Hooman Esfandiari1, Robyn Newell2, Carolyn Anglin3, John Street4, Antony J Hodgson5. 1. Biomedical Engineering, Surgical Technologies Lab, Robert H.N. Ho Research Centre, University of British Columbia, 6th Floor, 2635 Laurel St, Vancouver, BC, V5Z 1M9, Canada. hooman.esfandiari@ubc.ca. 2. Biomedical Engineering, Surgical Technologies Lab, University of British Columbia, Vancouver, Canada. 3. Biomedical Engineering, Civil Engineering, McCaig Institute for Bone and Joint Health, University of Calgary, Calgary, Canada. 4. Combined Neurosurgical and Orthopaedic Spine Program, University of British Columbia, Vancouver, Canada. 5. Department of Mechanical Engineering, Biomedical Engineering, Surgical Technologies Lab, University of British Columbia, Vancouver, Canada.
Abstract
PURPOSE: Pedicle screw fixation is a challenging procedure with a concerning rates of reoperation. After insertion of the screws is completed, the most common intraoperative verification approach is to acquire anterior-posterior and lateral radiographic images, based on which the surgeons try to visually assess the correctness of insertion. Given the limited accuracy of the existing verification techniques, we identified the need for an accurate and automated pedicle screw assessment system that can verify the screw insertion intraoperatively. For doing so, this paper offers a framework for automatic segmentation and pose estimation of pedicle screws based on deep learning principles. METHODS: Segmentation of pedicle screw X-ray projections was performed by a convolutional neural network. The network could isolate the input X-rays into three classes: screw head, screw shaft and background. Once all the screw shafts were segmented, knowledge about the spatial configuration of the acquired biplanar X-rays was used to identify the correspondence between the projections. Pose estimation was then performed to estimate the 6 degree-of-freedom pose of each screw. The performance of the proposed pose estimation method was tested on a porcine specimen. RESULTS: The developed machine learning framework was capable of segmenting the screw shafts with 93% and 83% accuracy when tested on synthetic X-rays and on clinically realistic X-rays, respectively. The pose estimation accuracy of this method was shown to be [Formula: see text] and [Formula: see text] on clinically realistic X-rays. CONCLUSIONS: The proposed system offers an accurate and fully automatic pedicle screw segmentation and pose assessment framework. Such a system can help to provide an intraoperative pedicle screw insertion assessment protocol with minimal interference with the existing surgical routines.
PURPOSE: Pedicle screw fixation is a challenging procedure with a concerning rates of reoperation. After insertion of the screws is completed, the most common intraoperative verification approach is to acquire anterior-posterior and lateral radiographic images, based on which the surgeons try to visually assess the correctness of insertion. Given the limited accuracy of the existing verification techniques, we identified the need for an accurate and automated pedicle screw assessment system that can verify the screw insertion intraoperatively. For doing so, this paper offers a framework for automatic segmentation and pose estimation of pedicle screws based on deep learning principles. METHODS: Segmentation of pedicle screw X-ray projections was performed by a convolutional neural network. The network could isolate the input X-rays into three classes: screw head, screw shaft and background. Once all the screw shafts were segmented, knowledge about the spatial configuration of the acquired biplanar X-rays was used to identify the correspondence between the projections. Pose estimation was then performed to estimate the 6 degree-of-freedom pose of each screw. The performance of the proposed pose estimation method was tested on a porcine specimen. RESULTS: The developed machine learning framework was capable of segmenting the screw shafts with 93% and 83% accuracy when tested on synthetic X-rays and on clinically realistic X-rays, respectively. The pose estimation accuracy of this method was shown to be [Formula: see text] and [Formula: see text] on clinically realistic X-rays. CONCLUSIONS: The proposed system offers an accurate and fully automatic pedicle screw segmentation and pose assessment framework. Such a system can help to provide an intraoperative pedicle screw insertion assessment protocol with minimal interference with the existing surgical routines.
Authors: Theodore J Choma; Francis Denis; John E Lonstein; Joseph H Perra; James D Schwender; Timothy A Garvey; William J Mullin Journal: J Spinal Disord Tech Date: 2006-12
Authors: Ioannis D Gelalis; Nikolaos K Paschos; Emilios E Pakos; Angelos N Politis; Christina M Arnaoutoglou; Athanasios C Karageorgos; Avraam Ploumis; Theodoros A Xenakis Journal: Eur Spine J Date: 2011-09-07 Impact factor: 3.134
Authors: A Uneri; T De Silva; J Goerres; M W Jacobson; M D Ketcha; S Reaungamornrat; G Kleinszig; S Vogt; A J Khanna; G M Osgood; J-P Wolinsky; J H Siewerdsen Journal: Phys Med Biol Date: 2017-02-24 Impact factor: 3.609
Authors: Y Otake; S Schafer; J W Stayman; W Zbijewski; G Kleinszig; R Graumann; A J Khanna; J H Siewerdsen Journal: Phys Med Biol Date: 2012-08-03 Impact factor: 3.609
Authors: A Uneri; X Zhang; T Yi; J W Stayman; P A Helm; G M Osgood; N Theodore; J H Siewerdsen Journal: Phys Med Biol Date: 2019-08-21 Impact factor: 3.609
Authors: Alexander L Hornung; Christopher M Hornung; G Michael Mallow; J Nicolás Barajas; Augustus Rush; Arash J Sayari; Fabio Galbusera; Hans-Joachim Wilke; Matthew Colman; Frank M Phillips; Howard S An; Dino Samartzis Journal: Eur Spine J Date: 2022-03-27 Impact factor: 2.721
Authors: Fabio Carrillo; Hooman Esfandiari; Sandro Müller; Marco von Atzigen; Aidana Massalimova; Daniel Suter; Christoph J Laux; José M Spirig; Mazda Farshad; Philipp Fürnstahl Journal: Front Surg Date: 2022-01-25