Weighted Functional Boxplot with Application to Statistical Atlas Construction
Atlas-building from population data is widely used in medical imaging. However, the emphasis of atlas-building approaches is typically to compute a mean / median shape or image based on population data. In this work, we focus on the statistical characterization of the population data, once spatial alignment has been achieved. We introduce and propose the use of the weighted functional boxplot. This allows the generalization of concepts such as the median, percentiles, or outliers to spaces where the data objects are functions, shapes, or images, and allows spatio-temporal atlas-building based on kernel regression. In our experiments, we demonstrate the utility of the approach to construct statistical atlases for pediatric upper airways and corpora callosa revealing their growth patterns. Furthermore, we show how such atlas information can be used to assess the effect of airway surgery in children.
KeywordsCorpus Callosum Kernel Regression Subglottic Stenosis Spatial Alignment Airway Surgery
Unable to display preview. Download preview PDF.
- 3.Fletcher, P., Venkatasubramanian, S., Joshi, S.: The geometric median on Riemannian manifolds with application to robust atlas estimation. NeuroImage 45(suppl. 1), S143–S152 (2009)Google Scholar
- 4.Fletcher, T.: Geodesic regression on Riemannian manifolds. In: 3rd MICCAI Workshop on Mathematical Foundations of Computational Anatomy, pp. 75–86 (2011)Google Scholar
- 6.Hong, Y., Niethammer, M., Andruejol, J., Kimbel, J., Pitkin, E., Superfine, R., Davis, S., Zdanski, C., Davis, B.: A pediatric airway atlas and its application in subglottic stenosis. In: International Symposium on Biomedical Imaging: From Nano to Macro, pp. 1194–1197 (2013)Google Scholar
- 7.Joshi, S., Davis, B., Jomier, M.: Unbiased diffeomorphic atlas construction for computational anatomy. Neuroimage 23(suppl. 1), S151–S160 (2004)Google Scholar
- 11.Ramsay, J., Silverman, B.: Functional Data Analysis. Springer (2005)Google Scholar