Automatic annotation of hip anatomy in fluoroscopy for robust and efficient 2D/3D registration

@article{Grupp2020AutomaticAO,
  title={Automatic annotation of hip anatomy in fluoroscopy for robust and efficient 2D/3D registration},
  author={Robert Grupp and M. Unberath and Cong Gao and Rachel A. Hegeman and Ryan J. Murphy and Clayton P. Alexander and Yoshito Otake and Benjamin A. McArthur and Mehran Armand and Russell H. Taylor},
  journal={International Journal of Computer Assisted Radiology and Surgery},
  year={2020},
  volume={15},
  pages={759-769}
}
Purpose Fluoroscopy is the standard imaging modality used to guide hip surgery and is therefore a natural sensor for computer-assisted navigation. In order to efficiently solve the complex registration problems presented during navigation, human-assisted annotations of the intraoperative image are typically required. This manual initialization interferes with the surgical workflow and diminishes any advantages gained from navigation. In this paper, we propose a method for fully automatic… Expand
Fast and Automatic Periacetabular Osteotomy Fragment Pose Estimation Using Intraoperatively Implanted Fiducials and Single-View Fluoroscopy
TLDR
The proposed computer assisted approach that uses a single fluoroscopic view and quickly reports the pose of an acetabular fragment without any user input or initialization demonstrates accuracy similar to other state of the art systems which require optical tracking systems or multiple-view 2D/3D registrations with manual input. Expand
Fiducial-Free 2D/3D Registration for Robot-Assisted Femoroplasty
TLDR
The fiducial-less 2D/3D registration is sufficiently accurate to guide robot assisted femoroplasty, and the biomechanical analysis showed that even with a 4 mm translational deviation from the optimal injection path, the yield load prior to fracture increased by 40%. Expand
Deep Learning compatible Differentiable X-ray Projections for Inverse Rendering
TLDR
This work proposes a differentiable renderer by deriving the distance travelled by a ray inside mesh structures to generate a distance map and shows its application by solving the inverse problem, namely reconstructing 3D models from real 2D fluoroscopy images of the pelvis, which is an ideal anatomical structure for patient registration. Expand
Extended Capture Range of Rigid 2D/3D Registration by Estimating Riemannian Pose Gradients
TLDR
On both synthetic and real X-ray images of the human pelvis, the proposed method can successfully recover large rotational and translational offsets, irrespective of initialization, and integrates seamlessly with conventional image-based registration frameworks. Expand
Generalizing Spatial Transformers to Projective Geometry with Applications to 2D/3D Registration
TLDR
This paper shows that the proposed Projective Spatial Transformer module enables end-to-end learning of an image processing and projection model that approximates an image similarity function that is convex with respect to the pose parameters, and can be optimized effectively using conventional gradient descent. Expand
Pose-Dependent Weights and Domain Randomization for Fully Automatic X-Ray to CT Registration
TLDR
This work provides a novel automatic initialization, which enables end to end registration, and proposes a domain randomization scheme to enable the network to overcome the challenge of being trained purely on simulated data and run inference on real X-rays. Expand
A new 2D-3D registration gold-standard dataset for the hip joint based on uncertainty modeling.
TLDR
A new methodology based on uncertainty propagation to estimate the accuracy of a gold standard dataset for validation of CT-to-X-ray registration of the hip joint was proposed and showed that considering possible noise anisotropy and including corrupted 3D fiducials in the optimization resulted in improved accuracy of the gold standard. Expand
...
1
2
...

References

SHOWING 1-10 OF 43 REFERENCES
Multi-task Localization and Segmentation for X-ray Guided Planning in Knee Surgery
TLDR
An automatic framework for planning and subsequent overlay of surgical planning is proposed and consistently performs surgical planning at expert-level precision without the need for manual correction. Expand
Fiducial-free 2D/3D registration of the proximal femur for robot-assisted femoroplasty
TLDR
A fiducial-free 2D/3D registration pipeline, which uses the pelvis to initialize the femur registration, which is sufficiently accurate for robotic drill positioning is proposed. Expand
Fast and Automatic Periacetabular Osteotomy Fragment Pose Estimation Using Intraoperatively Implanted Fiducials and Single-View Fluoroscopy
TLDR
The proposed computer assisted approach that uses a single fluoroscopic view and quickly reports the pose of an acetabular fragment without any user input or initialization demonstrates accuracy similar to other state of the art systems which require optical tracking systems or multiple-view 2D/3D registrations with manual input. Expand
Patch-Based Image Similarity for Intraoperative 2D/3D Pelvis Registration During Periacetabular Osteotomy
TLDR
Intense-based 2D/3D registration is used to estimate the pelvis pose with respect to fluoroscopic images, recover relative poses of multiple views, and triangulate landmarks which may be used for navigation of osteotomes and the relocated acetabular fragment. Expand
A fluoroscopy-based planning and guidance software tool for minimally invasive hip refixation by cement injection
  • D. Malan, S. Walt, +5 authors E. Valstar
  • Computer Science, Medicine
  • International Journal of Computer Assisted Radiology and Surgery
  • 2015
TLDR
HipRFX, a software tool for planning and guiding a cement injection procedure for stabilizing a loosening hip prosthesis, provided estimates of the fraction of injected cement deposited at its intended target location, as opposed to cement that leaked away. Expand
Towards Fully Automatic X-Ray to CT Registration
TLDR
This study introduces the first end-to-end fully-automatic registration framework for intraoperative pose-initialization in X-ray to CT registration, using a patient-specific refinement scheme to extract 2D landmarks resulting from the projection of CT-labels. Expand
Learning to detect anatomical landmarks of the pelvis in X-rays from arbitrary views
TLDR
This work presents the first tool to detect anatomical landmarks in X-ray images independent of their viewing direction, and constitutes a first step toward global initialization of 2D/3D registration without the need of calibration. Expand
Localizing dexterous surgical tools in X-ray for image-based navigation
TLDR
Learning-based retrieval of semantic information on imaged-objects as a stepping stone for robust initialization of image-based 2D/3D registration is discussed, which may be of interest to the IPCAI community. Expand
Fully Automatic and Real-Time Catheter Segmentation in X-Ray Fluoroscopy
TLDR
A real-time method to segment the catheter and guidewire in 2D X-ray fluoroscopic sequences based on deep convolutional neural networks is proposed, which is performed in a real- time fully-automatic manner. Expand
A review of 3D/2D registration methods for image-guided interventions
TLDR
The 3D/2D registration methods are reviewed with respect to image modality, image dimensionality, registration basis, geometric transformation, user interaction, optimization procedure, subject, and object of registration. Expand
...
1
2
3
4
5
...