Technological Advances in Spine Surgery: Navigation, Robotics, and Augmented Reality

Artificial Intelligence in Spine Surgery: Imaging-Based Applications for Diagnosis and Surgical Techniques

PURPOSE OF REVIEW

Artificial intelligence (AI) has rapidly proliferated though medicine with many novel applications to improve patient care and optimize healthcare delivery. This review investigates recent literature surrounding the influence of AI imaging technologies on spine surgical practice and diagnosis.

RECENT FINDINGS

Robotic-assisted pedicle screw placement has been shown to increase the rate of clinically acceptable screw placement while increasing operative time. AI technologies have also shown promise in creating 3D spine imaging while reducing patient radiation exposure. Several models using various imaging modalities have been shown to reliably identify vertebral osteoporotic fractures, stenosis and spine cancers. Complex spinal anatomy and pathology as well as integration of robotics make spine surgery a promising field for the deployment of AI-based imaging technologies. Imaging-based AI projects show potential to enhance diagnostic and surgical efficiency, facilitate trainee learning and improve operative outcomes.

Navigation Experience in Latin-American Spine Surgeons: A Survey

STUDY DESIGN

This is a cross-sectional survey.

OBJECTIVES

 This study aimed to evaluate the availability and knowledge of navigation technologies for educational purposes and patient management in spine surgeons in Latin America.

METHODS

A cross-sectional study was conducted among Latin American Spine Association members using a comprehensive 16-question survey to evaluate their knowledge and practices regarding navigation in spinal surgery. The questionnaire was reviewed and authorized by the AO Spine Latin America (LATAM) Degenerative & Deformity study group and distributed starting on January 29 and closed on February 28, 2024.

RESULTS

A total of 123 surveys were recorded; 95% were male gender, and 42% were neurosurgeons/orthopedists with specific training in spine surgery. Mexico led the response rate with 55 (45%) and then Brazil and Argentina with 13% and 9%, respectively; 54% are not involved in a spine surgery training program; 80 surgeons belong to AO Spine membership; and 35 of them have over 20 years of experience, with most respondents performing between 0 and 100 surgeries per year and degenerative pathology being the most common. Almost 90% of the respondents either use or are willing to use navigation technology, 100% express interest in attending a course on the subject, 80% cited improved accuracy in screw placement as a perceived advantage, and the disadvantage of high costs was the most frequently selected (85%).

CONCLUSIONS

Despite the benefits demonstrated by navigation technology, many spine surgeons in Latin America still lack access to this valuable resource. Even with their keen interest and clear understanding of its advantages and benefits, it is necessary to develop training programs and affordable navigation systems to improve spine surgery worldwide and ensure accessible care for all.

Challenges in Contemporary Spine Surgery: A Comprehensive Review of Surgical, Technological, and Patient-Specific Issues

Spine surgery has significantly progressed due to innovations in surgical techniques, technology, and a deeper understanding of spinal pathology. However, numerous challenges persist, complicating successful outcomes. Anatomical intricacies at transitional junctions demand precise surgical expertise to avoid complications. Technical challenges, such as underestimation of the density of fixed vertebrae, individual vertebral characteristics, and the angle of pedicle inclination, pose additional risks during surgery. Patient anatomical variability and prior surgeries add layers of difficulty, often necessitating thorough pre- and intraoperative planning. Technological challenges involve the integration of artificial intelligence (AI) and advanced visualization systems. AI offers predictive capabilities but is limited by the need for large, high-quality datasets and the "black box" nature of machine learning models, which complicates clinical decision making. Visualization technologies like augmented reality and robotic surgery enhance precision but come with operational and cost-related hurdles. Patient-specific challenges include managing postoperative complications such as adjacent segment disease, hardware failure, and neurological deficits. Effective patient outcome measurement is critical, yet existing metrics often fail to capture the full scope of patient experiences. Proper patient selection for procedures is essential to minimize risks and improve outcomes, but criteria can be inconsistent and complex. There is the need for continued technological innovation, improved patient-specific outcome measures, and enhanced surgical education through simulation-based training. Integrating AI in preoperative planning and developing comprehensive databases for spinal pathologies can aid in creating more accurate, generalizable models. A holistic approach that combines technological advancements with personalized patient care and ongoing education is essential for addressing these challenges and improving spine surgery outcomes.

Augmenting Reality in Spinal Surgery: A Narrative Review of Augmented Reality Applications in Pedicle Screw Instrumentation

Background and Objectives: The advent of augmented reality (AR) in spinal surgery represents a key technological evolution, enhancing precision and safety in procedures such as pedicle screw instrumentation. This review assesses the current applications, benefits, and challenges of AR technology in spinal surgery, focusing on its effects on surgical accuracy and patient outcomes. Materials and Methods: A comprehensive review of the literature published between January 2023 and December 2024 was conducted, focusing on AR and navigational technologies in spinal surgery. Key outcomes such as accuracy, efficiency, and complications were emphasized. Results: Thirteen studies were included, highlighting substantial improvements in surgical accuracy, efficiency, and safety with AR and navigational systems. AR technology was found to significantly reduce the learning curve for spinal surgeons, improve procedural efficiency, and potentially reduce surgical complications. The challenges identified include high system costs, the complexity of training requirements, the integration with existing workflows, and limited clinical evidence. Conclusions: AR technology holds promise for advancements in spinal surgery, particularly in improving the accuracy and safety of pedicle screw instrumentation. Despite existing challenges such as cost, training needs, and regulatory hurdles, AR has the potential to transform spinal surgical practices. Ongoing research, technological refinements, and the development of implementation strategies are essential to fully leverage AR's capabilities in enhancing patient care.

Deep Learning-Based Localization and Orientation Estimation of Pedicle Screws in Spinal Fusion Surgery

Objective

This study investigated the application of a deep learning-based object detection model for accurate localization and orientation estimation of spinal fixation surgical instruments during surgery.

Methods

We employed the You Only Look Once (YOLO) object detection framework with oriented bounding boxes (OBBs) to address the challenge of non-axis-aligned instruments in surgical scenes. The initial dataset of 100 images was created using brochure and website images from 11 manufacturers of commercially available pedicle screws used in spinal fusion surgeries, and data augmentation was used to expand 300 images. The model was trained, validated, and tested using 70%, 20%, and 10% of the images of lumbar pedicle screws, with the training process running for 100 epochs.

Results

The model testing results showed that it could detect the locations of the pedicle screws in the surgical scene as well as their direction angles through the OBBs. The F1 score of the model was 0.86 (precision: 1.00, recall: 0.80) at each confidence level and mAP50. The high precision suggests that the model effectively identifies true positive instrument detections, although the recall indicates a slight limitation in capturing all instruments present. This approach offers advantages over traditional object detection in bounding boxes for tasks where object orientation is crucial, and our findings suggest the potential of YOLOv8 OBB models in real-world surgical applications such as instrument tracking and surgical navigation.

Conclusion

Future work will explore incorporating additional data and the potential of hyperparameter optimization to improve overall model performance.

A Novel Intraoperative CT Navigation System for Spinal Fusion Surgery in Lumbar Degenerative Disease: Accuracy and Safety of Pedicle Screw Placement

Background: In recent years, intraoperative computed tomography (CT) navigation has become widely used for the insertion of pedicle screws in spinal fusion surgery. However, conventional intraoperative CT navigation may be impaired by infrared interference between the infrared camera and surgical instruments, which can lead to the misplacement of pedicle screws. Recently, a novel intraoperative CT navigation system, NextAR, has been developed. It uses a small infrared camera mounted on surgical instruments within the surgical field. NextAR navigation can minimize the problem of infrared interference and be expected to improve the accuracy of pedicle screw placement. Methods: This study investigated the accuracy of pedicle screw insertion under NextAR navigation in spinal fusion surgery for lumbar degenerative diseases. The accuracy of pedicle screw placement was evaluated in 15 consecutive patients using a CT grading scale. Results: Screw perforation occurred in only 1 of the total 70 screws (1.4%). Specifically, there was one grade 1 perforation within 2 mm, but no perforations larger than 2 mm. There were no reoperations or neurological complications due to screw misplacement. Conclusions: NextAR navigation can provide high accuracy for pedicle screw insertion and help ensure safe spinal fusion surgery for lumbar degenerative diseases.

Effectiveness and safety of robot-assisted versus fluoroscopy-assisted pedicle screw implantation in scoliosis surgery: a systematic review and meta-analysis

This study aimed to assess the effectiveness and safety of robot-assisted versus fluoroscopy-assisted pedicle screw implantation in scoliosis surgery. The study was registered in the PROSPERO (CRD42023471837). Two independent researchers searched PubMed, Web of Science, Cochrane Library, and China National Knowledge Infrastructure. The outcomes included operation time, pedicle screw implantation time, blood loss, number of fluoroscopic, accuracy of pedicle screw position, hospital stays, postoperative hospital stays, Visual Analog Scale (VAS), Japanese Orthopaedic Association (JOA) score, Scoliosis Research Society-22(SRS-22), cobb angle, cobb angle correction rate, sagittal vertical axis (SVA), and complications. Eight papers involving 473 patients met all the criteria. There was no significant difference between the two groups regarding the reduction in operation time. The effect of reducing the pedicle screw implantation time in the RA group was significant (WMD = -1.28; 95% CI: -1.76 to -0.80; P < 0.00001). The effect of reducing the blood loss in the RA group was significant (WMD=-105.57; 95% CI: -206.84 to -4.31; P = 0.04). The effect of reducing the number of fluoroscopic in the RA group was significant (WMD=-5.93; 95% CI: -8.24 to -3.62; P < ). The pedicle screw position of Grade A was significantly more in the RA group according to both the Gertzbein-Robbins scale and the Rampersaud scale. Compared with the FA group, the difference in the hospital stays in the RA group was not statistically significant, but the effect of reducing the postoperative hospital stays in the RA group was significant (WMD = -2.88; 95% CI: -4.13 to -1.63; P < 0.00001). The difference in the VAS, JOA, SRS-22, Cobb angle and Cobb angle correction rate, SVA, and complications between the two groups was not statistically significant. The robot-assisted technique achieved statistically significant results in terms of pedicle screw placement time, blood loss, number of fluoroscopies, accuracy of pedicle screw position, and postoperative hospital stay.

Pelvic Fixation Technique Using the Ilio-Sacral Screw for 173 Neuromuscular Scoliosis Patients

Pelvic fixation remains one of the main challenging issues in non-ambulatory neuromuscular scoliosis (NMS) patients, between clinical effectiveness and a high complication rate. The objective of this multicenter and retrospective study was to evaluate the outcomes of a technique that was applied to treat 173 NMS patients. The technique is not well-known but promising; it uses the ilio-sacral screw, combined with either the posterior spinal fusion or fusionless bipolar technique, with a minimum follow-up of two years. The mean operative age of the patients was 13 ± 7 years. The mean preoperative main coronal curve was 64° and improved by a mean of -39° postoperatively. The mean preoperative pelvic obliquity was 23°, which improved by a mean of -14° postoperatively. No decrease in the frontal or sagittal correction was observed during the last follow-up. The sitting posture improved in all cases. Twenty-nine patients (17%) had a postoperative infection: twenty-six were treated with local debridement and antibiotics, and three required hardware removal. Fourteen mechanical complications (8%) occurred: screw malposition (n = 6), skin prominence (n = 1), and connector failure (n = 1). This type of surgery is associated with a high risk for infection. Comorbidities, rather than the surgery itself, were the main risk factors that led to complications. The ilio-sacral screw was reliable and effective in correcting pelvic obliquity in NMS patients. The introduction of intraoperative navigation should minimize the risk of screw misplacement and facilitate revision or primary fixation.

Bibliometric Analysis of the Development, Current Status, and Trends in Adult Degenerative Scoliosis Research: A Systematic Review from 1998 to 2023

Purpose

Adult degenerative scoliosis (ADS) research lacks bibliometric analysis, despite numerous studies. This study aimed to systematically analyze the development, current status, hot topics, frontier areas, and trends in ADS research.

Patients and Methods

A systematic literature review was conducted in the Web of Science Core Collection database from January 1998 to June 2023. Information regarding the country, institution, author, journal, and keywords was collected for each article. Bibliometric analysis was performed using VOSviewer and Citespace software.

Results

The final analysis covered 1695 publications, demonstrating a steady increase in ADS research. The United States was the most prolific and influential country with 684 publications, followed by China and Japan. The University of California System was the most productive institution with 113 publications. Shaffrey, CI (47 publications) and Lenke, LG (41 publications) were top authors. The analysis revealed seven main research clusters: "intervertebral disc", "adult spinal deformity", "lumbar fusion", "minimally invasive surgery", "navigation", "postoperative complications", and "mental retardation". Keywords with strong bursts of activity included degeneration, prevalence, imbalance, classification, lumbar spinal stenosis, and kyphosis.

Conclusion

In conclusion, in recent years, ADS research has undergone rapid development. This study analyzed its hot topics, advancements, and research directions, making it the latest bibliometric analysis in this field. The findings aim to provide a new perspective and guidance for clinical practitioners and researchers.