System and method for constructing a statistical shape model

Patent metadata

Field	Value
Publication number	US-2016267352-A1
Application number	US-201615159541-A
Country	US
Kind code	A1
Filing date	May 19, 2016
Priority date	Nov 22, 2013
Publication date	Sep 15, 2016
Grant date	—

Abstract

Systems and methods are provided for constructing a statistical shape model from a set of training shapes. In one embodiment, two shapes in the training set can be parameterized to a common base domain. Correspondence between the shapes can be evaluated using shape-specific data, such as, for the case of anatomical shapes, anatomical curves and/or anatomical landmarks. In evaluating correspondence, the shape-specific data about the second shape can be mapped to the shape-specific data about the first shape, and the mapping can be optimized based at least in part on a deformation energy of the mapping.

First claim

What is claimed is:

1 . A system for constructing a statistical shape model from a set of training shapes, the system comprising:
a database configured to store a set of training shape images; an image processing module configured to parameterize a first shape and a second shape in the set of training shapes to a common base domain; and an analysis module configured to evaluate correspondence between the first and second shapes using shape-specific data about the first shape and shape-specific data about the second shape, wherein evaluating correspondence comprises mapping the shape-specific data about the second shape to the shape-specific data about the first shape, and optimizing the mapping based at least in part on a deformation energy of the mapping.

2 . The system of claim 1 , wherein the common base domain is spherical.

3 . The system of claim 2 , wherein evaluating correspondence comprises defining a diffeomorphism.

4 . The system of claim 3 , wherein the shape-specific data include anatomical information.

5 . The system of claim 4 , wherein the shape-specific data include curves.

6 . The system of claim 5 , wherein the curves are closed curves.

7 . The system of claim 5 , wherein the shape-specific data include points.

8 . The system of claim 5 , wherein the shape-specific data include curves and points.

9 . The system of claim 1 , wherein:
the image processing module is further configured to parameterize a third shape in the set of training shapes to the common base domain; and the analysis module is further configured to evaluate correspondence between the first and third shapes using shape-specific data about the first shape and shape-specific data about the third shape, wherein evaluating correspondence comprises mapping the shape-specific data about the third shape to the shape-specific data about the first shape, and optimizing the mapping based at least in part on a deformation energy of the mapping.

10 . A computer implemented method of constructing a statistical shape model from a set of training shapes, the method comprising:
parameterizing a first shape and a second shape in the set of training shapes to a common base domain; and evaluating correspondence between the first and second shapes using shape-specific data about the first shape and shape-specific data about the second shape, wherein evaluating correspondence comprises
mapping the shape-specific data about the second shape to the shape-specific data about the first shape, and
optimizing the mapping based at least in part on a deformation energy of the mapping.

11 . The computer implemented method of claim 10 , wherein mapping the shape-specific data comprises defining a diffeomorphism.

12 . The computer implemented method of claim 11 , wherein the common base domain is spherical.

13 . The computer implemented method of claim 12 , wherein the shape-specific data include anatomical information.

14 . The computer implemented method of claim 13 , wherein the shape-specific data include curves.

15 . The computer implemented method of claim 14 , wherein optimizing the mapping is based at least in part on points sampled from each curve.

16 . The computer implemented method of claim 14 , wherein the curves are closed curves.

17 . The computer implemented method of claim 14 , wherein the shape-specific data include points.

18 . The computer implemented method of claim 13 , wherein the shape-specific data include curves and points.

19 . The computer implemented method of claim 10 , further comprising repeating the parameterizing and evaluating steps for the first shape and a third shape in the set of training shapes.

20 . A computer readable medium comprising computer executable instructions stored thereon which when executed by a processor cause a computer to perform a method of constructing a statistical shape model from a set of training shapes, the method comprising:
parameterizing first and second shapes in the set of training shapes to a common base domain; and evaluating correspondence between the first and second shapes using shape-specific data about the first shape and shape-specific data about the second shape, wherein evaluating correspondence comprises mapping the shape-specific data about the second shape to the shape-specific data about the first shape, and optimizing the mapping based at least in part on a deformation energy of the mapping.

Assignees

• Mat Nv

Inventors

• Van Deun Joris

Classifications

• G06V10/772 Primary

  Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries · CPC title

• G06F18/28

  Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries · CPC title

• G06V10/754

  involving a deformation of the sample pattern or of the reference pattern; Elastic matching · CPC title

• G06K9/48

  Physics · mapped topic

• G06K2009/487

  Physics · mapped topic