US-12616421-B2 - System and method for generating a probability value for an epileptiform abnormality by neural network to identify signal spikes

US12616421B2US 12616421 B2US12616421 B2US 12616421B2US-12616421-B2

Abstract

A method and system for generating a probability value for an event. The system includes a source for generating a plurality of digital input signals, a processor connected to the source to receive the plurality of digital input signals from the source, and a display connected to the processor for displaying a final output. Preferably, the method further includes validating the probability value.

Inventors

Nicolas Nierenberg
Scott B. Wilson
Mark L. Scheuer

Assignees

PERSYST DEVELOPMENT CORPORATION

Dates

Publication Date: 20260505
Application Date: 20230724

Claims (4)

1 . A method for removing artifacts in an electroencephalogram (EEG) recording, the method comprising: generating an EEG recording from a machine comprising a plurality of electrodes for generating a plurality of EEG signals, at least one amplifier connected to each of the plurality of electrodes by a plurality of wires to amplify each of the plurality of EEG signals, a processor connected to the amplifier to generate an EEG recording from the plurality of EEG signals, wherein the processor is configured to execute a spike review program to the EEG recording to detect a plurality of spikes on the EEG recording, and a spike detector neural network algorithms to identify sharp transients to determine a probability of being epileptiform abnormalities as a epileptiform abnormality; and a display connected to the processor for displaying an EEG recording; displaying the EEG recording on the display, the EEG recording comprising a plurality of artifacts wherein the plurality of artifacts comprises at least two of a muscle artifact, an eye movement artifact, an electrical artifact, a heartbeat artifact, a tongue movement artifact, and a chewing artifact; selecting at least one of the plurality of artifacts to automatically be removed from the EEG recording using a user interface on the display; triggering a button on a computer display to apply at least one filter of a plurality of filters to remove the at least one artifact of the plurality of artifacts from the EEG recording, wherein the button is a keyboard button or a touchscreen button, and wherein the processor is configured to apply at least one filter program to remove a filter from the EEG recording; and generating a filtered EEG recording on the display for viewing.
2 . The method according to claim 1 further comprising selecting colors for traces and the amount of darkness.
3 . A method for removing artifacts in an electroencephalogram (EEG) recording, the method comprising: generating an EEG recording from a machine comprising a plurality of electrodes for generating a plurality of EEG signals, at least one amplifier connected to each of the plurality of electrodes by a plurality of wires to amplify each of the plurality of EEG signals, a processor connected to the amplifier to generate an EEG recording from the plurality of EEG signals, wherein the processor is configured to execute a spike review program to the EEG recording to detect a plurality of spikes on the EEG recording, and spike detector neural network algorithms to identify sharp transients to determine a probability of being epileptiform abnormalities as a epileptiform abnormality; and a display connected to the processor for displaying an EEG recording; displaying the EEG recording on the display, the EEG recording comprising a plurality of artifacts wherein the plurality of artifacts comprises at least two of a muscle artifact, an eye movement artifact, an electrical artifact, a heartbeat artifact, a tongue movement artifact, and a chewing artifact; filtering the EEG recording to remove a first artifact to generate a first filtered EEG recording to replace the EEG recording on the display, wherein the processor is configured to apply a first filter program to the EEG recording; filtering the first filtered EEG recording to remove a second artifact to generate a second filtered EEG recording to replace the first filtered EEG recording on the display wherein the processor is configured to apply a second filter program to the EEG recording; filtering the second filtered EEG recording to remove a third artifact to generate a third filtered EEG recording to replace the second filtered EEG recording on the display wherein the processor is configured to apply a third filter program to the EEG recording; filtering the third filtered EEG recording to remove a fourth artifact to generate a fourth filtered EEG recording to replace the third filtered EEG recording on the display wherein the processor is configured to apply a fourth filter program to the EEG recording; and generating a clean EEG recording for viewing from a last filtered EEG recording, wherein each of the first artifact, the second artifact, the third artifact and the fourth artifact is selected from the group comprising muscle artifact, eye movement artifact, electrical artifact, heartbeat artifact, tongue movement artifact, and chewing artifact.
4 . A non-transitory computer-readable medium that stores a program that causes a processor to perform functions for removing artifacts in an electroencephalogram (EEG) recording by executing the following steps: generating an EEG recording from a machine comprising a plurality of electrodes for generating a plurality of EEG signals, at least one amplifier connected to each of the plurality of electrodes by a plurality of wires to amplify each of the plurality of EEG signals, a processor connected to the amplifier to generate an EEG recording from the plurality of EEG signals, wherein the processor is configured to execute a spike review program to the EEG recording to detect a plurality of spikes on the EEG recording, and spike detector neural network algorithms to identify sharp transients to determine a probability of being epileptiform abnormalities as a epileptiform abnormality; and a display connected to the processor for displaying an EEG recording; displaying the EEG recording on the display, the EEG recording comprising a plurality of artifacts wherein the plurality of artifacts comprises at least two of a muscle artifact, an eye movement artifact, an electrical artifact, a heartbeat artifact, a tongue movement artifact, and a chewing artifact; selecting at least one of the plurality of artifacts to automatically be removed from the EEG recording using a user interface on the display; triggering, through use of a mouse, a button on a computer display to apply at least one filter of a plurality of filters to remove the at least one artifact of the plurality of artifacts from the EEG recording, and wherein the processor is configured to apply at least one filter program to remove a filter from the EEG recording; and generating a filtered EEG recording on the display for viewing.

Description

CROSS REFERENCES TO RELATED APPLICATIONS The Present application is a continuation of U.S. patent application Ser. No. 17/175,635, filed on Feb. 13, 2021, which is a continuation of U.S. patent application Ser. No. 16/101,485, filed on Aug. 12, 2018, now U.S. patent Ser. No. 10/929,753, issued on Feb. 23, 2021, which is a continuation of U.S. patent application Ser. No. 14/222,655, filed on Mar. 23, 2014, now abandoned, which claims priority to U.S. Provisional Patent Application No. 61/929,120, filed on Jan. 20, 2014, each of which is hereby incorporated by reference in its entirety. STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT Not Applicable BACKGROUND OF THE INVENTION Field of the Invention The present invention generally relates to a method and system for generating a probability value. More specifically, the present invention relates to a method and system for training a neural network for generating a probability value. Description of the Related Art Artificial neural networks are computational models capable of machine learning and pattern recognition. The artificial neural network generally is interconnected neurons that compute values from inputs by feeding data through the artificial neural network. Artificial neural networks have application in numerous areas including voice recognition, medical diagnosis, finance, trading, facial recognition, chemistry, game playing, decision making, robotics, and the like. General definitions for terms utilized in the pertinent art are set forth below. Boolean algebra is the subarea of algebra in which the values of the variables are the truth values true and false, usually denoted 1 and 0 respectively. A Boolean network (BN) is a mathematical model of biological systems based on Boolean logic. The BN has a network structure consisting of nodes that correspond to genes or proteins. Each node in a BN takes a value of 1 or 0, meaning that the gene is or is not expressed. Fuzzy logic is a form of many-valued logic; it deals with reasoning that is approximate rather than fixed and exact. Compared to traditional binary sets (where variables may take on true or false values) fuzzy logic variables may have a truth value that ranges in degree between 0 and 1. Fuzzy logic has been extended to handle the concept of partial truth, where the truth value may range between completely true and completely false. Furthermore, when linguistic variables are used, these degrees may be managed by specific functions. Irrationality can be described in terms of what is known as the “fuzzjective”. Multilayer perceptron (“MLP”) is a feedforward artificial neural network model that maps sets of input data onto a set of appropriate outputs. An MLP consists of multiple layers of nodes in a directed graph, with each layer fully connected to the next one. Except for the input nodes, each node is a neuron (or processing element) with a nonlinear activation function. Neural network (“NN”) is an interconnected group of natural or artificial neurons that uses a mathematical or computational model for information processing based on a connectionistic approach to computation. In more practical terms neural networks are non-linear statistical data modeling or decision making tools. They can be used to model complex relationships between inputs and outputs or to find patterns in data. Perceptron is a simple model of an artificial neuron which can predict boolean events after having been trained on past events. The perceptron is specified by the number of inputs N, and the weights connecting the inputs to the output node. The weights are the parameters which must be either set by hand or learned by a learning algorithm. ROC curve (receiver operating characteristic) is a graphical plot of test sensitivity as the y coordinate versus its 1 minus specificity or false positive rate (FPR), as the x coordinate. The ROC curve is an effective method of evaluating the performance of diagnostic tests. “Amplitude” refers to the vertical distance measured from the trough to the maximal peak (negative or positive). It expresses information about the size of the neuron population and its activation synchrony during the component generation. The term “analogue to digital conversion” refers to when an analogue signal is converted into a digital signal which can then be stored in a computer for further processing. Analogue signals are “real world” signals (e.g., physiological signals such as electroencephalogram, electrocardiogram or electrooculogram). In order for them to be stored and manipulated by a computer, these signals must be converted into a discrete digital form the computer can understand. An electroencephalogram (“EEG”) is a diagnostic tool that measures and records the electrical activity of a person's brain in order to evaluate cerebral functions. Multiple electrodes are attached to a person's head and connected to a machine by wires. The machine amplifies the signals and records the