AUTOMATIC ALIGNMENT OF ULTRASOUND VOLUMES

• US 20170238904A1
• Filed: 02/19/2016
• Published: 08/24/2017
• Est. Priority Date: 02/19/2016
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Perrey, Christian Fritz, Buckton, Daniel John, Singhal, Nitin, Krishnan, Kajoli Banerjee
• Granted Patent: US 10,398,411 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 8/0883 for diagnosis of the heart
• CPC Class Codes: A61B 8/145 characterised by scanning multiple planes
• CPC Class Codes: A61B 8/463 characterised by displaying multiple images or images and diagnostic data on one display composite display in devices for short-range imaging with acoustic waves G01S7/52074
• CPC Class Codes: A61B 8/465 adapted to display user selection data, e.g. icons or menus
• CPC Class Codes: A61B 8/466 adapted to display 3D data 3D imaging and stereoscopic displays in devices for short-range imaging with acoustic waves G01S15/8993 and G01S7/52068, respectively; 3D image rendering G06T15/00; manipulating 3D models for computer graphics G06T19/00
• CPC Class Codes: A61B 8/469 for selection of a region of interest
• CPC Class Codes: A61B 8/483 involving the acquisition of a 3D volume of data
• CPC Class Codes: A61B 8/5253 combining overlapping images, e.g. spatial compounding
• CPC Class Codes: G06T 19/00 Manipulating 3D models or images for computer graphics
• CPC Class Codes: G06T 2200/04 involving 3D image data
• CPC Class Codes: G06T 2207/10136 3D ultrasound image
• CPC Class Codes: G06T 2207/30048 Heart; Cardiac
• CPC Class Codes: G06T 2210/41 Medical
• CPC Class Codes: G06T 7/344 involving models

Abstract

Embodiments for aligning a volume to a standard alignment are provided. One example method of aligning a volume constructed from captured image data to a standard orientation includes determining an orientation and a scale of the volume based on a comparison of a volume model representing the volume to captured image data of the volume over time and adjusting the volume according to the determined orientation and scale.

Claims

1. A method of aligning a volume constructed from captured image data to a standard orientation, comprising:

determining an orientation and a scale of the volume based on a comparison of a volume model representing the volume to captured image data of the volume over time; and

adjusting the volume according to the determined orientation and scale.

2. The method of claim 1, wherein determining the orientation and scale of the volume based on the comparison of the volume model to captured image data of the volume over time comprises receiving an identification of an initial orientation and an initial scale of the volume within a single plane of the volume, and fitting the volume model to the captured image data based on the initial orientation and initial scale of the volume.

3. The method of claim 2, wherein the volume is a four-dimensional volume representing a heart, and wherein the volume model comprises a plurality of linked sub-models, each sub-model representing a respective chamber of the heart.

4. The method of claim 3, wherein receiving the identification of the initial orientation and the initial scale of the volume comprises receiving an identification of a position, size, and orientation of a selected sub-anatomical structure of the heart within the single plane of the heart and determining the initial orientation and the initial scale of the heart based on the identified position, size, and orientation of the selected sub-anatomical structure of the heart.

5. The method of claim 4, wherein the selected sub-anatomical structure of the heart comprises an interventricular septum.

6. The method of claim 4, wherein the identification of the position, size, and orientation of the selected sub-anatomical structure of the heart is received via user input.

7. The method of claim 6, wherein the user input is received only at the single plane of the heart.

8. The method of claim 4, wherein the identification of the position, size, and orientation of the selected sub-anatomical structure of the heart is received via automatic image recognition.

9. The method of claim 4, further comprising:

detecting an edge of a first chamber of the heart within the captured image data;

adjusting a first sub-model of the plurality of linked sub-models based on an error between an edge of the first sub-model and the edge of the first chamber; and

when the error is less than a threshold, indicating the first sub-model fits the captured image data.

10. The method of claim 9, further comprising adjusting each remaining sub-model of the plurality of linked sub-models based on the adjusting of the first sub-model.

11. The method of claim 9, wherein the volume model is a dynamic model configured to deform over time to reflect a change in chamber shape and size as the heart beats, and wherein indicating the volume model fits the captured image data comprises indicating the volume model fits the captured image data when the edge of the first sub-model tracks the edge of the first chamber over time.

12. The method of claim 9, wherein adjusting the volume according to the determined orientation and scale comprises, after indicating the volume model fits the captured image data, adjusting an orientation of the volume to match the orientation of the volume model and outputting one or more standard planes of the volume for display on a display device.

13. A method, comprising:

accessing a four-dimensional volume representing a heart; and

aligning the four-dimensional volume based on a dynamic volume model of the heart comprising a plurality of linked sub-models each representing a chamber of the heart.

14. The method of claim 13, wherein the four-dimensional volume is assembled from image data of the heart captured over time, and wherein aligning the four-dimensional volume based on the dynamic deformable model comprises:

generating an initial dynamic deformable model based on an initial orientation and scale of the four-dimensional volume identified based on user input to a single plane of the four-dimensional volume; and

adjusting the initial dynamic deformable model to fit the image data.

15. The method of claim 14, wherein adjusting the initial dynamic deformable model to fit the image data comprises:

detecting an inner edge of a first chamber of the heart within the image data; and

adjusting one or more of a size, position, and orientation of a first sub-model of the plurality of linked sub-models based on an error between an outer edge of the first sub-model and the inner edge of first chamber.

16. The method of claim 15, wherein the detecting the inner edge of the first chamber and the adjusting one or more of the size, position, and orientation of the first sub-model are performed for each of a plurality of frames of image data captured over time, and further comprising indicating the dynamic volume model fits the image data when an average of all errors determined for all frames is less than a threshold.

17. A system, comprising:

an ultrasound probe to emit ultrasonic signals;

an ultrasound receiver to receive echoes of the emitted ultrasonic signals; and

a computing system operably connected to the ultrasound probe, ultrasound receiver, and a display device, the computing system including instructions to;

acquire a plurality of images of an anatomical structure via a volumetric sweep of the ultrasound probe;

reconstruct the plurality of images into a four-dimensional volume; and

align the four-dimensional volume with respect to a dynamic volume model of the four-dimensional volume.

18. The system of claim 17, wherein to align the four-dimensional volume with respect to the dynamic volume model, the computing system includes instructions to:

adjust the dynamic volume model to fit image data obtained from the plurality of images of the anatomical structure;

determine an orientation of the four-dimensional volume based on an orientation of the adjusted dynamic volume model; and

align the four-dimensional volume to a standard orientation.

19. The system of claim 18, wherein the computing system includes further instructions to:

output one or more slices of the four-dimensional volume for display on the display device;

receive user input indicating an initial scale and orientation of the four-dimensional volume; and

build an initial dynamic volume model based on the initial scale and orientation of the four-dimensional volume, where the instructions to adjust the dynamic volume model to fit the image data include instructions to adjust the initial dynamic volume model.

20. The system of claim 17, wherein the computing system includes further instructions to, after aligning the four-dimensional volume with respect to the dynamic volume model, obtain one or more slices of the four-dimensional volume for display on the display device.