Application US20190328257

MACHINE LEARNING USING SIMULATED CARDIOGRAMS
[+] Show Details

US20190328257

1. A method performed by one or more computing systems for generating a classifier for classifying electromagnetic data derived from an electromagnetic source within a body, the method comprising: (6) (4)

accessing a computational model of the electromagnetic source, the computational model for modeling electromagnetic output of the electromagnetic source over time based on a source configuration of the electromagnetic source;

for each of a plurality of source configurations, generating using the computational model a modeled electromagnetic output of the electromagnetic source for that source configuration;

for each modeled electromagnetic output, deriving electromagnetic data for the modeled electromagnetic output; and

generating a label for the derived electromagnetic data based on the source configuration for the modeled electromagnetic data; and

training a classifier with the derived electromagnetic data and the labels as training data.

2. The method of claim 1 wherein the modeled electromagnetic output for a source configuration includes, for each of a plurality of time intervals, an electromagnetic mesh with a modeled electromagnetic value for each of a plurality of locations of the electromagnetic source. (1) (0)

3. The method of claim 2 wherein the derived electromagnetic data, for a time interval, is an equivalent source representation of the electromagnetic output. (2) (0)

9. The method of claim 1 wherein the classifier is a convolutional neural network. (1) (0)

11. The method of claim 1 wherein the classifier is a recurrent neural network, an autoencoder, or a restricted Boltzmann machine. (0)

12. The method of claim 1 wherein the classifier is a support vector machine. (0)

13. The method of claim 1 wherein the classifier is Bayesian. (0)

14. The method of claim 1 wherein the electromagnetic source is a heart, a source configuration represents source location and other properties of a heart disorder, the modeled electromagnetic output represents activation of the heart, and the derived electromagnetic data represents body-surface measurements. (1) (0)

16-21. (canceled) (0)

21. One or more computing systems for generating a classifier for classifying electromagnetic data derived from an electromagnetic source within a human body, the one or more computing systems comprising: (5) (2)

one or more computer-readable storage mediums storing computer-executable instructions for controlling the one or more computing systems to: access a computational model of the electromagnetic source, the computational model for modeling electromagnetic output of the electromagnetic source over time based on a source configuration of the electromagnetic source;

for each of a plurality of source configurations, generate using the computational model a modeled electromagnetic output of the electromagnetic source for that source configuration;

derive electromagnetic data for the modeled electromagnetic output; and

generate a label for the derived electromagnetic data based on the source configuration; and

train a classifier with the derived electromagnetic data and the labels as training data; and

one or more processors for executing the computer-executable instructions stored in the one or more computer-readable storage mediums.

22. The one or more computing systems of claim 21 wherein the modeled electromagnetic output for a source configuration includes, for each of a plurality of time intervals, an electromagnetic mesh with a modeled electromagnetic value for each of a plurality of locations of the electromagnetic source. (1) (0)

26. The one or more computing systems of claim 21 wherein the electromagnetic source is a heart, a source configuration represents source location and other properties of a heart, the modeled electromagnetic output represents activation of the heart, and the derived electromagnetic data represents an electrocardiogram. (1) (0)

30. The one or more computing systems of claim 21 wherein the electromagnetic source is a heart, a source configuration represents source location and other properties of a heart, the modeled electromagnetic output represents activation of the heart, and the derived electromagnetic data represents a vectorcardiogram. (0)

31. The one or more computing systems of claim 21 wherein the computer-executable instructions further control the one or more computing systems to: (0) (2)

32. The one or more computing systems of claim 21 wherein the electromagnetic source is a brain and the electromagnetic data represents an electroencephalogram. (0)

33. One or more computing systems for generating a classifier for classifying electromagnetic data derived from an electromagnetic source, the electromagnetic source being a human heart and the electromagnetic data representing a cardiogram, the one or more computing systems comprising: (2) (2)

one or more computer-readable storage mediums storing: a computational model of the heart, the computational model for modeling electromagnetic output that represents activation of the heart over time based on a source configuration of the heart; and

computer-executable instructions for controlling the one or more computing systems to: for each of a plurality of source configurations for a heart, generate training data that includes a cardiogram and a label, the cardiogram being derived from the electromagnetic output of the computational model that is based on the source configuration, the label being based on the source configuration; and

train the classifier using the training data, the classifier for identifying a label for a cardiogram collected from a target human; and

one or more processors for executing the computer-executable instructions stored in the one or more computer-readable storage mediums.

34. The one or more computing systems of claim 33 wherein the source configuration includes a source location of a heart disorder and the label is the source location of the source configuration that the cardiogram is based on. (0)

35. The one or more computing systems of claim 33 wherein the source configuration includes information selected from the group consisting of information on geometry and muscle fibers of the heart, torso anatomy, and electrical properties of a heart. (0)

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Application US20190328257

MACHINE LEARNING USING SIMULATED CARDIOGRAMS

Patent Matrix® Search