Ultrasound imaging plane alignment using neural networks and associated devices, systems, and methods

Patent metadata

Field	Value
Publication number	US-11712220-B2
Application number	US-201916980433-A
Country	US
Kind code	B2
Filing date	Mar 12, 2019
Priority date	Mar 12, 2018
Publication date	Aug 1, 2023
Grant date	Aug 1, 2023

Abstract

Ultrasound image devices, systems, and methods are provided. In one embodiment, a method of automated medical examination, comprising receiving, from an imaging device, a first image representative of a subject's body while the imaging device is positioned at a first imaging position with respect to the subject's body; determining a first motion control configuration for repositioning the imaging device from the first imaging position to a second imaging position based on a first predictive network, the first image, and a target image view including a clinical property; and repositioning, by a robotic system coupled to the imaging device, the imaging device to the second imaging position based on the first motion control configuration.

First claim

What is claimed is:

1. A method of automated medical examination, comprising:
receiving, from an imaging device, a first image representative of a subject's body while the imaging device is positioned at a first imaging position with respect to the subject's body;
determining a first motion control configuration for automatically repositioning the imaging device from the first imaging position to a second imaging position based on a first predictive network, the first image, and a target image view including a clinical property, wherein the first motion control configuration includes one or more parameters corresponding to at least one of a movement of the imaging device along a left-right plane of the subject's body, a movement of the imaging device along an anterior-posterior plane of the subject's body, an orientation of an imaging plane of the imaging device, or a rotation of the imaging device with respect to an axis of the imaging device;
repositioning, by a robotic system coupled to the imaging device, the imaging device to the second imaging position based on the first motion control configuration;
receiving, from the imaging device, a second image representative of the subject's body while the imaging device is positioned at the second imaging position;
determining, using a second predictive network, whether the second image includes the clinical property of the target image view;
determining an adjustment for the second imaging position when the second image is determined to include the clinical property of the target image view;
repositioning, by the robotic system, the imaging device to a third imaging position based on the adjustment
receiving, from the imaging device, a third image representative of the subject's body while the imaging device is positioned at the third imaging position with respect to the subject's body; and
selecting a target imaging position from among the second imaging position and the third imaging position, based on a third predictive network;
wherein the first predictive network is trained by: (i) providing a plurality of images obtained by the imaging device from at least two imaging positions to obtain the target image view; (ii) obtaining a plurality of motion control configurations based on an orientation or a movement of the imaging device associated with the at least two imaging positions; and (iii) assigning a score to a relationship between the plurality of motion control configurations and the plurality of images with respect to the target image view; and
wherein the third predictive network is trained by: (i) providing a third predictive network training dataset comprising a plurality of image pairs from a set of target images, and further comprising, for each of the plurality of image pairs, an identification of which of the image pairs comprises a higher-quality image; (ii) training, using the third predictive network training dataset, the third predictive network to determine which of two images representative of a subject's body comprise the higher-quality image.

2. The method of claim 1 , further comprising, when the second image is determined not to include the clinical property of the target image view:
determining a second motion control configuration;
repositioning the imaging device to a third imaging position based on the second motion control configuration; and
receiving a third image representative of the subject's body while the imaging device is positioned at the third imaging position with respect to the subject's body.

3. The method of claim 2 , further comprising:
repeating the determining the second motion control configuration, the repositioning the imaging device to the third imaging position, and receiving the third image until an image including the clinical property of the target image view is received from the imaging device.

4. The method of claim 1 , further comprising:
receiving, from the imaging device, a fourth image representative of the subject's body while the imaging device is positioned at the selected target imaging position; and
determining a medical examination result associated with the clinical property based on the fourth image.

5. The method of claim 1 , further comprising:
determining a plurality of candidate motion control configurations by sampling a set of movements for repositioning the imaging device,
wherein the determining the first motion control configuration further includes:
selecting the first motion control configuration from the plurality of candidate motion control configurations based on the first predictive network, the first image, and the target image view.

6. The method of claim 1 , wherein the imaging device is a transesophageal echocardiography (TEE) probe.

7. The method of claim 1 , wherein the imaging device is a transthoracic echocardiography (TTE) probe, and wherein the first motion control configuration includes one or more parameters corresponding to at least one of a linear velocity or an angular velocity for moving the imaging device.

8. An automated medical examination system, comprising:
communication circuitry in communication with an imaging device and configured to receive a first image representative of a subject's body while the imaging device is positioned at a first imaging position with respect to the subject's body;
a processor in communication with the communication circuitry and configured to determine a first motion control configuration for automatically repositioning the imaging device from the first imaging position to a second imaging position based on a first predictive network, the first image, and a target image view including a clinical property, wherein the first motion control configuration includes one or more parameters corresponding to at least one of a movement of the imaging device along a left-right plane of the subject's body, a movement of the imaging device along an anterior-posterior plane of the subject's body, an orientation of an imaging plane of the imaging device, or a rotation of the imaging device with respect to an axis of the imaging device; and
a robotic system in communication with the communication circuitry and coupled to the imaging device, the robotic system configured to reposition the imaging device to the second imaging position based on the first motion control configuration;
wherein the communication circuitry is further configured to receive, from the imaging device, a second image representative of the subject's body while the imaging device is positioned at the second imaging position and wherein the processor is further configured to determine, using a second predictive network, whether the second image includes the clinical property of the target image view;
wherein the processor is further configured to determine an adjustment for the second imaging position when the second image is determined to include the clinical property of the target image view, the robotic system is further configured to reposition the imaging device to a third imaging position based on the adjustment, the communication circuitry is further configured to receive, from the imaging device, a third image representative of the subject's body while the imaging device is positioned at the third imaging position with respect to the subject's body, and the processor is further configured to select a target imaging position from among the second imaging position and the third imaging position, based on a third predictive network;
wherein the first predictive network is trained by: (i) providing a plurality of images obtained by the imaging device from at least two imaging positions to obtain the target image view; (ii) obtaining a plurality of motion control configurations based on an orientati

Assignees

• Koninklijke Philips Nv

Inventors

• Toporek Grzegorz Andrzej
• Wang Haibo

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• A61B8/4218 Primary

  characterised by articulated arms · CPC title

• A61B8/0883

  for diagnosis of the heart · CPC title

• A61B8/12 Primary

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