Skip to main content
placeholder image

Statistical Shape Model Generation Using Diffeomorphic Surface Registration

Conference Paper


Abstract


  • Statistical shape modelling is an efficient and robust method for medical image segmentation in computer-aided diagnosis. The key step in building a statistical shape model is to find corresponding landmarks in each instance of a training set. In this paper, a novel landmark correspondence estimation method that uses edge collapse surface simplification and the sphere registration is proposed. All the landmarks are selected and transformed by spherical conformal mapping from the instances of the training set and the associated correspondence are automatically found on the spheres. We applied our method on 21 cases of 3-D right lung shapes. The results of image segmentation experiment indicate that our method has a positive influence on the accuracy of segmentation result.

Authors


  •   Wu, Jiaqi (external author)
  •   Li, Guangxu (external author)
  •   Lu, Huimin (external author)
  •   Kim, Hyoung (external author)
  •   Ogunbona, Philip O.

Publication Date


  • 2017

Citation


  • Wu, J., Li, G., Lu, H., Kim, H. & Ogunbona, P. O. (2017). Statistical Shape Model Generation Using Diffeomorphic Surface Registration. ICBIP 2017: Proceedings of the 2nd International Conference on Biomedical Signal and Image Processing (pp. 37-41). New York, United States: ACM.

Scopus Eid


  • 2-s2.0-85052679703

Start Page


  • 37

End Page


  • 41

Place Of Publication


  • New York, United States

Abstract


  • Statistical shape modelling is an efficient and robust method for medical image segmentation in computer-aided diagnosis. The key step in building a statistical shape model is to find corresponding landmarks in each instance of a training set. In this paper, a novel landmark correspondence estimation method that uses edge collapse surface simplification and the sphere registration is proposed. All the landmarks are selected and transformed by spherical conformal mapping from the instances of the training set and the associated correspondence are automatically found on the spheres. We applied our method on 21 cases of 3-D right lung shapes. The results of image segmentation experiment indicate that our method has a positive influence on the accuracy of segmentation result.

Authors


  •   Wu, Jiaqi (external author)
  •   Li, Guangxu (external author)
  •   Lu, Huimin (external author)
  •   Kim, Hyoung (external author)
  •   Ogunbona, Philip O.

Publication Date


  • 2017

Citation


  • Wu, J., Li, G., Lu, H., Kim, H. & Ogunbona, P. O. (2017). Statistical Shape Model Generation Using Diffeomorphic Surface Registration. ICBIP 2017: Proceedings of the 2nd International Conference on Biomedical Signal and Image Processing (pp. 37-41). New York, United States: ACM.

Scopus Eid


  • 2-s2.0-85052679703

Start Page


  • 37

End Page


  • 41

Place Of Publication


  • New York, United States