Advertisement

Learning a Sparse Database for Patch-Based Medical Image Segmentation

  • Moti FreimanEmail author
  • Hannes Nickisch
  • Holger Schmitt
  • Pal Maurovich-Horvat
  • Patrick Donnelly
  • Mani Vembar
  • Liran Goshen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10530)

Abstract

We introduce a functional for the learning of an optimal database for patch-based image segmentation with application to coronary lumen segmentation from coronary computed tomography angiography (CCTA) data. The proposed functional consists of fidelity, sparseness and robustness to small-variations terms and their associated weights. Existing work address database optimization by prototype selection aiming to optimize the database by either adding or removing prototypes according to a set of predefined rules. In contrast, we formulate the database optimization task as an energy minimization problem that can be solved using standard numerical tools. We apply the proposed database optimization functional to the task of optimizing a database for patch-base coronary lumen segmentation. Our experiments using the publicly available MICCAI 2012 coronary lumen segmentation challenge data show that optimizing the database using the proposed approach reduced database size by 96% while maintaining the same level of lumen segmentation accuracy. Moreover, we show that the optimized database yields an improved specificity of CCTA based fractional flow reserve (0.73 vs 0.7 for all lesions and 0.68 vs 0.65 for obstructive lesions) using a training set of 132 (76 obstructive) coronary lesions with invasively measured FFR as the reference.

Keywords

Energy minimization Prototype sampling K-nearest neighbor Coronary lumen segmentation 

References

  1. 1.
    Bien, J., Tibshirani, R.: Prototype selection for interpretable classification. Ann. Appl. Stat. 5(4), 2403–2424 (2011)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Cover, T., Hart, P.: Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 13(1), 21–27 (1967)CrossRefzbMATHGoogle Scholar
  3. 3.
    Freiman, M., et al.: Improving CCTA-based lesions’ hemodynamic significance assessment by accounting for partial volume modeling in automatic coronary lumen segmentation. Med. Phys. 44(3), 1040–1049 (2017)CrossRefGoogle Scholar
  4. 4.
    García, S., et al.: Prototype selection for nearest neighbor classification: taxonomy and empirical study. IEEE Trans. Pattern Anal. Mach. Intell. 34(3), 417–435 (2012)CrossRefGoogle Scholar
  5. 5.
    Kirişli, H., et al.: Standardized evaluation framework for evaluating coronary artery stenosis detection, stenosis quantification and lumen segmentation algorithms in computed tomography angiography. Med. Image Anal. 17(8), 859–876 (2013). http://coronary.bigr.nl/stenoses/ CrossRefGoogle Scholar
  6. 6.
    Lugauer, F., Zheng, Y., Hornegger, J., Kelm, B.M.: Precise lumen segmentation in coronary computed tomography angiography. In: Menze, B., Langs, G., Montillo, A., Kelm, M., Müller, H., Zhang, S., Cai, W.T., Metaxas, D. (eds.) MCV 2014. LNCS, vol. 8848, pp. 137–147. Springer, Cham (2014). doi: 10.1007/978-3-319-13972-2_13 Google Scholar
  7. 7.
    Mechrez, R., Goldberger, J., Greenspan, H.: Patch-based segmentation with spatial consistency: application to MS lesions in brain MRI. Int. J. Biomed. Imaging 2016, Article ID 7952541 (2016)Google Scholar
  8. 8.
    Nickisch, H., Lamash, Y., Prevrhal, S., Freiman, M., Vembar, M., Goshen, L., Schmitt, H.: Learning patient-specific lumped models for interactive coronary blood flow simulations. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A. (eds.) MICCAI 2015. LNCS, vol. 9350, pp. 433–441. Springer, Cham (2015). doi: 10.1007/978-3-319-24571-3_52 CrossRefGoogle Scholar
  9. 9.
    Olabarriaga, S.D., et al.: Segmentation of thrombus in abdominal aortic aneurysms from CTA with nonparametric statistical grey level appearance modeling. IEEE Trans. Med. Imaging 24(4), 477–485 (2005)CrossRefGoogle Scholar
  10. 10.
    Powell, M.: The BOBYQA algorithm for bound constrained optimization without derivatives. NA Report NA2009/06, p. 39 (2009). http://www6.cityu.edu.hk/rcms/publications/preprint26.pdf
  11. 11.
    Wang, Z., Bhatia, K.K., Glocker, B., Marvao, A., Dawes, T., Misawa, K., Mori, K., Rueckert, D.: Geodesic patch-based segmentation. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8673, pp. 666–673. Springer, Cham (2014). doi: 10.1007/978-3-319-10404-1_83 Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Moti Freiman
    • 1
    Email author
  • Hannes Nickisch
    • 2
  • Holger Schmitt
    • 2
  • Pal Maurovich-Horvat
    • 3
  • Patrick Donnelly
    • 4
  • Mani Vembar
    • 5
  • Liran Goshen
    • 1
  1. 1.GAT, CTPhilips HealthcareHaifaIsrael
  2. 2.Philips ResearchHamburgGermany
  3. 3.Heart and Vascular CenterSemmelweis UniversityBudapestHungary
  4. 4.South Eastern Health and Social Care TrustQueen’s UniversityBelfastIreland
  5. 5.Clinical Science, CTPhilips HealthcareClevelandUSA

Personalised recommendations