Model-based segmentation of an anatomical structure

Patent metadata

Field	Value
Publication number	US-2016307331-A1
Application number	US-201415101018-A
Country	US
Kind code	A1
Filing date	Dec 15, 2014
Priority date	Dec 17, 2013
Publication date	Oct 20, 2016
Grant date	—

Abstract

A system and method is provided which obtains different medical images ( 210 ) showing an anatomical structure of a patient and having been acquired by different medical imaging modalities and/or different medical imaging protocols. The system is configured for fitting a first deformable model to the anatomical structure in the first medical image ( 220 A), fitting a second deformable model to the anatomical structure in the second medical image ( 220 B), mutually aligning the first fitted model and the second fitted model ( 230 ), and subsequently fusing the first fitted model and the second fitted model to obtain a fused model ( 240 ) by augmenting the first fitted model with a part of the second fitted model which is missing in the first fitted model; or adjusting or replacing a part of the first fitted model based on a corresponding part of the second fitted model having obtained a better fit. The fused model represents a multimodal/multi-protocol segmentation of the anatomical structure, and provides a user with a more comprehensive understanding of the anatomical structure than known models.

First claim

1 . A system for fitting a deformable model to an anatomical structure in a medical image to obtain a segmentation of the anatomical structure, comprising:
an image interface for obtaining a first medical image of a patient and a second medical image of the patient, both medical images showing the anatomical structure and having been acquired by different medical imaging modalities or different medical imaging protocols, thereby establishing a different visual representation of the anatomical structure in both medical images; a processing subsystem configured for: i) fitting a first deformable model to the anatomical structure in the first medical image, thereby obtaining a first fitted model; ii) fitting a second deformable model to the anatomical structure in the second medical image, thereby obtaining a second fitted model wherein the second deformable model differs from the first deformable model for accommodating said different visual representation of the anatomical structure in both medical images; iii) mutually aligning the first fitted model and the second fitted model, and iv) after said mutual alignment, fusing the first fitted model and the second fitted model to obtain a fused model,
wherein the processing subsystem is configured for mutually aligning the first fitted model and the second fitted model by:
i) roughly aligning the first fitted model part of and the second fitted model, and ii) refining the alignment based on matching of pre-defined anchor structure.

2 . The system according to claim 1 ,
wherein the processing subsystem is configured for fusing the first fitted model and the second fitted model by, augmenting the first fitted model with a part of the second fitted model which is missing in the first fitted model; or adjusting or replacing a part of the first fitted model based on a corresponding part of the second fitted model having obtained a better fit, further comprising a visualization subsystem for visualizing the fused model.

3 . The system according to claim 2 , wherein the visualization subsystem is configured for visualizing the fused model by overlaying the fused model over a displayed image, the displayed image being at least one of the group of: the first medical image, the second medical image, and a fused medical image obtained by an image fusion of the first medical image and the second medical image.

4 . The system according to claim 3 , wherein the visualization subsystem is configured for processing the displayed image based on the fused model.

5 . The system according to claim 4 , wherein the visualization subsystem is configured for processing the displayed image by cropping the displayed image based on anatomical information derived from the fused model.

6 . The system according to claim 2 , wherein the processing subsystem is configured for determining a discrepancy between the first fitted model and the second fitted model, wherein the visualization subsystem is configured for visualizing the discrepancy in visual relation with the fused model.

7 . The system according to claim 6 , wherein the visualization subsystem is configured for visualizing the discrepancy by visually coding a display of the fused model.

8 . The system according to claim 2 , wherein the first medical image is constituted by a time-series of images, wherein the first deformable model is arranged for modeling a change in the anatomical structure over the time-series of images, and wherein the visualization subsystem is configured for visually representing the change in the visualizing of the fused model.

9 . The system according to claim 8 , wherein the visualization subsystem is configured for animating the fused model to visually represent the change.

10 . The system according to claim 2 , further comprising a user interaction subsystem for enabling a user to interact with the fused model.

11 . The system according to claim 10 , wherein the processing subsystem is configured for carrying out an action with respect to a part of, one of the group of: the first medical image, the second medical image, the first fitted model and the second fitted model, based on the user interacting with a corresponding part of the fused model.

12 . Workstation or imaging apparatus comprising the system according to claim 1 .

13 . A method for fitting a deformable model to an anatomical structure in a medical image to obtain a segmentation of the anatomical structure, comprising:
obtaining a first medical image of a patient and a second medical image of the patient, both medical images showing the anatomical structure and having been acquired by different medical imaging modalities or different medical imaging protocols, thereby establishing a different visual representation of the anatomical structure in both medical images; fitting a first deformable model to the anatomical structure in the first medical image, thereby obtaining a first fitted model; fitting a second deformable model to the anatomical structure in the second medical image, thereby obtaining a second fitted model; wherein the second deformable model differs from the first deformable model for accommodating said different visual representation of the anatomical structure in both medical images; mutually aligning the first fitted model and the second fitted model by i) roughly aligning the first fitted model and the second fitted model, and ii) refining the alignment based on matching of pre-defined anchor structure; and fusing the first fitted model and the second fitted model to obtain a fused model.

14 . A computer program product comprising instructions for causing a processor system to perform the method according to claim 13 .

Assignees

• Koninklijke Philips Nv

Inventors

• Mollus Sabine
• Saalbach Axel
• Weese Juergen

Classifications

• G16H30/20

  for handling medical images, e.g. DICOM, HL7 or PACS · CPC title

• G16H30/40

  for processing medical images, e.g. editing · CPC title

• G06T2207/30048

  Heart; Cardiac · CPC title

• G06T2207/20132

  Image cropping · CPC title

• G06T2207/20124

  Active shape model [ASM] · CPC title