Abstract
Osteoporosis is an important disorder that is underdiagnosed. We aim to develop a robust automated CT-based vertebral label-independent approach for localization and instance segmentation of the vertebral bodies (VB) which permits assessment of bone mineral density (BMD) and generates VB center data for subsequent fracture assessment tools. We utilize an nnU-Net adapted for segmentation of the surface vs interior of the VBs vs background. This allows delineation of individual VBs, segmentation of the cortical surface encompassing the cancellous bone for BMD assessment, and localization of VB centers. After training the performance was evaluated on an external test data set. Our approach detected 97.5% of the vertebral bodies showing robustness to spinal degenerations like osteophytes. VB centerswere determined with residual errors of 3.5±0.9 mm, sufficiently accurate as input for our fracture detection tool. BMD evaluated in Hounsfield Units (HU) correlated with ground truth values with r2 = 0.96, RMS error = 11.3 HU, sufficiently accurate for automated diagnosis and CT-based opportunistic screening for osteoporosis.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Willers C, Norton N, Harvey NC, Jacobson T, Johansson H, LorentzonMet al. Osteoporosis in Europe: a compendium of country-specific reports. Arch Osteoporos. 2022;17(1):23.
Mitchell RM, Jewell P, Javaid MK, et al. Reporting of vertebral fragility fractures: can radiologists help reduce the number of hip fractures? Arch Osteoporos. 2017;12(1):71.
Aggarwal V, Maslen C,Abel RL, Bhattacharya P, Bromiley PA, ClarkEMet al. Opportunistic diagnosis of osteoporosis, fragile bone strength and vertebral fractures from routine CT scans; a review. Ther Adv Musculoskelet Dis. 2021;13:1–19.
Smets J, Shevroja E, Hügle T, Leslie WD, Hans D. Machine learning solutions for osteoporosis— a review. J Bone Miner Res. 2021;36(5):833–51.
Sekuboyina A, Husseini ME, Bayat A, et al. VerSe: a vertebrae labelling and segmentation benchmark for multi-detector CT images. Med Image Anal. 2021;73:102166.
Payer C, Štern D, Bischof H, Urschler M. Integrating spatial configuration into heatmap regression based CNNs for landmark localization. Med Image Anal. 2019;54:207–19.
Mader AO, Lorenz C, Bergtholdt M, et al. Detection and localization of spatially correlated point landmarks in medical images using an automatically learned conditional random field. Comput Vis Image Underst. 2018;176-177:45–53.
Elton D, Sandfort V, Pickhardt PJ, Summers RM. Accurately identifying vertebral levels in large datasets. Medical Imaging 2020: Computer-Aided Diagnosis. SPIE, 2020.
Lessmann N, Ginneken B van, Jong PA de, et al. Iterative fully convolutional neural networks for automatic vertebra segmentation and identification. Med Image Anal. 2019;53:142–55.
Yilmaz EB, Buerger C, Fricke T, et al. Automated deep learning-based detection of osteoporotic fractures in CT images. Mach Learn Med Imaging. Vol. 12966. 2021:376–85.
Genant HK, Wu CY, Kuijk C van, Nevitt MC. Vertebral fracture assessment using a semiquantitative technique. J Bone Miner Res. 1993;8(9):1137–48.
Isensee F, Petersen J, Klein A, Zimmerer D, Jaeger PF, Kohl S et al. nnU-Net: self-adapting framework for U-Net-based medical image segmentation. Nat Methods. 2021;18:203–11.
Glüer CC, Krause M, Museyko O, et al. New horizons for the in vivo assessment of major aspects of bone quality microstructure and material properties assessed by quantitative computed tomography and quantitative ultrasound methods. Osteologie. 2013;22:223–33.
Glocker B, Zikic D, Konukoglu E, Haynor DR, Criminisi A. Vertebrae localization in pathological spine CT via dense classification from sparse annotations. Med Image Comput Comput Assist Interv. Springer, 2013:262–70.
Hempe H, Yilmaz EB, Meyer C, et al. Opportunistic CT screening for degenerative deformities and osteoporotic fractures with 3D DeepLab. Med Imag: Image Proc. Vol. 12032. SPIE, 2022:8.
Mastmeyer A, Engelke K, Fuchs C, Kalender WA. A hierarchical 3D segmentation method and the definition of vertebral body coordinate systems for QCT of the lumbar spine. Med Image Anal. 2006;10(4):560–77.
Engelke K, Adams JE, Armbrecht G, Augat P, Bogado CE, Bouxsein ML et al. Clinical use of quantitative computed tomography and peripheral quantitative computed tomography in the management of osteoporosis in adults. J Clin Densitom. 2008;11(1):123–62.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Der/die Autor(en), exklusiv lizenziert an Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature
About this paper
Cite this paper
Krekiehn, N.R., Yilmaz, E.B., Kruse, H.C., Meyer, C., Glüer, C.C. (2023). Automated Deep-learning-based Vertebral Body Localization and Instance Segmentation for Osteoporosis Assessment using CT. In: Deserno, T.M., Handels, H., Maier, A., Maier-Hein, K., Palm, C., Tolxdorff, T. (eds) Bildverarbeitung für die Medizin 2023. BVM 2023. Informatik aktuell. Springer Vieweg, Wiesbaden. https://doi.org/10.1007/978-3-658-41657-7_37
Download citation
DOI: https://doi.org/10.1007/978-3-658-41657-7_37
Published:
Publisher Name: Springer Vieweg, Wiesbaden
Print ISBN: 978-3-658-41656-0
Online ISBN: 978-3-658-41657-7
eBook Packages: Computer Science and Engineering (German Language)