Fabio Galbusera1, Frank Niemeyer2, Hans-Joachim Wilke2, Tito Bassani3, Gloria Casaroli3, Carla Anania4, Francesco Costa4, Marco Brayda-Bruno5, Luca Maria Sconfienza6,7. 1. Laboratory of Biological Structures Mechanics, IRCCS Istituto Ortopedico Galeazzi, Via Galeazzi 4, 20161, Milan, Italy. fabio.galbusera@grupposandonato.it. 2. Institute of Orthopedic Research and Biomechanics, Center for Trauma Research Ulm, Ulm University, Ulm, Germany. 3. Laboratory of Biological Structures Mechanics, IRCCS Istituto Ortopedico Galeazzi, Via Galeazzi 4, 20161, Milan, Italy. 4. Department of Neurosurgery, Humanitas Research Hospital, Rozzano, Italy. 5. Department of Spine Surgery III, IRCCS Istituto Ortopedico Galeazzi, Milan, Italy. 6. Unit of Diagnostic and Interventional Radiology, IRCCS Istituto Ortopedico Galeazzi, Milan, Italy. 7. Department of Biomedical Sciences for Health, Università degli Studi di Milano, Milan, Italy.
Abstract
PURPOSE: We present an automated method for extracting anatomical parameters from biplanar radiographs of the spine, which is able to deal with a wide scenario of conditions, including sagittal and coronal deformities, degenerative phenomena as well as images acquired with different fields of view. METHODS: The location of 78 landmarks (end plate centers, hip joint centers, and margins of the S1 end plate) was extracted from three-dimensional reconstructions of 493 spines of patients suffering from various disorders, including adolescent idiopathic scoliosis, adult deformities, and spinal stenosis. A fully convolutional neural network featuring an additional differentiable spatial to numerical (DSNT) layer was trained to predict the location of each landmark. The values of some parameters (T4-T12 kyphosis, L1-L5 lordosis, Cobb angle of scoliosis, pelvic incidence, sacral slope, and pelvic tilt) were then calculated based on the landmarks' locations. A quantitative comparison between the predicted parameters and the ground truth was performed on a set of 50 patients. RESULTS: The spine shape predicted by the models was perceptually convincing in all cases. All predicted parameters were strongly correlated with the ground truth. However, the standard errors of the estimated parameters ranged from 2.7° (for the pelvic tilt) to 11.5° (for the L1-L5 lordosis). CONCLUSIONS: The proposed method is able to automatically determine the spine shape in biplanar radiographs and calculate anatomical and posture parameters in a wide scenario of clinical conditions with a very good visual performance, despite limitations highlighted by the statistical analysis of the results. These slides can be retrieved under Electronic Supplementary Material.
PURPOSE: We present an automated method for extracting anatomical parameters from biplanar radiographs of the spine, which is able to deal with a wide scenario of conditions, including sagittal and coronal deformities, degenerative phenomena as well as images acquired with different fields of view. METHODS: The location of 78 landmarks (end plate centers, hip joint centers, and margins of the S1 end plate) was extracted from three-dimensional reconstructions of 493 spines of patients suffering from various disorders, including adolescent idiopathic scoliosis, adult deformities, and spinal stenosis. A fully convolutional neural network featuring an additional differentiable spatial to numerical (DSNT) layer was trained to predict the location of each landmark. The values of some parameters (T4-T12 kyphosis, L1-L5 lordosis, Cobb angle of scoliosis, pelvic incidence, sacral slope, and pelvic tilt) were then calculated based on the landmarks' locations. A quantitative comparison between the predicted parameters and the ground truth was performed on a set of 50 patients. RESULTS: The spine shape predicted by the models was perceptually convincing in all cases. All predicted parameters were strongly correlated with the ground truth. However, the standard errors of the estimated parameters ranged from 2.7° (for the pelvic tilt) to 11.5° (for the L1-L5 lordosis). CONCLUSIONS: The proposed method is able to automatically determine the spine shape in biplanar radiographs and calculate anatomical and posture parameters in a wide scenario of clinical conditions with a very good visual performance, despite limitations highlighted by the statistical analysis of the results. These slides can be retrieved under Electronic Supplementary Material.
Authors: Wesley M Durand; Renaud Lafage; D Kojo Hamilton; Peter G Passias; Han Jo Kim; Themistocles Protopsaltis; Virginie Lafage; Justin S Smith; Christopher Shaffrey; Munish Gupta; Michael P Kelly; Eric O Klineberg; Frank Schwab; Jeffrey L Gum; Gregory Mundis; Robert Eastlack; Khaled Kebaish; Alex Soroceanu; Richard A Hostin; Doug Burton; Shay Bess; Christopher Ames; Robert A Hart; Alan H Daniels Journal: Eur Spine J Date: 2021-04-15 Impact factor: 3.134
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: Alexander L Hornung; Christopher M Hornung; G Michael Mallow; J Nicolas Barajas; Alejandro A Espinoza Orías; Fabio Galbusera; Hans-Joachim Wilke; Matthew Colman; Frank M Phillips; Howard S An; Dino Samartzis Journal: Eur Spine J Date: 2022-01-27 Impact factor: 2.721
Authors: Zongshan Hu; Claudio Vergari; Laurent Gajny; Zhen Liu; Tsz-Ping Lam; Zezhang Zhu; Yong Qiu; Gene C W Man; Kwong-Hang Yeung; Winnie C W Chu; Jack C Y Cheng; Wafa Skalli Journal: Quant Imaging Med Surg Date: 2021-07
Authors: Nils Christian Lehnen; Robert Haase; Jennifer Faber; Theodor Rüber; Hartmut Vatter; Alexander Radbruch; Frederic Carsten Schmeel Journal: Diagnostics (Basel) Date: 2021-05-19