Perceiving Systems, Computer Vision

Learning a statistical full spine model from partial observations

2020

Conference Paper

ps


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)

Author(s): Di Meng and Marilyn Keller and Edmond Boyer and Michael Black and Sergi Pujades
Book Title: Shape in Medical Imaging
Pages: 122--133
Year: 2020
Month: October

Series: Lecture Notes in Computer Science, 12474
Editors: Reuter, Martin and Wachinger, Christian and Lombaert, Herv{\'e} and Paniagua, Beatriz and Goksel, Orcun and Rekik, Islem
Publisher: Springer

Department(s): Perceiving Systems
Research Project(s): Bodies in Medicine
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Workshop

DOI: 10.1007/978-3-030-61056-2_10
Event Name: International Workshop on Shape in Medical Imaging (ShapeMI 2020)
Event Place: Lima

Address: Cham
ISBN: 978-3-030-61056-2
State: Published

Links: Gitlab Code
Attachments: PDF

BibTex

@inproceedings{spine_model,
  title = {Learning a statistical full spine model from partial observations},
  author = {Meng, Di and Keller, Marilyn and Boyer, Edmond and Black, Michael and Pujades, Sergi},
  booktitle = {Shape in Medical Imaging},
  pages = {122--133},
  series = {Lecture Notes in Computer Science, 12474},
  editors = {Reuter, Martin and Wachinger, Christian and Lombaert, Herv{\'e} and Paniagua, Beatriz and Goksel, Orcun and Rekik, Islem},
  publisher = {Springer},
  address = {Cham},
  month = oct,
  year = {2020},
  doi = {10.1007/978-3-030-61056-2_10},
  month_numeric = {10}
}