Statistical Shape Modeling Using Partial Least Squares: Application to the Assessment of Myocardial Infarction
Statistical shape modeling (SSM) is a widely popular framework in cardiac image analysis, especially for image segmentation and computer-aided diagnosis. However, the conventional PCA-based models produce new axes of variation which are statistically motivated but thus are not necessarily clinically meaningful. In this paper, we propose an alternative method for statistical decomposition of the shape variability based on partial least squares (PLS). With this method, the model construction is achieved such that it is constrained by the specific clinical question of interest (e.g., estimation of disease state). To achieve this, instead of deriving modes of variation in the directions of maximal variation as in PCA, PLS searches for new axes of variation that correlate most with some output clinical response variables such as diagnostic labels, leading to a decomposition that is anatomically and clinically more meaningful. The validation carried out with 200 cases from the Cardiac Atlas Project database as part of the MICCAI 2015 challenge on SSM, including healthy and infarcted left ventricles, shows the strength of the proposed PLS-based statistical shape model, with 98 % prediction accuracy.
KeywordsPartial Less Square Independent Component Analysis Partial Less Square Discriminant Analysis Classification Fusion Infarcted Heart
- 2.Hoogendoorn, C., Pashaei, A., Sebastian, R., Sukno, F.M., Cámara, O., Frangi, A.F.: Sensitivity analysis of mesh warping and subsampling strategies for generating large scale electrophysiological simulation data. In: Metaxas, D.N., Axel, L. (eds.) FIMH 2011. LNCS, vol. 6666, pp. 418–426. Springer, Heidelberg (2011)CrossRefGoogle Scholar
- 5.Sjoestrand, K., Stegmann, M.B., Larsen, R.: Sparse principal component analysis in medical shape modeling. In: SPIE Medical Imaging: Image Processing (2006)Google Scholar
- 9.Suinesiaputra, A., Frangi, A.F., Kaandorp, T., Lamb, H.J., Bax, J.J., Reiber, J., Lelieveldt, B.: Automated detection of regional wall motion abnormalities based on a statistical model applied to multislice short-axis cardiac MR images. IEEE Trans. Med. Imaging 28(4), 595–607 (2009)CrossRefGoogle Scholar
- 17.Abdi, H.: Partial least squares regression (PLS-regression), Thousand Oaks, CA, Sage, pp. 792–795 (2003)Google Scholar
- 18.Pérez-Enciso, M., Tenenhaus, M.: Prediction of clinical outcome with microarray data: a partial least squares discriminant analysis (PLS-DA) approach. Hum. Genet. 112(5–6), 581–592 (2003)Google Scholar