Method and system for defining cut lines to generate a 3D fetal representation
AssigneeClarius Mobile Health Corp.
InventorsKris Dickie, Laurent Pelissier, Parisa Asgharzadeh
Life of this patent
Estimating the term…
Abstract
A plurality of ultrasound frames of a fetus are acquired using an ultrasound scanner, which may be oriented arbitrarily with respect to the fetus during the acquisition. The ultrasound frames are processed against an artificial intelligence model to predict a different cut line on each of the ultrasound frames. Each cut line is predicted to be exterior to an image of the fetus appearing on the ultrasound frame. The different cut lines on the plurality of ultrasound frames are then used to identify ultrasound data in the image frames to generate a 3D representation of the fetus.
Claims20
A method for defining cut lines to generate a three-dimensional (“3D”) representation of a fetus, the method comprising:
- acquiring a plurality of two-dimensional (“2D”) ultrasound frames of the fetus using an ultrasound scanner in an arbitrary orientation with respect to the fetus;
- processing, by a processor, each 2D acquired ultrasound frame of the plurality of 2D acquired ultrasound frames against an artificial intelligence (“AI”) model, the AI Model being trained with a plurality of 2D training ultrasound frames each frame being on a plane, as scanned, and each having a training cut line thereon, wherein a training cut line on a 2D training ultrasound frame is labeled as acceptable if all points on the training cut line are positioned around a fetal body part of the fetus imaged in the plane of the 2D training ultrasound frame, wherein the processing of the 2D acquired ultrasound frame against the AI model is to predict a cut line (predicted cut line) on each of the 2D acquired ultrasound frames;
- and
- using the different predicted cut lines on the plurality of 2D acquired ultrasound frames to generate the 3D representation of the fetus.
An ultrasound system for generating a three-dimensional (“3D”) representation of a fetus, the system comprising:
- an ultrasound scanner configured to acquire a plurality of two-dimensional (“2D”) acquired ultrasound frames of the fetus with the ultrasound scanner in an arbitrary orientation with respect to the fetus;
- and
- a processor configured to:
- process each 2D acquired ultrasound frame of the plurality of 2D acquired ultrasound frames against an artificial intelligence (“AI”) model, the AI model being trained with a plurality of 2D training ultrasound frames each frame being on a plane, as scanned, and each having a training cut line thereon, wherein a 2D training ultrasound frame wherein a training cut line on a 2D training ultrasound frame is labeled as acceptable if all points on the training cut line are positioned around a fetal body part of the fetus imaged in the plane of the 2D training ultrasound frame, wherein the processing of the 2D acquired ultrasound frame against the AI model is to predict a cut line (predicted cut line) on each of the 2D acquired ultrasound frames;
- and
- use the different predicted cut lines on the plurality of 2D acquired ultrasound frames to generate the 3D representation of the fetus.
A non-transitory computer-readable media storing computer-readable instructions, which, when executed by a processor cause the processor to:
- receive a plurality of two-dimensional (“2D”) acquired ultrasound frames of a fetus from an ultrasound scanner in an arbitrary orientation with respect to the fetus;
- process each 2D acquired ultrasound frame of the plurality of 2D acquired ultrasound frames against an artificial intelligence (“AI”) model, the AI model being trained with a plurality of 2D training ultrasound frames each frame being on a plane, as scanned, and each having a training cut line thereon, wherein a training cut line on a 2D training ultrasound frame is labeled as acceptable if all points on the training cut line are positioned around a fetal body part of the fetus imaged in the plane of the 2D training ultrasound frame, wherein the processing of the 2D acquired ultrasound frame against the AI model to predict a cut line (predicted cut line) on each of the 2D acquired ultrasound frames;
- and
- use the different predicted cut lines on the plurality of 2D acquired ultrasound frames to generate a three-dimensional (3D) representation of the fetus.
Dependencies are inferred from the claim text.