricle segmentation; appearance priors; shape priors; soft-to-hard probabilistic constraint; perfusion defects; spatiotemporal regularisation; maximum a posteriori framework; level set deformable model
Subjects: Nuclear medicine, emission tomography; Optical, image and video signal processing; Nuclear medicine, emission tomography; Computer vision and image processing techniques; Biology and medical computing; Patient diagnostic methods and instrumentation
References
-
-
1)
-
33. Ben-Ari, R., Aiger, D.: ‘Geodesic active contours with combined shape and appearance priors’ (ACIVS, 2008) pp. 494–505.
-
-
2)
-
40. Huang, X., Paragios, N., Metaxas, D.: ‘Shape registration in implicit spaces using information theory and free form deformations’, IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28, (8), pp. 1303–1318 (doi: 10.1109/TPAMI.2006.171).
-
-
3)
-
23. Kohlberger, T., Cremers, D., Rousson, M., Ramaraj, R., Funka-Lea, G.: ‘4D shape priors for a level set segmentation of the left myocardium in SPECT sequences’ (MICCAI, 2006), vol. 9, pp. 92–100.
-
-
4)
-
20. Leventon, M., Grimson, W., Faugeras, O.: ‘Statistical shape influence in geodesic active contours’ (CVPR, 2000) pp. 316–323.
-
-
5)
-
25. Kohlberger, T., Funka-Lea, G., Desh, V.: ‘Soft level set coupling for LV segmentation in gated perfusion SPECT’ (MICCAI, 2007), vol. 10, pp. 327–334.
-
-
6)
-
10. Hentschke, C., Engel, K., Schafer, S., Tonnies, K.: ‘Segmentation of the left ventricle in SPECT by an active surface’ (MIUA, 2009) pp. 1–5.
-
-
7)
-
36. Jalba, A.C., Wilkinson, M.H.F., Roerdink, J.B.T.M.: ‘CPM: a deformable model for shape recovery and segmentation based on charged particles’, IEEE Trans. Pattern Anal. Mach. Intell., 2004, 26, (10), pp. 1320–1335 (doi: 10.1109/TPAMI.2004.84).
-
-
8)
-
21. Tsai, A., Yezzi, A., Wells, W., et al.: ‘Model-based curve evolution technique for image segmentation’ (CVPR, 2001) pp. 463–468.
-
-
9)
-
27. Rousson, M., Paragios, N.: ‘Shape priors for level set representations’ (ECCV, 2002) pp. 78–92.
-
-
10)
-
29. Gleason, S., Abidi, M., Sari-Sarraf, H.: ‘Probabilistic shape and appearance model for scene segmentation’ (ICRA, 2002), vol. 3, pp. 2982–2987.
-
-
11)
-
19. Charnoz, A., Lingrand, D., Montagnat, J.: ‘A levelset based method for segmenting the heart in 3D + T gated SPECT images’, Int. Workshop on Functional Imaging and Modeling of the Heart, 2003, vol. 2674, pp. 87–100.
-
-
12)
-
11. Debreuve, E., Barlaud, M., Aubert, G., Laurette, I., Darcourt, J.: ‘Space-time segmentation using level set active contours applied to myocardial gated SPECT’, IEEE Trans. Med. Imaging, 2001, 20, (7), pp. 643–659 (doi: 10.1109/42.932748).
-
-
13)
-
30. Yang, J., Duncan, J.: ‘3D image segmentation of deformable objects with shape-appearance joint prior models’ (MICCAI, 2003) pp. 573–580.
-
-
14)
-
2. Bronnikov, A.: ‘SPECT imaging with resolution recovery’, IEEE Trans. Nucl. Sci., 2012, 59, (4), pp. 1458–1464 (doi: 10.1109/TNS.2012.2195675).
-
-
15)
-
28. Fisher, V., Lee, R., Gourin, A., Bolooki, H., Stuckey, J., Kavaler, F.: ‘Muscle fiber length: a determinant of left ventricular contraction pattern’, Am. J. Physiol., 1966, 211, pp. 301–306.
-
-
16)
-
3. Faro, A., Giordano, D., Spampinato, C., Ullo, S., Stefano, A.D.: ‘Basal ganglia activity measurement by automatic 3-D striatum segmentation in SPECT imaging’, IEEE Trans. Instrum. Meas., 2009, 60, (10), pp. 3269–3280 (doi: 10.1109/TIM.2011.2159315).
-
-
17)
-
15. Chandrashekara, R., Rao, A., Sanchez-Oritz, G., Mohiaddin, R., Rueckert, D.: ‘Construction of a statistical model for cardiac motion analysis using non-rigid image registration’, Inf. Process. Med. Imaging, 2003, 18, pp. 599–610 (doi: 10.1007/978-3-540-45087-0_50).
-
-
18)
-
12. McInerney, T., Terzopoulos, D.: ‘A dynamic finite element surface model for segmentation and tracking in multidimensional medical images with application to cardiac 4D image analysis’, Comput. Imaging Graph., 1995, 19, pp. 69–83 (doi: 10.1016/0895-6111(94)00040-9).
-
-
19)
-
34. Yang, R., Mirmehdi, M., Xie, X.: ‘A charged active contour based on electrostatics’ (ACIVS, 2006) pp. 173–184.
-
-
20)
-
7. Sermesant, M., Forest, C., Pennec, X., Delingette, H., Ayache, N.: ‘Deformable biomechanical models: application to 4D cardiac image analysis’, Med. Image Anal., 2003, 7, (4), pp. 475–488 (doi: 10.1016/S1361-8415(03)00068-9).
-
-
21)
-
13. Bardinet, E., Cohen, L., Ayache, N.: ‘Tracking and motion analysis of the left ventricle with deformable superquadrics’, Med. Image Anal., 1996, 1, pp. 129–149 (doi: 10.1016/S1361-8415(96)80009-0).
-
-
22)
-
4. Depuey, E., Garcia, E., Berman, D.: ‘Cardiac SPECT imaging’ (Lippincott Williams and Wilkins, Philadelphia, 2000, 2nd edn.).
-
-
23)
-
38. Paragios, N., Mellina-Gottardo, V., Ramesh, O.: ‘Gradient vector flow fast geodesic active contours’, IEEE Trans. Pattern Anal. Mach. Intell., 2004, 26, (3), pp. 402–407 (doi: 10.1109/TPAMI.2004.1262337).
-
-
24)
-
37. Caselles, V., Kimmel, R., Sapiro, G.: ‘Geodesic active contours’ (ICCV, 1995), pp. 694–699.
-
-
25)
-
16. O'Connor, M., Kanal, K., Gebhard, M., Rossman, P.: ‘Comparison of four motion correction techniques in SPECT imaging of the heart: a cardiac phantom study’, J. Nucl. Med., 1998, 39, pp. 2027–2034.
-
-
26)
-
26. Rousson, M., Cremers, D.: ‘Efficient kernel density estimation of shape and intensity priors for level set segmentation’ (MICCAI, 2005), vol. 8, pp. 335–342.
-
-
27)
-
1. Schumacher, H., Modersitzki, J., Fischer, B.: ‘Combined reconstruction and motion correction in SPECT imaging’, IEEE Trans. Nucl. Sci., 2009, 56, (1), pp. 73–80 (doi: 10.1109/TNS.2008.2007907).
-
-
28)
-
5. Loats, H.: ‘CT and SPECT image registration and fusion for spatial localization of metastatic processes using radiolabeled monoclonals’, J. Nucl. Med., 1993, 34, pp. 562–566.
-
-
29)
-
8. Dornheim, L., Tönnies, K.D., Dixon, K.: ‘Automatic segmentation of the left ventricle in 3D SPECT data by registration with a dynamic anatomic model’ (MICCAI, 2005), vol. 8, pp. 335–342.
-
-
30)
-
24. Chan, T., Vese, L.: ‘Active contour without edges’, IEEE Trans. Image Process., 2001, 10, (2), pp. 266–277 (doi: 10.1109/83.902291).
-
-
31)
-
35. Cootes, T., Edwards, G., Taylor, C.: ‘Active appearance models’ (ECCV, 1998), vol. 2, pp. 484–498.
-
-
32)
-
32. Litvin, A., Karl, W.C., Shah, J.: ‘Shape and appearance modeling with feature distributions for image segmentation’ (ISBI, 2006), pp. 1128–1131.
-
-
33)
-
39. Yang, R., Mirmehdi, M., Hall, D.: ‘Charged contour model for cardiac SPECT segmentation’ (MIUA, 2006) pp. 171–175.
-
-
34)
-
6. Montagnat, J., Delingette, H., Malandain, G.: ‘Cylindrical Echocar-diographic images segmentation based on 3D deformable models’ (MICCAI, 1999) pp. 168–175.
-
-
35)
-
18. Brankov, J., Yang, Y., Wernick, M.: ‘Spatiotemporal processing of gated cardiac SPECT images using deformable mesh modeling’, Med. Phys., 2005, 32, (9), pp. 2839–2849 (doi: 10.1118/1.2013027).
-
-
36)
-
31. Huang, X., Li, Z., Metaxas, D.: ‘Learning coupled prior shape and appearance models for segmentation’ (MICCAI, 2004), pp. 60–69.
-
-
37)
-
14. Montagnat, J., Delingette, H.: ‘4D deformable models with temporal constraints: application to 4D cardiac image segmentation’, Med. Image Anal., 2005, 9, (1), pp. 87–100 (doi: 10.1016/j.media.2004.06.025).
-
-
38)
-
17. Laading, J., McCulloch, C., Johnson, V., Gill, D., Jaszczak, R.A.: ‘Hierarchical feature based deformation model applied to 4D cardiac SPECT Data’. Int. Conf. Information Processing in Medical Imaging1999, (LNCS, 1613), pp. 266–279.
-
-
39)
-
9. Choi, S., Kim, H., Oh, J., Kang, T., Sun, K., Kim, M.: ‘Segmentation of the left ventricle in myocardial perfusion SPECT using variational level set formulation’. Nuclear Science Symp. Conf. Record, 2007, vol. 4, pp. 3060–3064.
-
-
40)
-
22. Cremers, D., Tischhauser, F., Weickert, J., Schnorr, C.: ‘Diffusion snakes: introducing statistical shape knowledge into the Mumford-Shah functional’, Comput. Vis., 2002, 50, (3), pp. 295–313 (doi: 10.1023/A:1020826424915).
-
-
1)