Learning a Statistical Full Spine Model from Partial Observations

The study of the morphology of the human spine has attracted research attention for its many potential applications, such as image segmentation, bio-mechanics or pathology detection. However, as of today there is no publicly available statistical model of the 3D surface of the full spine. This is mainly due to the lack of openly available 3D data where the full spine is imaged and segmented. In this paper we propose to learn a statistical surface model of the full-spine (7 cervical, 12 thoracic and 5 lumbar vertebrae) from partial and incomplete views of the spine. In order to deal with the partial observations we use probabilistic principal component analysis (PPCA) to learn a surface shape model of the full spine. Quantitative evaluation demonstrates that the obtained model faithfully captures the shape of the population in a low dimensional space and generalizes to left out data. Furthermore, we show that the model faithfully captures the global correlations among the vertebrae shape. Given a partial observation of the spine, i.e. a few vertebrae, the model can predict the shape of unseen vertebrae with a mean error under 3 mm. The full-spine statistical model is trained on the VerSe 2019 public dataset and is publicly made available to the community for non-commercial purposes. (https://gitlab.inria.fr/spine/spine_model)

[1]  Yiqiang Zhan,et al.  Robust MR Spine Detection Using Hierarchical Learning and Local Articulated Model , 2012, MICCAI.

[2]  Matías N. Bossa,et al.  MULTI-OBJECT STATISTICAL POSE+SHAPE MODELS , 2007, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[3]  Michael J. Black,et al.  Detailed Full-Body Reconstructions of Moving People from Monocular RGB-D Sequences , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[4]  Jan S. Kirschke,et al.  VerSe: A Vertebrae Labelling and Segmentation Benchmark , 2020, ArXiv.

[5]  B. Michael Kelm,et al.  Fast and robust 3D vertebra segmentation using statistical shape models , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[6]  Michael E. Tipping,et al.  Probabilistic Principal Component Analysis , 1999 .

[7]  Joachim Selbig,et al.  pcaMethods - a bioconductor package providing PCA methods for incomplete data , 2007, Bioinform..

[8]  Stefan Wesarg,et al.  3D Active Shape Model Segmentation with Nonlinear Shape Priors , 2011, MICCAI.

[9]  Bostjan Likar,et al.  A Framework for Automated Spine and Vertebrae Interpolation-Based Detection and Model-Based Segmentation , 2015, IEEE Transactions on Medical Imaging.

[10]  Shuo Li,et al.  Multi-Modality Vertebra Recognition in Arbitrary Views Using 3D Deformable Hierarchical Model , 2015, IEEE Transactions on Medical Imaging.

[11]  Thomas Schmitz-Rode,et al.  Electromagnetic tracking for CT-guided spine interventions: phantom, ex-vivo and in-vivo results , 2009, European Radiology.

[12]  K. S. Arun,et al.  Least-Squares Fitting of Two 3-D Point Sets , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Estanislao Arana,et al.  Automatic segmentation of the spine by means of a probabilistic atlas with a special focus on ribs suppression , 2017, Medical physics.

[14]  Hans-Peter Meinzer,et al.  Statistical shape models for 3D medical image segmentation: A review , 2009, Medical Image Anal..

[15]  Ben Glocker,et al.  Automatic Localization and Identification of Vertebrae in Arbitrary Field-of-View CT Scans , 2012, MICCAI.

[16]  Dorin Comaniciu,et al.  Hierarchical parsing and semantic navigation of full body CT data , 2009, Medical Imaging.

[17]  Sebastian P. M. Dries,et al.  Spine Detection and Labeling Using a Parts-Based Graphical Model , 2007, IPMI.

[18]  Cristian Lorenz,et al.  Automated model-based vertebra detection, identification, and segmentation in CT images , 2009, Medical Image Anal..

[19]  Purang Abolmaesumi,et al.  Lumbar Spine Segmentation Using a Statistical Multi-Vertebrae Anatomical Shape+Pose Model , 2013, IEEE Transactions on Medical Imaging.

[20]  J Q Campbell,et al.  Automated finite element modeling of the lumbar spine: Using a statistical shape model to generate a virtual population of models. , 2016, Journal of biomechanics.

[21]  Alejandro F. Frangi,et al.  Statistical Interspace Models (SIMs): Application to Robust 3D Spine Segmentation , 2015, IEEE Transactions on Medical Imaging.

[22]  Paul J Rullkoetter,et al.  Statistical shape modeling characterizes three-dimensional shape and alignment variability in the lumbar spine. , 2018, Journal of biomechanics.

[23]  Matthew Turk,et al.  A Morphable Model For The Synthesis Of 3D Faces , 1999, SIGGRAPH.

[24]  Nikos Paragios,et al.  Automatic inference of articulated spine models in CT images using high-order Markov Random Fields , 2011, Medical Image Anal..

[25]  Thomas Vetter,et al.  Building Shape Models from Lousy Data , 2009, MICCAI.