Bildverarbeitung für die Medizin 2019 pp 309-314 | Cite as
Enhancing Label-Driven Deep Deformable Image Registration with Local Distance Metrics for State-of-the-Art Cardiac Motion Tracking
Zusammenfassung
While deep learning has achieved significant advances in accuracy for medical image segmentation, its benefits for deformable image registration have so far remained limited to reduced computation times. Previous work has either focused on replacing the iterative optimization of distance and smoothness terms with CNN-layers or using supervised approaches driven by labels. Our method is the first to combine the complementary strengths of global semantic information (represented by segmentation labels) and local distance metrics that help align surrounding structures. We demonstrate significant higher Dice scores (of 86.5 %) for deformable cardiac image registration compared to classic registration (79.0 %) as well as label-driven deep learning frameworks (83.4%).
Preview
Unable to display preview. Download preview PDF.
Literatur
- 1.Rohé MM, Datar M, Heimann T, et al.; Springer. SVF-Net: learning deformable image registration using shape matching. Proc MICCAI. 2017; p. 266-274.Google Scholar
- 2.de Vos BD, Berendsen FF, ViergeverMA, et al. End-to-end unsupervised deformable image registration with a convolutional neural network. Proc MICCAI Workshop DLMIA, ML-CDS. 2017; p. 204-212.Google Scholar
- 3.Hu Y, Modat M, Gibson E, et al. Weakly-supervised convolutional neural networks for multimodal image registration. Med Image Anal. 2018;49:1-13.CrossRefGoogle Scholar
- 4.Krebs J, Mansi T, Mailhé B, et al. Unsupervised probabilistic deformation modeling for robust diffeomorphic registration. Proc MICCAI Workshop DLMIA, ML-CDS. 2018; p. 101-109.Google Scholar
- 5.Jaderberg M, Simonyan K, Zisserman A, et al. Spatial transformer networks. Adv Neural Inf Process Sys. 2015; p. 2017-2025.Google Scholar
- 6.Rühaak J, Heldmann S, Kipshagen T, et al. Highly accurate fast lung CT registration. Proc SPIE. 2013;8669:86690Y.Google Scholar
- 7.Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. Proc MICCAI. 2015; p. 234-241.Google Scholar
- 8.Jodoin PM, Lalande A, Bernard O. Automated cardiac diagnosis challenge (ACDC); 2017. Accessed: 2018-09-24. Available from: https://www.creatis.insalyon.fr/Challenge/acdc/databases.html.