Method and system of creating and displaying a visually distinct rendering of an ultrasound image

Patent metadata

Field	Value
Publication number	US-12567185-B2
Application number	US-202318387825-A
Country	US
Kind code	B2
Filing date	Nov 7, 2023
Priority date	Nov 7, 2023
Publication date	Mar 3, 2026
Grant date	Mar 3, 2026

Abstract

A method of creating and displaying a visually distinct rendering of an ultrasound image, acquired from an ultrasound scanner, comprises displaying, on a screen that is communicatively connected to the ultrasound scanner, an ultrasound image feed comprising ultrasound image frames, deploying an AI model to execute on a computing device communicably connected to the ultrasound scanner, wherein the AI model is trained so that when the AI model is deployed, the computing device identifies and segments boundaries of a feature or features, in whole or part, acquiring, at the computing device, a new ultrasound image during ultrasound scanning, processing, using the AI model, the new ultrasound image to identify and segment boundaries of a single feature or two or more features, in whole or part, on the new ultrasound image, thereby creating a single segmented boundary feature or two or more segmented boundary features, applying a graphic onto the single segmented boundary feature or the at least two segmented boundary features, thereby forming a graphic feature image and generating an output image, on the screen, comprising the graphic feature image.

First claim

What is claimed is:

1 . A method of creating and displaying a visually distinct rendering of an ultrasound image, acquired from an ultrasound scanner, the method comprising:
displaying, on a screen that is communicatively connected to the ultrasound scanner, an ultrasound image feed comprising ultrasound image frames; deploying an AI model to execute on a computing device communicably connected to the ultrasound scanner, wherein the AI model is trained so that when the AI model is deployed, the computing device identifies and segments boundaries of a feature or features, in whole or part; acquiring, at the computing device, a new ultrasound image during ultrasound scanning; processing, using the AI model, the new ultrasound image to identify and segment boundaries of two or more features, in whole or part, on the new ultrasound image, thereby creating two or more segmented boundary features; applying at least two graphics respectively, onto the at least two segmented boundary features, wherein the at least two graphics substantially fill within the boundaries of the at least two segmented boundary features, thereby forming a graphic feature image; and generating an output image, on the screen, comprising the graphic feature image.

2 . The method of claim 1 wherein each of the at least two graphics is a different graphic which is applied, respectively, to each of the at least two segmented boundary features to form the graphic feature image.

3 . The method of claim 1 wherein the AI model identifies and segments more than two segmented boundary features, within the new ultrasound image, and a different graphic is applied to each of the more than two segmented boundary features to form the graphic feature image.

4 . The method of claim 1 wherein the at least two graphics are applied in real time, during new ultrasound image acquisition.

5 . The method of claim 1 additionally comprising a step of tracking displacement of at least one aspect of the graphic feature image using a tracking algorithm, to direct adjustments to the graphic feature image within the segmented boundary features.

6 . The method of claim 5 wherein adjustments to the segmented boundary features creates a visual of dynamic motion of the graphic feature image.

7 . The method of claim 1 additionally comprising the steps of tracking a motion of one or more of an annotation and artifact associated with at the segmented boundary feature, such one or more of an annotation and artifact being associated with a first location of the segmented boundary feature on a first image; capturing an adjustment of the one or more of an annotation or artifact on a second image, the adjustment being indicative of a second location of the one or more of an annotation or artifact; adjusting a graphic on the segmented boundary feature using a positional difference in location of the one or more of an annotation and artifact, between the first location and the second location; and generating an updated graphic feature image which creates an illusion of applying movement to the graphic on the segmented boundary feature.

8 . The method of claim 7 wherein the artifact is a speckle artifact.

9 . The method of claim 1 wherein the at least two graphics is any visual representation selected from the group consisting of color, hue, contrast, shading, brightness, patterns, animation, line art, symbols, geometric designs, photorealistic designs, artistic designs, bitmap graphics, and vector graphics.

10 . The method of claim 1 wherein the new ultrasound image is one or a combination of a live acquired ultrasound image and a stored, previously acquired ultrasound image.

11 . The method of claim 1 wherein the AI model is trained with a plurality of training ultrasound images comprising labelled segmented boundaries of one or more features, which are, one of: i) generated by one of a manual or semi automatic means; or ii) tagged from an identifier menu by one of a manual, semi automatic means or fully automatic means.

12 . The method of claim 1 comprising training the AI model with one or more of the following: i) supervised learning; ii) unsupervised learning; iii) previously labelled ultrasound image datasets; and iv) cloud stored data.

13 . The method of claim 1 wherein the feature is selected from the group consisting of an organ, a portion of an organ, a boundary of an organ, a muscle, a boundary of a muscle, a blood vessel, a boundary of a blood vessel, a nerve, a boundary of a nerve, a fat layer, epithelium, bodily fluid, a tumor, and a cyst.

14 . A system for generating and displaying a visually distinct rendering of an ultrasound image comprising:
an ultrasound scanner configured to acquire a new ultrasound image frame; a computing device communicably connected to the ultrasound scanner and configured to:
process the new ultrasound image frame against an artificial intelligence model to identify and segment boundaries of two or more features, in whole or part, on the new ultrasound image frame, thereby creating two or more segmented boundary features;
apply at least two graphics, respectively, onto the at least two segmented boundary features, wherein the at least two graphics substantially fill within the boundaries of the at least two segmented boundary features, thereby forming a graphic feature image;
generate an output image comprising the graphic feature image; and
a display device configured to:
display the output image comprising the graphic feature image.

15 . The system of claim 14 wherein each of the at least two graphics is a different graphic which is applied, respectively, to each of the at least two segmented boundary features to form the graphic feature image.

16 . The system of claim 14 wherein the AI model identifies and segments more than two segmented boundary features, within the new ultrasound image, and a different graphic is applied to each of the more than two segmented boundary features to form the graphic feature image.

17 . The system of claim 14 wherein the computing device additionally tracks displacement of at least one aspect of the graphic feature image using a tracking algorithm, to direct adjustments to the graphic feature image within the segmented boundary features.

18 . The system of claim 17 wherein adjustments to the segmented boundary features creates a visual of dynamic motion of the graphic feature image.

19 . The system of claim 14 wherein the display device additionally displays, along with graphic feature image, at least one of: i) the new ultrasound image frame; and ii) an image frame showing the at least two segmented boundary features.

20 . A non-transitory computer-readable media storing computer-readable instructions, which, when executed by a processor cause the processor to:
display on a screen that is communicatively connected to an ultrasound scanner, an ultrasound image feed comprising ultrasound image frames; deploy an AI model to execute on a computing device communicably connected to the ultrasound scanner, wherein the AI model is trained so that when the AI model is deployed, the computing device identifies and segments boundaries of a feature or features, in whole or part; acquire, at the computing device a new ultrasound image during ultrasound scanning; process the new ultrasound image frame against the AI model to identify and segment boundaries of two or more features, in whole or part, on the new ultrasound image frame, thereby creating two or more seg

Assignees

• Clarius Mobile Health Corp

Inventors

• Dickie Kris
• Pelissier Laurent
• KERBY Benjamin Eric
• UNIYAL Nishant
• Potma Matt

Classifications

• G06T2207/10132

  Ultrasound image · CPC title

• G06T2207/30004

  Biomedical image processing · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/20221

  Image fusion; Image merging · CPC title

• A61B8/461

  Displaying means of special interest · CPC title