Vol 2, No 2 (2011)

Cover Page


Functional data analysis of three-dimensional cerebral vascular geometries. The widespread diffusion in science and medicine of sophisticated technological instruments, capable of recording high dimensional signals, calls for new methods of data analysis. In particular, some data exhibit a functional nature, i.e., they may be represented via suitable curves and surfaces. The analysis of this type of data poses new and fascinating problems to modern statistics. An instance of functional data, obtained from three-dimensional cerebral angiographic images, was analyzed within the AneuRisk Project. This scientific endeavor aimed at investigating the role of vessel morphology and hemodynamics on the pathogenesis of cerebral aneurysms. The cover image is a detail of a figure displaying the estimated first derivatives of Internal Carotid Arteries centerlines of 65 patients; for complete figure see Sangalli, Secchi, Vantini and Vitelli, CAIM, vol 1., n. 1., doi: 10.1685/2010CAIM486. The paper presented a technique for efficiently classifying multidimensional curves, even in presence of curve misalignment. Data misalignment, apparent in the image, is a peculiar issue to functional data, and specifically to data coming from medical imaging corresponding to different patients.

Image Credit: L.M. Sangalli, P. Secchi, S. Vantini; Politecnico di Milano and V. Vitelli; Ecole Centrale Paris e Supélec.

Creative Commons License

This work is licensed under a Creative Commons Attribution NonCommercial NoDerivs 3.0 License.

Communications in Applied and Industrial Mathematics
ISSN: 2038-0909