Augmented reality interface for assisting a user to operate an ultrasound device
Aspects of the technology described herein relate to techniques for guiding an operator to use an ultrasound device. Thereby, operators with little or no experience operating ultrasound devices may capture medically relevant ultrasound images and/or interpret the contents of the obtained ultrasound images. For example, some of the techniques disclosed herein may be used to identify a particular anatomical view of a subject to image with an ultrasound device, guide an operator of the ultrasound device to capture an ultrasound image of the subject that contains the particular anatomical view, and/or analyze the captured ultrasound image to identify medical information about the subject.
1. A system, comprising:
an ultrasound device configured to capture an ultrasound image of a subject, wherein the ultrasound device comprises a plurality of ultrasonic transducers; and
a processor configured to:
receive medical information about the subject,
identify a target anatomical view of the subject to image based on the received medical information about the subject, and wherein the identified target anatomical view is a parasternal long axis view of the subject to image and has been identified as the target anatomical view based on the received medical information about the subject indicating that subject has experienced paroxysmal nocturnal dyspnea,
obtain the ultrasound image of the subject wherein the ultrasound image contains the target anatomical view,
identify a location of at least one anatomical feature in the ultrasound image using a deep learning technique;
identify at least one medical parameter of the at least one anatomical feature at least in part by analyzing the ultrasound image, wherein the at least one medical parameter comprises an ejection fraction of the subject identified based on the medical information about the subject indicating that the subject has experienced paroxysmal nocturnal dyspnea;
produce an alert if the ejection fraction of the subject varies by more than a threshold amount from a baseline, and
determine that the ejection fraction of the subject is below a threshold and based at least in part on determining that the ejection fraction of the subject is below the threshold, recommend treatment of angiotensin-converting-enzyme inhibitors (ACE inhibitors) and/or angiotensin receptor blockers (ARB).
2. The system of claim 1 , wherein the system further comprises a display configured to simultaneously display the ultrasound image and the at least one medical parameter of the subject.
3. The system of claim 1 , wherein the processor is further configured to supply additional ultrasound images to a trained neural network as additional ultrasound images are generated.
4. The system of claim 1 , wherein the system further comprises a display, and the processor is configured, when producing the alert, to control the display to change a color of the at least one medical parameter on the display.
5. The system of claim 4 , wherein the processor is configured to display the at least one medical parameter in a first color when the at least one medical parameter is within a normal range, to display the at least one medical parameter in a second color when the at least one medical parameter is in a borderline abnormal range, and to display the at least one medical parameter in a third color when the at least one medical parameter is in an abnormal range.
6. The system of claim 1 , wherein the processor is configured to compare the at least one medical parameter with other medical information about the subject from an electronic health record of the subject.
7. The system of claim 1 , wherein the processor is further configured to display measurements on the at least one anatomical feature in the ultrasound image.
8. The system of claim 1 , wherein the processor is configured to receive the medical information about the subject from an electronic health record of the subject.
9. The system of claim 1 , wherein the medical information about the subject comprises a heart rate, a blood pressure, a body surface area, an age, a weight, a height, and/or a medication being taken by the subject.
10. The system of claim 1 , wherein the processor is configured to identify the target anatomical view of the subject to image based on medical information about the subject indicating that an organ is functioning abnormally and wherein the target anatomical view is a known type of perspective view of such an organ and wherein the processor is configured to select that perspective view as the target anatomical view for the ultrasound device to employ to collect an image that is relevant to a medical diagnosis associated with the abnormal functioning of the organ.
11. The system of claim 10 , wherein the target anatomical view contains the organ.
12. The system of claim 1 , wherein the processor is configured to identify the target anatomical view of the subject to image based on medical information about the subject indicating that the subject has experienced paroxysmal nocturnal dyspnea.
13. The system of claim 1 , wherein:
the processor is further configured to:
pose a clinical question to an operator regarding the subject; and receive an answer to the clinical question from the operator; and
the medical information about the subject comprises an answer to the clinical question provided by the operator.
14. The system of claim 1 , wherein the system further comprises a display in communication with the processor, the display configured to display a sponsor region indicating a name, symbol, and/or logo of a sponsoring entity providing a diagnostic application being run by the processor.