Quality indicators for collection of and automated measurement on ultrasound images

Patent metadata

Field	Value
Publication number	US-11847772-B2
Application number	US-202217886616-A
Country	US
Kind code	B2
Filing date	Aug 12, 2022
Priority date	Oct 27, 2017
Publication date	Dec 19, 2023
Grant date	Dec 19, 2023

Abstract

Aspects of the technology described herein relate to techniques for calculating, during imaging, a quality of a sequence of images collected during the imaging. Calculating the quality of the sequence of images may include calculating a probability that a medical professional would use a given image for clinical evaluation and a confidence that an automated analysis segmentation performed on the given image is correct. Techniques described herein also include receiving a trigger to perform an automatic measurement on a sequence of images, calculating a quality of the sequence of images, determining whether the quality of the sequence of images exceeds a threshold quality, and performing the automatic measurement on the sequence of images based on determining that the quality of the sequence of images exceeds the threshold quality.

First claim

What is claimed is:

1. A non-transitory computer-readable storage medium storing code that, when executed by a computer processor, causes the computer processor to perform a method of processing signals from an ultrasound device, wherein the method comprises:
receiving real-time input signals from the ultrasound device during an imaging operation;
causing a display device to display a sequence of ultrasound images in real-time during the imaging operation, the sequence of ultrasound images corresponding to the input signals;
calculating a live quality of the sequence of ultrasound images in real-time;
causing the display device to display a live quality indicator together with the sequence of ultrasound images;
wherein the live quality indicator comprises:
a frame having a first end and a second end;
a color bar within the frame and configured to:
indicate a first color when the live quality is in a first quality range, and
indicate a second color when the live quality is in a second quality range, and

an acceptability indicator at a location between a first end and a second end of the frame, wherein a distance from the first end of the frame to the location of the acceptability indicator relative to a distance from the first end to the second of the frame is proportional to a threshold quality for performing an automatic measurement.

2. The storage medium of claim 1 , wherein:
the first color is a reddish color, and
the second color is a greenish color.

3. The storage medium of claim 1 , wherein a length of the color bar indicates a quality level of the live quality such that an increase in the quality level corresponds to an increase in the length of the color bar.

4. The storage medium of claim 1 , wherein the method further comprises:
calculating the live quality using at least one trained statistical model.

5. The storage medium of claim 4 , wherein the at least one trained statistical model includes a deep-learning-trained neural network.

6. The storage medium of claim 5 , wherein the at least one trained statistical model includes a convolutional neural network.

7. The storage medium of claim 1 , wherein the method further comprises:
causing the display device to display guidance for a user to move the ultrasound device, the guidance being displayed in real-time during the imaging operation.

8. The storage medium of claim 1 , wherein the method further comprises:
recording a portion of the input signals;
calculating an ejection fraction from the recorded portion of the input signals; and
causing the display device to display the ejection fraction calculated from the recorded portion of the input signals.

9. The storage medium of claim 8 , wherein the method further comprises:
calculating the ejection fraction using at least one trained statistical model.

10. The storage medium of claim 9 , wherein the at least one trained statistical model includes a deep-learning-trained neural network.

11. The storage medium of claim 9 , wherein the at least one trained statistical model includes a convolutional neural network.

12. The storage medium of claim 1 , wherein:
the first color is a yellowish color, and
the second color is a greenish color.

Assignees

• Bfly Operations Inc

Inventors

• Rothberg Alex
• Lovchinsky Igor
• Jia Jimmy
• Gafner Tomer
• De Jonge Matthew
• Rothberg Jonathan M

Classifications

• G06T7/0002 Primary

  Inspection of images, e.g. flaw detection · CPC title

• G01S17/00

  Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems · CPC title

• A61B8/0883

  for diagnosis of the heart · CPC title

• A61B8/5215

  involving processing of medical diagnostic data · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title