Interior Object Geometry via Fitted Frames
Authors:
Preprint
Abstract
We describe a representation targeted for anatomic objects which is designed to enable strong locational correspondence within object populations and thus to provide powerful object statistics. The method generates fitted frames on the boundary and in the interior of objects and produces alignment-free geometric features from them. It accomplishes this by understanding an object as the diffeomorphic deformation of an ellipsoid and using a skeletal representation fitted throughout the deformation to produce a model of the target object, where the object is provided initially in the form of a boundary mesh. Via classification performance on hippocampi shape between individuals with a disorder vs. others, we compare our method to two state-of-the-art methods for producing object representations that are intended to capture geometric correspondence across a population of objects and to yield geometric features useful for statistics, and we show improved classification performance by this new representation, which we call the evolutionary s-rep. The geometric features that are derived from each of the representations, especially via fitted frames, is discussed.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- SlicerSALT: From Medical Images to Quantitative Insights of Anatomy2023
- Skeletons, Object Shape, StatisticsFrontiers in Computer Science, 2022
- Fitting unbranching skeletal structures to objectsMedical Image Analysis, 2021
- SlicerSALT: Shape AnaLysis Toolbox2018
- Statistical Shape Analysis of Large Datasets Based on Diffeomorphic Iterative CentroidsFrontiers in Neuroscience, 2018
- Fast Diffeomorphic Image Registration via Fourier-Approximated Lie AlgebrasInternational Journal of Computer Vision, 2018
- Morphometry of anatomical shape complexes with dense deformations and sparse parametersNeuroImage, 2014
- Geometry and Medial Structure2008
- SMOTE: Synthetic Minority Over-sampling TechniqueJournal of Artificial Intelligence Research, 2002
- Statistical models of appearance for medical image analysis and computer vision2001