A stochastic large deformation model for computational anatomy

TY - GEN

T1 - A stochastic large deformation model for computational anatomy

AU - Arnaudon, Alexis

AU - Holm, Darryl D.

AU - Pai, Akshay Sadananda Uppinakudru

AU - Sommer, Stefan Horst

N1 - Conference code: 25

PY - 2017

Y1 - 2017

N2 - In the study of shapes of human organs using computational anatomy, variations are found to arise from inter-subject anatomical differences, disease-specific effects, and measurement noise. This paper introduces a stochastic model for incorporating random variations into the Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework. By accounting for randomness in a particular setup which is crafted to fit the geometrical properties of LDDMM, we formulate the template estimation problem for landmarks with noise and give two methods for efficiently estimating the parameters of the noise fields from a prescribed data set. One method directly approximates the time evolution of the variance of each landmark by a finite set of differential equations, and the other is based on an Expectation-Maximisation algorithm. In the second method, the evaluation of the data likelihood is achieved without registering the landmarks, by applying bridge sampling using a stochastically perturbed version of the large deformation gradient flow algorithm. The method and the estimation algorithms are experimentally validated on synthetic examples and shape data of human corpora callosa.

AB - In the study of shapes of human organs using computational anatomy, variations are found to arise from inter-subject anatomical differences, disease-specific effects, and measurement noise. This paper introduces a stochastic model for incorporating random variations into the Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework. By accounting for randomness in a particular setup which is crafted to fit the geometrical properties of LDDMM, we formulate the template estimation problem for landmarks with noise and give two methods for efficiently estimating the parameters of the noise fields from a prescribed data set. One method directly approximates the time evolution of the variance of each landmark by a finite set of differential equations, and the other is based on an Expectation-Maximisation algorithm. In the second method, the evaluation of the data likelihood is achieved without registering the landmarks, by applying bridge sampling using a stochastically perturbed version of the large deformation gradient flow algorithm. The method and the estimation algorithms are experimentally validated on synthetic examples and shape data of human corpora callosa.

KW - Computational anatomy

KW - Large deformations

KW - LDDMM

KW - Stochastic processes

UR - http://www.scopus.com/inward/record.url?scp=85020552205&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-59050-9_45

DO - 10.1007/978-3-319-59050-9_45

M3 - Article in proceedings

AN - SCOPUS:85020552205

SN - 978-3-319-59049-3

T3 - Lecture notes in computer science

SP - 571

EP - 582

BT - Information Processing in Medical Imaging

PB - Springer

T2 - 25th International Conference on Information Processing in Medical Imaging

Y2 - 25 June 2017 through 30 June 2017

ER -