Skip to main content

2018 | OriginalPaper | Buchkapitel

Adversarial Deformation Regularization for Training Image Registration Neural Networks

verfasst von : Yipeng Hu, Eli Gibson, Nooshin Ghavami, Ester Bonmati, Caroline M. Moore, Mark Emberton, Tom Vercauteren, J. Alison Noble, Dean C. Barratt

Erschienen in: Medical Image Computing and Computer Assisted Intervention – MICCAI 2018

Verlag: Springer International Publishing

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

search-config
loading …

Abstract

We describe an adversarial learning approach to constrain convolutional neural network training for image registration, replacing heuristic smoothness measures of displacement fields often used in these tasks. Using minimally-invasive prostate cancer intervention as an example application, we demonstrate the feasibility of utilizing biomechanical simulations to regularize a weakly-supervised anatomical-label-driven registration network for aligning pre-procedural magnetic resonance (MR) and 3D intra-procedural transrectal ultrasound (TRUS) images. A discriminator network is optimized to distinguish the registration-predicted displacement fields from the motion data simulated by finite element analysis. During training, the registration network simultaneously aims to maximize similarity between anatomical labels that drives image alignment and to minimize an adversarial generator loss that measures divergence between the predicted- and simulated deformation. The end-to-end trained network enables efficient and fully-automated registration that only requires an MR and TRUS image pair as input, without anatomical labels or simulated data during inference. 108 pairs of labelled MR and TRUS images from 76 prostate cancer patients and 71,500 nonlinear finite-element simulations from 143 different patients were used for this study. We show that, with only gland segmentation as training labels, the proposed method can help predict physically plausible deformation without any other smoothness penalty. Based on cross-validation experiments using 834 pairs of independent validation landmarks, the proposed adversarial-regularized registration achieved a target registration error of 6.3 mm that is significantly lower than those from several other regularization methods.

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!

Literatur
1.
4.
Zurück zum Zitat Hu, Y., et al.: Label-driven weakly-supervised learning for multimodal deformable image registration. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI) (2018). arXiv:1711.01666 Hu, Y., et al.: Label-driven weakly-supervised learning for multimodal deformable image registration. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI) (2018). arXiv:​1711.​01666
5.
Zurück zum Zitat Wang, Y., et al.: Towards personalized statistical deformable model and hybrid point matching for robust MR-TRUS registration. IEEE-TMI 35(2), 589–604 (2016) Wang, Y., et al.: Towards personalized statistical deformable model and hybrid point matching for robust MR-TRUS registration. IEEE-TMI 35(2), 589–604 (2016)
6.
Zurück zum Zitat Hu, Y., et al.: MR to ultrasound registration for image-guided prostate interventions. Med. Image Anal. 16(3), 687–703 (2012)CrossRef Hu, Y., et al.: MR to ultrasound registration for image-guided prostate interventions. Med. Image Anal. 16(3), 687–703 (2012)CrossRef
7.
Zurück zum Zitat Khallaghi, S., et al.: Statistical biomechanical surface registration: application to MR-TRUS fusion for prostate interventions. IEEE-TMI 34(12), 2535–2549 (2015) Khallaghi, S., et al.: Statistical biomechanical surface registration: application to MR-TRUS fusion for prostate interventions. IEEE-TMI 34(12), 2535–2549 (2015)
8.
Zurück zum Zitat Valerio, M., et al.: Detection of clinically significant prostate cancer using magnetic resonance imaging-ultrasound fusion targeted biopsy. Eur. Urol. 68(1), 8–19 (2015)CrossRef Valerio, M., et al.: Detection of clinically significant prostate cancer using magnetic resonance imaging-ultrasound fusion targeted biopsy. Eur. Urol. 68(1), 8–19 (2015)CrossRef
9.
Zurück zum Zitat Goodfellow, I., et al.: Generative adversarial nets. In: NIPS 2014, pp. 2672–2680 (2014) Goodfellow, I., et al.: Generative adversarial nets. In: NIPS 2014, pp. 2672–2680 (2014)
10.
Zurück zum Zitat Roth, K., et al.: Stabilizing training of generative adversarial networks through regularization. In: NIPS 2017, pp. 2015–2025 (2017) Roth, K., et al.: Stabilizing training of generative adversarial networks through regularization. In: NIPS 2017, pp. 2015–2025 (2017)
11.
Zurück zum Zitat Radford, A., et al.: Unsupervised representation learning with deep convolutional generative adversarial networks (2015). arXiv preprint: arXiv:1511.06434 Radford, A., et al.: Unsupervised representation learning with deep convolutional generative adversarial networks (2015). arXiv preprint: arXiv:​1511.​06434
12.
Zurück zum Zitat Gibson, E., et al.: NiftyNet: a deep-learning platform for medical imaging. Comput. Methods Programs Biomed. 158, 113–122 (2018)CrossRef Gibson, E., et al.: NiftyNet: a deep-learning platform for medical imaging. Comput. Methods Programs Biomed. 158, 113–122 (2018)CrossRef
13.
Zurück zum Zitat Litjens, G., et al.: Evaluation of prostate segmentation algorithms for MRI: the PROMISE12 challenge. Med. Image Anal. 18(2), 359–373 (2014)CrossRef Litjens, G., et al.: Evaluation of prostate segmentation algorithms for MRI: the PROMISE12 challenge. Med. Image Anal. 18(2), 359–373 (2014)CrossRef
14.
Zurück zum Zitat Johnsen, S.F., et al.: NiftySim: a GPU-based nonlinear finite element package for simulation of soft tissue biomechanics. IJCARS 10(7), 1077–1095 (2015) Johnsen, S.F., et al.: NiftySim: a GPU-based nonlinear finite element package for simulation of soft tissue biomechanics. IJCARS 10(7), 1077–1095 (2015)
Metadaten
Titel
Adversarial Deformation Regularization for Training Image Registration Neural Networks
verfasst von
Yipeng Hu
Eli Gibson
Nooshin Ghavami
Ester Bonmati
Caroline M. Moore
Mark Emberton
Tom Vercauteren
J. Alison Noble
Dean C. Barratt
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-030-00928-1_87