Functional data analysis using a topological summary statistic: an application to brain cancer imagingMS16

We introduce a novel summary statistic derived from topological data analysis, the smooth Euler characteristic transform (SECT), with well-defined inner-product structure that can be used in a wide range of functional and nonparametric modeling approaches. We show that the topological quantification of tumor MRIs are better predictors of clinical outcomes in glioblastoma multiforme (GBM) patients. SECT features alone explain more of the variance in patient survival than gene expression, volumetric, and morphometric features.

This presentation is part of Minisymposium “MS16 - Topological Image Analysis: Methods, Algorithms, Applications (3 parts)
organized by: Patrizio Frosini (University of Bologna) , Massimo Ferri (University of Bologna) , Claudia Landi (University of Modena and Reggio Emilia) .

Anthea Monod (Columbia University)
Andrew X. Chen (Department of Systems Biology at Columbia University)
bayesian methods, image representation, integral equations for image analysis