Abstract
We extend the shape-prior based geometric approach developed for myocardial segmentation in cardiac CT imagery by incorporating minimal user input in the form of anatomical constraints to guide the segmentation process resulting in significantly improved results. The shape-prior based geometric approach involves estimating coefficients of a low-dimensional principal component analysis based shape representation along with a set of rigid 3D pose parameters of three separate surfaces corresponding to left (LV)/right (RV) ventricles and Epicardium (Epi) by optimizing a novel Chan-Vese like image appearance model with gradient descent. We enhance this framework by allowing experienced clinical users to identify the centers of the three anatomies in apical slices and a common anatomical cardiac base slice. We integrate this minimal user input as anatomical constraints in the segmentation process by replacing the rigid 3D pose model with a novel blended model which incorporates rigidity only within 2D slices while incorporating non-rigid effects of shear and torsion along the third (axial) dimension. With this new formulation we achieved significantly improved segmentation results in terms of average symmetric surface-to-surface distances (mm): LV 1.05 ± 0.27; RV 1.7 ± 0.40; Epi 1.22 ± 0.56 compared to LV 2.3 ± 0.50; RV 1.13 ± 0.21; Epi 3.3 ± 0.50 with rigid 3D pose model.
This work was supported by the National Institutes of Health (NIH) grant number R01-HL-143350.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
These penalties are experimentally determined for each case. Typically, in some cases RV and Myo penalties need to be tuned to allow proper segmentation of RV in extreme poor contrast cases while LV (\(=0.5\)) and BG (\(=1.0\)) penalties remain fixed.
References
van Assen, H.C., Danilouchkine, M.G., Dirksen, M.S., et al.: A 3-D active shape model driven by fuzzy inference: application to cardiac CT and MR. IEEE Trans. Inf. Technol. Biomed. 12(5), 595–605 (2008)
van Assen, H.C., Danilouchkine, M.G., Frangi, F.F., et al.: A 3D-ASM for segmentation of sparse and arbitrarily oriented cardiac MRI data. Med. Image Anal. 10(2), 286–303 (2006)
Bernard, O., Lalande, A., Zotti, C., et al.: Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans. Med. Imaging 37(11), 2514–2525 (2018). https://doi.org/10.1109/TMI.2018.2837502
Blankstein, R., Di Carli, M.F.: Integration of coronary anatomy and myocardial perfusion imaging. Nat. Rev. Cardiol. 7(4), 226–236 (2010). https://doi.org/10.1038/nrcardio.2010.15
Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. Int. J. Comput. Vis. 22(61), 61–79 (1997)
CDC: Heart disease: Scope and impact (2015). http://www.theheartfoundation.org/heart-disease-facts/heart-disease-statistics/
Chan, T., Vese, L.: An active contour model without edges. In: International Conference on Scale-Space Theories in Computer Vision, pp. 141–151 (1999)
Chan, T., Vese, L.: A level set algorithm for minimizing the Mumford-shah functional in image processing. In: IEEE Workshop on Variational and Level Set Methods in Computer Vision, pp. 161–168 (2001)
Chen, C., Qin, C., Qiu, H., et al.: Deep learning for cardiac image segmentation: a review. Front. Cardiovasc. Med. 7 (2020). https://doi.org/10.3389/fcvm.2020.00025
Chen, Y., Thiruvenkadam, S., Huang, F., et al.: On the incorporation of shape priors into geometric active contours. In: IEEE Workshop on Variational and Level Set Methods in Computer Vision, pp. 145–152 (2001)
Cootes, T., Edwards, G., Taylor, C.: Active appearance models. IEEE Trans. Pattern Recognit. Mach. Intell. 23(6), 681–685 (2001)
Cootes, T., Taylor, C.: Smart snakes. In: Proceedings of British Machine Vision Conference, pp. 266–275 (1992)
Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 484–498. Springer, Heidelberg (1998). https://doi.org/10.1007/BFb0054760
Cootes, T., Taylor, C., Cooper, C., et al.: Active shape models - their training and application. Comput. Vis. Image Underst. 61(9), 38–59 (1995)
Dahiya, N., Yezzi, A., Piccinelli, M., et al.: Integrated 3D anatomical model for automatic myocardial segmentation in cardiac CT imagery. Comput. Methods Biomech. Biomed. Eng. Imaging Vis. 7(5–6), 690–706 (2019). https://doi.org/10.1080/21681163.2019.1583607
Dahiya, N., Yezzi, A., Piccinelli, M., Garcia, E.: Integrated 3D anatomical model for automatic myocardial segmentation in cardiac CT imagery. In: Tavares, J.M.R.S., Natal Jorge, R.M. (eds.) ECCOMAS 2017. LNCVB, vol. 27, pp. 1115–1124. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-68195-5_123
Leventon, M., Grimson, E., Faugeras, O.: Statistical shape influence in geodesic active contours. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 316–323 (2000)
Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3D surface construction algorithm. SIGGRAPH Comput. Graph. 21(4), 163–169 (1987). https://doi.org/10.1145/37402.37422
Mitchell, S.C., Lelieveldt, B., Van Der Geest, et al.: Multistage hybrid active appearance model matching: segmentation of left and right ventricles in cardiac MR images. IEEE Trans. Med. Imaging 20(5), 415–423 (2001)
Mumford, D., Shah, J.: Optimal approximations by piecewise smooth functions and associated variational problems. Commun. Pure Appl. Math. 42(6), 577–685 (1989)
Piccinelli, M., et al.: Diagnostic performance of the quantification of myocardium at risk from MPI SPECT/CTA 2G fusion for detecting obstructive coronary disease: a multicenter trial. J. Nucl. Cardiol. 25(4), 1376–1386 (2017). https://doi.org/10.1007/s12350-017-0819-x
Rizvi, A., Han, D., Danad, I., et al.: Diagnostic performance of hybrid cardiac imaging methods for assessment of obstructive coronary artery disease compared with stand-alone coronary computed tomography angiography: a meta-analysis. JACC Cardiovasc. Imaging 11(4), 589–599 (2018)
Shahzad, R., Bos, D., Budde, R.P.J., et al.: Automatic segmentation and quantification of the cardiac structures from non-contrast-enhanced cardiac CT scans. Phys. Med. Biol. 62(9), 3798 (2017)
Tsai, A., Yezzi, A., Wells, W., et al.: A shape-based approach to the segmentation of medical imagery using level sets. IEEE Trans. Med. Imaging 22, 137–154 (2003)
Vikram, A., Ganapathy, B., Abufadel, A., et al.: A regions of confidence based approach to enhance segmentation with shape priors. In: Proceedings of the of SPIE-IS &T Electronic Imaging, SPIE, pp. 7533–12 (2010). https://doi.org/10.1117/12.850888
Weese, J., Kaus, M., Lorenz, C., Lobregt, S., Truyen, R., Pekar, V.: Shape constrained deformable models for 3D medical image segmentation. In: Insana, M.F., Leahy, R.M. (eds.) IPMI 2001. LNCS, vol. 2082, pp. 380–387. Springer, Heidelberg (2001). https://doi.org/10.1007/3-540-45729-1_38
Yezzi, A., Kichenassamy, S., Kumar, et al.: A geometric snake model for segmentation of medical imagery. IEEE Trans. Med. Imaging 16, 199–209 (1997)
Yezzi, A., Dahiya, N.: Shape adaptive accelerated parameter optimization. In: 2018 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI), pp. 1–4 (2018). https://doi.org/10.1109/SSIAI.2018.8470380
Zhuang, X., Li, L., Payer, C., et al.: Evaluation of algorithms for multi-modality whole heart segmentation: an open-access grand challenge. Med. Image Anal. 58, 101537 (2019). https://doi.org/10.1016/j.media.2019.101537
Bignardi, S., Dahiya, N., Comelli, A., et al.: Combining convolutional neural networks and anatomical shape-based priors for cardiac segmentation. To appear. In: AIRCAD 2022 1st International Workshop on Artificial Intelligence and Radiomics in Computer-Aided Diagnosis
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dahiya, N., Piccinelli, M., Garcia, E., Yezzi, A. (2022). Shape Prior Based Myocardial Segmentation with Anatomically Motivated Pose Model. In: Mazzeo, P.L., Frontoni, E., Sclaroff, S., Distante, C. (eds) Image Analysis and Processing. ICIAP 2022 Workshops. ICIAP 2022. Lecture Notes in Computer Science, vol 13373. Springer, Cham. https://doi.org/10.1007/978-3-031-13321-3_30
Download citation
DOI: https://doi.org/10.1007/978-3-031-13321-3_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-13320-6
Online ISBN: 978-3-031-13321-3
eBook Packages: Computer ScienceComputer Science (R0)