Development and evaluation of statistical shape modeling for principal inner organs on torso CT images
- 267 Downloads
The shapes of the inner organs are important information for medical image analysis. Statistical shape modeling provides a way of quantifying and measuring shape variations of the inner organs in different patients. In this study, we developed a universal scheme that can be used for building the statistical shape models for different inner organs efficiently. This scheme combines the traditional point distribution modeling with a group-wise optimization method based on a measure called minimum description length to provide a practical means for 3D organ shape modeling. In experiments, the proposed scheme was applied to the building of five statistical shape models for hearts, livers, spleens, and right and left kidneys by use of 50 cases of 3D torso CT images. The performance of these models was evaluated by three measures: model compactness, model generalization, and model specificity. The experimental results showed that the constructed shape models have good “compactness” and satisfied the “generalization” performance for different organ shape representations; however, the “specificity” of these models should be improved in the future.
KeywordsCT images 3D organ shapes Statistical shape model Point distribution model Minimum description length
The authors thank members of the Fujita Laboratory. This research work was funded in part by a Grant-in-Aid for Scientific Research on Innovative Areas, and in part by a Grant-in-Aid for Scientific Research, MEXT, Japan.
Conflict of interest
The authors declare that they have no conflict of interest.
- 1.Frumin M, Golland P, Kikinis R, Hirayasu Y, Salisbury DF, Hennen J, Dickey CC, Anderson M, Jolesz FA, Grimson WE, McCarley RW, Shenton ME. Shape differences in the corpus callosum in first-episode schizophrenia and first-episode psychotic affective disorder. Am J Psychiatry. 2002;159:866–8.PubMedCentralPubMedCrossRefGoogle Scholar
- 4.Berks M, Caulkin S, Rahim R, Boggis C, Astley S. Statistical appearance models of mammographic masses. Proc IWDM. 2008;2008:401–8.Google Scholar
- 8.Yamaguchi S, Zhou X, Xu R, Hara T, Yokoyama R, Kanematsu M, Hoshi H, Kido S, Fujita H. Construction of statistical shape models of organs in torso CT scans using MDL method. Proc Int Forum Med Imaging Asia. 2012;2012:2–33.Google Scholar
- 9.Xu R, Zhou X, Hirano Y, Tachibana R, Hara T, Kido S, Fujita H. Evaluation of group-wise based methods for statistical shape models construction. Japanese Society of Medical Imaging Technology 2011. 2011; CD-ROM, OP1-7.Google Scholar
- 10.Yamagichi S, Hayashi T, Zhou X, Hara T, Yokoyama R, Kanematsu M, Hoshi H, Fujita H. An interactive method for organ region segmentation in X-ray CT images, Japanese Society of Medical Imaging Technology 2011. 2011; CD-ROM, OP1-8.Google Scholar
- 12.The Visualization Toolkit (VTK). http://www.vtk.org. Accessed 25 Feb 2014.
- 14.Heimann T, Wolf I, Williams T, Meinzer H. 3D active shape models using gradient descent optimization of description length. Proc IPMI’05. 2005; 3565:566–77.Google Scholar
- 15.Xu R, Zhou X, Hirano Y, Tachibana R, Hara T, Kido S, Fujita H. Particle-system based adaptive sampling on spherical parameter space to improve the MDL method for construction of statistical shape models. Comput Math Methods Med. 2013;2013:1–9, Article ID 196259.Google Scholar