Skip to main content

2016 | OriginalPaper | Buchkapitel

Inertial Demons: A Momentum-Based Diffeomorphic Registration Framework

verfasst von : Andre Santos-Ribeiro, David J. Nutt, John McGonigle

Erschienen in: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Non-linear registration is an essential part of modern neuroimaging analysis, from morphometrics to functional studies. To be practical, non-linear registration methods must be precise and computational efficient. Current algorithms based on Thirion’s demons achieve high accuracies while having desirable properties such as diffeomorphic deformation fields. However, the increased complexity of these methods lead to a decrease in their efficiency. Here we propose a modification of the demons algorithm that both improves the accuracy and convergence speed, while maintaining the characteristics of a diffeomorphic registration. Our method outperforms all the analysed demons approaches in terms of speed and accuracy. Furthermore, this improvement is not limited to the demons algorithm, but applicable in most typical deformable registration algorithms.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Fußnoten
1
A value higher than 1 leads to instability of the registration process as the magnitude of the update field \(\left\| u(x) \right\| \) keeps increasing at each iteration.
 
2
The statistical comparison between each original and proposed methods was performed through a Mann-Whitney U test. Although not shown here a significant improvement is also seen if \(\left\| u(x) \right\| \le 0.4\) for all methods.
 
Literatur
1.
Zurück zum Zitat Arbel, T., De Nigris, D.: Fast and efficient image registration based on gradient orientations of minimal uncertainty. In: International Symposium on Biomed Imaging, pp. 1163–1166 (2015) Arbel, T., De Nigris, D.: Fast and efficient image registration based on gradient orientations of minimal uncertainty. In: International Symposium on Biomed Imaging, pp. 1163–1166 (2015)
2.
Zurück zum Zitat Ashburner, J.: A fast diffeomorphic image registration algorithm. Neuroimage 38, 95–113 (2007)CrossRef Ashburner, J.: A fast diffeomorphic image registration algorithm. Neuroimage 38, 95–113 (2007)CrossRef
3.
Zurück zum Zitat Avants, B., Epstein, C., Grossman, M., Gee, J.: Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain. Med. Image Anal. 12, 26–41 (2008)CrossRef Avants, B., Epstein, C., Grossman, M., Gee, J.: Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain. Med. Image Anal. 12, 26–41 (2008)CrossRef
4.
Zurück zum Zitat Cachier, P., Bardinet, E., Dormont, D., Pennec, X., Ayache, N.: Iconic feature based nonrigid registration: the PASHA algorithm. Comput. Vis. Image Und. 89, 272–298 (2003)CrossRefMATH Cachier, P., Bardinet, E., Dormont, D., Pennec, X., Ayache, N.: Iconic feature based nonrigid registration: the PASHA algorithm. Comput. Vis. Image Und. 89, 272–298 (2003)CrossRefMATH
5.
Zurück zum Zitat Cachier, P., Pennec, X., Ayache, N.: Fast non-rigid matching by gradient descent: study and improvement of the demons algorithm. INRIA RR-3706 (1999) Cachier, P., Pennec, X., Ayache, N.: Fast non-rigid matching by gradient descent: study and improvement of the demons algorithm. INRIA RR-3706 (1999)
6.
Zurück zum Zitat Demirovic, D., Serifovic-Trbalic, A., Prljaca, N., Cattin, P.: Bilateral filter regularized accelerated demons for improved discontinuity preserving registration. Comput. Med. Imaging Graph. 40, 94–99 (2015)CrossRefMATH Demirovic, D., Serifovic-Trbalic, A., Prljaca, N., Cattin, P.: Bilateral filter regularized accelerated demons for improved discontinuity preserving registration. Comput. Med. Imaging Graph. 40, 94–99 (2015)CrossRefMATH
7.
Zurück zum Zitat Lorenzi, M., Ayache, N., Frisoni, G., Pennec, X.: LCC-Demons: a robust and accurate symmetric diffeomorphic registration algorithm. Neuroimage 81, 470–483 (2013)CrossRef Lorenzi, M., Ayache, N., Frisoni, G., Pennec, X.: LCC-Demons: a robust and accurate symmetric diffeomorphic registration algorithm. Neuroimage 81, 470–483 (2013)CrossRef
8.
Zurück zum Zitat Lu, H., Reyes, M., Serifovi, A., Weber, S., Sakurai, Y., Yamagata, H., Cattin, P.: Multi-modal diffeomorphic demons registration based on point-wise mutual information. In: International Symposium on Biomed Imaging, pp. 372–375 (2010) Lu, H., Reyes, M., Serifovi, A., Weber, S., Sakurai, Y., Yamagata, H., Cattin, P.: Multi-modal diffeomorphic demons registration based on point-wise mutual information. In: International Symposium on Biomed Imaging, pp. 372–375 (2010)
9.
Zurück zum Zitat Malis, E.: Improving vision-based control using efficient second-order minimization techniques. IEEE Int. Conf. Robot. 2, 1843–1848 (2004) Malis, E.: Improving vision-based control using efficient second-order minimization techniques. IEEE Int. Conf. Robot. 2, 1843–1848 (2004)
10.
Zurück zum Zitat Moler, C., Van Loan, C.: Nineteen dubious ways to compute the exponential of a matrix, twenty-five years later. SIAM J. Appl. Math. 45(1), 3–49 (2003)MathSciNetMATH Moler, C., Van Loan, C.: Nineteen dubious ways to compute the exponential of a matrix, twenty-five years later. SIAM J. Appl. Math. 45(1), 3–49 (2003)MathSciNetMATH
11.
Zurück zum Zitat Pennec, X., Cachier, P., Ayache, N.: Understanding the “Demon’s Algorithm”: 3D non-rigid registration by gradient descent. In: Taylor, C., Colchester, A. (eds.) MICCAI 1999. LNCS, vol. 1679, pp. 597–605. Springer, Heidelberg (1999). doi:10.1007/10704282_64CrossRef Pennec, X., Cachier, P., Ayache, N.: Understanding the “Demon’s Algorithm”: 3D non-rigid registration by gradient descent. In: Taylor, C., Colchester, A. (eds.) MICCAI 1999. LNCS, vol. 1679, pp. 597–605. Springer, Heidelberg (1999). doi:10.​1007/​10704282_​64CrossRef
12.
Zurück zum Zitat Rueckert, D., Aljabar, P., Heckemann, R.A., Hajnal, J.V., Hammers, A.: Diffeomorphic registration using B-splines. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4191, pp. 702–709. Springer, Heidelberg (2006). doi:10.1007/11866763_86CrossRef Rueckert, D., Aljabar, P., Heckemann, R.A., Hajnal, J.V., Hammers, A.: Diffeomorphic registration using B-splines. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4191, pp. 702–709. Springer, Heidelberg (2006). doi:10.​1007/​11866763_​86CrossRef
13.
Zurück zum Zitat Ribeiro, A.S., Nutt, D.J., McGonigle, J.: Which metrics should be used in non-linear registration evaluation? In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9350, pp. 388–395. Springer, Heidelberg (2015). doi:10.1007/978-3-319-24571-3_47CrossRef Ribeiro, A.S., Nutt, D.J., McGonigle, J.: Which metrics should be used in non-linear registration evaluation? In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9350, pp. 388–395. Springer, Heidelberg (2015). doi:10.​1007/​978-3-319-24571-3_​47CrossRef
14.
Zurück zum Zitat Thirion, J.: Image matching as a diffusion process: an analogy with maxwells demons. Med. Image Anal. 2(3), 243–260 (1998)CrossRef Thirion, J.: Image matching as a diffusion process: an analogy with maxwells demons. Med. Image Anal. 2(3), 243–260 (1998)CrossRef
15.
Zurück zum Zitat Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Non-parametric diffeomorphic image registration with the demons algorithm. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007. LNCS, vol. 4792, pp. 319–326. Springer, Heidelberg (2007). doi:10.1007/978-3-540-75759-7_39CrossRef Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Non-parametric diffeomorphic image registration with the demons algorithm. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007. LNCS, vol. 4792, pp. 319–326. Springer, Heidelberg (2007). doi:10.​1007/​978-3-540-75759-7_​39CrossRef
16.
Zurück zum Zitat Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Symmetric log-domain diffeomorphic registration: a demons-based approach. In: Metaxas, D., Axel, L., Fichtinger, G., Székely, G. (eds.) MICCAI 2008. LNCS, vol. 5241, pp. 754–761. Springer, Heidelberg (2008). doi:10.1007/978-3-540-85988-8_90CrossRef Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Symmetric log-domain diffeomorphic registration: a demons-based approach. In: Metaxas, D., Axel, L., Fichtinger, G., Székely, G. (eds.) MICCAI 2008. LNCS, vol. 5241, pp. 754–761. Springer, Heidelberg (2008). doi:10.​1007/​978-3-540-85988-8_​90CrossRef
17.
Zurück zum Zitat Wang, H., Dong, L., O’Daniel, J., Mohan, R., Garden, A., Ang, K., Kuban, D., Bonnen, M., Chang, J., Cheung, R.: Validation of an accelerated ‘demons’ algorithm for deformable image registration in radiation therapy. Phys. Med. Biol. 50(12), 2887–2905 (2005)CrossRef Wang, H., Dong, L., O’Daniel, J., Mohan, R., Garden, A., Ang, K., Kuban, D., Bonnen, M., Chang, J., Cheung, R.: Validation of an accelerated ‘demons’ algorithm for deformable image registration in radiation therapy. Phys. Med. Biol. 50(12), 2887–2905 (2005)CrossRef
18.
Zurück zum Zitat Yang, D., Li, H., Low, D., Deasy, J., Naqa, I.: A fast inverse consistent deformable image registration method based on symmetric optical flow computation. Phys. Med. Biol. 53(21), 6143–6165 (2008)CrossRef Yang, D., Li, H., Low, D., Deasy, J., Naqa, I.: A fast inverse consistent deformable image registration method based on symmetric optical flow computation. Phys. Med. Biol. 53(21), 6143–6165 (2008)CrossRef
19.
Zurück zum Zitat Zikic, D., Baust, M., Kamen, A., Navab, N.: Natural gradients for deformable registration. In: Proceedings of the CVPR, pp. 2847–2854. IEEE (2010) Zikic, D., Baust, M., Kamen, A., Navab, N.: Natural gradients for deformable registration. In: Proceedings of the CVPR, pp. 2847–2854. IEEE (2010)
Metadaten
Titel
Inertial Demons: A Momentum-Based Diffeomorphic Registration Framework
verfasst von
Andre Santos-Ribeiro
David J. Nutt
John McGonigle
Copyright-Jahr
2016
DOI
https://doi.org/10.1007/978-3-319-46726-9_5