1
|
Khan M, Ahuja K, Tsirikos AI. AI and machine learning in paediatric spine deformity surgery. Bone Jt Open 2025; 6:569-581. [PMID: 40407025 PMCID: PMC12100669 DOI: 10.1302/2633-1462.65.bjo-2024-0089.r1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 05/26/2025] Open
Abstract
Paediatric spine deformity surgery is a high-stakes procedure. It demands the surgeon to have exceptional anatomical knowledge and precise visuospatial awareness. There is increasing demand for precision medicine, which rapid advancements in computational technologies have made possible with the recent explosion of AI and machine learning (ML). We present the surgical and ethical applications of AI and ML in diagnosis, prognosis, image processing, and outcomes in the field of paediatric spine deformity.
Collapse
Affiliation(s)
- Mohsin Khan
- Scottish National Spine Deformity Centre, Royal Hospital for Children and Young People, Edinburgh, UK
| | - Kaustubh Ahuja
- Scottish National Spine Deformity Centre, Royal Hospital for Children and Young People, Edinburgh, UK
| | - Athanasios I Tsirikos
- Scottish National Spine Deformity Centre, Royal Hospital for Children and Young People, Edinburgh, UK
| |
Collapse
|
2
|
Windermere SA, Shah S, Hey G, McGrath K, Rahman M. Applications of Artificial Intelligence in Neurosurgery for Improving Outcomes Through Diagnostics, Predictive Tools, and Resident Education. World Neurosurg 2025; 197:123809. [PMID: 40015674 DOI: 10.1016/j.wneu.2025.123809] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2025] [Accepted: 02/11/2025] [Indexed: 03/01/2025]
Abstract
BACKGROUND Artificial intelligence (AI) has become an increasingly prominent tool in the field of neurosurgery, revolutionizing various aspects of patient care and surgical practices. AI-powered systems can provide real-time feedback to surgeons, enhancing precision and reducing the risk of complications during surgical procedures. The objective of this study is to review the role of AI in training neurosurgical residents, improving accuracy during surgery, and reducing complications. METHODS The literature search method involved searching PubMed using relevant keywords to identify English literature publications, including full texts, and concerning human subject matter from its inception until May 2024, initially generating 247,747 results. Articles were then screened for topic relevancy by abstract contents. Further articles were retrieved from the sources cited by the initially reviewed articles. A comprehensive review was then performed on various studies, including observational studies, case-control studies, cohort studies, clinical trials, meta-analyses, and reviews by 4 reviewers individually and then collectively. RESULTS Studies on AI in neurosurgery reach more than 4000 produced over a decade alone. The majority of studies regarding clinical diagnosis, risk prediction, and intraoperative guidance remain retrospective in nature. In its current form, AI-based paradigm performed inferiorly to neurosurgery residents in test taking. CONCLUSIONS AI has potential for broad applications in neurosurgery from use as a diagnostic, predictive, intraoperative, or educational tool. Further research is warranted for prospective use of AI-based technology for delivery of neurosurgical care.
Collapse
Affiliation(s)
| | - Siddharth Shah
- Department of Neurosurgery, RCSM Government Medical College, Kolhapur, Maharashtra, India
| | - Grace Hey
- University of Florida College of Medicine, Gainesville, Florida, USA
| | - Kyle McGrath
- University of Florida College of Medicine, Gainesville, Florida, USA
| | - Maryam Rahman
- Lillian S. Wells Department of Neurosurgery, University of Florida, Gainesville, Florida, USA
| |
Collapse
|
3
|
MacLeod JS, Compton T, Bakaes Y, Chopra A, Akwuole F, Christenson C, Hsu W. Artificial Intelligence in Spine Surgery: Imaging-Based Applications for Diagnosis and Surgical Techniques. Curr Rev Musculoskelet Med 2025:10.1007/s12178-025-09972-9. [PMID: 40304942 DOI: 10.1007/s12178-025-09972-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 04/22/2025] [Indexed: 05/02/2025]
Abstract
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.
Collapse
Affiliation(s)
- James S MacLeod
- Department of Orthopaedic Surgery, Northwestern University, 259 E Erie St, Chicago, IL, 60611, USA.
- Center for Regenerative Nanomedicine, Northwestern University, Chicago, IL, USA.
| | - Tyler Compton
- Department of Orthopaedic Surgery, Northwestern University, 259 E Erie St, Chicago, IL, 60611, USA
| | - Yianni Bakaes
- Department of Orthopaedic Surgery, Northwestern University, 259 E Erie St, Chicago, IL, 60611, USA
- Center for Regenerative Nanomedicine, Northwestern University, Chicago, IL, USA
| | - Avani Chopra
- Department of Orthopaedic Surgery, Northwestern University, 259 E Erie St, Chicago, IL, 60611, USA
- Center for Regenerative Nanomedicine, Northwestern University, Chicago, IL, USA
| | - Frances Akwuole
- Department of Orthopaedic Surgery, Northwestern University, 259 E Erie St, Chicago, IL, 60611, USA
- Center for Regenerative Nanomedicine, Northwestern University, Chicago, IL, USA
| | - Cole Christenson
- Department of Orthopaedic Surgery, Northwestern University, 259 E Erie St, Chicago, IL, 60611, USA
- Center for Regenerative Nanomedicine, Northwestern University, Chicago, IL, USA
| | - Wellington Hsu
- Department of Orthopaedic Surgery, Northwestern University, 259 E Erie St, Chicago, IL, 60611, USA
- Center for Regenerative Nanomedicine, Northwestern University, Chicago, IL, USA
| |
Collapse
|
4
|
Yahanda AT, Joseph K, Bui T, Greenberg JK, Ray WZ, Ogunlade JI, Hafez D, Pallotta NA, Neuman BJ, Molina CA. Current Applications and Future Implications of Artificial Intelligence in Spine Surgery and Research: A Narrative Review and Commentary. Global Spine J 2025; 15:1445-1454. [PMID: 39359113 PMCID: PMC11559723 DOI: 10.1177/21925682241290752] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/04/2024] Open
Abstract
STUDY DESIGN Narrative review. OBJECTIVES Artificial intelligence (AI) is being increasingly applied to the domain of spine surgery. We present a review of AI in spine surgery, including its use across all stages of the perioperative process and applications for research. We also provide commentary regarding future ethical considerations of AI use and how it may affect surgeon-industry relations. METHODS We conducted a comprehensive literature review of peer-reviewed articles that examined applications of AI during the pre-, intra-, or postoperative spine surgery process. We also discussed the relationship among AI, spine industry partners, and surgeons. RESULTS Preoperatively, AI has been mainly applied to image analysis, patient diagnosis and stratification, decision-making. Intraoperatively, AI has been used to aid image guidance and navigation. Postoperatively, AI has been used for outcomes prediction and analysis. AI can enable curation and analysis of huge datasets that can enhance research efforts. Large amounts of data are being accrued by industry sources for use by their AI platforms, though the inner workings of these datasets or algorithms are not well known. CONCLUSIONS AI has found numerous uses in the pre-, intra-, or postoperative spine surgery process, and the applications of AI continue to grow. The clinical applications and benefits of AI will continue to be more fully realized, but so will certain ethical considerations. Making industry-sponsored databases open source, or at least somehow available to the public, will help alleviate potential biases and obscurities between surgeons and industry and will benefit patient care.
Collapse
Affiliation(s)
- Alexander T. Yahanda
- Department of Neurological Surgery, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - Karan Joseph
- Department of Neurological Surgery, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - Tim Bui
- Department of Neurological Surgery, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - Jacob K. Greenberg
- Department of Neurological Surgery, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - Wilson Z. Ray
- Department of Neurological Surgery, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - John I. Ogunlade
- Department of Neurological Surgery, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - Daniel Hafez
- Department of Neurological Surgery, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - Nicholas A. Pallotta
- Department of Orthopedic Surgery, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - Brian J. Neuman
- Department of Orthopedic Surgery, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - Camilo A. Molina
- Department of Neurological Surgery, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| |
Collapse
|
5
|
Tabarestani TQ, Salven DS, Sykes DAW, Bardeesi AM, Bartlett AM, Wang TY, Paturu MR, Dibble CF, Shaffrey CI, Ray WZ, Chi JH, Wiggins WF, Abd-El-Barr MM. Using Novel Segmentation Technology to Define Safe Corridors for Minimally Invasive Posterior Lumbar Interbody Fusion. Oper Neurosurg (Hagerstown) 2024; 27:14-22. [PMID: 38149852 DOI: 10.1227/ons.0000000000001046] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2023] [Accepted: 11/15/2023] [Indexed: 12/28/2023] Open
Abstract
BACKGROUND AND OBJECTIVES There has been a rise in minimally invasive methods to access the intervertebral disk space posteriorly given their decreased tissue destruction, lower blood loss, and earlier return to work. Two such options include the percutaneous lumbar interbody fusion through the Kambin triangle and the endoscopic transfacet approach. However, without accurate preoperative visualization, these approaches carry risks of damaging surrounding structures, especially the nerve roots. Using novel segmentation technology, our goal was to analyze the anatomic borders and relative sizes of the safe triangle, trans-Kambin, and the transfacet corridors to assist surgeons in planning a safe approach and determining cannula diameters. METHODS The areas of the safe triangle, Kambin, and transfacet corridors were measured using commercially available software (BrainLab, Munich, Germany). For each approach, the exiting nerve root, traversing nerve roots, theca, disk, and vertebrae were manually segmented on 3-dimensional T2-SPACE magnetic resonance imaging using a region-growing algorithm. The triangles' borders were delineated ensuring no overlap between the area and the nerves. RESULTS A total of 11 patients (65.4 ± 12.5 years, 33.3% female) were retrospectively reviewed. The Kambin, safe, and transfacet corridors were measured bilaterally at the operative level. The mean area (124.1 ± 19.7 mm 2 vs 83.0 ± 11.7 mm 2 vs 49.5 ± 11.4 mm 2 ) and maximum permissible cannula diameter (9.9 ± 0.7 mm vs 6.8 ± 0.5 mm vs 6.05 ± 0.7 mm) for the transfacet triangles were significantly larger than Kambin and the traditional safe triangles, respectively ( P < .001). CONCLUSION We identified, in 3-dimensional, the borders for the transfacet corridor: the traversing nerve root extending inferiorly until the caudal pedicle, the theca medially, and the exiting nerve root superiorly. These results illustrate the utility of preoperatively segmenting anatomic landmarks, specifically the nerve roots, to help guide decision-making when selecting the optimal operative approach.
Collapse
Affiliation(s)
- Troy Q Tabarestani
- Department of Neurosurgery, Duke University School of Medicine, Durham , North Carolina , USA
| | - David S Salven
- Department of Neurosurgery, Duke University School of Medicine, Durham , North Carolina , USA
| | - David A W Sykes
- Department of Neurosurgery, Duke University School of Medicine, Durham , North Carolina , USA
| | - Anas M Bardeesi
- Department of Neurosurgery, Duke University Hospital, Durham , North Carolina , USA
| | - Alyssa M Bartlett
- Department of Neurosurgery, Duke University School of Medicine, Durham , North Carolina , USA
| | - Timothy Y Wang
- Department of Neurosurgery, Duke University Hospital, Durham , North Carolina , USA
| | - Mounica R Paturu
- Department of Neurosurgery, Duke University Hospital, Durham , North Carolina , USA
| | - Christopher F Dibble
- Department of Neurosurgery, Duke University Hospital, Durham , North Carolina , USA
| | | | - Wilson Z Ray
- Department of Neurosurgery, Washington University, St. Louis , Missouri , USA
| | - John H Chi
- Department of Neurosurgery, Brigham and Women's Hospital, Boston , Massachusetts , USA
| | - Walter F Wiggins
- Department of Radiology, Duke University Hospital, Durham , North Carolina , USA
| | | |
Collapse
|
6
|
Lee S, Jung JY, Mahatthanatrakul A, Kim JS. Artificial Intelligence in Spinal Imaging and Patient Care: A Review of Recent Advances. Neurospine 2024; 21:474-486. [PMID: 38955525 PMCID: PMC11224760 DOI: 10.14245/ns.2448388.194] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/16/2024] [Revised: 05/14/2024] [Accepted: 05/23/2024] [Indexed: 07/04/2024] Open
Abstract
Artificial intelligence (AI) is transforming spinal imaging and patient care through automated analysis and enhanced decision-making. This review presents a clinical task-based evaluation, highlighting the specific impact of AI techniques on different aspects of spinal imaging and patient care. We first discuss how AI can potentially improve image quality through techniques like denoising or artifact reduction. We then explore how AI enables efficient quantification of anatomical measurements, spinal curvature parameters, vertebral segmentation, and disc grading. This facilitates objective, accurate interpretation and diagnosis. AI models now reliably detect key spinal pathologies, achieving expert-level performance in tasks like identifying fractures, stenosis, infections, and tumors. Beyond diagnosis, AI also assists surgical planning via synthetic computed tomography generation, augmented reality systems, and robotic guidance. Furthermore, AI image analysis combined with clinical data enables personalized predictions to guide treatment decisions, such as forecasting spine surgery outcomes. However, challenges still need to be addressed in implementing AI clinically, including model interpretability, generalizability, and data limitations. Multicenter collaboration using large, diverse datasets is critical to advance the field further. While adoption barriers persist, AI presents a transformative opportunity to revolutionize spinal imaging workflows, empowering clinicians to translate data into actionable insights for improved patient care.
Collapse
Affiliation(s)
- Sungwon Lee
- Department of Radiology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea
- Visual Analysis and Learning for Improved Diagnostics (VALID) Lab, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Joon-Yong Jung
- Department of Radiology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea
- Visual Analysis and Learning for Improved Diagnostics (VALID) Lab, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Akaworn Mahatthanatrakul
- Department of Orthopaedics, Faculty of Medicine, Naresuan University Hospital, Phitsanulok, Thailand
| | - Jin-Sung Kim
- Spine Center, Department of Neurosurgery, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea
| |
Collapse
|
7
|
Kim KH, Koo HW, Lee BJ. Deep Learning-Based Localization and Orientation Estimation of Pedicle Screws in Spinal Fusion Surgery. Korean J Neurotrauma 2024; 20:90-100. [PMID: 39021752 PMCID: PMC11249586 DOI: 10.13004/kjnt.2024.20.e17] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/25/2024] [Revised: 06/03/2024] [Accepted: 06/04/2024] [Indexed: 07/20/2024] Open
Abstract
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.
Collapse
Affiliation(s)
- Kwang Hyeon Kim
- Clinical Research Support Center, Inje University Ilsan Paik Hospital, Goyang, Korea
| | - Hae-Won Koo
- Department of Neurosurgery, Inje University Ilsan Paik Hospital, Inje University College of Medicine, Goyang, Korea
| | - Byung-Jou Lee
- Department of Neurosurgery, Inje University Ilsan Paik Hospital, Inje University College of Medicine, Goyang, Korea
| |
Collapse
|
8
|
Bcharah G, Gupta N, Panico N, Winspear S, Bagley A, Turnow M, D'Amico R, Ukachukwu AEK. Innovations in Spine Surgery: A Narrative Review of Current Integrative Technologies. World Neurosurg 2024; 184:127-136. [PMID: 38159609 DOI: 10.1016/j.wneu.2023.12.124] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2023] [Accepted: 12/22/2023] [Indexed: 01/03/2024]
Abstract
Neurosurgical technologies have become increasingly more adaptive, featuring real-time and patient-specific guidance in preoperative, intraoperative, and postoperative settings. This review offers insight into how these integrative innovations compare with conventional approaches in spine surgery, focusing on machine learning (ML), artificial intelligence, augmented reality and virtual reality, and spinal navigation systems. Data on technology applications, diagnostic and procedural accuracy, intraoperative times, radiation exposures, postoperative outcomes, and costs were extracted and compared with conventional methods to assess their advantages and limitations. Preoperatively, augmented reality and virtual reality have applications in surgical training and planning that are more immersive, case specific, and risk-free and have been shown to enhance accuracy and reduce complications. ML algorithms have demonstrated high accuracy in predicting surgical candidacy (up to 92.1%) and tailoring personalized treatments based on patient-specific variables. Intraoperatively, advantages include more accurate pedicle screw insertion (96%-99% with ML), enhanced visualization, reduced radiation exposure (49 μSv with O-arm navigation vs. 556 μSv with fluoroscopy), increased efficiency, and potential for fewer intraoperative complications compared with conventional approaches. Postoperatively, certain ML and artificial intelligence models have outperformed conventional methods in predicting all postoperative complications of >6000 patients as well as predicting variables contributing to in-hospital and 90-day mortality. However, applying these technologies comes with limitations, such as longer operative times (up to 35.6% longer) with navigation, dependency on datasets, costs, accessibility, steep learning curve, and inherent software malfunctions. As these technologies advance, continuing to assess their efficacy and limitations will be crucial to their successful integration within spine surgery.
Collapse
Affiliation(s)
- George Bcharah
- Mayo Clinic Alix School of Medicine, Scottsdale, Arizona, USA
| | - Nithin Gupta
- Campbell University School of Osteopathic Medicine, Lillington, North Carolina, USA
| | - Nicholas Panico
- Lake Erie College of Osteopathic Medicine, Erie, Pennsylvania, USA
| | - Spencer Winspear
- Campbell University School of Osteopathic Medicine, Lillington, North Carolina, USA
| | - Austin Bagley
- Campbell University School of Osteopathic Medicine, Lillington, North Carolina, USA
| | - Morgan Turnow
- Kentucky College of Osteopathic Medicine, Pikeville, Kentucky, USA
| | - Randy D'Amico
- Department of Neurosurgery, Lenox Hill Hospital, New York, New York, USA
| | - Alvan-Emeka K Ukachukwu
- Department of Neurosurgery, Duke University, Durham, North Carolina, USA; Duke Global Neurosurgery and Neurology, Durham, North Carolina, USA.
| |
Collapse
|
9
|
Adida S, Legarreta AD, Hudson JS, McCarthy D, Andrews E, Shanahan R, Taori S, Lavadi RS, Buell TJ, Hamilton DK, Agarwal N, Gerszten PC. Machine Learning in Spine Surgery: A Narrative Review. Neurosurgery 2024; 94:53-64. [PMID: 37930259 DOI: 10.1227/neu.0000000000002660] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2023] [Accepted: 07/06/2023] [Indexed: 11/07/2023] Open
Abstract
Artificial intelligence and machine learning (ML) can offer revolutionary advances in their application to the field of spine surgery. Within the past 5 years, novel applications of ML have assisted in surgical decision-making, intraoperative imaging and navigation, and optimization of clinical outcomes. ML has the capacity to address many different clinical needs and improve diagnostic and surgical techniques. This review will discuss current applications of ML in the context of spine surgery by breaking down its implementation preoperatively, intraoperatively, and postoperatively. Ethical considerations to ML and challenges in ML implementation must be addressed to maximally benefit patients, spine surgeons, and the healthcare system. Areas for future research in augmented reality and mixed reality, along with limitations in generalizability and bias, will also be highlighted.
Collapse
Affiliation(s)
- Samuel Adida
- Department of Neurosurgery, University of Pittsburgh School of Medicine, Pittsburgh , Pennsylvania , USA
| | - Andrew D Legarreta
- Department of Neurosurgery, University of Pittsburgh School of Medicine, Pittsburgh , Pennsylvania , USA
| | - Joseph S Hudson
- Department of Neurosurgery, University of Pittsburgh School of Medicine, Pittsburgh , Pennsylvania , USA
| | - David McCarthy
- Department of Neurosurgery, University of Pittsburgh School of Medicine, Pittsburgh , Pennsylvania , USA
| | - Edward Andrews
- Department of Neurosurgery, University of Pittsburgh School of Medicine, Pittsburgh , Pennsylvania , USA
| | - Regan Shanahan
- Department of Neurosurgery, University of Pittsburgh School of Medicine, Pittsburgh , Pennsylvania , USA
| | - Suchet Taori
- Department of Neurosurgery, University of Pittsburgh School of Medicine, Pittsburgh , Pennsylvania , USA
| | - Raj Swaroop Lavadi
- Department of Neurosurgery, University of Pittsburgh School of Medicine, Pittsburgh , Pennsylvania , USA
| | - Thomas J Buell
- Department of Neurosurgery, University of Pittsburgh School of Medicine, Pittsburgh , Pennsylvania , USA
| | - D Kojo Hamilton
- Department of Neurosurgery, University of Pittsburgh School of Medicine, Pittsburgh , Pennsylvania , USA
| | - Nitin Agarwal
- Department of Neurosurgery, University of Pittsburgh School of Medicine, Pittsburgh , Pennsylvania , USA
- Department of Neurosurgery, University of Pittsburgh Medical Center, Pittsburgh , Pennsylvania , USA
| | - Peter C Gerszten
- Department of Neurosurgery, University of Pittsburgh School of Medicine, Pittsburgh , Pennsylvania , USA
| |
Collapse
|
10
|
Levy AS, Bhatia S, Merenzon MA, Andryski AL, Rivera CA, Daggubati LC, Di L, Shah AH, Komotar RJ, Ivan ME. Exploring the Landscape of Machine Learning Applications in Neurosurgery: A Bibliometric Analysis and Narrative Review of Trends and Future Directions. World Neurosurg 2024; 181:108-115. [PMID: 37839564 DOI: 10.1016/j.wneu.2023.10.042] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2023] [Revised: 10/08/2023] [Accepted: 10/08/2023] [Indexed: 10/17/2023]
Abstract
BACKGROUND The field of neurosurgery has consistently represented an area of innovation and integration of technology since its inception. As such, machine learning (ML) has found its way into applications within neurosurgery relatively rapidly. Through this bibliometric review and cluster analysis, we seek to identify trends and emerging applications of ML within neurosurgery. METHODS A bibliometric analysis was carried out in the Web of Science database on publications from January 2000 to March 2023. The full data set of the 200 most cited publications including title, author information, journal, citation count, keywords, and abstracts for each publication was evaluated in CiteSpace. CiteSpace was used to elucidate publication characteristics, trends, and topic clusters via collaborate network analysis using the Kamada-Kawai algorithm. RESULTS The 25 most cited titles were included in our analysis. Harvard University and its affiliates represented the top institution, contributing nearly 25% of publications in the literature. WORLD NEUROSURGERY was the journal with the highest net citation count of 747 (29%). Collaborative network analysis generated 12 unique clusters, the largest of which was machine learning, followed by feature importance and deep brain stimulation. CONCLUSION This review highlights the most impactful articles pertaining to ML in the field of neurosurgery. ML has been applied into several sub-specialties within neurosurgery to optimize patient care, with special attention to outcome predictors, patient selection, and surgical decision making.
Collapse
Affiliation(s)
- Adam S Levy
- Department of Neurological Surgery, University of Miami, Miller School of Medicine, Miami, Florida, USA.
| | - Shovan Bhatia
- Department of Neurological Surgery, University of Miami, Miller School of Medicine, Miami, Florida, USA
| | - Martin A Merenzon
- Department of Neurological Surgery, University of Miami, Miller School of Medicine, Miami, Florida, USA
| | - Allie L Andryski
- Department of Neurological Surgery, University of Miami, Miller School of Medicine, Miami, Florida, USA
| | - Cameron A Rivera
- Department of Neurological Surgery, University of Miami, Miller School of Medicine, Miami, Florida, USA
| | - Lekhaj C Daggubati
- Department of Neurological Surgery, University of Miami, Miller School of Medicine, Miami, Florida, USA
| | - Long Di
- Department of Neurological Surgery, University of Miami, Miller School of Medicine, Miami, Florida, USA
| | - Ashish H Shah
- Department of Neurological Surgery, University of Miami, Miller School of Medicine, Miami, Florida, USA
| | - Ricardo J Komotar
- Department of Neurological Surgery, University of Miami, Miller School of Medicine, Miami, Florida, USA; Sylvester Cancer Center, University of Miami Health System, Miami, Florida, USA
| | - Michael E Ivan
- Department of Neurological Surgery, University of Miami, Miller School of Medicine, Miami, Florida, USA; Sylvester Cancer Center, University of Miami Health System, Miami, Florida, USA
| |
Collapse
|
11
|
Bertram U, Köveshazi I, Michaelis M, Weidert S, Schmidt TP, Blume C, Zastrow FSV, Müller CA, Szabo S. Man versus machine: Automatic pedicle screw planning using registration-based techniques compared with manual screw planning for thoracolumbar fusion surgeries. Int J Med Robot 2023:e2570. [PMID: 37690099 DOI: 10.1002/rcs.2570] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2022] [Revised: 08/14/2023] [Accepted: 08/16/2023] [Indexed: 09/12/2023]
Abstract
OBJECTIVE This study evaluates the precision of a commercially available spine planning software in automatic spine labelling and screw-trajectory proposal. METHODS The software uses automatic segmentation and registration of the vertebra to generate screw proposals. 877 trajectories were compared. Four neurosurgeons assessed suggested trajectories, performed corrections, and manually planned pedicle screws. Additionally, automatic identification/labelling was evaluated. RESULTS Automatic labelling was correct in 89% of the cases. 92.9% of automatically planned trajectories were in accordance with G&R grade A + B. Automatic mode reduced the time spent planning screw trajectories by 7 s per screw to 20 s per vertebra. Manual mode yielded differences in screw-length between surgeons (largest distribution peak: 5 mm), automatic in contrast at 0 mm. The size of suggested pedicle screws was significantly smaller (largest peaks in difference between 0.5 and 3 mm) than the surgeon's choice. CONCLUSION Automatic identification of vertebrae works in most cases and suggested pedicle screw trajectories are acceptable. So far, it does not substitute for an experienced surgeon's assessment.
Collapse
Affiliation(s)
- Ulf Bertram
- Department of Neurosurgery, RWTH Aachen University, Aachen, Germany
| | - Istvan Köveshazi
- Department of Orthopedics and Trauma Surgery, Musculoskeletal University Center Munich (MUM), University Hospital, LMU Munich, Munich, Germany
- M3i Industry-in-Clinic-Platform GmbH, Munich, Germany
| | | | - Simon Weidert
- Department of Orthopedics and Trauma Surgery, Musculoskeletal University Center Munich (MUM), University Hospital, LMU Munich, Munich, Germany
- M3i Industry-in-Clinic-Platform GmbH, Munich, Germany
| | | | - Christian Blume
- Department of Neurosurgery, RWTH Aachen University, Aachen, Germany
| | - Felix Swamy V Zastrow
- M3i Industry-in-Clinic-Platform GmbH, Munich, Germany
- Department of Neurology, University Hospital, LMU Munich, Munich, Germany
| | | | - Szilard Szabo
- M3i Industry-in-Clinic-Platform GmbH, Munich, Germany
| |
Collapse
|
12
|
Gharios M, El-Hajj VG, Frisk H, Ohlsson M, Omar A, Edström E, Elmi-Terander A. The use of hybrid operating rooms in neurosurgery, advantages, disadvantages, and future perspectives: a systematic review. Acta Neurochir (Wien) 2023; 165:2343-2358. [PMID: 37584860 PMCID: PMC10477240 DOI: 10.1007/s00701-023-05756-7] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2023] [Accepted: 08/08/2023] [Indexed: 08/17/2023]
Abstract
BACKGROUND Hybrid operating rooms (hybrid-ORs) combine the functionalities of a conventional surgical theater with the advanced imaging technologies of a radiological suite. Hybrid-ORs are usually equipped with CBCT devices providing both 2D and 3D imaging capability that can be used for both interventional radiology and image guided surgical applications. Across all fields of surgery, the use of hybrid-ORs is gaining in traction, and neurosurgery is no exception. We hence aimed to comprehensively review the use of hybrid-ORs, the associated advantages, and disadvantages specific to the field of neurosurgery. MATERIALS AND METHODS Electronic databases were searched for all studies on hybrid-ORs from inception to May 2022. Findings of matching studies were pooled to strengthen the current body of evidence. RESULTS Seventy-four studies were included in this review. Hybrid-ORs were mainly used in endovascular surgery (n = 41) and spine surgery (n = 33). Navigation systems were the most common additional technology employed along with the CBCT systems in the hybrid-ORs. Reported advantages of hybrid-ORs included immediate assessment of outcomes, reduced surgical revision rate, and the ability to perform combined open and endovascular procedures, among others. Concerns about increased radiation exposure and procedural time were some of the limitations mentioned. CONCLUSION In the field of neurosurgery, the use of hybrid-ORs for different applications is increasing. Hybrid-ORs provide preprocedure, intraprocedure, and end-of-procedure imaging capabilities, thereby increasing surgical precision, and reducing the need for postoperative imaging and correction surgeries. Despite these advantages, radiation exposure to patient and staff is an important concern.
Collapse
Affiliation(s)
- Maria Gharios
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
| | - Victor Gabriel El-Hajj
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.
- Department of Neurosurgery, Karolinska University Hospital, Eugeniavägen 6, 4Th Floor, Solna, 17164, Stockholm, Sweden.
| | - Henrik Frisk
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
| | - Marcus Ohlsson
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
- Department of Neuroradiology, Karolinska University Hospital, Stockholm, Sweden
| | - Artur Omar
- Department of Medical Radiation Physics and Nuclear Medicine, Karolinska University Hospital, Stockholm, Sweden
| | - Erik Edström
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
| | - Adrian Elmi-Terander
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
- Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
| |
Collapse
|
13
|
Scherer M, Kausch L, Bajwa A, Neumann JO, Ishak B, Naser P, Vollmuth P, Kiening K, Maier-Hein K, Unterberg A. Automatic Planning Tools for Lumbar Pedicle Screws: Comparison and Validation of Planning Accuracy for Self-Derived Deep-Learning-Based and Commercial Atlas-Based Approaches. J Clin Med 2023; 12:jcm12072646. [PMID: 37048730 PMCID: PMC10094754 DOI: 10.3390/jcm12072646] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2023] [Revised: 03/28/2023] [Accepted: 03/29/2023] [Indexed: 04/05/2023] Open
Abstract
Background: This ex vivo experimental study sought to compare screw planning accuracy of a self-derived deep-learning-based (DL) and a commercial atlas-based (ATL) tool and to assess robustness towards pathologic spinal anatomy. Methods: From a consecutive registry, 50 cases (256 screws in L1-L5) were randomly selected for experimental planning. Reference screws were manually planned by two independent raters. Additional planning sets were created using the automatic DL and ATL tools. Using Python, automatic planning was compared to the reference in 3D space by calculating minimal absolute distances (MAD) for screw head and tip points (mm) and angular deviation (degree). Results were evaluated for interrater variability of reference screws. Robustness was evaluated in subgroups stratified for alteration of spinal anatomy. Results: Planning was successful in all 256 screws using DL and in 208/256 (81%) using ATL. MAD to the reference for head and tip points and angular deviation was 3.93 ± 2.08 mm, 3.49 ± 1.80 mm and 4.46 ± 2.86° for DL and 7.77 ± 3.65 mm, 7.81 ± 4.75 mm and 6.70 ± 3.53° for ATL, respectively. Corresponding interrater variance for reference screws was 4.89 ± 2.04 mm, 4.36 ± 2.25 mm and 5.27 ± 3.20°, respectively. Planning accuracy was comparable to the manual reference for DL, while ATL produced significantly inferior results (p < 0.0001). DL was robust to altered spinal anatomy while planning failure was pronounced for ATL in 28/82 screws (34%) in the subgroup with severely altered spinal anatomy and alignment (p < 0.0001). Conclusions: Deep learning appears to be a promising approach to reliable automated screw planning, coping well with anatomic variations of the spine that severely limit the accuracy of ATL systems.
Collapse
Affiliation(s)
- Moritz Scherer
- Department of Neurosurgery, Heidelberg University Hospital, 69120 Heidelberg, Germany
| | - Lisa Kausch
- Division of Medical Image Computing, German Cancer Research Center (DKFZ) Heidelberg, 69120 Heidelberg, Germany
| | - Akbar Bajwa
- Department of Neurosurgery, Heidelberg University Hospital, 69120 Heidelberg, Germany
| | - Jan-Oliver Neumann
- Department of Neurosurgery, Heidelberg University Hospital, 69120 Heidelberg, Germany
| | - Basem Ishak
- Department of Neurosurgery, Heidelberg University Hospital, 69120 Heidelberg, Germany
| | - Paul Naser
- Department of Neurosurgery, Heidelberg University Hospital, 69120 Heidelberg, Germany
| | - Philipp Vollmuth
- Department of Neuroradiology, Heidelberg University Hospital, 69120 Heidelberg, Germany
| | - Karl Kiening
- Department of Neurosurgery, Heidelberg University Hospital, 69120 Heidelberg, Germany
| | - Klaus Maier-Hein
- Division of Medical Image Computing, German Cancer Research Center (DKFZ) Heidelberg, 69120 Heidelberg, Germany
- Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital, 69120 Heidelberg, Germany
| | - Andreas Unterberg
- Department of Neurosurgery, Heidelberg University Hospital, 69120 Heidelberg, Germany
| |
Collapse
|
14
|
Noh SH, Cho PG, Kim KN, Kim SH, Shin DA. Artificial Intelligence for Neurosurgery : Current State and Future Directions. J Korean Neurosurg Soc 2023; 66:113-120. [PMID: 36124365 PMCID: PMC10009243 DOI: 10.3340/jkns.2022.0130] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2022] [Accepted: 09/12/2022] [Indexed: 11/27/2022] Open
Abstract
Artificial intelligence (AI) is a field of computer science that equips machines with human-like intelligence and enables them to learn, reason, and solve problems when presented with data in various formats. Neurosurgery is often at the forefront of innovative and disruptive technologies, which have similarly altered the course of acute and chronic diseases. In diagnostic imaging, such as X-rays, computed tomography, and magnetic resonance imaging, AI is used to analyze images. The use of robots in the field of neurosurgery is also increasing. In neurointensive care units, AI is used to analyze data and provide care to critically ill patients. Moreover, AI can be used to predict a patient's prognosis. Several AI applications have already been introduced in the field of neurosurgery, and many more are expected in the near future. Ultimately, it is our responsibility to keep pace with this evolution to provide meaningful outcomes and personalize each patient's care. Rather than blindly relying on AI in the future, neurosurgeons should gain a thorough understanding of it and use it to enhance their patient care.
Collapse
Affiliation(s)
- Sung Hyun Noh
- Department of Neurosurgery, Ajou University College of Medicine, Suwon, Korea.,Department of Neurosurgery, Yonsei University College of Medicine, Seoul, Korea
| | - Pyung Goo Cho
- Department of Neurosurgery, Ajou University College of Medicine, Suwon, Korea
| | - Keung Nyun Kim
- Department of Neurosurgery, Yonsei University College of Medicine, Seoul, Korea.,Department of Neurosurgery, Spine and Spinal Cord Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea
| | - Sang Hyun Kim
- Department of Neurosurgery, Ajou University College of Medicine, Suwon, Korea
| | - Dong Ah Shin
- Department of Neurosurgery, Yonsei University College of Medicine, Seoul, Korea.,Department of Neurosurgery, Spine and Spinal Cord Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea
| |
Collapse
|
15
|
Charles YP, Lamas V, Ntilikina Y. Artificial intelligence and treatment algorithms in spine surgery. Orthop Traumatol Surg Res 2023; 109:103456. [PMID: 36302452 DOI: 10.1016/j.otsr.2022.103456] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/28/2021] [Revised: 05/12/2022] [Accepted: 05/25/2022] [Indexed: 12/24/2022]
Abstract
Artificial intelligence (AI) is a set of theories and techniques in which machines are used to simulate human intelligence with complex computer programs. The various machine learning (ML) methods are a subtype of AI. They originate from computer science and use algorithms established from analyzing a database to accomplish certain tasks. Among these methods are decision trees or random forests, support vector machines along with artificial neural networks. Convolutive neural networks were inspired from the visual cortex; they process combinations of information used in image or voice recognition. Deep learning (DL) groups together a set of ML methods and is useful for modeling complex relationships with a high degree of abstraction by using multiple layers of artificial neurons. ML techniques have a growing role in spine surgery. The main applications are the segmentation of intraoperative images for surgical navigation or robotics used for pedicle screw placement, the interpretation of images of intervertebral discs or full spine radiographs, which can be automated using ML algorithms. ML techniques can also be used as aids for surgical decision-making in complex fields, such as preoperative evaluation of adult spinal deformity. ML algorithms "learn" from large clinical databases. They make it possible to establish the intraoperative risk level and make a prognosis on how the postoperative functional scores will change over time as a function of the patient profile. These applications open a new path relative to standard statistical analyses. They make it possible to explore more complex relationships with multiple indirect interactions. In the future, AI algorithms could have a greater role in clinical research, evaluating clinical and surgical practices, and conducting health economics analyses.
Collapse
Affiliation(s)
- Yann Philippe Charles
- Service de chirurgie du rachis, hôpitaux universitaires de Strasbourg, université de Strasbourg, 1, avenue Molière, 67200 Strasbourg, France.
| | - Vincent Lamas
- Service de chirurgie du rachis, hôpitaux universitaires de Strasbourg, université de Strasbourg, 1, avenue Molière, 67200 Strasbourg, France
| | - Yves Ntilikina
- Service de chirurgie du rachis, hôpitaux universitaires de Strasbourg, université de Strasbourg, 1, avenue Molière, 67200 Strasbourg, France
| |
Collapse
|
16
|
Ren G, Yu K, Xie Z, Wang P, Zhang W, Huang Y, Wang Y, Wu X. Current Applications of Machine Learning in Spine: From Clinical View. Global Spine J 2022; 12:1827-1840. [PMID: 34628966 PMCID: PMC9609532 DOI: 10.1177/21925682211035363] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/17/2022] Open
Abstract
STUDY DESIGN Narrative review. OBJECTIVES This review aims to present current applications of machine learning (ML) in spine domain to clinicians. METHODS We conducted a comprehensive PubMed search of peer-reviewed articles that were published between 2006 and 2020 using terms (spine, spinal, lumbar, cervical, thoracic, machine learning) to examine ML in spine. Then exclude research of other domain, case report, review or meta-analysis, and which without available abstract or full text. RESULTS Total 1738 articles were retrieved from database, and 292 studies were finally included. Key findings of current applications were compiled and summarized in this review. Main clinical applications of those techniques including image processing, diagnosis, decision supporting, operative assistance, rehabilitation, surgery outcomes, complications, hospitalization and cost. CONCLUSIONS ML had achieved excellent performance and hold immense potential in spine. ML could help clinical staff to improve medical level, enhance work efficiency, and reduce adverse events. However more randomized controlled trials and improvement of interpretability are essential to clinicians accepting models' assistance in real work.
Collapse
Affiliation(s)
- GuanRui Ren
- Southeast University Medical College,
Nanjing, Jiangsu, China
| | - Kun Yu
- Nanjing Jiangbei Hospital, Nanjing,
Jiangsu, China
| | - ZhiYang Xie
- Department of Spine Surgery, Zhongda
Hospital, School of Medicine, Southeast University, Nanjing, Jiangsu, China
| | - PeiYang Wang
- Southeast University Medical College,
Nanjing, Jiangsu, China
| | - Wei Zhang
- Southeast University Medical College,
Nanjing, Jiangsu, China
| | - Yong Huang
- Southeast University Medical College,
Nanjing, Jiangsu, China
| | - YunTao Wang
- Department of Spine Surgery, Zhongda
Hospital, School of Medicine, Southeast University, Nanjing, Jiangsu, China,YunTao Wang, Department of Spine Surgery,
Zhongda Hospital, School of Medicine, Southeast University, No. 87, Dingjiaqiao
Road, Nanjing, Jiangsu 210009, China.
| | - XiaoTao Wu
- Department of Spine Surgery, Zhongda
Hospital, School of Medicine, Southeast University, Nanjing, Jiangsu, China,XiaoTao Wu, Department of Spine Surgery,
Zhongda Hospital, School of Medicine, Southeast University, No. 87, Dingjiaqiao
Road, Nanjing, Jiangsu 210009, China.
| |
Collapse
|
17
|
The intraoperative use of augmented and mixed reality technology to improve surgical outcomes: A systematic review. Int J Med Robot 2022; 18:e2450. [DOI: 10.1002/rcs.2450] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2022] [Revised: 07/23/2022] [Accepted: 07/27/2022] [Indexed: 11/07/2022]
|
18
|
Assessing the accuracy of a new 3D2D registration algorithm based on a non-invasive skin marker model for navigated spine surgery. Int J Comput Assist Radiol Surg 2022; 17:1933-1945. [PMID: 35986831 PMCID: PMC9468112 DOI: 10.1007/s11548-022-02733-w] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2021] [Accepted: 08/04/2022] [Indexed: 11/24/2022]
Abstract
Purpose 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. Methods 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. Results 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. Conclusion 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. Supplementary Information The online version contains supplementary material available at 10.1007/s11548-022-02733-w.
Collapse
|
19
|
Hornung AL, Hornung CM, Mallow GM, Barajas JN, Rush A, Sayari AJ, Galbusera F, Wilke HJ, Colman M, Phillips FM, An HS, Samartzis D. Artificial intelligence in spine care: current applications and future utility. EUROPEAN SPINE JOURNAL : OFFICIAL PUBLICATION OF THE EUROPEAN SPINE SOCIETY, THE EUROPEAN SPINAL DEFORMITY SOCIETY, AND THE EUROPEAN SECTION OF THE CERVICAL SPINE RESEARCH SOCIETY 2022; 31:2057-2081. [PMID: 35347425 DOI: 10.1007/s00586-022-07176-0] [Citation(s) in RCA: 34] [Impact Index Per Article: 11.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/17/2021] [Revised: 01/18/2022] [Accepted: 03/08/2022] [Indexed: 01/20/2023]
Abstract
PURPOSE The field of artificial intelligence is ever growing and the applications of machine learning in spine care are continuously advancing. Given the advent of the intelligence-based spine care model, understanding the evolution of computation as it applies to diagnosis, treatment, and adverse event prediction is of great importance. Therefore, the current review sought to synthesize findings from the literature at the interface of artificial intelligence and spine research. METHODS A narrative review was performed based on the literature of three databases (MEDLINE, CINAHL, and Scopus) from January 2015 to March 2021 that examined historical and recent advancements in the understanding of artificial intelligence and machine learning in spine research. Studies were appraised for their role in, or description of, advancements within image recognition and predictive modeling for spinal research. Only English articles that fulfilled inclusion criteria were ultimately incorporated in this review. RESULTS This review briefly summarizes the history and applications of artificial intelligence and machine learning in spine. Three basic machine learning training paradigms: supervised learning, unsupervised learning, and reinforced learning are also discussed. Artificial intelligence and machine learning have been utilized in almost every facet of spine ranging from localization and segmentation techniques in spinal imaging to pathology specific algorithms which include but not limited to; preoperative risk assessment of postoperative complications, screening algorithms for patients at risk of osteoporosis and clustering analysis to identify subgroups within adolescent idiopathic scoliosis. The future of artificial intelligence and machine learning in spine surgery is also discussed with focusing on novel algorithms, data collection techniques and increased utilization of automated systems. CONCLUSION Improvements to modern-day computing and accessibility to various imaging modalities allow for innovative discoveries that may arise, for example, from management. Given the imminent future of AI in spine surgery, it is of great importance that practitioners continue to inform themselves regarding AI, its goals, use, and progression. In the future, it will be critical for the spine specialist to be able to discern the utility of novel AI research, particularly as it continues to pervade facets of everyday spine surgery.
Collapse
Affiliation(s)
- Alexander L Hornung
- Department of Orthopaedic Surgery, Rush University Medical Center, Chicago, IL, USA
| | | | - G Michael Mallow
- Department of Orthopaedic Surgery, Rush University Medical Center, Chicago, IL, USA
| | - J Nicolás Barajas
- Department of Orthopaedic Surgery, Rush University Medical Center, Chicago, IL, USA
| | - Augustus Rush
- Department of Orthopaedic Surgery, Rush University Medical Center, Chicago, IL, USA
| | - Arash J Sayari
- Department of Orthopaedic Surgery, Rush University Medical Center, Chicago, IL, USA
| | | | - Hans-Joachim Wilke
- Institute of Orthopaedic Research and Biomechanics, Trauma Research Center Ulm, Ulm University, Ulm, Germany
| | - Matthew Colman
- Department of Orthopaedic Surgery, Rush University Medical Center, Chicago, IL, USA
| | - Frank M Phillips
- Department of Orthopaedic Surgery, Rush University Medical Center, Chicago, IL, USA
| | - Howard S An
- Department of Orthopaedic Surgery, Rush University Medical Center, Chicago, IL, USA
| | - Dino Samartzis
- Department of Orthopaedic Surgery, Rush University Medical Center, Chicago, IL, USA.
| |
Collapse
|
20
|
Sumanas M, Petronis A, Bucinskas V, Dzedzickis A, Virzonis D, Morkvenaite-Vilkonciene I. Deep Q-Learning in Robotics: Improvement of Accuracy and Repeatability. SENSORS 2022; 22:s22103911. [PMID: 35632319 PMCID: PMC9147322 DOI: 10.3390/s22103911] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/24/2022] [Revised: 04/20/2022] [Accepted: 05/17/2022] [Indexed: 02/04/2023]
Abstract
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.
Collapse
|
21
|
Karandikar P, Massaad E, Hadzipasic M, Kiapour A, Joshi RS, Shankar GM, Shin JH. Machine Learning Applications of Surgical Imaging for the Diagnosis and Treatment of Spine Disorders: Current State of the Art. Neurosurgery 2022; 90:372-382. [PMID: 35107085 DOI: 10.1227/neu.0000000000001853] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2021] [Accepted: 11/10/2021] [Indexed: 01/18/2023] Open
Abstract
Recent developments in machine learning (ML) methods demonstrate unparalleled potential for application in the spine. The ability for ML to provide diagnostic faculty, produce novel insights from existing capabilities, and augment or accelerate elements of surgical planning and decision making at levels equivalent or superior to humans will tremendously benefit spine surgeons and patients alike. In this review, we aim to provide a clinically relevant outline of ML-based technology in the contexts of spinal deformity, degeneration, and trauma, as well as an overview of commercial-level and precommercial-level surgical assist systems and decisional support tools. Furthermore, we briefly discuss potential applications of generative networks before highlighting some of the limitations of ML applications. We conclude that ML in spine imaging represents a significant addition to the neurosurgeon's armamentarium-it has the capacity to directly address and manifest clinical needs and improve diagnostic and procedural quality and safety-but is yet subject to challenges that must be addressed before widespread implementation.
Collapse
Affiliation(s)
- Paramesh Karandikar
- Department of Neurosurgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
- T.H. Chan School of Medicine, University of Massachusetts, Worcester, Massachusetts, USA
| | - Elie Massaad
- Department of Neurosurgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Muhamed Hadzipasic
- Department of Neurosurgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Ali Kiapour
- Department of Neurosurgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Rushikesh S Joshi
- Department of Neurosurgery, University of Michigan, Ann Arbor, Michigan, USA
| | - Ganesh M Shankar
- Department of Neurosurgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - John H Shin
- Department of Neurosurgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
22
|
Evaluating the Relationship between Mandibular Third Molar and Mandibular Canal with Semiautomatic Segmentation: A Pilot Study on CBCT Datasets. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12010502] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/18/2023]
Abstract
Inferior alveolar nerve injury is the main complication in mandibular third molar surgery. In this context, cone-beam computed tomography (CBCT) has become of crucial importance in evaluating the relationship between mandibular third molar and inferior alveolar nerve. Due to the growing interest in preoperative planning in oral surgery, several post-processing techniques have been implemented to obtain three-dimensional reconstructions of a volume of interest. In the present study, segmentation techniques were retrospectively applied to CBCT images in order to evaluate whether post-processing could offer better visualization of the structures of interest. Forty CBCT examinations performed for inferior third molar impaction were analyzed. Segmentation and volumetric reconstructions were performed. A dataset composed of multiplanar reconstructions for each study case, including segmented images, was submitted for evaluation to two oral surgeons, two general practitioners and four residents in oral surgery. The visualization of root morphology, canal course, and the relationship with mandibular cortical bone on both native CBCT and segmented images were assessed. Inter-rater agreement showed values of intraclass correlation coefficient (ICC) above 0.8 for all the examined parameters. Oral surgeons presented higher ICC values (p < 0.05). Segmented images can improve preoperative evaluation of the third molar and its relationship with the surrounding anatomical structures compared to native CBCT images. Further evaluation is needed to validate these preliminary results.
Collapse
|
23
|
Artificial Intelligence in Adult Spinal Deformity. ACTA NEUROCHIRURGICA. SUPPLEMENT 2021; 134:313-318. [PMID: 34862555 DOI: 10.1007/978-3-030-85292-4_35] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Abstract
Artificial Intelligence is gaining traction in medicine for its ease of use and advancements in technology. This study evaluates the current literature on the use of artificial intelligence in adult spinal deformity.
Collapse
|
24
|
Siemionow KB, Forsthoefel CW, Foy MP, Gawel D, Luciano CJ. Autonomous lumbar spine pedicle screw planning using machine learning: A validation study. JOURNAL OF CRANIOVERTEBRAL JUNCTION AND SPINE 2021; 12:223-227. [PMID: 34728987 PMCID: PMC8501821 DOI: 10.4103/jcvjs.jcvjs_94_21] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2021] [Accepted: 07/28/2021] [Indexed: 11/06/2022] Open
Abstract
Introduction: 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. Materials and Methods: 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. Results: 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). Conclusion: 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.
Collapse
Affiliation(s)
| | | | - Michael P Foy
- Department of Orthopaedics, University of Illinois, Chicago, IL, USA
| | - Dominik Gawel
- Department of Research, Holo Surgical Inc, Chicago, IL, USA
| | | |
Collapse
|
25
|
Takahashi T, Watanabe S, Ito T. Current and future of anterior cruciate ligament reconstruction techniques. World J Meta-Anal 2021; 9:411-437. [DOI: 10.13105/wjma.v9.i5.411] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/31/2021] [Revised: 08/09/2021] [Accepted: 10/25/2021] [Indexed: 02/06/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- Toshiaki Takahashi
- Department of Sports and Health Science, Ehime University, Matsuyama 790-8577, Ehime, Japan
| | - Seiji Watanabe
- Department of Orthopedic Surgery, Ehime University Graduate School of Medicine, Toon 791-0295, Ehime, Japan
| | - Toshio Ito
- Department of Orthopaedic Surgery, Murakami Memorial Hospital, Saijo 793-0030, Ehime, Japan
| |
Collapse
|
26
|
Tariciotti L, Palmisciano P, Giordano M, Remoli G, Lacorte E, Bertani G, Locatelli M, Dimeco F, Caccavella VM, Prada F. Artificial intelligence-enhanced intraoperative neurosurgical workflow: state of the art and future perspectives. J Neurosurg Sci 2021; 66:139-150. [PMID: 34545735 DOI: 10.23736/s0390-5616.21.05483-7] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Abstract
BACKGROUND Artificial Intelligence (AI) and Machine Learning (ML) augment decision-making processes and productivity by supporting surgeons over a range of clinical activities: from diagnosis and preoperative planning to intraoperative surgical assistance. We reviewed the literature to identify current AI platforms applied to neurosurgical perioperative and intraoperative settings and describe their role in multiple subspecialties. METHODS A systematic review of the literature was conducted following the PRISMA guidelines. PubMed, EMBASE, and Scopus databases were searched from inception to December 31, 2020. Original articles were included if they: presented AI platforms implemented in perioperative, intraoperative settings and reported ML models' performance metrics. Due to the heterogeneity in neurosurgical applications, a qualitative synthesis was deemed appropriate. The risk of bias and applicability of predicted outcomes were assessed using the PROBAST tool. RESULTS 41 articles were included. All studies evaluated a supervised learning algorithm. A total of 10 ML models were described; the most frequent were neural networks (n = 15) and tree-based models (n = 13). Overall, the risk of bias was medium-high, but applicability was considered positive for all studies. Articles were grouped into 4 categories according to the subspecialty of interest: neuro-oncology, spine, functional and other. For each category, different prediction tasks were identified. CONCLUSIONS In this review, we summarize the state-of-art applications of AI for the intraoperative augmentation of neurosurgical workflows across multiple subspecialties. ML models may boost surgical team performances by reducing human errors and providing patient-tailored surgical plans, but further and higher-quality studies need to be conducted.
Collapse
Affiliation(s)
- Leonardo Tariciotti
- Unit of Neurosurgery, Fondazione IRCCS Cà Granda Ospedale Maggiore Policlinico, Milan, Italy.,Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy.,NEVRALIS, Milan, Italy
| | - Paolo Palmisciano
- NEVRALIS, Milan, Italy.,Department of Neurosurgery, Trauma, Gamma Knife Center Cannizzaro Hospital, Catania, Italy
| | - Martina Giordano
- NEVRALIS, Milan, Italy.,Department of Neurosurgery, Fondazione Policlinico Universitario A Gemelli IRCCS, Università Cattolica del Sacro Cuore, Rome, Italy
| | - Giulia Remoli
- NEVRALIS, Milan, Italy.,National Center for Disease Prevention and Health Promotion, Italian National Institute of Health, Rome, Italy
| | - Eleonora Lacorte
- National Center for Disease Prevention and Health Promotion, Italian National Institute of Health, Rome, Italy
| | - Giulio Bertani
- Unit of Neurosurgery, Fondazione IRCCS Cà Granda Ospedale Maggiore Policlinico, Milan, Italy
| | - Marco Locatelli
- Unit of Neurosurgery, Fondazione IRCCS Cà Granda Ospedale Maggiore Policlinico, Milan, Italy.,Department of Pathophysiology and Transplantation, University of Milan, Milan, Italy.,Aldo Ravelli Research Center for Neurotechnology and Experimental Brain Therapeutics, University of Milan, Milan, Italy
| | - Francesco Dimeco
- Department of Neurosurgery, Fondazione IRCCS Istituto Neurologico C. Besta, Milan, Italy
| | - Valerio M Caccavella
- NEVRALIS, Milan, Italy - .,Department of Neurosurgery, Fondazione Policlinico Universitario A Gemelli IRCCS, Università Cattolica del Sacro Cuore, Rome, Italy
| | - Francesco Prada
- Department of Neurosurgery, Fondazione IRCCS Istituto Neurologico C. Besta, Milan, Italy.,Department of Neurological Surgery, University of Virginia Health Science Center, Charlottesville, VA, USA
| |
Collapse
|
27
|
Raju B, Jumah F, Ashraf O, Narayan V, Gupta G, Sun H, Hilden P, Nanda A. Big data, machine learning, and artificial intelligence: a field guide for neurosurgeons. J Neurosurg 2021; 135:373-383. [PMID: 33007750 DOI: 10.3171/2020.5.jns201288] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/16/2020] [Accepted: 05/27/2020] [Indexed: 11/06/2022]
Abstract
Big data has transformed into a trend phrase in healthcare and neurosurgery, becoming a pervasive and inescapable phrase in everyday life. The upsurge in big data applications is a direct consequence of the drastic boom in information technology as well as the growing number of internet-connected devices called the Internet of Things in healthcare. Compared with business, marketing, and other sectors, healthcare applications are lagging due to a lack of technical knowledge among healthcare workers, technological limitations in acquiring and analyzing the data, and improper governance of healthcare big data. Despite these limitations, the medical literature is flooded with big data-related articles, and most of these are filled with abstruse terminologies such as machine learning, artificial intelligence, artificial neural network, and algorithm. Many of the recent articles are restricted to neurosurgical registries, creating a false impression that big data is synonymous with registries. Others advocate that the utilization of big data will be the panacea to all healthcare problems and research in the future. Without a proper understanding of these principles, it becomes easy to get lost without the ability to differentiate hype from reality. To that end, the authors give a brief narrative of big data analysis in neurosurgery and review its applications, limitations, and the challenges it presents for neurosurgeons and healthcare professionals naive to this field. Awareness of these basic concepts will allow neurosurgeons to understand the literature regarding big data, enabling them to make better decisions and deliver personalized care.
Collapse
Affiliation(s)
- Bharath Raju
- 1Department of Neurosurgery, Rutgers-Robert Wood Johnson Medical School and University Hospital; and
| | - Fareed Jumah
- 1Department of Neurosurgery, Rutgers-Robert Wood Johnson Medical School and University Hospital; and
| | - Omar Ashraf
- 1Department of Neurosurgery, Rutgers-Robert Wood Johnson Medical School and University Hospital; and
| | - Vinayak Narayan
- 1Department of Neurosurgery, Rutgers-Robert Wood Johnson Medical School and University Hospital; and
| | - Gaurav Gupta
- 1Department of Neurosurgery, Rutgers-Robert Wood Johnson Medical School and University Hospital; and
| | - Hai Sun
- 1Department of Neurosurgery, Rutgers-Robert Wood Johnson Medical School and University Hospital; and
| | - Patrick Hilden
- 2Rutgers Neurosurgery Health Outcomes, Policy, and Economics (HOPE) Center, New Brunswick, New Jersey
| | - Anil Nanda
- 1Department of Neurosurgery, Rutgers-Robert Wood Johnson Medical School and University Hospital; and
| |
Collapse
|
28
|
Skyrman S, Lai M, Edström E, Burström G, Förander P, Homan R, Kor F, Holthuizen R, Hendriks BHW, Persson O, Elmi-Terander A. Augmented reality navigation for cranial biopsy and external ventricular drain insertion. Neurosurg Focus 2021; 51:E7. [PMID: 34333469 DOI: 10.3171/2021.5.focus20813] [Citation(s) in RCA: 25] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2020] [Accepted: 05/17/2021] [Indexed: 11/06/2022]
Abstract
OBJECTIVE The aim of this study was to evaluate the accuracy (deviation from the target or intended path) and efficacy (insertion time) of an augmented reality surgical navigation (ARSN) system for insertion of biopsy needles and external ventricular drains (EVDs), two common neurosurgical procedures that require high precision. METHODS The hybrid operating room-based ARSN system, comprising a robotic C-arm with intraoperative cone-beam CT (CBCT) and integrated video tracking of the patient and instruments using nonobtrusive adhesive optical markers, was used. A 3D-printed skull phantom with a realistic gelatinous brain model containing air-filled ventricles and 2-mm spherical biopsy targets was obtained. After initial CBCT acquisition for target registration and planning, ARSN was used for 30 cranial biopsies and 10 EVD insertions. Needle positions were verified by CBCT. RESULTS The mean accuracy of the biopsy needle insertions (n = 30) was 0.8 mm ± 0.43 mm. The median path length was 39 mm (range 16-104 mm) and did not correlate to accuracy (p = 0.15). The median device insertion time was 149 seconds (range 87-233 seconds). The mean accuracy for the EVD insertions (n = 10) was 2.9 mm ± 0.8 mm at the tip with a 0.7° ± 0.5° angular deviation compared with the planned path, and the median insertion time was 188 seconds (range 135-400 seconds). CONCLUSIONS This study demonstrated that ARSN can be used for navigation of percutaneous cranial biopsies and EVDs with high accuracy and efficacy.
Collapse
Affiliation(s)
- Simon Skyrman
- 1Department of Neurosurgery, Karolinska University Hospital, and Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
| | - Marco Lai
- 2Philips Research, High Tech Campus 34, Eindhoven.,3Eindhoven University of Technology (TU/e), Eindhoven
| | - Erik Edström
- 1Department of Neurosurgery, Karolinska University Hospital, and Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
| | - Gustav Burström
- 1Department of Neurosurgery, Karolinska University Hospital, and Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
| | - Petter Förander
- 1Department of Neurosurgery, Karolinska University Hospital, and Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
| | | | - Flip Kor
- 5Department of Biomechanical Engineering, Delft University of Technology, Delft, The Netherlands
| | | | - Benno H W Hendriks
- 2Philips Research, High Tech Campus 34, Eindhoven.,5Department of Biomechanical Engineering, Delft University of Technology, Delft, The Netherlands
| | - Oscar Persson
- 1Department of Neurosurgery, Karolinska University Hospital, and Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
| | - Adrian Elmi-Terander
- 1Department of Neurosurgery, Karolinska University Hospital, and Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
| |
Collapse
|
29
|
Pojskić M, Bopp M, Saß B, Kirschbaum A, Nimsky C, Carl B. Intraoperative Computed Tomography-Based Navigation with Augmented Reality for Lateral Approaches to the Spine. Brain Sci 2021; 11:brainsci11050646. [PMID: 34063546 PMCID: PMC8156391 DOI: 10.3390/brainsci11050646] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2021] [Revised: 05/10/2021] [Accepted: 05/12/2021] [Indexed: 11/23/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Mirza Pojskić
- Department of Neurosurgery, University of Marburg, Baldingerstraße, 35043 Marburg, Germany; (M.B.); (B.S.); (C.N.); (B.C.)
- Correspondence: ; Tel.: +49-64215869848
| | - Miriam Bopp
- Department of Neurosurgery, University of Marburg, Baldingerstraße, 35043 Marburg, Germany; (M.B.); (B.S.); (C.N.); (B.C.)
- Marburg Center for Mind, Brain and Behavior (MCMBB), 35043 Marburg, Germany
| | - Benjamin Saß
- Department of Neurosurgery, University of Marburg, Baldingerstraße, 35043 Marburg, Germany; (M.B.); (B.S.); (C.N.); (B.C.)
| | - Andreas Kirschbaum
- Department of Visceral, Thoracic and Vascular Surgery, University of Marburg, 35043 Marburg, Germany;
| | - Christopher Nimsky
- Department of Neurosurgery, University of Marburg, Baldingerstraße, 35043 Marburg, Germany; (M.B.); (B.S.); (C.N.); (B.C.)
- Marburg Center for Mind, Brain and Behavior (MCMBB), 35043 Marburg, Germany
| | - Barbara Carl
- Department of Neurosurgery, University of Marburg, Baldingerstraße, 35043 Marburg, Germany; (M.B.); (B.S.); (C.N.); (B.C.)
- Department of Neurosurgery, Helios Dr. Horst Schmidt Kliniken, 65199 Wiesbaden, Germany
| |
Collapse
|
30
|
Burström G, Persson O, Edström E, Elmi-Terander A. Augmented reality navigation in spine surgery: a systematic review. Acta Neurochir (Wien) 2021; 163:843-852. [PMID: 33506289 PMCID: PMC7886712 DOI: 10.1007/s00701-021-04708-3] [Citation(s) in RCA: 70] [Impact Index Per Article: 17.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2020] [Accepted: 01/06/2021] [Indexed: 02/07/2023]
Abstract
BACKGROUND Conventional spinal navigation solutions have been criticized for having a negative impact on time in the operating room and workflow. AR navigation could potentially alleviate some of these concerns while retaining the benefits of navigated spine surgery. The objective of this study is to summarize the current evidence for using augmented reality (AR) navigation in spine surgery. METHODS We performed a systematic review to explore the current evidence for using AR navigation in spine surgery. PubMed and Web of Science were searched from database inception to November 27, 2020, for data on the AR navigation solutions; the reported efficacy of the systems; and their impact on workflow, radiation, and cost-benefit relationships. RESULTS In this systematic review, 28 studies were included in the final analysis. The main findings were superior workflow and non-inferior accuracy when comparing AR to free-hand (FH) or conventional surgical navigation techniques. A limited number of studies indicated decreased use of radiation. There were no studies reporting mortality, morbidity, or cost-benefit relationships. CONCLUSIONS AR provides a meaningful addition to FH surgery and traditional navigation methods for spine surgery. However, the current evidence base is limited and prospective studies on clinical outcomes and cost-benefit relationships are needed.
Collapse
|
31
|
Manni F, Mamprin M, Holthuizen R, Shan C, Burström G, Elmi-Terander A, Edström E, Zinger S, de With PHN. Multi-view 3D skin feature recognition and localization for patient tracking in spinal surgery applications. Biomed Eng Online 2021; 20:6. [PMID: 33413426 PMCID: PMC7792004 DOI: 10.1186/s12938-020-00843-7] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2020] [Accepted: 12/19/2020] [Indexed: 11/25/2022] Open
Abstract
BACKGROUND Minimally invasive spine surgery is dependent on accurate navigation. Computer-assisted navigation is increasingly used in minimally invasive surgery (MIS), but current solutions require the use of reference markers in the surgical field for both patient and instruments tracking. PURPOSE To improve reliability and facilitate clinical workflow, this study proposes a new marker-free tracking framework based on skin feature recognition. METHODS Maximally Stable Extremal Regions (MSER) and Speeded Up Robust Feature (SURF) algorithms are applied for skin feature detection. The proposed tracking framework is based on a multi-camera setup for obtaining multi-view acquisitions of the surgical area. Features can then be accurately detected using MSER and SURF and afterward localized by triangulation. The triangulation error is used for assessing the localization quality in 3D. RESULTS The framework was tested on a cadaver dataset and in eight clinical cases. The detected features for the entire patient datasets were found to have an overall triangulation error of 0.207 mm for MSER and 0.204 mm for SURF. The localization accuracy was compared to a system with conventional markers, serving as a ground truth. An average accuracy of 0.627 and 0.622 mm was achieved for MSER and SURF, respectively. CONCLUSIONS This study demonstrates that skin feature localization for patient tracking in a surgical setting is feasible. The technology shows promising results in terms of detected features and localization accuracy. In the future, the framework may be further improved by exploiting extended feature processing using modern optical imaging techniques for clinical applications where patient tracking is crucial.
Collapse
Affiliation(s)
- Francesca Manni
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands.
| | - Marco Mamprin
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
| | | | - Caifeng Shan
- Shandong University of Science and Technology, Qingdao, China
| | - Gustav Burström
- Department of Neurosurgery, Karolinska University Hospital and Department of Clinical Neuroscience, Karolinska Institute, Stockholm, Sweden
| | - Adrian Elmi-Terander
- Department of Neurosurgery, Karolinska University Hospital and Department of Clinical Neuroscience, Karolinska Institute, Stockholm, Sweden
| | - Erik Edström
- Department of Neurosurgery, Karolinska University Hospital and Department of Clinical Neuroscience, Karolinska Institute, Stockholm, Sweden
| | - Svitlana Zinger
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
| | - Peter H N de With
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
| |
Collapse
|
32
|
Danilov G, Shifrin M, Kotik K, Ishankulov T, Orlov Y, Kulikov A, Potapov A. Artificial Intelligence Technologies in Neurosurgery: a Systematic Literature Review Using Topic Modeling. Part II: Research Objectives and Perspectives. Sovrem Tekhnologii Med 2020; 12:111-118. [PMID: 34796024 PMCID: PMC8596229 DOI: 10.17691/stm2020.12.6.12] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2020] [Indexed: 12/29/2022] Open
Abstract
The current increase in the number of publications on the use of artificial intelligence (AI) technologies in neurosurgery indicates a new trend in clinical neuroscience. The aim of the study was to conduct a systematic literature review to highlight the main directions and trends in the use of AI in neurosurgery. METHODS Using the PubMed search engine, 327 original journal articles published from 1996 to July 2019 and related to the use of AI technologies in neurosurgery, were selected. The typical issues addressed by using AI were identified for each area of neurosurgery. RESULTS The typical AI applications within each of the five main areas of neurosurgery (neuro-oncology, functional, vascular, spinal neurosurgery, and traumatic brain injury) were defined. CONCLUSION The article highlights the main areas and trends in the up-to-date AI research in neurosurgery, which might be helpful in planning new scientific projects.
Collapse
Affiliation(s)
- G.V. Danilov
- Scientific Board Secretary; N.N. Burdenko National Medical Research Center for Neurosurgery, Ministry of Health of the Russian Federation, 16, 4 Tverskaya-Yamskaya St., Moscow, 125047, Russia; Head of the Laboratory of Biomedical Informatics and Artificial Intelligence; N.N. Burdenko National Medical Research Center for Neurosurgery, Ministry of Health of the Russian Federation, 16, 4 Tverskaya-Yamskaya St., Moscow, 125047, Russia
| | - M.A. Shifrin
- Scientific Consultant, Laboratory of Biomedical Informatics and Artificial Intelligence; N.N. Burdenko National Medical Research Center for Neurosurgery, Ministry of Health of the Russian Federation, 16, 4 Tverskaya-Yamskaya St., Moscow, 125047, Russia
| | - K.V. Kotik
- Physics Engineer, Laboratory of Biomedical Informatics and Artificial Intelligence; N.N. Burdenko National Medical Research Center for Neurosurgery, Ministry of Health of the Russian Federation, 16, 4 Tverskaya-Yamskaya St., Moscow, 125047, Russia
| | - T.A. Ishankulov
- Engineer, Laboratory of Biomedical Informatics and Artificial Intelligence; N.N. Burdenko National Medical Research Center for Neurosurgery, Ministry of Health of the Russian Federation, 16, 4 Tverskaya-Yamskaya St., Moscow, 125047, Russia
| | - Yu.N. Orlov
- Head of the Department of Computational Physics and Kinetic Equations; Keldysh Institute of Applied Mathematics, Russian Academy of Sciences, 4 Miusskaya Sq., Moscow, 125047, Russia
| | - A.S. Kulikov
- Staff Anesthesiologist; N.N. Burdenko National Medical Research Center for Neurosurgery, Ministry of Health of the Russian Federation, 16, 4 Tverskaya-Yamskaya St., Moscow, 125047, Russia
| | - A.A. Potapov
- Professor, Academician of the Russian Academy of Sciences, Chief Scientific Supervisor N.N. Burdenko National Medical Research Center for Neurosurgery, Ministry of Health of the Russian Federation, 16, 4 Tverskaya-Yamskaya St., Moscow, 125047, Russia
| |
Collapse
|
33
|
Frameless Patient Tracking With Adhesive Optical Skin Markers for Augmented Reality Surgical Navigation in Spine Surgery. Spine (Phila Pa 1976) 2020; 45:1598-1604. [PMID: 32756274 DOI: 10.1097/brs.0000000000003628] [Citation(s) in RCA: 25] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
STUDY DESIGN Observational study. OBJECTIVE The aim of this study was to evaluate the accuracy of a new frameless reference marker system for patient tracking by analyzing the effect of vertebral position within the surgical field. SUMMARY OF BACKGROUND DATA Most modern navigation systems for spine surgery rely on a dynamic reference frame attached to a vertebra for tracking the patient. This solution has the drawback of being bulky and obstructing the surgical field, while requiring that the dynamic reference frame is moved between vertebras to maintain accuracy. METHODS An augmented reality surgical navigation (ARSN) system with intraoperative cone beam computed tomography (CBCT) capability was installed in a hybrid operating room. The ARSN system used input from four video cameras for tracking adhesive skin markers placed around the surgical field. The frameless reference marker system was evaluated first in four human cadavers, and then in 20 patients undergoing navigated spine surgery. In each CBCT, the impact of vertebral position in the surgical field on technical accuracy was analyzed. The technical accuracy of the inserted pedicle devices was determined by measuring the distance between the planned position and the placed pedicle device, at the bone entry point. RESULTS The overall mean technical accuracy was 1.65 ± 1.24 mm at the bone entry point (n = 366). There was no statistically significant difference in technical accuracy between levels within CBCTs (P ≥ 0.12 for all comparisons). Linear regressions showed that null- to negligible parts of the effect on technical accuracy could be explained by the number of absolute levels away from the index vertebrae (r ≤ 0.007 for all, β ≤ 0.071 for all). CONCLUSION The frameless reference marker system based on adhesive skin markers is unobtrusive and affords the ARSN system a high accuracy throughout the navigated surgical field, independent of vertebral position. LEVEL OF EVIDENCE 3.
Collapse
|
34
|
Intraoperative cone beam computed tomography is as reliable as conventional computed tomography for identification of pedicle screw breach in thoracolumbar spine surgery. Eur Radiol 2020; 31:2349-2356. [PMID: 33006659 PMCID: PMC7979653 DOI: 10.1007/s00330-020-07315-5] [Citation(s) in RCA: 17] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/24/2020] [Revised: 08/04/2020] [Accepted: 09/17/2020] [Indexed: 12/01/2022]
Abstract
Objectives 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. Methods 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. Results 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%). Conclusions 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. Key Points • 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%.
Collapse
|
35
|
Siemionow K, Luciano C, Forsthoefel C, Aydogmus S. Autonomous image segmentation and identification of anatomical landmarks from lumbar spine intraoperative computed tomography scans using machine learning: A validation study. JOURNAL OF CRANIOVERTEBRAL JUNCTION AND SPINE 2020; 11:99-103. [PMID: 32904970 PMCID: PMC7462134 DOI: 10.4103/jcvjs.jcvjs_37_20] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2020] [Accepted: 03/31/2020] [Indexed: 11/04/2022] Open
Abstract
Purpose Machine-learning algorithms are a subset of artificial intelligence that have proven to enhance analytics in medicine across various platforms. Spine surgery has the potential to benefit from improved hardware placement utilizing algorithms that autonomously and accurately measure pedicle and vertebral body anatomy. The purpose of this study was to assess the accuracy of an autonomous convolutional neural network (CNN) in measuring vertebral body anatomy utilizing clinical lumbar computed tomography (CT) scans and automatically segment vertebral body anatomy. Methods The CNN was trained utilizing 8000 manually segmented CT slices from 15 cadaveric specimens and 30 adult diagnostic scans. Validation was performed with twenty randomly selected patient datasets. Anatomic landmarks that were segmented included the pedicle, vertebral body, spinous process, transverse process, facet joint, and lamina. Morphometric measurement of the vertebral body was compared between manual measurements and automatic measurements. Results Automatic segmentation was found to have a mean accuracy ranging from 96.38% to 98.96%. Coaxial distance from the lamina to the anterior cortex was 99.10% with pedicle angulation error of 3.47%. Conclusion The CNN algorithm tested in this study provides an accurate means to automatically identify the vertebral body anatomy and provide measurements for implants and placement trajectories.
Collapse
Affiliation(s)
| | - Cristian Luciano
- HoloSurgical, Inc., University of Illinois Hospital, Chicago, IL, USA
| | - Craig Forsthoefel
- Department of Orthopedic Surgery, University of Illinois Hospital, Chicago, IL, USA
| | - Suavi Aydogmus
- HoloSurgical, Inc., University of Illinois Hospital, Chicago, IL, USA
| |
Collapse
|
36
|
Does Augmented Reality Navigation Increase Pedicle Screw Density Compared to Free-Hand Technique in Deformity Surgery? Single Surgeon Case Series of 44 Patients. Spine (Phila Pa 1976) 2020; 45:E1085-E1090. [PMID: 32355149 DOI: 10.1097/brs.0000000000003518] [Citation(s) in RCA: 25] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
STUDY DESIGN Retrospective comparison between an interventional and a control cohort. OBJECTIVE The aim of this study was to investigate whether the use of an augmented reality surgical navigation (ARSN) system for pedicle screw (PS) placement in deformity cases could alter the total implant density and PS to hook ratio compared to free-hand (FH) technique. SUMMARY OF BACKGROUND DATA Surgical navigation in deformity surgery provides the possibility to place PS in small and deformed pedicles were hooks would otherwise have been placed, and thereby achieve a higher screw density in the constructs that may result in better long-term patient outcomes. METHODS Fifteen deformity cases treated with ARSN were compared to 29 cases treated by FH. All surgeries were performed by the same orthopedic spine surgeon. PS, hook, and combined implant density were primary outcomes. Procedure time, deformity correction, length of hospital stay, and blood loss were secondary outcomes. The surgeries in the ARSN group were performed in a hybrid operating room (OR) with a ceiling-mounted robotic C-arm with integrated video cameras for AR navigation. The FH group was operated with or without fluoroscopy as deemed necessary by the surgeon. RESULTS Both groups had an overall high-density construct (>80% total implant density). The ARSN group, had a significantly higher PS density, 86.3% ± 14.6% versus 74.7% ± 13.9% in the FH group (P < 0.05), whereas the hook density was 2.2% ± 3.0% versus 9.7% ± 9.6% (P < 0.001). Neither the total procedure time (min) 431 ± 98 versus 417 ± 145 nor the deformity correction 59.3% ± 16.6% versus 60.1% ± 17.8% between the groups were significantly affected. CONCLUSION This study indicates that ARSN enables the surgeon to increase the PS density and thereby minimize the use of hooks in deformity surgery without prolonging the OR time. This may result in better constructs with possible long-term advantage and less need for revision surgery. LEVEL OF EVIDENCE 3.
Collapse
|
37
|
Manni F, Elmi-Terander A, Burström G, Persson O, Edström E, Holthuizen R, Shan C, Zinger S, van der Sommen F, de With PHN. Towards Optical Imaging for Spine Tracking without Markers in Navigated Spine Surgery. SENSORS (BASEL, SWITZERLAND) 2020; 20:E3641. [PMID: 32610555 PMCID: PMC7374436 DOI: 10.3390/s20133641] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/19/2020] [Revised: 06/13/2020] [Accepted: 06/22/2020] [Indexed: 12/18/2022]
Abstract
Surgical navigation systems are increasingly used for complex spine procedures to avoid neurovascular injuries and minimize the risk for reoperations. Accurate patient tracking is one of the prerequisites for optimal motion compensation and navigation. Most current optical tracking systems use dynamic reference frames (DRFs) attached to the spine, for patient movement tracking. However, the spine itself is subject to intrinsic movements which can impact the accuracy of the navigation system. In this study, we aimed to detect the actual patient spine features in different image views captured by optical cameras, in an augmented reality surgical navigation (ARSN) system. Using optical images from open spinal surgery cases, acquired by two gray-scale cameras, spinal landmarks were identified and matched in different camera views. A computer vision framework was created for preprocessing of the spine images, detecting and matching local invariant image regions. We compared four feature detection algorithms, Speeded Up Robust Feature (SURF), Maximal Stable Extremal Region (MSER), Features from Accelerated Segment Test (FAST), and Oriented FAST and Rotated BRIEF (ORB) to elucidate the best approach. The framework was validated in 23 patients and the 3D triangulation error of the matched features was < 0 . 5 mm. Thus, the findings indicate that spine feature detection can be used for accurate tracking in navigated surgery.
Collapse
Affiliation(s)
- Francesca Manni
- Department of Electrical Engineering, Eindhoven University of Technology, 5600 MB Eindhoven, The Netherlands; (S.Z.); (F.v.d.S.); (P.H.N.d.W.)
| | - Adrian Elmi-Terander
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm SE-171 46, Sweden & Department of Neurosurgery, Karolinska University Hospital, SE-171 46 Stockholm, Sweden; (A.E.-T.); (G.B.); (O.P.); (E.E.)
| | - Gustav Burström
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm SE-171 46, Sweden & Department of Neurosurgery, Karolinska University Hospital, SE-171 46 Stockholm, Sweden; (A.E.-T.); (G.B.); (O.P.); (E.E.)
| | - Oscar Persson
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm SE-171 46, Sweden & Department of Neurosurgery, Karolinska University Hospital, SE-171 46 Stockholm, Sweden; (A.E.-T.); (G.B.); (O.P.); (E.E.)
| | - Erik Edström
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm SE-171 46, Sweden & Department of Neurosurgery, Karolinska University Hospital, SE-171 46 Stockholm, Sweden; (A.E.-T.); (G.B.); (O.P.); (E.E.)
| | | | - Caifeng Shan
- Philips Research, High Tech Campus 36, 5656 AE Eindhoven, The Netherlands;
| | - Svitlana Zinger
- Department of Electrical Engineering, Eindhoven University of Technology, 5600 MB Eindhoven, The Netherlands; (S.Z.); (F.v.d.S.); (P.H.N.d.W.)
| | - Fons van der Sommen
- Department of Electrical Engineering, Eindhoven University of Technology, 5600 MB Eindhoven, The Netherlands; (S.Z.); (F.v.d.S.); (P.H.N.d.W.)
| | - Peter H. N. de With
- Department of Electrical Engineering, Eindhoven University of Technology, 5600 MB Eindhoven, The Netherlands; (S.Z.); (F.v.d.S.); (P.H.N.d.W.)
| |
Collapse
|
38
|
Hyperspectral Imaging for Skin Feature Detection: Advances in Markerless Tracking for Spine Surgery. APPLIED SCIENCES-BASEL 2020. [DOI: 10.3390/app10124078] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
In spinal surgery, surgical navigation is an essential tool for safe intervention, including the placement of pedicle screws without injury to nerves and blood vessels. Commercially available systems typically rely on the tracking of a dynamic reference frame attached to the spine of the patient. However, the reference frame can be dislodged or obscured during the surgical procedure, resulting in loss of navigation. Hyperspectral imaging (HSI) captures a large number of spectral information bands across the electromagnetic spectrum, providing image information unseen by the human eye. We aim to exploit HSI to detect skin features in a novel methodology to track patient position in navigated spinal surgery. In our approach, we adopt two local feature detection methods, namely a conventional handcrafted local feature and a deep learning-based feature detection method, which are compared to estimate the feature displacement between different frames due to motion. To demonstrate the ability of the system in tracking skin features, we acquire hyperspectral images of the skin of 17 healthy volunteers. Deep-learned skin features are detected and localized with an average error of only 0.25 mm, outperforming the handcrafted local features with respect to the ground truth based on the use of optical markers.
Collapse
|
39
|
Balicki M, Kyne S, Toporek G, Holthuizen R, Homan R, Popovic A, Burström G, Persson O, Edström E, Elmi-Terander A, Patriciu A. Design and control of an image-guided robot for spine surgery in a hybrid OR. Int J Med Robot 2020; 16:e2108. [PMID: 32270913 DOI: 10.1002/rcs.2108] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2019] [Revised: 03/17/2020] [Accepted: 03/29/2020] [Indexed: 11/07/2022]
Abstract
BACKGROUND Minimally invasive spine (MIS) fusion surgery requires image guidance and expert manual dexterity for a successful, efficient, and accurate pedicle screw placement. Operating room (OR)-integrated robotic solution can provide precise assistance to potentially minimize complication rates and facilitate difficult MIS procedures. METHODS A 5-degrees of freedom robot was designed specifically for a hybrid OR with integrated surgical navigation for guiding pedicle screw pilot holes. The system automatically aligns an instrument following the surgical plan using only instrument tracking feedback. Contrary to commercially available robotic systems, no tracking markers on the robotic arm are required. The system was evaluated in a cadaver study. RESULTS The mean targeting error (N = 34) was 1.27±0.57 mm and 1.62±0.85°, with 100% of insertions graded as clinically acceptable. CONCLUSIONS A fully integrated robotic guidance system, including intra-op imaging, planning, and physical guidance with optimized robot design and control, can improve workflow and provide pedicle screw guidance with less than 2 mm targeting error.
Collapse
Affiliation(s)
- Marcin Balicki
- Philips Research North America, Cambridge, Massachusetts, USA
| | - Sean Kyne
- Philips Research North America, Cambridge, Massachusetts, USA
| | | | | | | | | | - Gustav Burström
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.,Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| | - Oscar Persson
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.,Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| | - Erik Edström
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.,Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| | - Adrian Elmi-Terander
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.,Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| | | |
Collapse
|
40
|
Burström G, Balicki M, Patriciu A, Kyne S, Popovic A, Holthuizen R, Homan R, Skulason H, Persson O, Edström E, Elmi-Terander A. Feasibility and accuracy of a robotic guidance system for navigated spine surgery in a hybrid operating room: a cadaver study. Sci Rep 2020; 10:7522. [PMID: 32371880 PMCID: PMC7200720 DOI: 10.1038/s41598-020-64462-x] [Citation(s) in RCA: 21] [Impact Index Per Article: 4.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2019] [Accepted: 04/15/2020] [Indexed: 12/11/2022] Open
Abstract
The combination of navigation and robotics in spine surgery has the potential to accurately identify and maintain bone entry position and planned trajectory. The goal of this study was to examine the feasibility, accuracy and efficacy of a new robot-guided system for semi-automated, minimally invasive, pedicle screw placement. A custom robotic arm was integrated into a hybrid operating room (OR) equipped with an augmented reality surgical navigation system (ARSN). The robot was mounted on the OR-table and used to assist in placing Jamshidi needles in 113 pedicles in four cadavers. The ARSN system was used for planning screw paths and directing the robot. The robot arm autonomously aligned with the planned screw trajectory, and the surgeon inserted the Jamshidi needle into the pedicle. Accuracy measurements were performed on verification cone beam computed tomographies with the planned paths superimposed. To provide a clinical grading according to the Gertzbein scale, pedicle screw diameters were simulated on the placed Jamshidi needles. A technical accuracy at bone entry point of 0.48 ± 0.44 mm and 0.68 ± 0.58 mm was achieved in the axial and sagittal views, respectively. The corresponding angular errors were 0.94 ± 0.83° and 0.87 ± 0.82°. The accuracy was statistically superior (p < 0.001) to ARSN without robotic assistance. Simulated pedicle screw grading resulted in a clinical accuracy of 100%. This study demonstrates that the use of a semi-automated surgical robot for pedicle screw placement provides an accuracy well above what is clinically acceptable.
Collapse
Affiliation(s)
- Gustav Burström
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.
- Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden.
| | | | | | - Sean Kyne
- Philips Research North America, Cambridge, USA
| | | | - Ronald Holthuizen
- Department of Image Guided Therapy Systems, Philips Healthcare, Best, the Netherlands
| | - Robert Homan
- Department of Image Guided Therapy Systems, Philips Healthcare, Best, the Netherlands
| | - Halldor Skulason
- Department of Neurosurgery, Landspitali University Hospital, Reykjavik, Iceland
| | - Oscar Persson
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
- Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| | - Erik Edström
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
- Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| | - Adrian Elmi-Terander
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
- Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| |
Collapse
|
41
|
Elmi-Terander A, Burström G, Nachabé R, Fagerlund M, Ståhl F, Charalampidis A, Edström E, Gerdhem P. Augmented reality navigation with intraoperative 3D imaging vs fluoroscopy-assisted free-hand surgery for spine fixation surgery: a matched-control study comparing accuracy. Sci Rep 2020; 10:707. [PMID: 31959895 PMCID: PMC6971085 DOI: 10.1038/s41598-020-57693-5] [Citation(s) in RCA: 68] [Impact Index Per Article: 13.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2019] [Accepted: 12/09/2019] [Indexed: 02/06/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- Adrian Elmi-Terander
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.,Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| | - Gustav Burström
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.,Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| | - Rami Nachabé
- Department of Image Guided Therapy Systems, Philips Healthcare, Best, the Netherlands.
| | - Michael Fagerlund
- Department of Neuroradiology, Karolinska University Hospital, Stockholm, Sweden
| | - Fredrik Ståhl
- Department of Neuroradiology, Karolinska University Hospital, Stockholm, Sweden
| | - Anastasios Charalampidis
- Department of Clinical Sciences, Intervention and Technology (CLINTEC), Karolinska Institutet, Stockholm, Sweden; Department of Orthopedics, Karolinska University Hospital, Stockholm, Sweden
| | - Erik Edström
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.,Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| | - Paul Gerdhem
- Department of Clinical Sciences, Intervention and Technology (CLINTEC), Karolinska Institutet, Stockholm, Sweden; Department of Orthopedics, Karolinska University Hospital, Stockholm, Sweden
| |
Collapse
|
42
|
Fusion of augmented reality imaging with the endoscopic view for endonasal skull base surgery; a novel application for surgical navigation based on intraoperative cone beam computed tomography and optical tracking. PLoS One 2020; 15:e0227312. [PMID: 31945082 PMCID: PMC6964902 DOI: 10.1371/journal.pone.0227312] [Citation(s) in RCA: 16] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2019] [Accepted: 12/16/2019] [Indexed: 01/11/2023] Open
Abstract
Objective 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. Material and methods 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. Results 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. Conclusion We present a novel augmented reality surgical navigation system, with fusion of intraoperative CBCT on the endoscopic view. The system shows sub-millimeter accuracy.
Collapse
|
43
|
Schwartz JT, Gao M, Geng EA, Mody KS, Mikhail CM, Cho SK. Applications of Machine Learning Using Electronic Medical Records in Spine Surgery. Neurospine 2019; 16:643-653. [PMID: 31905452 PMCID: PMC6945000 DOI: 10.14245/ns.1938386.193] [Citation(s) in RCA: 26] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2019] [Accepted: 12/04/2019] [Indexed: 12/15/2022] Open
Abstract
Developments in machine learning in recent years have precipitated a surge in research on the applications of artificial intelligence within medicine. Machine learning algorithms are beginning to impact medicine broadly, and the field of spine surgery is no exception. Electronic medical records are a key source of medical data that can be leveraged for the creation of clinically valuable machine learning algorithms. This review examines the current state of machine learning using electronic medical records as it applies to spine surgery. Studies across the electronic medical record data domains of imaging, text, and structured data are reviewed. Discussed applications include clinical prognostication, preoperative planning, diagnostics, and dynamic clinical assistance, among others. The limitations and future challenges for machine learning research using electronic medical records are also discussed.
Collapse
Affiliation(s)
- John T. Schwartz
- Department of Orthopaedic Surgery, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Michael Gao
- Department of Orthopaedic Surgery, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Eric A. Geng
- Department of Orthopaedic Surgery, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Kush S. Mody
- Department of Orthopaedic Surgery, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Christopher M. Mikhail
- Department of Orthopaedic Surgery, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Samuel K. Cho
- Department of Orthopaedic Surgery, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| |
Collapse
|
44
|
Harada GK, Siyaji ZK, Younis S, Louie PK, Samartzis D, An HS. Imaging in Spine Surgery: Current Concepts and Future Directions. Spine Surg Relat Res 2019; 4:99-110. [PMID: 32405554 PMCID: PMC7217684 DOI: 10.22603/ssrr.2020-0011] [Citation(s) in RCA: 31] [Impact Index Per Article: 5.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/06/2019] [Accepted: 10/03/2019] [Indexed: 12/23/2022] Open
Abstract
OBJECTIVE To review and highlight the historical and recent advances of imaging in spine surgery and to discuss current applications and future directions. METHODS A PubMed review of the current literature was performed on all relevant articles that examined historical and recent imaging techniques used in spine surgery. Studies were examined for their thoroughness in description of various modalities and applications in current and future management. RESULTS We reviewed 97 articles that discussed past, present, and future applications for imaging in spine surgery. Although most historical approaches relied heavily upon basic radiography, more recent advances have begun to expand upon advanced modalities, including the integration of more sophisticated equipment and artificial intelligence. CONCLUSIONS Since the days of conventional radiography, various modalities have emerged and become integral components of the spinal surgeon's diagnostic armamentarium. As such, it behooves the practitioner to remain informed on the current trends and potential developments in spinal imaging, as rapid adoption and interpretation of new techniques may make significant differences in patient management and outcomes. Future directions will likely become increasingly sophisticated as the implementation of machine learning, and artificial intelligence has become more commonplace in clinical practice.
Collapse
Affiliation(s)
- Garrett K Harada
- Department of Orthopaedic Surgery, Division of Spine Surgery, Rush University Medical Center, Chicago, USA
- International Spine Research and Innovation Initiative, Rush University Medical Center, Chicago, USA
| | - Zakariah K Siyaji
- Department of Orthopaedic Surgery, Division of Spine Surgery, Rush University Medical Center, Chicago, USA
- International Spine Research and Innovation Initiative, Rush University Medical Center, Chicago, USA
| | - Sadaf Younis
- Department of Orthopaedic Surgery, Division of Spine Surgery, Rush University Medical Center, Chicago, USA
- International Spine Research and Innovation Initiative, Rush University Medical Center, Chicago, USA
| | - Philip K Louie
- Department of Orthopaedic Surgery, Division of Spine Surgery, Rush University Medical Center, Chicago, USA
- International Spine Research and Innovation Initiative, Rush University Medical Center, Chicago, USA
| | - Dino Samartzis
- Department of Orthopaedic Surgery, Division of Spine Surgery, Rush University Medical Center, Chicago, USA
- International Spine Research and Innovation Initiative, Rush University Medical Center, Chicago, USA
| | - Howard S An
- Department of Orthopaedic Surgery, Division of Spine Surgery, Rush University Medical Center, Chicago, USA
- International Spine Research and Innovation Initiative, Rush University Medical Center, Chicago, USA
| |
Collapse
|
45
|
Burström G, Swamy A, Spliethoff JW, Reich C, Babic D, Hendriks BHW, Skulason H, Persson O, Elmi Terander A, Edström E. Diffuse reflectance spectroscopy accurately identifies the pre-cortical zone to avoid impending pedicle screw breach in spinal fixation surgery. BIOMEDICAL OPTICS EXPRESS 2019; 10:5905-5920. [PMID: 31799054 PMCID: PMC6865097 DOI: 10.1364/boe.10.005905] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/07/2019] [Revised: 10/09/2019] [Accepted: 10/09/2019] [Indexed: 05/03/2023]
Abstract
Pedicle screw placement accuracy during spinal fixation surgery varies greatly and severe misplacement has been reported in 1-6.5% of screws. Diffuse reflectance (DR) spectroscopy has previously been shown to reliably discriminate between tissues in the human body. We postulate that it could be used to discriminate between cancellous and cortical bone. Therefore, the purpose of this study is to validate DR spectroscopy as a warning system to detect impending pedicle screw breach in a cadaveric surgical setting using typical clinical breach scenarios. DR spectroscopy was incorporated at the tip of an integrated pedicle screw and screw driver used for tissue probing during pedicle screw insertions on six cadavers. Measurements were collected in the wavelength range of 400-1600 nm and each insertion was planned to result in a breach. Measurements were labelled as cancellous, cortical or representing a pre-cortical zone (PCZ) in between, based on information from cone beam computed tomographies at corresponding positions. In addition, DR spectroscopy data was recorded after breach. Four typical pedicle breach types were performed, and a total of 45 pedicle breaches were recorded. For each breach direction, the technology was able to detect the transition of the screw tip from the cancellous bone to the PCZ (P < 0.001), to cortical bone (P < 0.001), and to a subsequent breach (P < 0.001). Using support vector machine (SVM) classification, breach could reliably be detected with a sensitivity of 98.3 % [94.3-100 %] and a specificity of 97.7 % [91.0-100 %]. We conclude that DR spectroscopy reliably identifies the area of transition from cancellous to cortical bone in typical breach scenarios and can warn the surgeon of impending pedicle breach, thereby resulting in safer spinal fixation surgeries.
Collapse
Affiliation(s)
- Gustav Burström
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
- Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| | - Akash Swamy
- Delft University of Technology, Department of Biomechanical Engineering, Delft, The Netherlands
- Department of In-body Systems, Philips Research, Royal Philips NV, Eindhoven, The Netherlands
| | - Jarich W. Spliethoff
- Department of In-body Systems, Philips Research, Royal Philips NV, Eindhoven, The Netherlands
| | - Christian Reich
- Department of In-body Systems, Philips Research, Royal Philips NV, Eindhoven, The Netherlands
| | - Drazenko Babic
- Department of In-body Systems, Philips Research, Royal Philips NV, Eindhoven, The Netherlands
| | - Benno H. W. Hendriks
- Delft University of Technology, Department of Biomechanical Engineering, Delft, The Netherlands
- Department of In-body Systems, Philips Research, Royal Philips NV, Eindhoven, The Netherlands
| | - Halldor Skulason
- Department of Neurosurgery, Landspitali University Hospital, Reykjavik, Iceland
| | - Oscar Persson
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
- Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| | - Adrian Elmi Terander
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
- Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| | - Erik Edström
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
- Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| |
Collapse
|
46
|
Edström E, Burström G, Nachabe R, Gerdhem P, Elmi Terander A. A Novel Augmented-Reality-Based Surgical Navigation System for Spine Surgery in a Hybrid Operating Room: Design, Workflow, and Clinical Applications. Oper Neurosurg (Hagerstown) 2019; 18:496-502. [DOI: 10.1093/ons/opz236] [Citation(s) in RCA: 52] [Impact Index Per Article: 8.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2019] [Accepted: 05/31/2019] [Indexed: 12/29/2022] Open
Abstract
Abstract
BACKGROUND
Treatment of several spine disorders requires placement of pedicle screws. Detailed 3-dimensional (3D) anatomic information facilitates this process and improves accuracy.
OBJECTIVE
To present a workflow for a novel augmented-reality-based surgical navigation (ARSN) system installed in a hybrid operating room for anatomy visualization and instrument guidance during pedicle screw placement.
METHODS
The workflow includes surgical exposure, imaging, automatic creation of a 3D model, and pedicle screw path planning for instrument guidance during surgery as well as the actual screw placement, spinal fixation, and wound closure and intraoperative verification of the treatment results. Special focus was given to process integration and minimization of overhead time. Efforts were made to manage staff radiation exposure avoiding the need for lead aprons. Time was kept throughout the procedure and subdivided to reflect key steps. The navigation workflow was validated in a trial with 20 cases requiring pedicle screw placement (13/20 scoliosis).
RESULTS
Navigated interventions were performed with a median total time of 379 min per procedure (range 232-548 min for 4-24 implanted pedicle screws).
The total procedure time was subdivided into surgical exposure (28%), cone beam computed tomography imaging and 3D segmentation (2%), software planning (6%), navigated surgery for screw placement (17%) and non-navigated instrumentation, wound closure, etc (47%).
CONCLUSION
Intraoperative imaging and preparation for surgical navigation totaled 8% of the surgical time. Consequently, ARSN can routinely be used to perform highly accurate surgery potentially decreasing the risk for complications and revision surgery while minimizing radiation exposure to the staff.
Collapse
Affiliation(s)
- Erik Edström
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
- Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| | - Gustav Burström
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
- Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| | - Rami Nachabe
- Image-Guided Therapy, Philips Healthcare, Best, the Netherlands
| | - Paul Gerdhem
- Department of Clinical Sciences, Intervention and Technology (CLINTEC), Karolinska Institutet, Stockholm, Sweden
- Department of Reconstructive Orthopaedics, Karolinska University Hospital, Stockholm, Sweden
| | - Adrian Elmi Terander
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden
- Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
| |
Collapse
|
47
|
Cuocolo R, Cipullo MB, Stanzione A, Ugga L, Romeo V, Radice L, Brunetti A, Imbriaco M. Machine learning applications in prostate cancer magnetic resonance imaging. Eur Radiol Exp 2019; 3:35. [PMID: 31392526 PMCID: PMC6686027 DOI: 10.1186/s41747-019-0109-2] [Citation(s) in RCA: 108] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2019] [Accepted: 07/02/2019] [Indexed: 12/17/2022] Open
Abstract
With this review, we aimed to provide a synopsis of recently proposed applications of machine learning (ML) in radiology focusing on prostate magnetic resonance imaging (MRI). After defining the difference between ML and classical rule-based algorithms and the distinction among supervised, unsupervised and reinforcement learning, we explain the characteristic of deep learning (DL), a particular new type of ML, including its structure mimicking human neural networks and its 'black box' nature. Differences in the pipeline for applying ML and DL to prostate MRI are highlighted. The following potential clinical applications in different settings are outlined, many of them based only on MRI-unenhanced sequences: gland segmentation; assessment of lesion aggressiveness to distinguish between clinically significant and indolent cancers, allowing for active surveillance; cancer detection/diagnosis and localisation (transition versus peripheral zone, use of prostate imaging reporting and data system (PI-RADS) version 2), reading reproducibility, differentiation of cancers from prostatitis benign hyperplasia; local staging and pre-treatment assessment (detection of extraprostatic disease extension, planning of radiation therapy); and prediction of biochemical recurrence. Results are promising, but clinical applicability still requires more robust validation across scanner vendors, field strengths and institutions.
Collapse
Affiliation(s)
- Renato Cuocolo
- Department of Advanced Biomedical Sciences, University of Naples "Federico II", Via S. Pansini, 5, 80131, Naples, Italy
| | - Maria Brunella Cipullo
- Department of Advanced Biomedical Sciences, University of Naples "Federico II", Via S. Pansini, 5, 80131, Naples, Italy
| | - Arnaldo Stanzione
- Department of Advanced Biomedical Sciences, University of Naples "Federico II", Via S. Pansini, 5, 80131, Naples, Italy.
| | - Lorenzo Ugga
- Department of Advanced Biomedical Sciences, University of Naples "Federico II", Via S. Pansini, 5, 80131, Naples, Italy
| | - Valeria Romeo
- Department of Advanced Biomedical Sciences, University of Naples "Federico II", Via S. Pansini, 5, 80131, Naples, Italy
| | - Leonardo Radice
- Department of Advanced Biomedical Sciences, University of Naples "Federico II", Via S. Pansini, 5, 80131, Naples, Italy
| | - Arturo Brunetti
- Department of Advanced Biomedical Sciences, University of Naples "Federico II", Via S. Pansini, 5, 80131, Naples, Italy
| | - Massimo Imbriaco
- Department of Advanced Biomedical Sciences, University of Naples "Federico II", Via S. Pansini, 5, 80131, Naples, Italy
| |
Collapse
|