Automated ultrasound video interpretation of a body part with one or more convolutional neural networks

Patent metadata

Field	Value
Publication number	US-2022386998-A1
Application number	US-202217820072-A
Country	US
Kind code	A1
Filing date	Aug 16, 2022
Priority date	Aug 17, 2018
Publication date	Dec 8, 2022
Grant date	—

Abstract

In an embodiment, an intelligent system includes an electronic circuit configured to execute a neural network, to detect at least one feature in an image of a body portion while executing the neural network, and to determine a respective position and a respective class of each of the detected at least one feature while executing the neural network. For example, such a system can execute a neural network to detect at least one feature in an image of a lung, to determine a respective position within the image of each detected feature, and to classify each of the detected features as one of the following: A-line, B-line, pleural line, consolidation, and pleural effusion.

First claim

1 .- 23 . (canceled)

24 . A method executed by a computing device, comprising:
receiving an image of a body portion; and executing a classifier neural network by the computing device, the computing device is configured to execute the classifier neural network to determine a probability that the image indicates a state of a function of the body portion, the function belonging to a particular class.

25 . The method of claim 24 wherein the particular class is lung sliding.

26 . The method of claim 24 , further comprising determining that the image includes a feature belonging to the particular class in response to the probability being greater than or equal to a threshold.

27 .- 90 . (canceled)

91 . A system, comprising:
an electronic circuit configured to execute a classifier neural network, to receive, while executing the classifier neural network, an image of a body portion, and to determine, while executing the classifier neural network, a probability that the image indicates a state of a function of the body portion, the function belonging to a particular class.

92 . The system of claim 91 wherein the electronic circuit is configured:
to receive, while executing the classifier neural network, a time sequence of images of the body portion, the time sequence of images including the image; and
to determine, while executing the classifier neural network, the probability that the images indicate the state of the function of the body portion.

93 . The system of claim 91 wherein the electronic circuit is configured:
to receive, while executing the classifier neural network, a video of the body portion, the video including the image; and
to determine, while executing the classifier neural network, the probability that the video indicates the state of the function of the body portion.

94 . The system of claim 91 wherein the image includes an M-mode image.

95 . The system of claim 91 wherein the state of the function can be function exhibited or function not exhibited.

96 . The system of claim 91 wherein the body portion includes a lung and the function is lung sliding.

97 . The system of claim 91 wherein the particular class is lung sliding.

98 . The system of claim 91 , wherein the electronic circuit, while executing the neural network, is configured to determine that the image indicates a state of a function belonging to the particular class in response to the probability being greater than or equal to a threshold.

99 . The system of claim 91 wherein the electronic circuit includes a control circuit.

100 . The system of claim 91 wherein the electronic circuit includes a microprocessor.

101 . The system of claim 91 wherein the electronic circuit includes a microcontroller.

102 .- 150 . (canceled)

151 . The method of claim 24 wherein the body portion includes a lung, and the function is lung sliding.

152 . The method of claim 24 , further comprising:
receiving, while executing the classifier neural network, a time sequence of images of the body portion, the time sequence of images including the image; and determining, while executing the classifier neural network, the probability that the images indicate the state of the function of the body portion.

153 . The method of claim 24 , further comprising:
receiving, while executing the classifier neural network, a video of the body portion, the video including the image; and determining, while executing the classifier neural network, the probability that the video indicates the state of the function of the body portion.

154 . The method of claim 24 wherein the image includes an M-mode image.

155 . The method of claim 24 wherein the state of the function can be function exhibited or function not exhibited.

Assignees

• Tokitae Llc

Inventors

• Mehanian Courosh
• Kulhare Sourabh
• Zheng Xinliang
• Wilson Benjamin K

Classifications

• A61B8/5207 Primary

  involving processing of raw data to produce diagnostic data, e.g. for generating an image · CPC title

• A61B8/08 Primary

  Clinical applications (A61B8/02, A61B8/04, A61B8/06 take precedence) · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06V10/82

  using neural networks · CPC title

• G06F18/2431

  Multiple classes · CPC title