banner image
No data available.
Please log in to see this content.
You have no subscription access to this content.
No metrics data to plot.
The attempt to load metrics for this article has failed.
The attempt to plot a graph for these metrics has failed.
Concurrent segmentation of the prostate on MRI and CT via linked statistical shape models for radiotherapy planning
Rent this article for
Access full text Article
1. J. Dowling, J. Lambert, J. Parker, P. Greer, J. Fripp, J. Denham, S. Ourselin, and O. Salvado, “Automatic MRI atlas-based external beam radiation therapy treatment planning for prostate cancer,” in Prostate Cancer Imaging. Computer-Aided Diagnosis, Prognosis, and Intervention, Lecture Notes in Computer Science Vol. 6367 (Springer, Berlin/Heidelberg, 2010), pp. 2533.
2. M. Guckenberger and M. Flentje, “Intensity-modulated radiotherapy (IMRT) of localized prostate cancer,” Strahlenther. Onkol. 183, 5762 (2007).
3. A. Bayley, T. Rosewall, T. Craig, R. Bristow, P. Chung, M. Gospodarowicz, C. Mnard, M. Milosevic, P. Warde, and C. Catton, “Clinical application of high-dose, image-guided intensity-modulated radiotherapy in high-risk prostate cancer,” Int. J. Radiat. Oncol., Biol., Phys. 77, 477483 (2010).
4. P. W. McLaughlin, C. Evans, M. Feng, and V. Narayana, “Radiographic and anatomic basis for prostate contouring errors and methods to improve prostate contouring accuracy,” Int. J. Radiat. Oncol., Biol., Phys. 76, 369378 (2010).
5. C. Rasch, I. Barillot, P. Remeijer, A. Touw, M. van Herk, and J. V. Lebesque, “Definition of the prostate in CT and MRI: A multi-observer study,” Int. J. Radiat. Oncol., Biol., Phys. 43, 5766 (1999).
6. Z. Gao, D. Wilkins, L. Eapen, C. Morash, Y. Wassef, and L. Gerig, “A study of prostate delineation referenced against a gold standard created from the visible human data,” Radiother. Oncol. 85, 239246 (2007).
7. X. Gual-Arnau, M. Ibanez-Gual, F. Lliso, and S. Roldan, “Organ contouring for prostate cancer: Interobserver and internal organ motion variability,” Comput. Med. Imaging Graph. 29, 639647 (2005).
8. C. C. Parker, A. Damyanovich, T. Haycocks, M. Haider, A. Bayley, and C. N. Catton, “Magnetic resonance imaging in the radiation treatment planning of localized prostate cancer using intra-prostatic fiducial markers for computed tomography co-registration,” Radiother. Oncol. 66, 217224 (2003).
9. R. Prabhakar, P. K. Julka, T. Ganesh, A. Munshi, R. C. Joshi, and G. K. Rath, “Feasibility of using MRI alone for 3D radiation treatment planning in brain tumors,” Jpn. J. Clin. Oncol. 37, 405411 (2007).
10. G. L. Sannazzari, R. Ragona, M. G. R. Redda, F. R. Giglioli, G. Isolato, and A. Guarneri, “CT-MRI image fusion for delineation of volumes in three-dimensional conformal radiation therapy in the treatment of localized prostate cancer,” Br. J. Radiol. 75, 603607 (2002).
11. J. Stough, R. Broadhurst, S. Pizer, and E. Chaney, “Regional appearance in deformable model segmentation,” in Information Processing in Medical Imaging, Lecture Notes in Computer Science Vol. 4584 (Springer, Berlin/Heidelberg, 2007), pp. 532543.
12. Q. Feng, M. Foskey, W. Chen, and D. Shen, “Segmenting CT prostate images using population and patient-specific statistics for radiotherapy,” Med. Phys. 37, 41214132 (2010).
13. S. Chen, D. M. Lovelock, and R. J. Radke, “Segmenting the prostate and rectum in CT imagery using anatomical constraints,” Med. Image Anal. 15, 111 (2011).
14. M. Rousson, A. Khamene, M. Diallo, J. Celi, and F. Sauer, “Constrained Surface Evolutions for Prostate and Bladder Segmentation in CT Images,” in Computer Vision for Biomedical Image Applications, Lecture Notes in Computer Science, Vol. 3765, edited by Y. Liu, T. Jiang, and C. Zhang (Springer Berlin/Heidelberg, Berlin, Heidelberg, 2005), Chap. 26, pp. 251260.
15. M. Mazonakis, J. Damilakis, H. Varveris, P. Prassopoulos, and N. Gourtsoyiannis, “Image segmentation in treatment planning for prostate cancer using the region growing technique,” Br. J. Radiol. 74, 243249 (2001).
16. B. Haas, T. Coradi, M. Scholz, P. Kunz, M. Huber, U. Oppitz, L. Andr, V. Lengkeek, D. Huyskens, A. van Esch, and R. Reddick, “Automatic segmentation of thoracic and pelvic CT images for radiotherapy planning using implicit anatomic knowledge and organ-specific segmentation strategies,” Phys. Med. Biol. 53, 1751 (2008).
17. Y. Jeong and R. Radke, “Modeling inter- and intra-patient anatomical variation using a bilinear model,” Computer Vision and Pattern Recognition Workshop, CVPRW (2006), p. 76.
18. M. Costa, H. Delingette, S. Novellas, and N. Ayache, “Automatic segmentation of bladder and prostate using coupled 3D deformable models,” in Medical Image Computing and Computer-Assisted Intervention MICCAI 2007, Lecture Notes in Computer Science Vol. 4791 (Springer, Berlin/Heidelberg, 2007), pp. 252260.
19. T. F. Cootes, C. J. Taylor, D. H. Cooper, and J. Graham, “Active shape models-their training and application,” Comput. Vis. Image Underst. 61, 3859 (1995).
20. R. Toth, P. Tiwari, M. Rosen, G. Reed, J. Kurhanewicz, A. Kalyanpur, S. Pungavkar, and A. Madabhushi, “A magnetic resonance spectroscopy driven initialization scheme for active shape model based prostate segmentation,” Med. Image Anal. 15, 214225 (2011).
21. S. Martin, J. Troccaz, and V. Daanen, “Automated segmentation of the prostate in 3D MR images using a probabilistic atlas and a spatially constrained deformable model,” Med. Phys. 37, 15791590 (2010).
22. N. Makni, P. Puech, R. Lopes, A. Dewalle, O. Colot, and N. Betrouni, “Combining a deformable model and a probabilistic framework for an automatic 3D segmentation of prostate on MRI,” Int. J. Comput. Assist. Radiol. Surg. 4, 181188 (2009).
23. A. Tsai, W. Wells, C. Tempany, E. Grimson, and A. Willsky, “Mutual information in coupled multi-shape model for medical image segmentation,” Med. Image Anal. 8, 429445 (2004).
24. Y. Cao, Y. Yuan, X. Li, B. Turkbey, P. Choyke, and P. Yan, Segmenting Images by Combining Selected Atlases on Manifold (Springer, Berlin/Heidelberg, 2011), pp. 272279.
25. W. Zhang, P. Yan, and X. Li, “Estimating patient-specific shape prior for medical image segmentation,” Proceedings of IEEE International Biomedical Imaging: From Nano to Macro Symposium (2011), pp. 14511454.
26. P. Yan, X. Zhou, M. Shah, and S. T. C. Wong, “Automatic segmentation of high-throughput rnai fluorescent cellular images,” IEEE Trans. Inf. Technol. Biomed. 12, 109117 (2008).
27. P. Yan, A. A. Kassim, W. Shen, and M. Shah, “Modeling interaction for segmentation of neighboring structures,” IEEE Trans. Inf. Technol. Biomed. 13, 252262 (2009).
28. H. C. van Assen, R. J. van der Geest, M. G. Danilouchkine, H. J. Lamb, J. H. C. Reiber, and B. P. F. Lelieveldt, Three-Dimensional Active Shape Model Matching for Left Ventricle Segmentation in Cardiac CT (SPIE Medical Imaging, San Diego, CA, 2003), pp. 384393.
29. H. J. Huisman, J. J. Ftterer, E. N. J. T. van Lin, A. Welmers, T. W. J. Scheenen, J. A. van Dalen, A. G. Visser, J. A. Witjes, and J. O. Barentsz, “Prostate cancer: Precision of integrating functional MR imaging with radiation therapy treatment by using fiducial gold markers,” Radiology 236, 311317 (2005).
30. J. Chappelow, S. Both, S. Viswanath, S. Hahn, M. Feldman, M. Rosen, J. Tomaszewski, N. Vapiwala, P. Patel, and A. Madabhushi, Computer-Assisted Targeted Therapy (CATT) for Prostate Radiotherapy Planning by Fusion of CT and MRI (SPIE Medical Imaging, San Diego, CA, February 2010), p. 76252C.
31. N. Chowdhury, J. Chappelow, R. Toth, S. Kim, S. Hahn, N. Vapiwala, H. Lin, S. Both, and A. Madabhushi, Linked Statistical Shape Models for Multi-Modal Segmentation: Application to Prostate CT-MR Segmentation in Radiotherapy Planning (SPIE Medical Imaging, Lake Buena Vista, FL, 2011), p. 796314.
32. I. E. Naqa, D. Yang, A. Apte, D. Khullar, S. Mutic, J. Zheng, J. D. Bradley, P. Grigsby, and J. O. Deasy, “Concurrent multimodality image segmentation by active contours for radiotherapy treatment planning,” Med. Phys. 34, 47384749 (2007).
33. L. Breiman, “Random forests,” Mach. Learn. 45, 532 (2001).
34. C. Studholme, D. L. G. Hill, and D. J. Hawkes, “An overlap invariant entropy measure of 3D medical image alignment,” Pattern Recogn. 32, 7186 (1999).
35. M. Turk and A. Pentland, “Face recognition using eigenfaces,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (1991), pp. 586591.
36. S. Raya and J. Udupa, “Shape-based interpolation of multidimensional objects,” IEEE Trans. Med. Imaging 9, 3242 (1990).
37. P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” IEEE Comput. Vis. Pattern Recogn. 1, 511518 (2001).
38. F. A. Cosío, “Automatic initialization of an active shape model of the prostate,” Med. Image Anal. 12, 469483 (2008).
39. P. E. Gill, W. Murray, and M. H. Wright, Practical Optimization (Academic, London, 1981).
40. M. S. Cohen, R. M. DuBois, and M. M. Zeineh, “Rapid and effective correction of rf inhomogeneity for high field magnetic resonance imaging,” Hum. Brain Mapp. 10, 204211 (2000).
41. A. Madabhushi, J. K. Udupa, and A. Souza, “Generalized scale: Theory, algorithms, and application to image inhomogeneity correction,” Comput. Vis. Image Underst. 101, 100121 (2006).
42. A. Madabhushi and J. K. Udupa, “Interplay between intensity standardization and inhomogeneity correction in MR image processing,” IEEE Trans. Med. Imaging 24, 561576 (2005).
43. R. A. Hummel, “Histogram modification techniques,” Comput. Graph. Image Process. 4, 209224 (1975).
44. G. M. Villeirs, K. Van Vaerenbergh, L. Vakaet, S. Bral, F. Claus, W. J. De Neve, K. L. Verstraete, and G. O. De Meerleer, “Interobserver delineation variation using CT versus combined CT + MRI in intensitymodulated radiotherapy for prostate cancer,” Strahlenther. Onkol. 181, 424430 (2005).
45. F. V. Coakley and H. Hricak, “Radiologic anatomy of the prostate gland: A clinical approach,” Radiol. Clin. North Am. 38, 1530 (2000).
46. S. Klein, U. A. van der Heide, I. M. Lips, M. van Vulpen, M. Staring, and J. P. W. Pluim, “Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information,” Med. Phys. 35, 14071417 (2008).


Image of FIG. 1.

Click to view

FIG. 1.

(a) MR image with prostate gland boundary delineated in 2D. (b) 3D rendering of the prostate shape as seen on MRI. (c) 2D CT image of the prostate, and (d) 2D CT image with delineation of the prostate gland overlaid. (e) 3D rendering of the prostate as seen on CT.

Image of FIG. 2.

Click to view

FIG. 2.

Examples of (a) small FOV diagnostic MRI, (b) large FOV planning MRI, and (c) planning CT images of the prostate. Note that unlike in Figs. 2(a) and 2(b), the prostate is not discernible on the CT [Fig. 2(c)]. The planning MRI serves as a conduit, by overcoming the differences in FOV between CT and diagnostic MRI, to register the diagnostic MRI with the corresponding planning CT.

Image of FIG. 3.

Click to view

FIG. 3.

Summary of the fLSSM strategy for prostate segmentation on CT and MRI. The first step (module 1) shows the fusion of MR and CT imagery. The diagnostic and planning MRI are first affinely registered (shown via a checker-board form) followed by an elastic registration of planning MRI to corresponding CT. The diagnostic MRI can then be transformed to the planning CT (shown as overlayed images). The second step (module 2) shows the construction of the fLSSM where PCA is performed on aligned training samples of prostates from both CT and MRI such that their shape variations are then linked together. Thus, for any standard deviation from the mean shape, two different but corresponding prostate shapes can be generated on MRI and CT. The last step (module 3) illustrates the fLSSM-based MRI-CT segmentation process, where we extract different kinds of features from each image to train a random forest classifier which is combined with a probabilistic atlas to identify voxels that are likely to be inside the prostate. The fLSSM, which is concurrently initialized on the classification result on both MRI and CT, is subsequently evolved to yield concurrent segmentations on both modalities.

Image of FIG. 4.

Click to view

FIG. 4.

Representative gradient feature images (a) and (b) on MRI, (c) and (d) on CT.

Image of FIG. 5.

Click to view

FIG. 5.

Summary of the different types of ground truth used for training and testing the various SSMs considered in this study. Expert, trainee and MRI-CT registration based ground truth are shown on the left side of the figure (respectively in red, green and blue). The right side of the figure shows the automatic segmentations via the different SSMs compared against the expert ground truth, the automated segmentations are shown in yellow.

Image of FIG. 6.

Click to view

FIG. 6.

3D renderings of MRI and CT segmentation results for a patient study, where the surface is colored to reflect the surface errors (in mm) between prostate surface segmentation and the associated . Segmentation of prostate on (a) CT using the ctSSM evaluated agianst , (b) CT using the xLSSM evaluated agianst , (c) CT using fLSSM evaluated against , (d) CT using tLSSM(1) evaluated against , (e) CT using tLSSM(2) evaluated against , and (f) MRI using any LSSM evaluated against .

Image of FIG. 7.

Click to view

FIG. 7.

Leave-one-out reconstruction accuracy obtained for each patient study using both MRI and CT shapes. The bars on the left for a patient study represent the DSC obtained on MRI, while the bars on the right represent the DSC obtained on CT.

Image of FIG. 8.

Click to view

FIG. 8.

The average DSC obtained over ten runs when evolving the fLSSM on each patient study. For each of the ten runs, a random subset of voxels was sampled for the random forest classifier and a random perturbation was added to the centroid initialization. The bars on the left for a patient study represent the DSC obtained on MRI, while the bars on the right represent the DSC obtained on CT. The error bars represent the standard deviation in DSC for the ten runs on each patient study.

Image of FIG. 9.

Click to view

FIG. 9.

Prostate CT segmentation results for each of the 20 patient studies used in this study. Error bars representing the standard deviation in DSC over ten runs are also shown.


Generic image for table

Click to view


Table of commonly used notation.

Generic image for table

Click to view


Summary of the prostate image data sets acquired for each of 20 patients considered in this study.

Generic image for table

Click to view


Mean DSC and MAD for prostate MRI to CT registration, along with their associated standard deviations, calculated over all 20 patient studies.

Generic image for table

Click to view


Mean DSC and MAD for prostate MRI segmentation using the different LSSMs.

Generic image for table

Click to view


Mean DSC and MAD for prostate CT segmentation using the different SSMs.

Generic image for table

Click to view


p-values from two-tailed paired t-tests to identify whether there are statistically significant differences between CT segmentation results (in terms of DSC) of different pairs of SSMs.


Article metrics loading...




: Prostate gland segmentation is a critical step in prostate radiotherapy planning, where dose plans are typically formulated on CT. Pretreatment MRI is now beginning to be acquired at several medical centers. Delineation of the prostate on MRI is acknowledged as being significantly simpler to perform, compared to delineation on CT. In this work, the authors present a novel framework for building a linked statistical shape model (LSSM), a statistical shape model (SSM) that links the shape variation of a structure of interest (SOI) across multiple imaging modalities. This framework is particularly relevant in scenarios where accurate boundary delineations of the SOI on one of the modalities may not be readily available, or difficult to obtain, for training a SSM. In this work the authors apply the LSSM in the context of multimodal prostate segmentation for radiotherapy planning, where the prostate is concurrently segmented on MRI and CT.


: The framework comprises a number of logically connected steps. The first step utilizes multimodal registration of MRI and CT to map 2D boundary delineations of the prostate from MRI onto corresponding CTimages, for a set of training studies. Hence, the scheme obviates the need for expert delineations of the gland on CT for explicitly constructing a SSM for prostate segmentation on CT. The delineations of the prostate gland on MRI and CT allows for 3D reconstruction of the prostate shape which facilitates the building of the LSSM. In order to perform concurrent prostate MRI and CT segmentation using the LSSM, the authors employ a region-based level set approach where the authors deform the evolving prostate boundary to simultaneously fit to MRI and CTimages in which voxels are classified to be either part of the prostate or outside the prostate. The classification is facilitated by using a combination of MRI-CT probabilistic spatial atlases and a random forest classifier, driven by gradient and Haar features.


: The authors acquire a total of 20 MRI-CT patient studies and use the leave-one-out strategy to train and evaluate four different LSSMs. First, a fusion-based LSSM (fLSSM) is built using expert ground truth delineations of the prostate on MRI alone, where the ground truth for the gland on CT is obtained via coregistration of the corresponding MRI and CT slices. The authors compare the fLSSM against another LSSM (xLSSM), where expert delineations of the gland on both MRI and CT are employed in the model building; xLSSM representing the idealized LSSM. The authors also compare the fLSSM against an exclusive CT-based SSM (ctSSM), built from expert delineations of the gland on CT alone. In addition, two LSSMs trained using trainee delineations (tLSSM) on CT are compared with the fLSSM. The results indicate that the xLSSM, tLSSMs, and the fLSSM perform equivalently, all of them out-performing the ctSSM.


: The fLSSM provides an accurate alternative to SSMs that require careful expert delineations of the SOI that may be difficult or laborious to obtain. Additionally, the fLSSM has the added benefit of providing concurrent segmentations of the SOI on multiple imaging modalities.


Full text loading...

This is a required field
Please enter a valid email address
752b84549af89a08dbdd7fdb8b9568b5 journal.articlezxybnytfddd
Scitation: Concurrent segmentation of the prostate on MRI and CT via linked statistical shape models for radiotherapy planning