Pose and gesture detection for control of ultrasound imaging systems

1. A method comprising:

receiving image or video data from a camera of an ultrasound imaging system;

detecting a pose or gesture in the image or video data using a machine learning (ML) model, wherein the pose or gesture is detected independent of proximity to control inputs of the ultrasound imaging system; and

implementing a command for the ultrasound imaging system based on the detected pose or gesture.

2. The method of claim 1 , wherein the ML model comprises a neural network.

3. The method of claim 2 , wherein the neural network is one of a deep neural network, a convolutional neural network, or a deep-learning convolutional neural network.

4. The method of claim 1 , further comprising determining that the command corresponds to the detected pose or gesture using the ML model.

5. The method of claim 1 , wherein the pose or gesture is detected using a first software application and the command corresponding to the detected pose or gesture is determined using a second software application based on an indication provided by the first software application of the detected pose or gesture to the second software application.

6. The method of claim 5 , wherein the second software application further controls operation of the ultrasound imaging system.

7. The method of claim 1 , wherein the pose or gesture is detected based on positions of keypoints of a user detected in the image or video data.

8. The method of claim 7 , wherein a pose is detected based on static positions of the keypoints of the user with respect to one another.

9. The method of claim 7 , wherein a gesture is detected based on changes in positions of the keypoints of the user with respect to one another.

10. The method of claim 1 , wherein the pose or gesture is detected in a hand of a user.

11. The method of claim 1 , wherein the command is to perform at least one of: taking snapshot of an image displayed by the ultrasound imaging system, causing an image displayed by the ultrasound imaging system to be printed, making a selection in a menu displayed by the ultrasound imaging system, zooming in or out of an image displayed by the ultrasound imaging system, scrolling a menu or image displayed by ultrasound imaging system, and changing a screen or menu displayed by the ultrasound imaging system.

12. One or more computer-readable media comprising instructions that, when executed by one or more processors, cause the one or more processors to:

access image or video data from a camera;

detect a pose or gesture based on the image or video data using a machine learning (ML) model, wherein the detected pose or gesture is independent of proximity to control inputs of the ultrasound imaging system; and

cause a command to be implemented in the ultrasound imaging system based on the detected a pose or gesture.

13. The computer-readable media of claim 12 , wherein the instructions are further to cause the one or more processors to determine that the command corresponds to the detected pose or gesture using the ML model.

14. The computer-readable media of claim 12 , wherein the instructions are further to cause the one or more processors to cause an indication of the detected pose or gesture to be provided to a control circuitry of the ultrasound imaging system.

15. The computer-readable media of claim 12 , wherein the instructions are further to cause the one or more processors to detect keypoints of a user in the image or video data and detect the pose or gesture based on positions of the keypoints with respect to one another.

16. The computer-readable media of claim 12 , wherein the pose or gesture is detected based on a hand of a user detected in the image or video data from the camera.

17. The computer-readable media of claim 12 , wherein the ML model is a neural network.

18. An ultrasound imaging system comprising:

a camera;

a memory storing instructions; and

processor circuitry to execute the instructions to:

access image or video data from the camera;

detect a pose or gesture in the image or video data using a machine learning (ML) model, wherein the pose or gesture is independent of proximity to control inputs of the ultrasound imaging system; and

implement a command for the ultrasound imaging system based on the detected pose or gesture.

19. The system of claim 18 , wherein the processor circuitry is to execute the instructions to detect keypoints of a user in the image or video data and detect the pose or gesture based on positions of the keypoints with respect to one another.

20. The system of claim 18 , wherein the pose or gesture is detected based on a hand of a user detected in the image or video data from the camera.