DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-6, 9-13, and 16-20 are rejected under 35 U.S.C. 103 as being unpatentable over Kaemmerer(CN 112999518 A) and further in view of McIntyre(US 20060017749 A1).
Regarding claim 1, Kaemmerer discloses a method for recommending a stimulation electrode combination, comprising: receiving potentials of a plurality of electrodes in a process of treatment delivery; calculating a difference between potentials of any two electrodes of the plurality of electrodes based on the potentials of the plurality of electrodes to obtain a voltage between the any two electrodes; acquiring, based on the voltage between the any two electrodes within a preset time range, a feature signal corresponding to an electrode combination formed by the any two electrodes; and determining a recommended stimulation electrode combination from all electrode combinations based on a feature signal corresponding to each electrode combination(For example, as shown in FIG. 6, processor 80 such as programmer 14 can determine a plurality of electrical signal representation, each electrical signal representation of the plurality of electrical signal representation associated with the corresponding electrode combination (602)(see attached translation, page 18, paragraph 3). For example, in the form of electrical pulse to deliver electrical stimulation, the treatment parameter may include an electrode configuration (the electrode configuration comprises electrode combination and electrode polarity), amplitude (the amplitude can be current amplitude or voltage amplitude), pulse width and pulse rate(see attached translation, page 2, paragraph 4). The one or more processors may include in the specific patient is configured to be configured for using the one or more implantable electrodes to deliver electrical stimulation to the specific patient in the device; and the one or more processors may be further configured to determine the electrical signal representation for the particular patient based on the electrical signal measured between one or more contact combinations in the plurality of electrode combinations(see attached translation, page 23, paragraph 3). Kaemmerer fails to disclose “calculating a difference between potentials of any two electrodes of the plurality of electrodes based on the potentials of the plurality of electrodes”.
However, McIntyre teaches “A computer-assisted method comprising: obtaining volumetric imaging data representing an anatomic volume of a patient; calculating at least one volume of influence in a region near at least one candidate electrode target location in the anatomic volume, in which the calculating includes using a computer model that allows a non-uniform conductivity in the region to represent inhomogeneous and anisotropic tissue properties; and selecting a recommended electrode target location in the anatomic volume using the at least one calculated volume of influence[claim 1]. The method of claim 1, in which the calculating the volume of influence near the candidate electrode target location in the anatomic volume includes calculating a second difference of a potential distribution to represent the volume of influence[claim 4]”.
It would be obvious to one of ordinary skill in the art before the effective filing date to configure the electrode selection for stimulation therapy of Kaemmerer with the potential differences of the brain stimulation models of McIntyre. Doing so would specify the differences in electrical parameters between electrodes in each configuration to determine the optimal placement.
Regarding claim 2, Kaemmerer in view of McIntyre teaches the method according to claim 1, wherein determining the recommended stimulation electrode combination from the all electrode combinations based on the feature signal corresponding to the each electrode combination comprises: acquiring, based on one or more of a signal strength of the feature signal corresponding to the each electrode combination, a pulse width of the feature signal corresponding to the each electrode combination, or a similarity between the feature signal and a desired signal, a score corresponding to the each electrode combination; and taking an electrode combination with a highest score as the recommended stimulation electrode combination based on scores corresponding to the all electrode combinations(As shown in FIG. 4, the electrode selection module 78 may include a plurality of machine learning models 94A to 94N (collectively referred to as "machine learning model 94"). In some examples, each model of the model 94 may be based on a plurality of electrical signal representation of a plurality of electrical signal representation of the one or more electrical signal representation of the training support vector machine (SVM) classifier(see attached translation, page 15, paragraph 6).The machine learning model 94B may determine a score 96B that indicates the patient's electrical signal pattern to a degree similar to the pattern from the patient received via the electrode 24B for effective electrical stimulation therapy; The machine learning model 94N may determine a fraction 96N that indicates the patient's electrical signal pattern to a degree similar to that of a patient from the combination of both the electrode 24A and the electrode 24C receiving the effective electrical stimulation therapy(see attached translation, page 16, paragraph 1). As shown in FIG. 4, the electrode selection module 78 may include a selector 98, the selector may be configured for selecting for delivering electrical stimulation to the patient electrode combination. For example, the selector 98 can select electrode combination based on fraction 96. In some examples, the machine learning model determines the higher the score, associated with the machine learning model of the electrode combination will be more likely to be beneficial to delivery treatment to a particular patient. As an example, the selector 98 may select a contact or electrode combination associated with a machine learning model that determines the highest score in fraction 96 in the machine learning model 94(see attached translation, page 16, paragraph 2)).
Regarding claim 5, Kaemmerer discloses a system for recommending a stimulation electrode combination, comprising: an apparatus configured to receive potentials of a plurality of electrodes in a process of treatment delivery; an apparatus configured to calculate a difference between potentials of any two electrodes of the plurality of electrodes based on the potentials of the plurality of electrodes to obtain a voltage between the any two electrodes; an apparatus configured to acquire, based on the voltage between the any two electrodes within a preset time range, a feature signal corresponding to an electrode combination formed by the any two electrodes; and an apparatus configured to determine a recommended stimulation electrode combination from all electrode combinations based on a feature signal corresponding to each electrode combination(For example, as shown in FIG. 6, processor 80 such as programmer 14 can determine a plurality of electrical signal representation, each electrical signal representation of the plurality of electrical signal representation associated with the corresponding electrode combination (602)(see attached translation, page 18, paragraph 3). For example, in the form of electrical pulse to deliver electrical stimulation, the treatment parameter may include an electrode configuration (the electrode configuration comprises electrode combination and electrode polarity), amplitude (the amplitude can be current amplitude or voltage amplitude), pulse width and pulse rate(see attached translation, page 2, paragraph 4). The one or more processors may include in the specific patient is configured to be configured for using the one or more implantable electrodes to deliver electrical stimulation to the specific patient in the device; and the one or more processors may be further configured to determine the electrical signal representation for the particular patient based on the electrical signal measured between one or more contact combinations in the plurality of electrode combinations(see attached translation, page 23, paragraph 3)). Kaemmerer fails to disclose “calculating a difference between potentials of any two electrodes of the plurality of electrodes based on the potentials of the plurality of electrodes”.
However, McIntyre discloses “FIG. 1A illustrates examples of a potential distribution (V.sub.e) and its second difference (.DELTA..sup.2V.sub.e). FIG. 1A compares (for an isotropic tissue medium) a monopolar point source (-1 mA stimulation current; illustrated in the left column of FIG. 1A), a monopolar DBS leadwire electrode (-1 V stimulation voltage, illustrated in the middle two columns of FIG. 1A), and a bipolar DBS leadwire with two electrode contacts (+/-1 V stimulation voltages, respectively, illustrated in the right column of FIG. 1A)[0033]. in which the calculating includes using a computer model that allows a non-uniform conductivity in the region to represent inhomogeneous and anisotropic tissue properties; and selecting a recommended electrode target location in the anatomic volume using the at least one calculated volume of influence[claim 1]”.
It would be obvious to one of ordinary skill in the art before the effective filing date to configure the electrode selection for stimulation therapy of Kaemmerer with the potential differences of the brain stimulation models of McIntyre. Doing so would specify the differences in electrical parameters between electrodes in each configuration to determine the optimal placement.
Regarding claim 6, Kaemmerer in view of McIntyre teaches the system according to claim 5, wherein the apparatus configured to determine the recommended stimulation electrode combination from the all electrode combinations based on the feature signal corresponding to the each electrode combination comprises: an apparatus configured to acquire, based on one or more of a signal strength of the feature signal corresponding to the each electrode combination, a pulse width of the feature signal corresponding to the each electrode combination, or a similarity between the feature signal and a desired signal, a score corresponding to the each electrode combination; and an apparatus configured to take an electrode combination with a highest score as the recommended stimulation electrode combination based on scores corresponding to the all electrode combinations(According to this embodiment, in order to select the electrode combination, the one or more processors are configured to determine a corresponding score for each corresponding SVM in the plurality of SVM; the score indicates that the sensing electrical signal for the particular patient represents a degree similar to the sensing electrical signal from a plurality of patients; the corresponding electrode combination associated with the corresponding SVM has been therapeutically effective for delivering electrical stimulation to the plurality of patients. In addition, the one or more processors are configured for based on the fraction to select the electrode combination for delivering stimulation to the particular patient. In this embodiment, each corresponding sensing electrical signal representation of the plurality of sensing electrical signal representation may optionally be selected for the plurality of electrodes in the plurality of patient corresponding to the corresponding electrode combination of the patient delivery electrical stimulation associated with the patient(see attached translation, page 23, paragraph 1). In some examples, the machine learning model determines the higher the score, associated with the machine learning model of the electrode combination will be more likely to be beneficial to delivery treatment to a particular patient(see attached translation, page 16, paragraph 2)).
Regarding claim 9, Kaemmerer in view of McIntyre teaches the system according to claim 6, wherein the apparatus configured to acquire, based on one or more of the signal strength of the feature signal corresponding to the each electrode combination, the pulse width of the feature signal corresponding to the each electrode combination, or the similarity between the feature signal and the desired signal, the score corresponding to the each electrode combination comprises: an apparatus configured to acquire, based on one or more of the signal strength of the feature signal corresponding to the each electrode combination, the pulse width of the feature signal corresponding to the each electrode combination, or the similarity between the feature signal and the desired signal, a score corresponding to an electrode combination when a feature signal corresponding to the electrode combination meets a preset condition, wherein the preset condition comprises one or more of the signal strength of the feature signal being greater than a preset signal strength or the pulse width of the feature signal satisfying a preset pulse width range(In the example shown in FIG. 2, the memory 62 may store the treatment program 74, the operation instruction 76 and the electrode selection module 78 stored in a separate memory, such as memory 62, or a separate area within the memory 62. each therapeutic procedure 74 stored according to the electrical stimulation parameter (such as electrode combination, current or voltage amplitude) corresponding value defining a specific treatment program, and, if the stimulation generator 64 generates and delivers the stimulation pulse, the treatment program can define the pulse width and pulse rate of the stimulation signal value(see attached translation, page 12, paragraph 2)).
Regarding claim 10, Kaemmerer in view of McIntyre teaches the system according to claim 6, wherein an acquisition process of the similarity between the feature signal and the desired signal is as follows: inputting the feature signal and the desired signal into a similarity model to obtain the similarity between the feature signal and the desired signal, wherein the similarity model is trained and obtained using a preset deep learning neural network(In some examples, the processor 60 may be configured to use the plurality of SVM by determining a corresponding score for each corresponding SVM in the plurality of SVM; The fraction indicates a patient ' s electrical signal pattern similar to a pattern from a patient receiving an effective electrical stimulation therapy from a corresponding electrode combination associated with a corresponding SVM. In some examples, the electric signal for a particular patient indicates that the corresponding electrode combination to receive the effective electrical stimulation treatment of patient mode similar to the degree is larger, through the corresponding electrode combination to deliver treatment will be beneficial to a particular patient the possibility is larger. Thus, the processor 60 may be configured for based on the fraction to select the electrode combination for delivering stimulation to a particular patient(see attached translation, page 16, paragraph 2)).
Regarding claim 11, Kaemmerer in view of McIntyre teaches the system according to claim 10, wherein a training process of the similarity model is as follows: inputting a first training signal and a second training signal into the preset deep learning neural network to obtain a predicted similarity between the first training signal and the second training signal; calculating and obtaining a predicted loss value based on the predicted similarity between the first training signal and the second training signal and an annotated similarity between the first training signal and the second training signal; and updating a parameter of the preset deep learning neural network based on the predicted loss value to obtain the similarity model(As shown in FIG. 4, the electrode selection module 78 may include a plurality of machine learning models 94A to 94N (collectively referred to as "machine learning model 94"). In some examples, each model of the model 94 may be based on a plurality of electrical signal representation of a plurality of electrical signal representation of the one or more electrical signal representation of the training support vector machine (SVM) classifier. Each machine learning model in machine learning model 94 may be associated with a particular electrode combination in the plurality of electrodes. For example, machine learning model 94A can be associated with the electrode 24A (i.e., when the electrode 24A is selected for monopolar stimulation, can be based on the sensed electric signal representation to train the machine learning model 94A); machine learning model 94B can be associated with the electrode 24B (i.e., when the electrode 24B is selected for unipolar stimulation, can be based on the sensed electric signal representation to train the machine learning model 94B); and the machine learning model 94N can be associated with the electrode 24A and electrode 24C (i.e., when the electrode 24A and electrode 24C is selected for bipolar stimulation, can be based on the sensed electric signal representation to train the machine learning model 94N). Each machine learning model in machine learning model 94 can be configured for determining the corresponding score (respectively score 96A to 96N, collectively referred to as "score 96") the fraction indicating the electrical signal mode for a particular patient and prior to a plurality of patients with the following fact to obtain the electric signal pattern similar to the degree: A particular electrode selection for delivering electrical stimuli produces an effective treatment for the patient. For example, machine learning model 94A can determine the score 96A, the score indicating the patient electric signal mode from the mode similar to the mode from the electrode 24A receiving the effective electrical stimulation treatment of the patient; The machine learning model 94B may determine a score 96B that indicates the patient's electrical signal pattern to a degree similar to the pattern from the patient received via the electrode 24B for effective electrical stimulation therapy; The machine learning model 94N may determine a fraction 96N that indicates the patient's electrical signal pattern to a degree similar to that of a patient from the combination of both the electrode 24A and the electrode 24C receiving the effective electrical stimulation therapy(see attached translation, page 16, paragraph 1)).
Regarding claim 12, Kaemmerer discloses a system for recommending a stimulation electrode combination, comprising: a plurality of electrodes able to be positioned within a brain of a patient to deliver treatment to the patient or sense an electrical activity; a treatment delivery circuit operably coupled to the plurality of electrodes to deliver the treatment to the patient; a sensing circuit operably coupled to the plurality of electrodes to sense the electrical activity; and a controller comprising a processing circuit system operably coupled to the treatment delivery circuit and the sensing circuit, wherein the controller is configured to: control, through the treatment delivery circuit, one or more of the plurality of electrodes to deliver the treatment to the patient; sense potentials of the plurality of electrodes through the sensing circuit in a process of treatment delivery; calculate a difference between potentials of any two electrodes of the plurality of electrodes based on the potentials of the plurality of electrodes to obtain a voltage between the any two electrodes; acquire, based on the voltage between the any two electrodes within a preset time range, a feature signal corresponding to an electrode combination formed by the any two electrodes; and determine a recommended stimulation electrode combination from all electrode combinations based on a feature signal corresponding to each electrode combination(For example, as shown in FIG. 6, processor 80 such as programmer 14 can determine a plurality of electrical signal representation, each electrical signal representation of the plurality of electrical signal representation associated with the corresponding electrode combination (602)( see attached translation, page 18, paragraph 3). For example, in the form of electrical pulse to deliver electrical stimulation, the treatment parameter may include an electrode configuration (the electrode configuration comprises electrode combination and electrode polarity), amplitude (the amplitude can be current amplitude or voltage amplitude), pulse width and pulse rate(see attached translation, page 2, paragraph 4). the one or more processors may include in the specific patient is configured to be configured for using the one or more implantable electrodes to deliver electrical stimulation to the specific patient in the device; and the one or more processors may be further configured to determine the electrical signal representation for the particular patient based on the electrical signal measured between one or more contact combinations in the plurality of electrode combinations(see attached translation, page 23, paragraph 3). Sensing module 66 under the control of the processor 60 is configured to be used for through electrode 24 and/or electrode 26 of the selected or subset one or more electrode 24 and/or electrode 26 and IMD 16 of the conductive shell 34 of at least a portion; An electrode on the housing of the IMD16 or another reference is used to sense the bioelectrical brain signal of the patient 12. The processor 60 may control the switch module 68 to electrically connect the sensing module 66 to the selected electrode 24 and/or the electrode 26(see attached translation, page 13, paragraph 3)). Kaemmerer fails to disclose the circuitry and the difference potentials between electrodes.
However, McIntyre teaches “A computer-assisted method comprising: obtaining volumetric imaging data representing an anatomic volume of a patient; calculating at least one volume of influence in a region near at least one candidate electrode target location in the anatomic volume, in which the calculating includes using a computer model that allows a non-uniform conductivity in the region to represent inhomogeneous and anisotropic tissue properties; and selecting a recommended electrode target location in the anatomic volume using the at least one calculated volume of influence[claim 1]. The method of claim 1, in which the calculating the volume of influence near the candidate electrode target location in the anatomic volume includes calculating a second difference of a potential distribution to represent the volume of influence[claim 4]. In a further example, the computer 402 includes a telemetry circuit 432 for programming or otherwise communicating with an implantable DBS controller circuit 434, such as to adjust electrical stimulation parameters using the VOA or scoring information discussed above. Although FIG. 4 illustrates an IGS workstation example, it is understood that portions of the system 400 could alternatively be implemented outside the context of an IGS workstation such as, for example, in an external programmer device for an implantable DBS controller circuit 434[0073]”.
It would be obvious to one of ordinary skill in the art before the effective filing date to configure the electrode selection for stimulation therapy of Kaemmerer with the potential differences of the brain stimulation models of McIntyre. Doing so would specify the differences in electrical parameters between electrodes in each configuration to determine the optimal placement.
Regarding claim 13, Kaemmerer in view of McIntyre teaches the system according to claim 12, wherein determining the recommended stimulation electrode combination from the all electrode combinations based on the feature signal corresponding to the each electrode combination comprises: acquiring, based on one or more of a signal strength of the feature signal corresponding to the each electrode combination, a pulse width of the feature signal corresponding to the each electrode combination, or a similarity between the feature signal and a desired signal, a score corresponding to the each electrode combination; and taking an electrode combination with a highest score as the recommended stimulation electrode combination based on scores corresponding to the all electrode combinations(As shown in FIG. 4, the electrode selection module 78 may include a plurality of machine learning models 94A to 94N (collectively referred to as "machine learning model 94"). In some examples, each model of the model 94 may be based on a plurality of electrical signal representation of a plurality of electrical signal representation of the one or more electrical signal representation of the training support vector machine (SVM) classifier(see attached translation, page 15, paragraph 6).The machine learning model 94B may determine a score 96B that indicates the patient's electrical signal pattern to a degree similar to the pattern from the patient received via the electrode 24B for effective electrical stimulation therapy; The machine learning model 94N may determine a fraction 96N that indicates the patient's electrical signal pattern to a degree similar to that of a patient from the combination of both the electrode 24A and the electrode 24C receiving the effective electrical stimulation therapy(see attached translation, page 16, paragraph 1). As shown in FIG. 4, the electrode selection module 78 may include a selector 98, the selector may be configured for selecting for delivering electrical stimulation to the patient electrode combination. For example, the selector 98 can select electrode combination based on fraction 96. In some examples, the machine learning model determines the higher the score, associated with the machine learning model of the electrode combination will be more likely to be beneficial to delivery treatment to a particular patient. As an example, the selector 98 may select a contact or electrode combination associated with a machine learning model that determines the highest score in fraction 96 in the machine learning model 94(see attached translation, page 16, paragraph 2)).
Regarding claim 16, Kaemmerer in view of McIntyre teaches the system according to claim 13, wherein acquiring, based on one or more of the signal strength of the feature signal corresponding to the each electrode combination, the pulse width of the feature signal corresponding to the each electrode combination, or the similarity between the feature signal and the desired signal, the score corresponding to the each electrode combination comprises: acquiring, based on one or more of the signal strength of the feature signal corresponding to the each electrode combination, the pulse width of the feature signal corresponding to the each electrode combination, or the similarity between the feature signal and the desired signal, a score corresponding to an electrode combination when a feature signal corresponding to the electrode combination meets a preset condition, wherein the preset condition comprises one or more of the signal strength of the feature signal being greater than a preset signal strength or the pulse width of the feature signal satisfying a preset pulse width range(In the example shown in FIG. 2, the memory 62 may store the treatment program 74, the operation instruction 76 and the electrode selection module 78 stored in a separate memory, such as memory 62, or a separate area within the memory 62. each therapeutic procedure 74 stored according to the electrical stimulation parameter (such as electrode combination, current or voltage amplitude) corresponding value defining a specific treatment program, and, if the stimulation generator 64 generates and delivers the stimulation pulse, the treatment program can define the pulse width and pulse rate of the stimulation signal value(see attached translation, page 12, paragraph 2)).
Regarding claim 17, Kaemmerer in view of McIntyre teaches the system according to claim 13, wherein an acquisition process of the similarity between the feature signal and the desired signal is as follows: inputting the feature signal and the desired signal into a similarity model to obtain the similarity between the feature signal and the desired signal, wherein the similarity model is trained and obtained using a preset deep learning neural network(In some examples, the processor 60 may be configured to use the plurality of SVM by determining a corresponding score for each corresponding SVM in the plurality of SVM; The fraction indicates a patient ' s electrical signal pattern similar to a pattern from a patient receiving an effective electrical stimulation therapy from a corresponding electrode combination associated with a corresponding SVM. In some examples, the electric signal for a particular patient indicates that the corresponding electrode combination to receive the effective electrical stimulation treatment of patient mode similar to the degree is larger, through the corresponding electrode combination to deliver treatment will be beneficial to a particular patient the possibility is larger. Thus, the processor 60 may be configured for based on the fraction to select the electrode combination for delivering stimulation to a particular patient(see attached translation, page 16, paragraph 2). For example, the device may be based on the plurality of patient of the plurality of electrical signal representation of one or more electrical signal representation to train the SVM. In some examples, the device can use machine learning form (i.e., in addition to SVM). For example, the device can use any kind of supervised or unsupervised form of machine learning to select contact combination(see attached translation, page 3, paragraph 1)).
Regarding claim 18, Kaemmerer in view of McIntyre teaches the system according to claim 17, wherein a training process of the similarity model is as follows: inputting a first training signal and a second training signal into the preset deep learning neural network to obtain a predicted similarity between the first training signal and the second training signal; calculating and obtaining a predicted loss value based on the predicted similarity between the first training signal and the second training signal and an annotated similarity between the first training signal and the second training signal; and updating a parameter of the preset deep learning neural network based on the predicted loss value to obtain the similarity model(As shown in FIG. 4, the electrode selection module 78 may include a plurality of machine learning models 94A to 94N (collectively referred to as "machine learning model 94"). In some examples, each model of the model 94 may be based on a plurality of electrical signal representation of a plurality of electrical signal representation of the one or more electrical signal representation of the training support vector machine (SVM) classifier. Each machine learning model in machine learning model 94 may be associated with a particular electrode combination in the plurality of electrodes. For example, machine learning model 94A can be associated with the electrode 24A (i.e., when the electrode 24A is selected for monopolar stimulation, can be based on the sensed electric signal representation to train the machine learning model 94A); machine learning model 94B can be associated with the electrode 24B (i.e., when the electrode 24B is selected for unipolar stimulation, can be based on the sensed electric signal representation to train the machine learning model 94B); and the machine learning model 94N can be associated with the electrode 24A and electrode 24C (i.e., when the electrode 24A and electrode 24C is selected for bipolar stimulation, can be based on the sensed electric signal representation to train the machine learning model 94N). Each machine learning model in machine learning model 94 can be configured for determining the corresponding score (respectively score 96A to 96N, collectively referred to as "score 96") the fraction indicating the electrical signal mode for a particular patient and prior to a plurality of patients with the following fact to obtain the electric signal pattern similar to the degree: A particular electrode selection for delivering electrical stimuli produces an effective treatment for the patient. For example, machine learning model 94A can determine the score 96A, the score indicating the patient electric signal mode from the mode similar to the mode from the electrode 24A receiving the effective electrical stimulation treatment of the patient; The machine learning model 94B may determine a score 96B that indicates the patient's electrical signal pattern to a degree similar to the pattern from the patient received via the electrode 24B for effective electrical stimulation therapy; The machine learning model 94N may determine a fraction 96N that indicates the patient's electrical signal pattern to a degree similar to that of a patient from the combination of both the electrode 24A and the electrode 24C receiving the effective electrical stimulation therapy(see attached translation, page 16, paragraph 1)).
Regarding claim 19, Kaemmerer in view McIntyre teaches the system according to claim 12, wherein the electrical activity able to be sensed by the plurality of electrodes comprises an electrical activity of delivering the treatment to the patient and a bioelectrical activity of the patient(In some examples, the sensing module of the IMD 16 can be via one or more electrodes 24, 26 to sense the bioelectric brain signal, the one or more electrodes are further used for delivering electrical stimulation to the brain 28. In other examples, the electrode 24, one or more of the electrodes 26 can be used for sensing a bioelectric brain signal, and one or more different electrodes 24, 26 can be used for delivering electrical stimulation(see attached translation, page 9, paragraph 1)).
Regarding claim 20, Kaemmerer in view McIntyre teaches the system according to claim 19, but Kaemmerer fails to explicitly state wherein the bioelectrical activity of the patient is an electrical activity of a single cell, an electrical activity of a nucleus, or an electrical activity of a part of a nucleus. However, McIntyre teaches “Our example demonstration of PSNSMS is based on deep brain stimulation (DBS) of the subthalamic nucleus (STN), but the concepts described in this document are transferable to any electrode design or to stimulation of any region of the nervous system[0086]”.
It would be obvious to one of ordinary skill in the art before the effective filing date to configure the electrode selection for stimulation therapy of Kaemmerer with the nucleus stimulation of the brain stimulation models of McIntyre. Doing so would specify the areas of the brain cells that are targeted via electrodes to obtain bioelectric activity.
Claim(s) 3, 4, 7, 8, 14, and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Kaemmerer in view of McIntyre, and further in view of Minami(JP 2001142867 A).
Regarding claim 3, Kaemmerer in view of McIntyre teaches the method according to claim 2, wherein acquiring, based on one or more of the signal strength of the feature signal corresponding to the each electrode combination, the pulse width of the feature signal corresponding to the each electrode combination, or the similarity between the feature signal and the desired signal, the score corresponding to the each electrode combination comprises: configuring a weight coefficient corresponding to the signal strength of the feature signal, a weight coefficient corresponding to the pulse width of the feature signal, and a weight coefficient corresponding to the similarity between the feature signal and the desired signal separately; acquiring a score of the signal strength of the feature signal corresponding to the each electrode combination, a score of the pulse width of the feature signal corresponding to the each electrode combination, and a score of the similarity between the feature signal and the desired signal separately; and performing, based on corresponding weight coefficients, weighted summation on the score of the signal strength of the feature signal corresponding to the each electrode combination, the score of the pulse width of the feature signal corresponding to the each electrode combination, and the score of the similarity between the feature signal and the desired signal to obtain the score corresponding to the each electrode combination(According to this embodiment, in order to select the electrode combination, the one or more processors are configured to determine a corresponding score for each corresponding SVM in the plurality of SVM; the score indicates that the sensing electrical signal for the particular patient represents a degree similar to the sensing electrical signal from a plurality of patients; the corresponding electrode combination associated with the corresponding SVM has been therapeutically effective for delivering electrical stimulation to the plurality of patients. In addition, the one or more processors are configured for based on the fraction to select the electrode combination for delivering stimulation to the particular patient. In this embodiment, each corresponding sensing electrical signal representation of the plurality of sensing electrical signal representation may optionally be selected for the plurality of electrodes in the plurality of patient corresponding to the corresponding electrode combination of the patient delivery electrical stimulation associated with the patient(see attached translation, page 23, paragraph 1). In some examples, the machine learning model determines the higher the score, associated with the machine learning model of the electrode combination will be more likely to be beneficial to delivery treatment to a particular patient(see attached translation, page 16, paragraph 2)). Kaemmerer fails to teach signal strength and weight coefficients.
However, Minami teaches “The signal strength is obtained by using a formula of (distance strength) = (x .sub.k −A .sub.k1 ) / (A .sub.k1 −A .sub.k2 ) (9) using a proportional calculation of the distance. This method is applied to all dimensions to calculate the signal strength. Next, in the second unit recognition unit 3 shown in FIG. 3, the signal output from the selection output path 13 of the first unit recognition unit 2 in the previous layer is input, and the weight coefficient corresponding to the input signal is inputted. The weight coefficient stored in the storage unit 21(see attached translation, page 9, paragraph 2). That examples of criteria, when the maximum value of the absolute value is equal to or greater than a predetermined threshold value of e .sub.s determines to change the weighting coefficient, if it is less than the threshold value, it determines not to change the weighting coefficient There is a way. If it is determined that the weight coefficient should be changed, an error .sub.es is output(see attached translation, page 9, paragraph 14).”.
It would be obvious to one of ordinary skill in the art before the effective filing date to configure the electrode selection for stimulation therapy of Kaemmerer with the weight coefficients of the learning type device of Minami. Doing so would specify the machine learning model to include weight coefficients with the input signals to help create accurate scoring for the electrode configurations.
Regarding claim 4, Kaemmerer in view of McIntyre and further in view of Minami teaches the method according to claim 3, but Kaemmerer fails to teach wherein the weight coefficient corresponding to the similarity between the feature signal and the desired signal is greater than the weight coefficient of the signal strength of the feature signal, and the weight coefficient of the signal strength of the feature signal is greater than the weight coefficient of the pulse width of the feature signal.
However, McIntyre teaches “A model computes a volume of influence region for a simulated electrical stimulation using certain stimulation parameters, such as amplitude, pulse width, frequency, pulse morphology, electrode contact selection or location, return path electrode selection, pulse polarity, etc[abstract]. For example, the computer algorithm can evaluate various VOAs against either or both of the following input criteria: (a) one or more regions in which activation is desired; or (b) one or more regions in which activation should be avoided. In one example, at 314, the computer algorithm creates a score of how such candidate VOAs map against desired and undesired regions. In one example, the score is computed by counting how many VOA voxels map to the one or more regions in which activation is desired, then counting how many VOA voxels map to the one or more regions in which activation is undesired, and subtracting the second quantity from the first to yield the score. In another example, these two quantities may be weighted differently such as, for example, when avoiding activation of certain regions is more important than obtaining activation of other regions (or vice-versa). In yet another example, these two quantities may be used as separate scores[0068]. At 316, the score can be displayed to the user to help the user select a particular VOA (represented by a particular electrode location and parameter settings). Alternatively, the algorithm can also automatically select the target electrode location and parameter settings that provide the best score for the given input criteria[0069]”.
It would be obvious to one of ordinary skill in the art before the effective filing date to configure the electrode selection for stimulation therapy of Kaemmerer with the weighted input of the brain stimulation models of McIntyre. Doing so would allow the scoring system to include different weights for different signals or parameters to ensure proper scoring to select the optimal configuration.
Regarding claim 7, Kaemmerer in view McIntyre teaches the system according to claim 6, wherein the apparatus configured to acquire, based on one or more of the signal strength of the feature signal corresponding to the each electrode combination, the pulse width of the feature signal corresponding to the each electrode combination, or the similarity between the feature signal and the desired signal, the score corresponding to the each electrode combination comprises: an apparatus configured to acquire a weight coefficient corresponding to the signal strength of the feature signal, a weight coefficient corresponding to the pulse width of the feature signal, and a weight coefficient corresponding to the similarity between the feature signal and the desired signal separately; an apparatus configured to acquire a score of the signal strength of the feature signal corresponding to the each electrode combination, a score of the pulse width of the feature signal corresponding to the each electrode combination, and a score of the similarity between the feature signal and the desired signal separately; and an apparatus configured to perform, based on corresponding weight coefficients, weighted summation on the score of the signal strength of the feature signal corresponding to the each electrode combination, the score of the pulse width of the feature signal corresponding to the each electrode combination, and the score of the similarity between the feature signal and the desired signal to obtain the score corresponding to the each electrode combination(According to this embodiment, in order to select the electrode combination, the one or more processors are configured to determine a corresponding score for each corresponding SVM in the plurality of SVM; the score indicates that the sensing electrical signal for the particular patient represents a degree similar to the sensing electrical signal from a plurality of patients; the corresponding electrode combination associated with the corresponding SVM has been therapeutically effective for delivering electrical stimulation to the plurality of patients. In addition, the one or more processors are configured for based on the fraction to select the electrode combination for delivering stimulation to the particular patient. In this embodiment, each corresponding sensing electrical signal representation of the plurality of sensing electrical signal representation may optionally be selected for the plurality of electrodes in the plurality of patient corresponding to the corresponding electrode combination of the patient delivery electrical stimulation associated with the patient(see attached translation, page 23, paragraph 1). In some examples, the machine learning model determines the higher the score, associated with the machine learning model of the electrode combination will be more likely to be beneficial to delivery treatment to a particular patient(see attached translation, page 16, paragraph 2)). )). Kaemmerer fails to teach signal strength and weight coefficients.
However, Minami teaches “The signal strength is obtained by using a formula of (distance strength) = (x .sub.k −A .sub.k1 ) / (A .sub.k1 −A .sub.k2 ) (9) using a proportional calculation of the distance. This method is applied to all dimensions to calculate the signal strength. Next, in the second unit recognition unit 3 shown in FIG. 3, the signal output from the selection output path 13 of the first unit recognition unit 2 in the previous layer is input, and the weight coefficient corresponding to the input signal is inputted. The weight coefficient stored in the storage unit 21(see attached translation, page 9, paragraph 2). That examples of criteria, when the maximum value of the absolute value is equal to or greater than a predetermined threshold value of e .sub.s determines to change the weighting coefficient, if it is less than the threshold value, it determines not to change the weighting coefficient There is a way. If it is determined that the weight coefficient should be changed, an error .sub.es is output(see attached translation, page 9, paragraph 14)”.
It would be obvious to one of ordinary skill in the art before the effective filing date to configure the electrode selection for stimulation therapy of Kaemmerer with the weight coefficients of the learning type device of Minami. Doing so would specify the machine learning model to include weight coefficients with the input signals to help create accurate scoring for the electrode configurations.
Regarding claim 8, Kaemmerer in view of McIntyre and Minami teaches the system according to claim 7, but Kaemmerer fails to teach wherein the weight coefficient corresponding to the similarity between the feature signal and the desired signal is greater than the weight coefficient of the signal strength of the feature signal, and the weight coefficient of the signal strength of the feature signal is greater than the weight coefficient of the pulse width of the feature signal.
However, Minami teaches “The signal strength is obtained by using a formula of (distance strength) = (x .sub.k −A .sub.k1 ) / (A .sub.k1 −A .sub.k2 ) (9) using a proportional calculation of the distance. This method is applied to all dimensions to calculate the signal strength. Next, in the second unit recognition unit 3 shown in FIG. 3, the signal output from the selection output path 13 of the first unit recognition unit 2 in the previous layer is input, and the weight coefficient corresponding to the input signal is inputted. The weight coefficient stored in the storage unit 21(see attached translation, page 9, paragraph 2). That examples of criteria, when the maximum value of the absolute value is equal to or greater than a predetermined threshold value of e .sub.s determines to change the weighting coefficient, if it is less than the threshold value, it determines not to change the weighting coefficient There is a way. If it is determined that the weight coefficient should be changed, an error .sub.es is output(see attached translation, page 9, paragraph 14)”.
It would be obvious to one of ordinary skill in the art before the effective filing date to configure the electrode selection for stimulation therapy of Kaemmerer with the weight coefficients of the learning type device of Minami. Doing so would specify the machine learning model to include weight coefficients with the input signals to help create accurate scoring for the electrode configurations.
Regarding claim 14, Kaemmerer in view of McIntyre teaches the system according to claim 13, wherein acquiring, based on one or more of the signal strength of the feature signal corresponding to the each electrode combination, the pulse width of the feature signal corresponding to the each electrode combination, or the similarity between the feature signal and the desired signal, the score corresponding to the each electrode combination comprises: configuring a weight coefficient corresponding to the signal strength of the feature signal, a weight coefficient corresponding to the pulse width of the feature signal, and a weight coefficient corresponding to the similarity between the feature signal and the desired signal separately; acquiring a score of the signal strength of the feature signal corresponding to the each electrode combination, a score of the pulse width of the feature signal corresponding to the each electrode combination, and a score of the similarity between the feature signal and the desired signal 26separately; and performing, based on corresponding weight coefficients, weighted summation on the score of the signal strength of the feature signal corresponding to the each electrode combination, the score of the pulse width of the feature signal corresponding to the each electrode combination, and the score of the similarity between the feature signal and the desired signal to obtain the score corresponding to the each electrode combination. Kaemmerer fails to teach signal strength and weight coefficients.
However, Minami teaches “The signal strength is obtained by using a formula of (distance strength) = (x .sub.k −A .sub.k1 ) / (A .sub.k1 −A .sub.k2 ) (9) using a proportional calculation of the distance. This method is applied to all dimensions to calculate the signal strength. Next, in the second unit recognition unit 3 shown in FIG. 3, the signal output from the selection output path 13 of the first unit recognition unit 2 in the previous layer is input, and the weight coefficient corresponding to the input signal is inputted. The weight coefficient stored in the storage unit 21(see attached translation, page 9, paragraph 2). That examples of criteria, when the maximum value of the absolute value is equal to or greater than a predetermined threshold value of e .sub.s determines to change the weighting coefficient, if it is less than the threshold value, it determines not to change the weighting coefficient There is a way. If it is determined that the weight coefficient should be changed, an error .sub.es is output(see attached translation, page 9, paragraph 14).”.
It would be obvious to one of ordinary skill in the art before the effective filing date to configure the electrode selection for stimulation therapy of Kaemmerer with the weight coefficients of the learning type device of Minami. Doing so would specify the machine learning model to include weight coefficients with the input signals to help create accurate scoring for the electrode configurations.
Regarding claim 15, Kaemmerer in view of McIntyre and Minami teaches the system according to claim 14, but Kaemmerer fails to teach wherein the weight coefficient corresponding to the similarity between the feature signal and the desired signal is greater than the weight coefficient of the signal strength of the feature signal, and the weight coefficient of the signal strength of the feature signal is greater than the weight coefficient of the pulse width of the feature signal.
However, McIntyre teaches “A model computes a volume of influence region for a simulated electrical stimulation using certain stimulation parameters, such as amplitude, pulse width, frequency, pulse morphology, electrode contact selection or location, return path electrode selection, pulse polarity, etc[abstract]. For example, the computer algorithm can evaluate various VOAs against either or both of the following input criteria: (a) one or more regions in which activation is desired; or (b) one or more regions in which activation should be avoided. In one example, at 314, the computer algorithm creates a score of how such candidate VOAs map against desired and undesired regions. In one example, the score is computed by counting how many VOA voxels map to the one or more regions in which activation is desired, then counting how many VOA voxels map to the one or more regions in which activation is undesired, and subtracting the second quantity from the first to yield the score. In another example, these two quantities may be weighted differently such as, for example, when avoiding activation of certain regions is more important than obtaining activation of other regions (or vice-versa). In yet another example, these two quantities may be used as separate scores[0068]. At 316, the score can be displayed to the user to help the user select a particular VOA (represented by a particular electrode location and parameter settings). Alternatively, the algorithm can also automatically select the target electrode location and parameter settings that provide the best score for the given input criteria[0069]”.
It would be obvious to one of ordinary skill in the art before the effective filing date to configure the electrode selection for stimulation therapy of Kaemmerer with the weighted input of the brain stimulation models of McIntyre. Doing so would allow the scoring system to include different weights for different signals or parameters to ensure proper scoring to select the optimal configuration.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MARIA CATHERINE ANTHONY whose telephone number is (703)756-4514. The examiner can normally be reached 7:30 am - 4:30 pm, EST, M-F.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, CARL LAYNO can be reached at (571) 272-4949. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/MARIA CATHERINE ANTHONY/Examiner, Art Unit 3796
/CARL H LAYNO/Supervisory Patent Examiner, Art Unit 3796