SYSTEMS AND METHODS FOR IMPEDANCE ANALYSIS OF CONDUCTIVE MEDIUM

• US 20160195484A1
• Filed: 03/15/2016
• Published: 07/07/2016
• Est. Priority Date: 04/20/2006
• Status: Active Grant

• Current Assignee: Jack S. Emery
• Original Assignee: Jack S. Emery
• Inventors: Emery, Jack S.
• Granted Patent: US 10,154,819 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A61B 2576/00 Medical imaging apparatus involving image processing or analysis A61B1/00009, A61B6/52 and A61B8/52 take precedence; image processing per se G06T; details of algorithms for analysing medical images G06T7/0012
• CPC Class Codes: A61B 5/0536 Impedance imaging, e.g. by tomography
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G01N 27/026 Dielectric impedance spectroscopy electrochemical impedance spectroscopy for measuring corrosion G01N17/02
• CPC Class Codes: G01N 33/4833 of solid biological material, e.g. tissue samples, cell cultures tissue in vivo A61B5/00; cell suspensions G01N33/48735
• CPC Class Codes: G01R 19/0084 measuring voltage only all subgroups of G01R19/00 take precedence
• CPC Class Codes: G01R 19/0092 measuring current only all subgroups of G01R19/00 take precedence
• CPC Class Codes: G01R 27/02 Measuring real or complex resistance, reactance, impedance, or other two-pole characteristics derived therefrom, e.g. time constant by measuring phase angle only G01R25/00
• CPC Class Codes: G01R 27/08 Measuring resistance by measuring both voltage and current
• CPC Class Codes: G01R 27/14 Measuring resistance by measuring current or voltage obtained from a reference source G01R27/16, G01R27/20, G01R27/22 take precedence
• CPC Class Codes: G01R 27/16 Measuring impedance of element or network through which a current is passing from another source, e.g. cable, power line
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Embodiments of systems and methods are disclosed for classifying a condition of an entity comprising a conductive medium having multiple conductive paths, using a pattern recognition strategy to classify a signature constructed from impedance-interrogation measurements.

Claims

1. A method of classifying a condition of an entity comprising a plurality of points separated by a conductive medium offering a plurality of conductive paths between the points, the method comprising:

obtaining a plurality of impedance-interrogation measurements;

processing the plurality of impedance-interrogation measurements into a signature; and

from the signature, classifying a condition of the entity by machine execution of a pattern recognition strategy.

2. The method of claim 1, wherein each impedance-interrogation measurement comprises at least one value obtained by a method comprising applying an interrogation signal at at least one of the points and measuring an electrical quantity comprising a response to the interrogation signal, wherein the response may comprise a null response.

3. The method of claim 1, wherein the entity comprises a living organism and the conductive medium comprises all or a portion of the living organism.

4. The method of claim 1, wherein classifying a condition of an entity comprises classifying the condition of the entity as corresponding or not corresponding to a pathological state.

5. The method of claim 1, wherein classifying a condition of an entity comprises classifying the condition of the entity as corresponding or not corresponding to a specific pathological state.

6. The method of claim 1, wherein applying an electrical signal comprises inducing an ionic current in the conductive medium.

7. The method of claim 1, wherein the signature comprises a feature vector.

8. The method of claim 1, wherein the signature comprises a feature vector and the pattern recognition strategy comprises comparing said feature vector with at least one reference feature vector.

9. The method of claim 1, wherein the signature comprises a feature vector and the pattern recognition strategy comprises classifying the feature vector using a pattern recognizer trained on a training set of reference feature vectors.

10. The method of claim 1, wherein the signature comprises a feature vector and the pattern recognition strategy comprises classifying the feature vector using a pattern recognition method selected from:

a neural network, a genetic algorithm, an evolutionary algorithm, a deep learning algorithm, a supervised machine learning algorithm, an unsupervised machine learning algorithm, a dimension reduction strategy, a support vector machine, a linear classifier, a binary tree classifier, a Gaussian process classifier, a k-nearest neighbor classifier, and a Bayesian network classifier.

11. The method of claim 1, wherein at least one impedance-interrogation measurement comprises an estimate of an impedance property of the conductive medium.

12. The method of claim 1, wherein the signature further comprises at least one value derived from a measurement or observation that is not an impedance-interrogation measurement.

13. The method of claim 1, wherein the plurality of impedance-interrogation measurements are not processed into a graphical representation or image.

14. The method of claim 1, wherein processing the plurality of impedance-interrogation measurements into a signature comprises selecting a predetermined set of impedance-interrogation measurements or values derived therefrom for inclusion, and ordering the values in a predetermined manner.

15. The method of claim 1, wherein processing the plurality of impedance-interrogation measurements into a signature comprises assigning weights to the values comprising the signature.

16. A system for classifying a condition of an entity comprising a plurality of points separated by a conductive medium offering a plurality of conductive paths between the points, the system comprising:

a signal source for applying one or more electrical signals at one or more points;

a measuring component for measuring one or more electrical properties of the entity;

a controller adapted and configured to (a) control the signal source and the measuring component to make a plurality of impedance-interrogation measurements, and (b) produce an output comprising the values obtained from the plurality of impedance-interrogation measurements; and

a signature processor adapted and configured to process the plurality of electrical properties into a signature.

17. The system of claim 16, further comprising a pattern recognizer programmed to classify, from the signature, a condition of the entity by machine execution of a pattern recognition strategy.

18. The system of claim 16, further comprising a user interface component.

19. The system of claim 16, further comprising an interrogation interface component and a measuring interface component.