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

  • PDF / 1,090,377 Bytes
  • 11 Pages / 595.276 x 790.866 pts Page_size
  • 63 Downloads / 157 Views

DOWNLOAD

REPORT


ORIGINAL ARTICLE

Automatic annotation of hip anatomy in fluoroscopy for robust and efficient 2D/3D registration Robert B. Grupp1 · Mathias Unberath1 · Cong Gao1 · Rachel A. Hegeman2 · Ryan J. Murphy3 · Clayton P. Alexander4 · Yoshito Otake5 · Benjamin A. McArthur6,7 · Mehran Armand2,4,8 · Russell H. Taylor1 Received: 15 November 2019 / Accepted: 3 April 2020 © CARS 2020

Abstract 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 registration using anatomical annotations produced by a neural network. Methods Neural networks are trained to simultaneously segment anatomy and identify landmarks in fluoroscopy. Training data are obtained using a computationally intensive, intraoperatively incompatible, 2D/3D registration of the pelvis and each femur. Ground truth 2D segmentation labels and anatomical landmark locations are established using projected 3D annotations. Intraoperative registration couples a traditional intensity-based strategy with annotations inferred by the network and requires no human assistance. Results Ground truth segmentation labels and anatomical landmarks were obtained in 366 fluoroscopic images across 6 cadaveric specimens. In a leave-one-subject-out experiment, networks trained on these data obtained mean dice coefficients for left and right hemipelves, left and right femurs of 0.86, 0.87, 0.90, and 0.84, respectively. The mean 2D landmark localization error was 5.0 mm. The pelvis was registered within 1◦ for 86% of the images when using the proposed intraoperative approach with an average runtime of 7 s. In comparison, an intensity-only approach without manual initialization registered the pelvis to 1◦ in 18% of images. Conclusions We have created the first accurately annotated, non-synthetic, dataset of hip fluoroscopy. By using these annotations as training data for neural networks, state-of-the-art performance in fluoroscopic segmentation and landmark localization was achieved. Integrating these annotations allows for a robust, fully automatic, and efficient intraoperative registration during fluoroscopic navigation of the hip. Keywords Landmark detection · Semantic segmentation · 2D/3D registration · X-ray navigation · Orthopedics

Electronic supplementary material The online version of this article (https://doi.org/10.1007/s11548-020-02162-7) contains supplementary material, which is available to authorized users.

B 1

2

3

Robert B. Grupp [email protected] Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA Research and Exploratory Development Department, Johns Hopkins University Applied Physics Laboratory, Laurel, MD, USA Auris H