Artificial intelligence (AI)-based guidance for an ultrasound device to improve capture of echo image views

1. A computer-implemented method for artificial intelligence (AI)-based guidance for an ultrasound device to improve capture of echo image views, the method comprising:

receiving, by at least one processor, a plurality of the echo images captured by a probe of the ultrasound device, the ultrasound device including a display and a user interface (UI) that displays the echo images to a user, the echo images comprising 2D images and Doppler modality images of a heart;

processing, by one or more neural networks, the echo images to continuously attempt to automatically classify the echo images by view type and generate corresponding classification confidence scores;

simultaneously displaying the view type of the echo images in the UI of the ultrasound device along with the echo images; and

displaying in the UI, feedback indications to the user including which directions to move the probe of the ultrasound device so the probe can be placed in a correct position to capture and successfully classify the echo images, the feedback indications comprising both informational guidance and directional guidance instructions,

the informational guidance comprising setup instructions, a list of view types to be captured, the view type currently being captured, confidence scores of the view types, remaining view types to be captured, all view types captured, or any combination thereof, and

the directional guidance instructions comprising i) macro-guidance instructions that instruct the user to adjust alignment or position of the probe to a known view type, or ii) micro-guidance instructions that instruct the user to optimize the view type of an echo image in progress, wherein the feedback indications comprise any combination of alphanumeric characters and graphical objects, audio, and any combination thereof.

2. The method of claim 1 , wherein the macro-guidance instructions and the micro-guidance instructions comprise probe movement instructions including: up/down or side-side, diagonal movements, rotation clockwise or counter-clockwise, tilt up/down or side-side, hold, or a combination thereof.

3. The method of claim 1 , further comprising associating the directional guidance instructions with a distance value or a time value.

4. The method of claim 1 , wherein displaying in the UI of the ultrasound device feedback indications to the user further comprises responsive to determining that the classification confidence scores meet a predetermined threshold, displaying the view type and a directional guidance instruction to the user to optimize the view type.

5. The method of claim 4 , further comprising responsive to determining that the classification confidence scores do not meet the predetermined threshold, displaying an estimated view type and a feedback instruction in a form of directional guidance instructions to adjust alignment or position of the probe to a known view type.

6. The method of claim 1 , further comprising displaying the feedback indications in a form of informational setup instructions in the UI of the ultrasound device prior to receiving the echo images.

7. The method of claim 1 , further comprising executing by the at least one processor an echo workflow engine, the at least one processor in electronic communication with the ultrasound device.

8. The method of claim 1 , further comprising executing by one or more servers an echo workflow engine in communication over a network with a client component executing on a computer, the computer in electronic communication with the ultrasound device.

9. The method of claim 1 , further comprising adding software as an echo workflow engine to the ultrasound device.

10. A system, comprising:

a memory storing an artificial intelligence (AI) workflow instructions; and

one or more processors coupled to the memory, wherein when the artificial intelligence workflow instructions are executed cause the one or more processors to:

receive a plurality of echo images captured by a probe of an ultrasound device, the ultrasound device including a display and a user interface (UI) that displays the echo images to a user, the echo images comprising 2D images and Doppler modality images of a heart;

process, by one or more neural networks, the echo images to continuously attempt to automatically classify the echo images by view type and generate corresponding classification confidence scores;

simultaneously display the view type of the echo images in the UI of the ultrasound device along with the echo images; and

display in the UI, feedback indications to the user including which directions to move the probe of the ultrasound device so the probe can be placed in a correct position to capture and successfully classify the echo images, the feedback indications comprising both informational guidance and directional guidance instructions,

the informational guidance comprising setup instructions, a list of view types to be captured, the view type currently being captured, confidence scores of the view types, remaining view types to be captured, all view types captured, or any combination thereof, and

directional guidance instructions comprising i) macro-guidance instructions that instruct the user to adjust alignment or position of the probe to a known view type, or ii) micro-guidance instructions that instruct the user to optimize the view type of an echo image in progress; wherein the feedback indications comprise any combination of alphanumeric characters and graphical objects, audio, and any combination thereof.

11. The system of claim 10 , wherein the macro-guidance instructions and the micro-guidance instructions comprise probe movement instructions including: up/down or side-side, diagonal movements, rotation clockwise or counter-clockwise, tilt up/down or side-side, hold, or a combination thereof.

12. The system of claim 10 , further comprising associating the directional guidance instructions with a distance value or a time value.

13. The system of claim 10 , wherein displaying in the UI of the ultrasound device feedback indications to the user further comprises responsive to determining that the classification confidence scores meet a predetermined threshold, displaying the view type and a directional guidance instruction to the user to optimize the view type.

14. The system of claim 13 , further comprising responsive to determining that the classification confidence scores do not meet the predetermined threshold, displaying an estimated view type and a feedback instruction in a form of directional guidance instructions to adjust alignment or position of the probe to a known view type.

15. The system of claim 10 , further comprising displaying the feedback indications in a form of informational setup instructions in the UI of the ultrasound device prior to receiving the echo images.

16. The system of claim 10 , further wherein the AI workflow instructions execute on a computer in electronic communication with the ultrasound device.

17. The system of claim 10 , wherein the artificial intelligence workflow instructions execute on one or more servers in communication over a network with a client component executing on a computer, the computer in electronic communication with the ultrasound device.

18. The system of claim 10 , wherein the artificial intelligence workflow instructions are added to the ultrasound device.

19. A non-transitory computer-readable medium containing program instructions for implementing artificial intelligence (AI)-based guidance for an ultrasound device to improve capture of echo image views, which when executed by a processor system configure the processor system for:

receiving a plurality of the echo images captured by a probe of the ultrasound device, the ultrasound device including a display and a user interface (UI) that displays the echo images to a user, the echo images comprising 2D images and Doppler modality images of a heart;

processing, by one or more neural networks, the echo images to continuously attempt to automatically classify the echo images by view type and generate corresponding classification confidence scores;

simultaneously displaying the view type of the echo images in the UI of the ultrasound device along with the echo images; and

displaying in the UI, feedback indications to the user including which directions to move the probe of the ultrasound device so the probe can be placed in a correct position to capture and successfully classify the echo images, the feedback indications comprising both informational guidance and directional guidance instructions,

the informational guidance comprising setup instructions, a list of view types to be captured, the view type currently being captured, confidence scores of the view types, remaining view types to be captured, all view types captured, or any combination thereof, and

directional guidance instructions comprising i) macro-guidance instructions that instruct the user to adjust alignment or position of the probe to a known view type, or ii) micro-guidance instructions that instruct the user to optimize the view type of an echo image in progress; wherein the feedback indications comprise any combination of alphanumeric characters and graphical objects, audio, and any combination thereof.