3D/2D model-to-image registration by imitation learning for cardiac procedures

By D. Toth, Shun Miao, T. Kurzendorfer, C. Rinaldi, Rui Liao, Tommaso Mansi, K. Rhode, P. Mountney. 2018

42 citations recorded by the source corpus.

PurposeIn cardiac interventions, such as cardiac resynchronization therapy (CRT), image guidance can be enhanced by involving preoperative models. Multimodality 3D/2D registration for image guidance, however, remains a significant research challenge for fundamentally different image data, i.e., MR to X-ray. Registration methods must account for differences in intensity, contrast levels, resolution, dimensionality, field of view. Furthermore, same anatomical structures may not be visible in both modalities. Current approaches have focused on developing modality-specific solutions for individual clinical use cases, by introducing constraints, or identifying cross-modality information manually. Machine learning approaches have the potential to create more general registration platforms. However, training image to image methods would require large multimodal datasets and ground truth for each target application.MethodsThis paper proposes a model-to-image registration approach instead, because it is common in image-guided interventions to create anatomical models for diagnosis, planning or guidance prior to procedures. An imitation learning-based method, trained on 702 datasets, is used to register preoperative models to intraoperative X-ray images.ResultsAccuracy is demonstrated on cardiac models and artificial X-rays generated from CTs. The registration error was $$2.92\pm 2.22\,\hbox { mm}$$2.92±2.22mm on 1000 test cases, superior to that of manual ($$6.48\pm 5.6\,\hbox { mm}$$6.48±5.6mm) and gradient-based ($$6.79\pm 4.75\,\hbox { mm}$$6.79±4.75mm) registration. High robustness is shown in 19 clinical CRT cases.ConclusionBesides the proposed methods feasibility in a clinical environment, evaluation has shown good accuracy and high robustness indicating that it could be applied in image-guided interventions.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

  1. Arvid Lundervold

In Computer Vision and Pattern Recognition

  1. Arvid Lundervold

In Radiology, Nuclear Medicine and Imaging

  1. Arvid Lundervold
  2. Florian Tramèr
  3. Dan Boneh

Citations in the corpus