scholarly journals SpineDepth: A Multi-Modal Data Collection Approach for Automatic Labelling and Intraoperative Spinal Shape Reconstruction Based on RGB-D Data

2021 ◽  
Vol 7 (9) ◽  
pp. 164
Author(s):  
Florentin Liebmann ◽  
Dominik Stütz ◽  
Daniel Suter ◽  
Sascha Jecklin ◽  
Jess G. Snedeker ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Pedicle Screw ◽  
Tracking System ◽  
Ground Truth ◽  
Shape Reconstruction ◽  
Optical Tracking ◽  
Data Driven ◽  
Screw Placement ◽  
Pedicle Screw Placement ◽  
Optical Tracking System

Computer aided orthopedic surgery suffers from low clinical adoption, despite increased accuracy and patient safety. This can partly be attributed to cumbersome and often radiation intensive registration methods. Emerging RGB-D sensors combined with artificial intelligence data-driven methods have the potential to streamline these procedures. However, developing such methods requires vast amount of data. To this end, a multi-modal approach that enables acquisition of large clinical data, tailored to pedicle screw placement, using RGB-D sensors and a co-calibrated high-end optical tracking system was developed. The resulting dataset comprises RGB-D recordings of pedicle screw placement along with individually tracked ground truth poses and shapes of spine levels L1–L5 from ten cadaveric specimens. Besides a detailed description of our setup, quantitative and qualitative outcome measures are provided. We found a mean target registration error of 1.5 mm. The median deviation between measured and ground truth bone surface was 2.4 mm. In addition, a surgeon rated the overall alignment based on 10% random samples as 5.8 on a scale from 1 to 6. Generation of labeled RGB-D data for orthopedic interventions with satisfactory accuracy is feasible, and its publication shall promote future development of data-driven artificial intelligence methods for fast and reliable intraoperative registration.

Accuracy and technical limits of percutaneous pedicle screw placement in the thoracolumbar spine

2021 ◽  
Author(s):  
Yann Philippe Charles ◽  
Yves Ntilikina ◽  
Arnaud Collinet ◽  
Sébastien Schuller ◽  
Julien Garnon ◽  
...  
Keyword(s):  
Pedicle Screw ◽  
Thoracolumbar Spine ◽  
Screw Placement ◽  
Pedicle Screw Placement ◽  
Percutaneous Pedicle Screw

scholarly journals Overview of Robotic Technology in Spine Surgery

2021 ◽  
pp. 155633162110266
Author(s):  
Ram K. Alluri ◽  
Fedan Avrumova ◽  
Ahilan Sivaganesan ◽  
Avani S. Vaishnav ◽  
Darren R. Lebl ◽  
...  
Keyword(s):  
Economic Impact ◽  
Pedicle Screw ◽  
Clinical Outcomes ◽  
Spine Surgery ◽  
Screw Placement ◽  
Complication Rates ◽  
Robotic Technology ◽  
Pedicle Screw Placement ◽  
The Past ◽  
Compare And Contrast

As robotics in spine surgery has progressed over the past 2 decades, studies have shown mixed results on its clinical outcomes and economic impact. In this review, we highlight the evolution of robotic technology over the past 30 years, discussing early limitations and failures. We provide an overview of the history and evolution of currently available spinal robotic platforms and compare and contrast the available features of each. We conclude by summarizing the literature on robotic instrumentation accuracy in pedicle screw placement and clinical outcomes such as complication rates and briefly discuss the future of robotic spine surgery.

Variability Analysis of Manual and Computer-Assisted Preoperative Thoracic Pedicle Screw Placement Planning

Spine ◽  
2018 ◽  
Vol 43 (21) ◽  
pp. 1487-1495 ◽  
Author(s):  
Dejan Knez ◽  
Janez Mohar ◽  
Robert J. Cirman ◽  
Boštjan Likar ◽  
Franjo Pernuš ◽  
...  
Keyword(s):  
Pedicle Screw ◽  
Screw Placement ◽  
Computer Assisted ◽  
Pedicle Screw Placement ◽  
Variability Analysis ◽  
Thoracic Pedicle Screw

scholarly journals Learning Retention of Thoracic Pedicle Screw Placement Using a High-Resolution Augmented Reality Simulator With Haptic Feedback

2011 ◽  
Vol 69 (suppl_1) ◽  
pp. ons14-ons19 ◽  
Author(s):  
Cristian J Luciano ◽  
P Pat Banerjee ◽  
Brad Bellotte ◽  
G Michael Oh ◽  
Michael Lemole ◽  
...  
Keyword(s):  
Augmented Reality ◽  
Pedicle Screw ◽  
Haptic Feedback ◽  
Screw Placement ◽  
Pedicle Screw Placement ◽  
Data Set ◽  
Learning Retention ◽  
Performance Accuracy ◽  
Thoracic Pedicle Screw ◽  
Thoracic Pedicle Screws

Abstract BACKGROUND: We evaluated the use of a part-task simulator with 3D and haptic feedback as a training tool for a common neurosurgical procedure - placement of thoracic pedicle screws. OBJECTIVE: To evaluate the learning retention of thoracic pedicle screw placement on a high-performance augmented reality and haptic technology workstation. METHODS: Fifty-one fellows and residents performed thoracic pedicle screw placement on the simulator. The virtual screws were drilled into a virtual patient's thoracic spine derived from a computed tomography data set of a real patient. RESULTS: With a 12.5% failure rate, a 2-proportion z test yielded P = .08. For performance accuracy, an aggregate Euclidean distance deviation from entry landmark on the pedicle and a similar deviation from the target landmark in the vertebral body yielded P = .04 from a 2-sample t test in which the rejected null hypothesis assumes no improvement in performance accuracy from the practice to the test sessions, and the alternative hypothesis assumes an improvement. CONCLUSION: The performance accuracy on the simulator was comparable to the accuracy reported in literature on recent retrospective evaluation of such placements. The failure rates indicated a minor drop from practice to test sessions, and also indicated a trend (P = .08) toward learning retention resulting in improvement from practice to test sessions. The performance accuracy showed a 15% mean score improvement and more than a 50% reduction in standard deviation from practice to test. It showed evidence (P = .04) of performance accuracy improvement from practice to test session.

The accuracy of pedicle screw placement using intraoperative image guidance systems

2014 ◽  
Vol 20 (2) ◽  
pp. 196-203 ◽  
Author(s):  
Alexander Mason ◽  
Renee Paulsen ◽  
Jason M. Babuska ◽  
Sharad Rajpal ◽  
Sigita Burneikiene ◽  
...  
Keyword(s):  
Pedicle Screw ◽  
Image Guidance ◽  
Pedicle Screws ◽  
Screw Placement ◽  
Data Sets ◽  
Pedicle Screw Placement ◽  
Fluoroscopic Image ◽  
Fluoroscopic Navigation ◽  
Guidance Systems ◽  
Accuracy Rates

Object Several retrospective studies have demonstrated higher accuracy rates and increased safety for navigated pedicle screw placement than for free-hand techniques; however, the accuracy differences between navigation systems has not been extensively studied. In some instances, 3D fluoroscopic navigation methods have been reported to not be more accurate than 2D navigation methods for pedicle screw placement. The authors of this study endeavored to identify if 3D fluoroscopic navigation methods resulted in a higher placement accuracy of pedicle screws. Methods A systematic analysis was conducted to examine pedicle screw insertion accuracy based on the use of 2D, 3D, and conventional fluoroscopic image guidance systems. A PubMed and MEDLINE database search was conducted to review the published literature that focused on the accuracy of pedicle screw placement using intraoperative, real-time fluoroscopic image guidance in spine fusion surgeries. The pedicle screw accuracy rates were segregated according to spinal level because each spinal region has individual anatomical and morphological variations. Descriptive statistics were used to compare the pedicle screw insertion accuracy rate differences among the navigation methods. Results A total of 30 studies were included in the analysis. The data were abstracted and analyzed for the following groups: 12 data sets that used conventional fluoroscopy, 8 data sets that used 2D fluoroscopic navigation, and 20 data sets that used 3D fluoroscopic navigation. These studies included 1973 patients in whom 9310 pedicle screws were inserted. With conventional fluoroscopy, 2532 of 3719 screws were inserted accurately (68.1% accuracy); with 2D fluoroscopic navigation, 1031 of 1223 screws were inserted accurately (84.3% accuracy); and with 3D fluoroscopic navigation, 4170 of 4368 screws were inserted accurately (95.5% accuracy). The accuracy rates when 3D was compared with 2D fluoroscopic navigation were also consistently higher throughout all individual spinal levels. Conclusions Three-dimensional fluoroscopic image guidance systems demonstrated a significantly higher pedicle screw placement accuracy than conventional fluoroscopy or 2D fluoroscopic image guidance methods.

Sign in / Sign up

Export Citation Format

Share Document