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

Autor: Robert B. Grupp, Benjamin A. McArthur, Cong Gao, Mehran Armand, Ryan J. Murphy, Yoshito Otake, Rachel Hegeman, Mathias Unberath, Clayton P. Alexander, Russell H. Taylor
Rok vydání: 2020
Předmět:
FOS: Computer and information sciences
Computer science
Computer Vision and Pattern Recognition (cs.CV)
0206 medical engineering
Computer Science - Computer Vision and Pattern Recognition
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Biomedical Engineering
Initialization
Health Informatics
02 engineering and technology
Article
Pelvis
030218 nuclear medicine & medical imaging
03 medical and health sciences
Imaging
Three-Dimensional
0302 clinical medicine
FOS: Electrical engineering
electronic engineering
information engineering
medicine
Humans
Fluoroscopy
Radiology
Nuclear Medicine and imaging
Segmentation
Femur
Hip surgery
Ground truth
Modality (human–computer interaction)
medicine.diagnostic_test
Image and Video Processing (eess.IV)
General Medicine
Anatomy
Electrical Engineering and Systems Science - Image and Video Processing
020601 biomedical engineering
Computer Graphics and Computer-Aided Design
Computer Science Applications
medicine.anatomical_structure
Surgery
Neural Networks
Computer
Computer Vision and Pattern Recognition
Tomography
X-Ray Computed
Algorithms
Zdroj: Int J Comput Assist Radiol Surg
ISSN: 1861-6429
1861-6410
Popis: 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. We propose a method for fully automatic registration using annotations produced by a neural network. Neural networks are trained to simultaneously segment anatomy and identify landmarks in fluoroscopy. Training data is obtained using an intraoperatively incompatible 2D/3D registration of hip anatomy. Ground truth 2D labels are established using projected 3D annotations. Intraoperative registration couples an intensity-based strategy with annotations inferred by the network and requires no human assistance. Ground truth labels were obtained in 366 fluoroscopic images across 6 cadaveric specimens. In a leave-one-subject-out experiment, networks obtained mean dice coefficients for left and right hemipelves, left and right femurs of 0.86, 0.87, 0.90, and 0.84. The mean 2D landmark error was 5.0 mm. The pelvis was registered within 1 degree for 86% of the images when using the proposed intraoperative approach with an average runtime of 7 seconds. In comparison, an intensity-only approach without manual initialization, registered the pelvis to 1 degree in 18% of images. 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.
Comment: Revised article to address reviewer comments. Accepted to IPCAI 2020. Supplementary video at https://youtu.be/5AwGlNkcp9o and dataset/code at https://github.com/rg2/DeepFluoroLabeling-IPCAI2020
Databáze: OpenAIRE
Externí odkaz: