SYSTEM AND METHOD TO ESTIMATE REGION OF TISSUE ACTIVATION

• US 20110191275A1
• Filed: 08/26/2010
• Published: 08/04/2011
• Est. Priority Date: 08/27/2009
• Status: Active Grant

• Current Assignee: Cleveland Clinic Foundation
• Original Assignee: Cleveland Clinic Foundation
• Inventors: Chaturvedi, Ashu, Lujan, J. Luis, McIntyre, Cameron C.
• Granted Patent: US 8,589,316 B2
• Time in Patent Office: Days
• US Class Current: 706/12
• CPC Class Codes: A61N 1/0534 Electrodes for deep brain stimulation
• CPC Class Codes: A61N 1/36082 Cognitive or psychiatric applications, e.g. dementia or Alzheimer's disease
• CPC Class Codes: A61N 1/36185 Selection of the electrode configuration
• CPC Class Codes: A61N 1/37252 Details of algorithms or data aspects of communication system, e.g. handshaking, transmitting specific data or segmenting data
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06F 18/2411 based on the proximity to a decision surface, e.g. support vector machines
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
• CPC Class Codes: G16H 20/40 relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

A computer-implemented method for determining the volume of activation of neural tissue. In one embodiment, the method uses one or more parametric equations that define a volume of activation, wherein the parameters for the one or more parametric equations are given as a function of an input vector that includes stimulation parameters. After receiving input data that includes values for the stimulation parameters and defining the input vector using the input data, the input vector is applied to the function to obtain the parameters for the one or more parametric equations. The parametric equation is solved to obtain a calculated volume of activation.

Claims

1. A computer-implemented method for determining the volume of activation of neural tissue, comprising:

having one or more parametric equations that define a volume of activation, wherein the parameters for the one or more parametric equations are given as a function of an input vector that includes stimulation parameters;

receiving input data that includes values for the stimulation parameters and defining the input vector using the input data;

applying the input vector to the function and obtaining the parameters for the one or more parametric equations;

solving the parametric equation to calculate the volume of activation; and

displaying the calculated volume of activation on a display screen.

2. The method of claim 1, wherein equation parameters are given as a linear function of the input vector.

3. The method of claim 1, wherein the input vector further includes electrode configuration parameters, and wherein the input data further includes values for the electrode configuration parameters.

4. The method of claim 1, wherein the one or more parametric equations represent a geometric shape.

5. The method of claim 4, wherein the geometric shape is an ellipsoid shape.

6. The method of claim 1, wherein the function is generated from a computational training algorithm that maps a range of stimulation parameters and electrode configuration parameters to volumes of activation produced by the range of stimulation parameters and electrode configuration parameters.

7. The method of claim 6, wherein the volumes of activation produced by the range of stimulation parameters and electrode configuration parameters are represented as geometric shapes that are defined by the one or more parametric equations.

8. The method of claim 6, wherein the volumes of activation are obtained from the coupling of an electric field model of an electrode inserted into neural tissue to a neural tissue model.

9. The method of claim 6, wherein the computational training algorithm uses one or more artificial neural networks.

10. The method of claim 1, wherein the input vector include one or more of pulse width, electrode contact impedance, encapsulation tissue conductivity, voltage, or electrode contact configuration.

11. The method of claim 1, wherein the calculated volume of activation is obtained directly from the solution to the parametric equation.

12. A computer system that is programmed to perform steps that comprise:

providing one or more parametric equations that define a volume of activation, wherein the parameters for the one or more parametric equations are given as a function of an input vector that includes stimulation parameters;

receiving input data that includes values for the stimulation parameters and defining the input vector using the input data;

applying the input vector to the function and obtaining the parameters for the one or more parametric equations; and

solving the parametric equation to calculate the volume of activation.

13. A non-transitory computer-readable storage medium comprising instructions for:

providing one or more parametric equations that define a volume of activation, wherein the parameters for the one or more parametric equations are given as a function of an input vector that includes stimulation parameters;

receiving input data that includes values for the stimulation parameters and defining the input vector using the input data;

applying the input vector to the function and obtaining the parameters for the one or more parametric equations; and

solving the parametric equation to calculate the volume of activation.

14. A method for determining a function that outputs the parameters of one or more parametric equations that define a volume of activation, comprising:

having an electric field model of an electrode and a neural tissue model;

coupling the electric field model to the neural tissue model to obtain volumes of activation for multiple different sets of stimulation parameters and electrode configuration parameters;

fitting a geometric shape to the volumes of activation, wherein the geometric shape is defined by one or more parametric equations; and

using a computational training algorithm to design a function that correlates the different sets of stimulation parameters and electrode configuration parameters to the parameters for the one or more parametric equations that represent the geometric shapes that are fitted to the volumes of activation.

15. The method of claim 14, wherein the fitting of the geometric shape to the volume of activation is performed using an optimization algorithm.

16. The method of claim 14, wherein the geometric shape is an ellipsoid.

17. The method of claim 14, wherein the computational training algorithm uses one or more artificial neural networks.

18. A non-transitory computer-readable storage medium comprising instructions for determining the volume of activation using one or more parametric equations whose parameters are given as a function of an input vector that includes stimulation parameters and electrode configuration parameters, wherein the function is obtained by the method of claim 14.

19. A computer-implemented method comprising:

providing a volume of tissue activation (VTA) estimator that includes artificial intelligence trained to output parameters corresponding to an estimated volume of tissue activation (VTA) for a set of input parameters, the input parameters including stimulation parameters and configuration parameters relating to configuration of electrode contact configurations; and

employing the VTA estimator to determine the estimated VTA for input parameters for which no simulations or clinical studies have been performed.

20. The method of claim 19, further comprising correlating the estimated VTA with a target VTA to provide an indication of theoretically optimal stimulation parameter settings for a given patient.