Generating shape difference data between multiple imaging modalities

Patent metadata

Field	Value
Publication number	US-11830197-B2
Application number	US-202217840708-A
Country	US
Kind code	B2
Filing date	Jun 15, 2022
Priority date	Mar 9, 2017
Publication date	Nov 28, 2023
Grant date	Nov 28, 2023

Abstract

Systems and methods are provided for generating and using statistical data which is indicative of a difference in shape of a type of anatomical structure between images acquired by a first imaging modality and images acquired by a second imaging modality. This statistical data may then be used to modify a first segmentation of the anatomical structure which is obtained from an image acquired by the first imaging modality so as to predict the shape of the anatomical structure in the second imaging modality, or in general, to generate a second segmentation of the anatomical structure as it may appear in the second imaging modality based on the statistical data and the first segmentation.

First claim

The invention claimed is:

1. A system configured for generating statistical data for use in image segmentation, comprising: an image data interface configured to access a first set and a second set of images of a type of anatomical structure, wherein the first set of images is acquired by a first imaging modality and the second set of images is acquired by a second imaging modality; a memory comprising instruction data representing a set of instructions; a processor configured to communicate with the image data interface and the memory and to execute the set of instructions, wherein the set of instructions, when executed by the processor, cause the processor to: segment individual images of the first set of images to obtain a first set of segmentations of the type of anatomical structure; segment individual images of the second set of images to obtain a second set of segmentations of the type of anatomical structure; and based on the first set of segmentations and the second set of segmentations, generate shape difference data associated with the type of anatomical structure and the first and second imaging modalities.

2. The system according to claim 1 , wherein the first set of images and the second set of images comprise a set of image pairs, wherein each image pair is constituted by an image acquired by the first imaging modality and an image acquired by the second imaging modality, wherein both images of an image pair belong to a same patient.

3. The system according to claim 1 , wherein the set of instructions, when executed by the processor, cause the processor to generate the statistical data by performing a principle component analysis of the first set of segmentations and the second set of segmentations simultaneously.

4. The system according to claim 3 , wherein the set of instructions, when executed by the processor, cause the processor to generate the statistical data by:
computing a first mean shape of the type of anatomical structure from the first set of segmentations;
computing a second mean shape of the type of anatomical structure from the second set of segmentations;
constructing a matrix A for the principle component analysis from the differences between the first set of segmentations and the first mean shape and the differences between the second set of segmentations and the second mean shape;
generating the statistical data based on the first mean shape, the second mean shape and the Eigenvectors of the matrix AAt.

5. The system according to claim 3 , wherein the set of instructions, when executed by the processor, cause the processor to mutually register the first set of segmentations, to mutually register the second set of segmentations and to mutually register the first mean shape and the second mean shape before performing the principle component analysis.

6. The system according to claim 1 , wherein the set of instructions, when executed by the processor, cause the processor to generate at least one of: the first set of segmentations and the second set of segmentations using model-based segmentation.

7. A computer-implemented method for generating statistical data for use in image segmentation, comprising:
accessing a first set and a second set of images of a type of anatomical structure, wherein the first set of images is acquired by a first imaging modality and the second set of images is acquired by a second imaging modality;
segmenting individual images of the first set of images to obtain a first set of segmentations of the type of anatomical structure;
segmenting individual images of the second set of images to obtain a second set of segmentations of the type of anatomical structure; and
based on the first set of segmentations and the second set of segmentations, generating shape difference data associated with the type of anatomical structure and the first and second imaging modalities.

8. A non-transitory computer readable medium comprising instructions arranged to cause a processor system to:
access a first set and a second set of images of a type of anatomical structure, wherein the first set of images is acquired by a first imaging modality and the second set of images is acquired by a second imaging modality;
segment individual images of the first set of images to obtain a first set of segmentations of the type of anatomical structure;
segment individual images of the second set of images to obtain a second set of segmentations of the type of anatomical structure; and
generate, based on the first set of segmentations and the second set of segmentations, shape difference data associated with the type of anatomical structure and the first and second imaging modalities.

9. The non-transitory computer readable medium of claim 8 , wherein the first set of images and the second set of images comprise a set of image pairs, wherein each image pair is constituted by an image acquired by the first imaging modality and an image acquired by the second imaging modality, wherein both images of an image pair belong to a same patient.

10. The non-transitory computer readable medium of claim 8 , wherein the instructions further cause the processor system to generate the statistical data by performing a principle component analysis of the first set of segmentations and the second set of segmentations simultaneously.

11. The non-transitory computer readable medium of claim 10 , wherein the instructions further cause the processor system to generate the statistical data by:
computing a first mean shape of the type of anatomical structure from the first set of segmentations;
computing a second mean shape of the type of anatomical structure from the second set of segmentations;
constructing a matrix A for the principle component analysis from the differences between the first set of segmentations and the first mean shape and the differences between the second set of segmentations and the second mean shape;
generating the statistical data based on the first mean shape, the second mean shape and the Eigenvectors of the matrix AAt.

12. The non-transitory computer readable medium of claim 10 , wherein the instructions further cause the processor system to mutually register the first set of segmentations, to mutually register the second set of segmentations and to mutually register the first mean shape and the second mean shape before performing the principle component analysis.

13. The non-transitory computer readable medium of claim 8 , wherein the instructions further cause the processor system to generate at least one of: the first set of segmentations and the second set of segmentations using model-based segmentation.

Assignees

• Koninklijke Philips Nv

Inventors

• Weese Rolf Jürgen
• Groth Alexandra
• Peters Jochen

Classifications

• G06T7/12 Primary

  Edge-based segmentation · CPC title

• G06F17/16

  Matrix or vector computation {, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization (matrix transposition G06F7/78)} · CPC title

• G06T5/006

  Physics · mapped topic

• G06T7/149

  involving deformable models, e.g. active contour models · CPC title

• G06T7/174

  involving the use of two or more images · CPC title