• paediatric spine
• scoliosis
• artificial intelligence
• machine learning
• paediatric spine deformity
• prognosis
• scoliotic curves
• cobb angles
• spinal deformities
• radiographs
• deformities
• spine
• pedicle screw
• clinicians

• Artificial intelligence
• Complications
• Machine-based learning
• Neurosurgery

• Humans
• Artificial Intelligence
• Internship and Residency/methods
• Neurosurgery/education
• Neurosurgical Procedures/education
• Neurosurgical Procedures/methods
• Clinical Competence

• Artificial intelligence
• Imaging
• Oncology
• Robotics
• Spine surgery
• Surgical navigation

• AI
• artificial intelligence
• data mining
• databases
• deep learning
• machine learning
• open source
• spine surgery

• K23 AR082986 NIAMS NIH HHS

• Humans
• Spinal Fusion/methods
• Lumbar Vertebrae/surgery
• Lumbar Vertebrae/diagnostic imaging
• Female
• Male
• Middle Aged
• Minimally Invasive Surgical Procedures/methods
• Aged
• Magnetic Resonance Imaging
• Spinal Nerve Roots/diagnostic imaging
• Retrospective Studies
• Imaging, Three-Dimensional

• Artificial intelligence
• Clinical decision-making
• Deep learning
• Machine learning
• Patient care
• Spine

• 17111 96789 Korea Medical Device Development Fund
• RS-2023-00252804 Korea Medical Device Development Fund
• Ministry of Science and ICT
• Ministry of Trade, Industry and Energy
• Ministry of Health and Welfare
• Ministry of Food and Drug Safety

• Deep learning
• Localization
• Pedicle screw
• Spine
• Surgical instruments

• 3D printing
• Artificial intelligence
• Augmented reality
• Machine learning
• Navigation technology
• Spine surgery
• Virtual reality

• Humans
• Surgery, Computer-Assisted/methods
• Imaging, Three-Dimensional/methods
• Artificial Intelligence
• Tomography, X-Ray Computed/methods
• Spine/surgery
• Pedicle Screws

• Humans
• Artificial Intelligence
• Machine Learning
• Spine/surgery
• Surgeons

• Artificial intelligence
• Cranial
• Functional
• Machine Learning
• Neural network
• Neuroimaging
• Spine

• Humans
• Neurosurgery
• Neurosurgical Procedures
• Algorithms
• Bibliometrics
• Machine Learning

• accuracy
• automated screw placement
• navigation
• pedicle screws
• spine surgery

• 13GW0249 German government, Federal Ministry of Education and Research

• CBCT
• Hybrid operating rooms
• Neurointerventional procedures
• Neurosurgery
• Spine
• Surgery

• Humans
• Neurosurgery
• Operating Rooms/methods
• Neurosurgical Procedures/methods
• Endovascular Procedures
• Radiation Exposure

• Karolinska Institute

• Artificial intelligence
• Big data
• Machine learning
• Robotics

• Artificial intelligence
• Artificial neurons
• Imaging
• Machine learning
• Spine surgery

• artificial intelligence
• current applications
• deep learning
• machine learning
• spine

We assessed the accuracy of a new 3D2D registration algorithm to be used for navigated spine surgery and explored anatomical and radiologic parameters affecting the registration accuracy. Compared to existing 3D2D registration algorithms, the algorithm does not need bone-mounted or table-mounted instruments for registration. Neither does the intraoperative imaging device have to be tracked or calibrated.

The rigid registration algorithm required imaging data (a pre-existing CT scan (3D) and two angulated fluoroscopic images (2D)) to register positions of vertebrae in 3D and is based on non-invasive skin markers. The algorithm registered five adjacent vertebrae and was tested in the thoracic and lumbar spine from three human cadaveric specimens. The registration accuracy was calculated for each registered vertebra and measured with the target registration error (TRE) in millimeters. We used multivariable analysis to identify parameters independently affecting the algorithm’s accuracy such as the angulation between the two fluoroscopic images (between 40° and 90°), the detector-skin distance, the number of skin markers applied, and waist circumference.

The algorithm registered 780 vertebrae with a median TRE of 0.51 mm [interquartile range 0.32–0.73 mm] and a maximum TRE of 2.06 mm. The TRE was most affected by the angulation between the two fluoroscopic images obtained (p < 0.001): larger angulations resulted in higher accuracy. The algorithm was more accurate in thoracic vertebrae (p = 0.004) and in the specimen with the smallest waist circumference (p = 0.003). The algorithm registered all five adjacent vertebrae with similar accuracy.

We studied the accuracy of a new 3D2D registration algorithm based on non-invasive skin markers. The algorithm registered five adjacent vertebrae with similar accuracy in the thoracic and lumbar spine and showed a maximum target registration error of approximately 2 mm. To further evaluate its potential for navigated spine surgery, the algorithm may now be integrated into a complete navigation system.

The online version contains supplementary material available at 10.1007/s11548-022-02733-w.

• Artificial intelligence
• Clinical utility
• Machine learning
• Neural network
• Research
• Spine

Recent industrial robotics covers a broad part of the manufacturing spectrum and other human everyday life applications; the performance of these devices has become increasingly important. Positioning accuracy and repeatability, as well as operating speed, are essential in any industrial robotics application. Robot positioning errors are complex due to the extensive combination of their sources and cannot be compensated for using conventional methods. Some robot positioning errors can be compensated for only using machine learning (ML) procedures. Reinforced machine learning increases the robot’s positioning accuracy and expands its implementation capabilities. The provided methodology presents an easy and focused approach for industrial in situ robot position adjustment in real-time during production setup or readjustment cases. The scientific value of this approach is a methodology using an ML procedure without huge external datasets for the procedure and extensive computing facilities. This paper presents a deep q-learning algorithm applied to improve the positioning accuracy of an articulated KUKA youBot robot during operation. A significant improvement of the positioning accuracy was achieved approximately after 260 iterations in the online mode and initial simulation of the ML procedure.

• Algorithms
• Humans
• Machine Learning
• Robotics/methods

• Diagnostic Imaging
• Humans
• Machine Learning
• Spinal Diseases/diagnostic imaging
• Spinal Diseases/surgery
• Spine/diagnostic imaging
• Spine/surgery
• Surgeons

• ASD
• Adult spinal deformity
• Artificial intelligence
• Machine learning

Several techniques for pedicle screw placement have been described including freehand techniques, fluoroscopy assisted, computed tomography (CT) guidance, and robotics. Image-guided surgery offers the potential to combine the benefits of CT guidance without the added radiation. This study investigated the ability of a neural network to place lumbar pedicle screws with the correct length, diameter, and angulation autonomously within radiographs without the need for human involvement.

The neural network was trained using a machine learning process. The method combines the previously reported autonomous spine segmentation solution with a landmark localization solution. The pedicle screw placement was evaluated using the Zdichavsky, Ravi, and Gertzbein grading systems.

In total, the program placed 208 pedicle screws between the L1 and S1 spinal levels. Of the 208 placed pedicle screws, 208 (100%) had a Zdichavsky Score 1A, 206 (99.0%) of all screws were Ravi Grade 1, and Gertzbein Grade A indicating no breech. The final two screws (1.0%) had a Ravi score of 2 (<2 mm breech) and a Gertzbein grade of B (<2 mm breech).

The results of this experiment can be combined with an image-guided platform to provide an efficient and highly effective method of placing pedicle screws during spinal stabilization surgery.

• Augmented reality
• computed tomography radiography
• fusion
• lumbar spine
• machine learning
• pedicle placement

In recent years, anterior cruciate ligament (ACL) reconstruction has generally yielded favorable outcomes. However, ACL reconstruction has not provided satisfactory results in terms of the rate of returning to sports and prevention of osteoarthritis (OA) progression. In this paper, we outline current techniques for ACL reconstruction such as graft materials, double-bundle or single-bundle reconstruction, femoral tunnel drilling, all-inside technique, graft fixation, preservation of remnant, anterolateral ligament reconstruction, ACL repair, revision surgery, treatment for ACL injury with OA and problems, and discuss expected future trends. To enable many more orthopedic surgeons to achieve excellent ACL reconstruction outcomes with less invasive surgery, further studies aimed at improving surgical techniques are warranted. Further development of biological augmentation and robotic surgery technologies for ACL reconstruction is also required.

• Anterior cruciate ligament reconstruction
• Surgical techniques
• Revision surgery
• Biological augmentation
• Computer-aided surgery

• algorithm
• artificial intelligence
• artificial neural network
• big data
• deep learning
• machine learning
• robotics

• augmented reality
• brain biopsy
• external ventricular drainage
• image-guided surgery
• neurosurgery
• surgical navigation

Background. Lateral approaches to the spine have gained increased popularity due to enabling minimally invasive access to the spine, less blood loss, decreased operative time, and less postoperative pain. The objective of the study was to analyze the use of intraoperative computed tomography with navigation and the implementation of augmented reality in facilitating a lateral approach to the spine. Methods. We prospectively analyzed all patients who underwent surgery with a lateral approach to the spine from September 2016 to January 2021 using intraoperative CT applying a 32-slice movable CT scanner, which was used for automatic navigation registration. Sixteen patients, with a median age of 64.3 years, were operated on using a lateral approach to the thoracic and lumbar spine and using intraoperative CT with navigation. Indications included a herniated disc (six patients), tumors (seven), instability following the fracture of the thoracic or lumbar vertebra (two), and spondylodiscitis (one). Results. Automatic registration, applying intraoperative CT, resulted in high accuracy (target registration error: 0.84 ± 0.10 mm). The effective radiation dose of the registration CT scans was 6.16 ± 3.91 mSv. In seven patients, a control iCT scan was performed for resection and implant control, with an ED of 4.51 ± 2.48 mSv. Augmented reality (AR) was used to support surgery in 11 cases, by visualizing the tumor outline, pedicle screws, herniated discs, and surrounding structures. Of the 16 patients, corpectomy was performed in six patients with the implantation of an expandable cage, and one patient underwent discectomy using the XLIF technique. One patient experienced perioperative complications. One patient died in the early postoperative course due to severe cardiorespiratory failure. Ten patients had improved and five had unchanged neurological status at the 3-month follow up. Conclusions. Intraoperative computed tomography with navigation facilitates the application of lateral approaches to the spine for a variety of indications, including fusion procedures, tumor resection, and herniated disc surgery.

• augmented reality
• computer-assisted surgery
• effective radiation dose
• image-guided surgery
• intraoperative imaging
• lateral approach to the spine
• spine navigation

• Accuracy
• Augmented reality
• Pedicle screw
• Surgical navigation
• Systematic review
• Virtual path tracking

• Feature localization
• Patient tracking
• Skin tracking
• Spinal surgery
• Surgical guidance

• Humans
• Skin/diagnostic imaging
• Imaging, Three-Dimensional
• Spine/surgery
• Spine/diagnostic imaging
• Surgery, Computer-Assisted/methods
• Algorithms
• Minimally Invasive Surgical Procedures

• 692470 Electronic Components and Systems for European Leadership

• artificial intelligence
• natural language processing
• neurosurgery
• topic modeling in neurosurgery

• Artificial Intelligence
• Neurosurgery
• Neurosurgical Procedures
• PubMed
• Technology

To test the hypothesis that intraoperative cone beam computed tomography (CBCT) using the Allura augmented reality surgical navigation (ARSN) system in a dedicated hybrid operating room (OR) matches computed tomography (CT) for identification of pedicle screw breach during spine surgery.

Twenty patients treated with spinal fixation surgery (260 screws) underwent intraoperative CBCT as well as conventional postoperative CT scans (median 12 months after surgery) to identify and grade the degree of pedicle screw breach on both scan types, according to the Gertzbein grading scale. Blinded assessments were performed by three independent spine surgeons and the CT served as the standard of reference. Screws graded as Gertzbein 0 or 1 were considered clinically accurate while grades 2 or 3 were considered inaccurate. Sensitivity, specificity, and negative predictive value were the primary metrics of diagnostic performance.

For this patient group, the negative predictive value of an intraoperative CBCT to rule out pedicle screw breach was 99.6% (CI 97.75–99.99%). Among 10 screws graded as inaccurate on CT, 9 were graded as such on the CBCT, giving a sensitivity of 90.0% (CI 55.5–99.75%). Among the 250 screws graded as accurate on CT, 244 were graded as such on the CBCT, giving a specificity of 97.6% (CI 94.85–99.11%).

CBCT, performed intraoperatively with the Allura ARSN system, is comparable and non-inferior to a conventional postoperative CT scan for ruling out misplaced pedicle screws in spinal deformity cases, eliminating the need for a postoperative CT.

• Intraoperative cone beam computed tomography (CT) using the Allura ARSN is comparable with conventional CT for ruling out pedicle screw breaches after spinal fixation surgery.

• Intraoperative cone beam computed tomography can be used to assess need for revisions of pedicle screws making routine postoperative CT scans unnecessary.

• Using cone beam computed tomography, the specificity was 97.6% and the sensitivity was 90% for detecting pedicle screw breaches and the negative predictive value for ruling out a pedicle screw breach was 99.6%.

• Cone beam computed tomography
• Image-guided surgery
• Pedicle screws
• Sensitivity and specificity

• Artificial intelligence
• navigation
• spine surgery

• image analysis for markerless tracking
• image processing
• image-guided surgery
• optical sensing
• patient tracking
• spinal surgery

• Algorithms
• Augmented Reality
• Humans
• Imaging, Three-Dimensional
• Optical Imaging
• Phantoms, Imaging
• Spine/diagnostic imaging
• Spine/surgery
• Surgery, Computer-Assisted
• Surgical Navigation Systems

• 692470 Electronic Components and Systems for European Leadership

• hybrid OR
• image guidance
• medical robotics
• pedicle fixation
• robot-assisted surgery
• spine fusion
• surgical navigation

• neuropathic pain
• spinal cord diseases
• three-dimensional imaging
• outcomes research

• Aged
• Aged, 80 and over
• Augmented Reality
• Cadaver
• Cone-Beam Computed Tomography
• Feasibility Studies
• Female
• Humans
• Male
• Middle Aged
• Operating Rooms
• Pedicle Screws
• Reproducibility of Results
• Robotic Surgical Procedures/instrumentation
• Robotic Surgical Procedures/methods
• Spine/diagnostic imaging
• Spine/surgery

This study aimed to compare screw placement accuracy and clinical aspects between Augmented Reality Surgical Navigation (ARSN) and free-hand (FH) technique. Twenty patients underwent spine surgery with screw placement using ARSN and were matched retrospectively to a cohort of 20 FH technique cases for comparison. All ARSN and FH cases were performed by the same surgeon. Matching was based on clinical diagnosis and similar proportions of screws placed in the thoracic and lumbosacral vertebrae in both groups. Accuracy of screw placement was assessed on postoperative scans according to the Gertzbein scale and grades 0 and 1 were considered accurate. Procedure time, blood loss and length of hospital stay, were collected as secondary endpoints. A total of 262 and 288 screws were assessed in the ARSN and FH groups, respectively. The share of clinically accurate screws was significantly higher in the ARSN vs FH group (93.9% vs 89.6%, p < 0.05). The proportion of screws placed without a cortical breach was twice as high in the ARSN group compared to the FH group (63.4% vs 30.6%, p < 0.0001). No statistical difference was observed for the secondary endpoints between both groups. This matched-control study demonstrated that ARSN provided higher screw placement accuracy compared to free-hand.

Surgical navigation is a well-established tool in endoscopic skull base surgery. However, navigational and endoscopic views are usually displayed on separate monitors, forcing the surgeon to focus on one or the other. Aiming to provide real-time integration of endoscopic and diagnostic imaging information, we present a new navigation technique based on augmented reality with fusion of intraoperative cone beam computed tomography (CBCT) on the endoscopic view. The aim of this study was to evaluate the accuracy of the method.

An augmented reality surgical navigation system (ARSN) with 3D CBCT capability was used. The navigation system incorporates an optical tracking system (OTS) with four video cameras embedded in the flat detector of the motorized C-arm. Intra-operative CBCT images were fused with the view of the surgical field obtained by the endoscope’s camera. Accuracy of CBCT image co-registration was tested using a custom-made grid with incorporated 3D spheres.

Co-registration of the CBCT image on the endoscopic view was performed. Accuracy of the overlay, measured as mean target registration error (TRE), was 0.55 mm with a standard deviation of 0.24 mm and with a median value of 0.51mm and interquartile range of 0.39˗˗0.68 mm.

We present a novel augmented reality surgical navigation system, with fusion of intraoperative CBCT on the endoscopic view. The system shows sub-millimeter accuracy.

• Artificial intelligence
• Deep learning
• Electronic medical records
• Machine learning
• Spine surgery

• artificial intelligence
• computed tomography
• guided navigation
• imaging
• machine learning
• magnetic resonance
• radiograph
• spine surgery

• Machine learning
• Magnetic resonance imaging
• Prostate
• Prostatic neoplasms
• Radiomics

• Humans
• Machine Learning
• Magnetic Resonance Imaging
• Male
• Prostatic Neoplasms/diagnostic imaging