Ultrasound imaging dataset acquisition for neural network training and associated devices, systems, and methods

Patent metadata

Field	Value
Publication number	US-12380686-B2
Application number	US-201916979613-A
Country	US
Kind code	B2
Filing date	Mar 5, 2019
Priority date	Mar 12, 2018
Publication date	Aug 5, 2025
Grant date	Aug 5, 2025

Abstract

Ultrasound image devices, systems, and methods are provided. A medical ultrasound image system, comprising an communication interface in communication with an imaging device and configured to receive a first image representative of a subject's body from the imaging device while the imaging device is positioned at a first imaging position with respect to the subject's body; and transmit a motion control configuration for repositioning the imaging device from the first imaging position to a second imaging position; a processor in communication with the communication interface and configured to generate a database by associating the first image, the motion control configuration, and a score associated with the second imaging position and a target image view including a clinical property; and a storage device in communication with the processor and configured to store the database to facilitate training of a predictive network for aligning the imaging device to the target image view.

First claim

What is claimed is:

1. An apparatus, comprising:
an ultrasound imaging probe;
a memory;
a processor configured for communication with the ultrasound imaging probe and the memory, wherein the processor is configured to:
control, with an output of a motion control configuration, the ultrasound imaging probe to be physically repositioned from a first imaging position to a second imaging position;
control the ultrasound imaging probe to obtain an ultrasound image representative of a subject's body while the ultrasound imaging probe is positioned at the second imaging position;
retrieve a target imaging position for the ultrasound imaging probe from the memory;
determine a score based on a comparison between the second imaging position and the target imaging position;
generate a data tuple comprising the ultrasound image, the motion control configuration, and the score; and
store the data tuple in the memory and train a predictive network for aligning the imaging probe to the target imaging position based on the data tuple.

2. The apparatus of claim 1 , wherein the motion control configuration includes one or more parameters for repositioning the ultrasound imaging probe to the second imaging position.

3. The apparatus of claim 2 , wherein the processor is further configured to determine the one or more parameters.

4. The apparatus of claim 3 , wherein the processor is further configured to determine the one or more parameters based on a random function.

5. The apparatus of claim 2 , wherein the one or more parameters correspond to one or more of a movement of the ultrasound imaging probe along a left-right plane of the subject's body, a movement of the ultrasound imaging probe along an anterior-posterior plane of the subject's body, an orientation of an imaging plane of the ultrasound imaging probe, or a rotation of the ultrasound imaging probe with respect to an axis of the ultrasound imaging probe.

6. The apparatus of claim 5 , wherein the ultrasound imaging probe is a transesophageal echocardiography (TEE) probe.

7. The apparatus of claim 2 , wherein the one or more parameters correspond to at least one of a linear velocity or an angular velocity for ultrasound imaging probe.

8. The apparatus of claim 7 , wherein the ultrasound imaging probe is a transthoracic echocardiography (TTE) probe.

9. The apparatus of claim 1 , wherein the processor is configured to:
determine a plurality of motion control configurations;
control, with an output of the plurality of motion control configuration, the ultrasound imaging probe to be physically repositioned to a plurality of imaging positions;
control the ultrasound imaging probe to obtain a plurality of ultrasound images representative of a subject's body while the ultrasound imaging probe is positioned at the plurality of imaging positions;
retrieve a target imaging position for the ultrasound imaging probe from the memory;
determine a plurality of scores based on a comparison between the plurality of imaging positions and the target imaging position;
generate a plurality of data tuples, each data tuple comprising one of each of the plurality of ultrasound images, the plurality of motion control configurations, and the plurality of scores; and
store the plurality of data tuples in the memory.

10. The apparatus of claim 9 , wherein the plurality of data tuples are stored in the memory as an ordered sequence, the ordering based on the sequence of imaging positions.

11. The apparatus of claim 9 , wherein each of the plurality motion control configurations is determined based on a difference between associated sequential imaging positions.

12. The apparatus of claim 1 , wherein the processor is further configured to determine the motion control configuration, and wherein the processor configured to control, with an output of a motion control configuration, the ultrasound imaging probe to be physically repositioned further comprises transmit the motion control configuration to a robotic system that controls the ultrasound imaging probe based on the motion control configuration.

13. A method of medical ultrasound image data acquisition, comprising:
controlling, with an output of a motion control configuration, an ultrasound imaging probe to be physically repositioned from a first imaging position to a second imaging position;
controlling the ultrasound imaging probe to obtain an ultrasound image representative of a subject's body while the ultrasound imaging probe is positioned at the second imaging position;
retrieving a target imaging position for the ultrasound imaging probe from a memory;
determining a score based on a comparison between the second imaging position and the target imaging position;
generating a data tuple comprising the ultrasound image, the motion control configuration, and the score; and
storing the data tuple in the memory and train a predictive network for aligning the imaging probe to the target imaging position based on the data tuple.

14. The method of claim 13 , wherein the motion control configuration includes one or more parameters for moving the ultrasound imaging probe to the second imaging position.

15. The method of claim 14 , further comprising determining the one or more parameters.

16. The method of claim 14 , wherein the ultrasound imaging probe is a transesophageal echocardiography (TEE) probe, and wherein the one or more parameters correspond to one or more of a movement of the ultrasound imaging probe along a left-right plane of the subject's body, a movement of the ultrasound imaging probe along an anterior-posterior plane of the subject's body, an orientation of an imaging plane of the ultrasound imaging probe, or a rotation of the ultrasound imaging probe with respect to an axis of the ultrasound imaging probe.

17. The method of claim 14 , wherein the ultrasound imaging probe is a transthoracic echocardiography (TTE) probe, and wherein the one or more parameters correspond to at least one of a linear velocity or an angular velocity for moving the ultrasound imaging probe.

18. The method of claim 13 , further comprising determine the motion control configuration, and wherein controlling, with an output of a motion control configuration, the ultrasound imaging probe to be physically repositioned further comprises transmitting the motion control configuration to a robotic system that controls the ultrasound imaging probe based on the motion control configuration.

19. The method of claim 13 , further comprising:
determine a plurality of motion control configurations;
controlling, with an output of the plurality of motion control configurations, the ultrasound imaging probe to be physically repositioned to a plurality of imaging positions;
controlling the ultrasound imaging probe to obtain a plurality of ultrasound images representative of a subject's body while the ultrasound imaging probe is positioned at the plurality of imaging positions;
retrieving a target imaging position for the ultrasound imaging probe from the memory;
determining a plurality of scores based on a comparison between the plurality of imaging positions and the target imaging position;
generating a plurality of data tuples, each data tuple comprising one of each of the plurality of ultrasound images, the plurality of motion control configurations, and the plurality of scores; and
storing the plurality of data tuples in the memory.

20. The method of claim 19 , wherein the plurality of data tuples are stored in the memory as an ordered sequenc

Assignees

• Koninklijke Philips Nv

Inventors

• Toporek Grzegorz Andrzej
• Wang Haibo

Classifications

• G06V10/764

  using classification, e.g. of video objects · CPC title

• A61B8/54

  Control of the diagnostic device · CPC title

• A61B8/4218

  characterised by articulated arms · CPC title

• A61B8/14

  Echo-tomography · CPC title

• A61B8/12

  in body cavities or body tracts, e.g. by using catheters · CPC title