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 .
Claims Pending
Applicant’s cancellation of claims 14 and 19-22 and addition of claims 23-25, in the response filed 06/11/2026 is acknowledged.
Claims 1-13, 15-18, and 23-25 are hereby under examination.
Election/Restrictions
Applicant’s election without traverse of Invention I, Species A1, Claims 1-13 and 15-18, in the reply filed on 06/11/2026 is acknowledged.
Claims 14 and 19-22 are withdrawn from further consideration pursuant to 37 CFR 1.142(b) as being drawn to nonelected Inventions, there being no allowable generic or linking claim. Election was made without traverse in the reply filed on 06/11/2026.
Applicant is reminded that upon the cancelation of claims to a non-elected invention, the inventorship must be corrected in compliance with 37 CFR 1.48(a) if one or more of the currently named inventors is no longer an inventor of at least one claim remaining in the application. A request to correct inventorship under 37 CFR 1.48(a) must be accompanied by an application data sheet in accordance with 37 CFR 1.76 that identifies each inventor by his or her legal name and by the processing fee required under 37 CFR 1.17(i).
Claims 1-13, 15-18, and 23-25 are hereby under examination.
Claim Objections
Claims 2-13, 15-18, 23-25 objected to because of the following informalities:
In claims 2-13, 15-18, 23-25, “the method of claim…” “… wherein…” (first line), should contain a comma prior to the word “wherein”
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-13, 15-18, 23-25 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites the limitation “the brain” in line 2. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, this will be interpreted as -a brain-. Claims 2-13, 15-18, and 23-25 are dependent on claim 1, and as such are also rejected.
Claim 1 recites the limitation “using the training data to train an inverse neural network model to perform an electrophysiological source imaging task to identify and localize regions generating the said neural oscillations in a brain”. This is a “use” claim that is indefinite, as the applicant fails to effectively define the metes and bounds of the claim. The applicant merely recites the use, without providing further detail as to how the use is practiced, and as such the claim indefinite. For examination purposes, this will be interpreted as if the applicant’s claim contained sufficient detail.
Claim 4 recites the limitation “wherein a source space is modeled as a distribution of sources in the brain”, which fails to effectively define the metes and bounds of the claim as it is unclear as to the manner in which the limitation is connected to the independent claim. For example, which brain is this referring to? Claim 1, which clam 4 is dependent on, recites both “a forward source model of the brain” and “neural oscillations in a brain”. Additionally, is the “source space” from the “forward source model” of claim 1? As such, the claim is indefinite as the applicant has failed to effectively define the metes and bounds of the claim. For examination purposes, this will be interpreted as being modeled by the forward source model.
Claim 12 recites the limitation “the seizure-generating tissues” in line 2 There is insufficient antecedent basis for this limitation in the claim. For examination purposes, this will be interpreted as – the seizure generating tissues of the epileptic brain-.
Claim 18 recites the limitation “a spatial filter that takes into account spatial information of the training data”, which fails to effectively define the metes and bounds of the claim as it is unclear as to the manner in which the spatial filter “takes into account spatial information”. Does the filter function as a filter? Are there any
Claim 18 recites the limitation “spatial information projecting sensor space measurements to source space signals in specific source regions in the brain”, which fails to effectively define the metes and bounds of the claim as it is unclear as to the manner in which the spatial information is able to perform the function of “projecting sensor space measurements to source space signals in specific source regions in the brain”. “Projecting” has multiple definitions, two of which include “to plan, figure, or estimate for the future” and “to display outwardly especially to an audience” (Merriam-Webster dictionary), neither of which appear to fit within the applicant’s use of the word. As such, the claim is indefinite as the applicant has failed to effectively define the metes and bounds of the claim. For examination purposes, this limitation will be interpreted as -the spatial information including information sensor space measurements and source space signals in specific source regions in the brain-
Claim 18 recites the limitation “the output unit” in line 9. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, this will be interpreted as without the output unit. (Examiner's Note: The entirety of the limitation involving the output unit states “to estimate activity of the sources at given time in the output unit over a time interval”, where there was no previous indication as any type of data being sent to an output unit.)
Claim 23 recites the limitation “a plurality of synthetic EEG, MEG or iEEG traces simulated by stimulating sources in a model of the brain and projecting source signals generated by the stimulations onto a model of a scalp to create the synthetic EEG or MEG or iEEG trace” which fails to effectively define the metes and bounds of the claim as it is unclear as to which model is being referred to by “a model”. For example, claim 1 recites “providing a forward source model of the brain;”, where the claim 23 limitation recites “a model of the brain”. Is this the same training data as in claim 1, where the model of claim 1 also generates the indicated training data of claim 23? Is this a new model? Is this different training data? As such, the claim is indefinite as the applicant has failed to effectively define the metes and bounds of the claim. For examination purposes, data will be interpreted as being from the forward source model of claim 1.
Claim 25 recites the limitation “wherein the inverse neural network model is trained to localize and image sources from ictal oscillations in an EEG, MEG or iEEG trace of an epilepsy patient”. This is a “use” claim that is indefinite, as the applicant fails to effectively define the metes and bounds of the claim. The applicant merely recites the use, without providing further detail as to how the use is practiced, and as such the claim indefinite. For examination purposes, this will be interpreted as if the applicant’s claim contained sufficient detail.
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 claims are generally directed towards a method comprising providing a forward source model of the brain, causing the forward source model to generate training data comprising neural oscillations, and using the generated training data to train an inverse neural network model to perform an imaging task to identify regions of the brain generating neural oscillations.
Claim(s) 1, 4-7, 16, 18 and 23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cui et al. (“EEG source localization using spatio-temporal neural network”, 2019) hereinafter Cui, and further in view of Ardizzone et al. (“Analyzing Inverse Problems with Invertible Neural Networks", 2019) hereinafter Ardizzone.
Regarding claim 1, Cui discloses A method comprising:
providing a forward source model of the brain (Fig. 1, Page 135, “traditional forward model is used for the generation of simulated signal and the head model is obtained from the segmentation of MRI data.”);
causing the forward source model to generate training data comprising neural oscillations produced by the forward source model (Fig. 1, Page 135, “traditional forward model is used for the generation of simulated signal and the head model is obtained from the segmentation of MRI data.”, “With simulated sEEG signal and source position, the networks are trained to locate the source position.” (sEEG data generated)) (Fig. 3, Page 137, “The flow chart of the simulated sEEG signal generation is shown in figure 3.” (sEEG signal generation));
using the training data to train a neural network model to perform an electrophysiological source imaging task to identify and localize regions generating the said neural oscillations in a brain (Fig. 1, Page 135, “traditional forward model is used for the generation of simulated signal and the head model is obtained from the segmentation of MRI data.”, “With simulated sEEG signal and source position, the networks are trained to locate the source position.” (model trained on simulated data and subsequently tested for estimated source location)) (Fig. 3, Page 137, “The flow chart of the simulated sEEG signal generation is shown in figure 3.”).
Cui fails to explicitly disclose an inverse neural network.
However, Ardizzone teaches an inverse neural network (Abstract (invertible neural networks)) (Conclusion (improvement of data models)) (Fig. 1 (Invertible Neural Network)).
Cui and Ardizzone are considered to be analogous art to the claimed invention as they are involved with data modeling techniques.
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Cui with that of Ardizzone to include an inverse neural network through the substitution of neural network types as it would have yielded the predictable result of improving the data modeling (Ardizzone (Conclusion)).
Regarding claim 4, modified Cui further discloses wherein a source space is modeled as a distribution of sources in the brain (Cui (Page 133, “correlation between n distributed sources and sensor EEG activity…”) (Fig. 1, (testing of trained model with output being the estimated source location))).
Regarding claim 5, modified Cui further discloses wherein the sources are current dipoles (Cui (Fig. 1, Page 135, “Moreover, the source activities including position, dipole moment and source signal are settled based on source estimation…”)).
Regarding claim 6, modified Cui further discloses wherein the inverse neural network (Ardizzone (as indicated in claim 1 above)) learns the distribution of sources via the training data (Cui (Fig. 1, Page 135, “Moreover, the source activities including position, dipole moment and source signal are settled based on source estimation. For source position, the source is among the position of white and gray matters. To make the network more robust, noise is added to the generated signal. The network can learn how to deal with noise from the abundant mixed training signals. With simulated sEEG signal and source position, the networks are trained to locate the source position.”)(Page 135, “The network contains two pathways to model combination of information from sEEG and source signal. For sEEG encoding, an LSTM is used to learn the spatial and temporal information from sEEG signal. For source decoding, the source location is decoded from implicit location in hidden layers of LSTM.”)).
Regarding claim 7, modified Cui further discloses wherein the training data comprises a plurality of source-sensor signal pairs (Cui (Page 135, “In training phase, traditional forward model is used for the generation of simulated signal and the head model is obtained from the segmentation of MRI data. The electrodes position is aligned and matched in the head model.”)(Page 137, “We have generated 15000 and 1000 simulated single source signals with different positions for training and testing, respectively. Each signal is a one-second segment with 250 Hz sampling rate and 128 channels located by the standard BIOSEMI-128 EEG system”)).
Regarding claim 16, modified Cui further discloses does further teach wherein the inverse neural network (Ardizzone (Inverse as neural network as indicated in claim 1 above)) model comprises a spatial module and a temporal module (Cui (Page 135, Fig. 2, (spatial and temporal encoding))).
Regarding claim 18, modified Cui further discloses wherein the inverse neural network (Ardizzone (Inverse as neural network as indicated in claim 1 above)) model comprises:
a spatial filter that takes into account spatial information of the training data (Cui (Fig. 2, Page 135, “The network contains two pathways to model combination of information from sEEG and source signal. For sEEG encoding, an LSTM is used to learn the spatial and temporal information from sEEG signal. For source decoding, the source location is decoded from implicit location in hidden layers of LSTM. The network structure is given in figure 2….”)), the spatial information projecting sensor space measurements to source space signals in specific source regions in the brain (Cui (Fig. 2, Page 135, “The network contains two pathways to model combination of information from sEEG and source signal. For sEEG encoding, an LSTM is used to learn the spatial and temporal information from sEEG signal. For source decoding, the source location is decoded from implicit location in hidden layers of LSTM. The network structure is given in figure 2….” (source position and source decoding)); and
a temporal filter that takes into account temporal information of the training data (Cui (Fig. 2, Page 135, “The network contains two pathways to model combination of information from sEEG and source signal. For sEEG encoding, an LSTM is used to learn the spatial and temporal information from sEEG signal. For source decoding, the source location is decoded from implicit location in hidden layers of LSTM. The network structure is given in figure 2….”)), to estimate activity of the sources at given time in the output unit over a time interval (Cui (Fig. 2, Page 135, “The network contains two pathways to model combination of information from sEEG and source signal. For sEEG encoding, an LSTM is used to learn the spatial and temporal information from sEEG signal. For source decoding, the source location is decoded from implicit location in hidden layers of LSTM. The network structure is given in figure 2….”) (Page 135-136 (source decoding based on output)).
Regarding claim 23, modified Cui further discloses wherein the training data comprises: a plurality of synthetic EEG, MEG or iEEG traces simulated by stimulating sources in a model of the brain and projecting source signals generated by the stimulations onto a model of a scalp to create the synthetic EEG or MEG or iEEG trace (Cui (Page 135, “In training phase, traditional forward model is used for the generation of simulated signal and the head model is obtained from the segmentation of MRI data. The electrodes position is aligned and matched in the head model.”)(Page 137, “We have generated 15000 and 1000 simulated single source signals with different positions for training and testing, respectively. Each signal is a one-second segment with 250 Hz sampling rate and 128 channels located by the standard BIOSEMI-128 EEG system”)).
Claim(s) 2, 12, 13, 15, 17, and 25 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cui in view of Ardizzone as applied to claim 1 above, and further in view of He et al. “Electrophysiological Source Imaging: A Noninvasive Window to Brain Dynamics, 2018) hereinafter He.
Cui and Ardizzone teach the method of claim 1 above.
Regarding claim 2, modified Cui fails to explicitly disclose the limitations of the claim.
However, He teaches wherein the neural oscillations are ictal oscillations in an epileptic brain (Fig. 3, Page 180, “Electrophysiological source imaging of seizure. Seizure onset zones (SOZs) and the source time–frequency representations (TFRs) estimated from a typical seizure in (top) patient 1 with frontal lobe epilepsy and (bottom) patient 2 with temporal lobe epilepsy.”).
Cui, Ardizzone, and He are considered to be analogous art to the claimed invention as they are involved with data modeling.
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Cui and Ardizzone with that of He to include wherein the neural oscillations are ictal oscillations in an epileptic brain through the combination of references as it would have yielded the predictable result of evaluating signals in patients suffering from epilepsy (He (Figure 3, Page 180)).
Regarding claim 12, modified Cui fails to explicitly disclose the limitations of the claim.
However, He further teaches wherein the seizure-generating tissues are modelled as a source patch of brain tissue (He (Fig. 3, Page 180, “Electrophysiological source imaging of seizure. Seizure onset zones (SOZs) and the source time–frequency representations (TFRs) estimated from a typical seizure in (top) patient 1 with frontal lobe epilepsy and (bottom) patient 2 with temporal lobe epilepsy.”)).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Cui, Ardizzone, and He with that of He to include wherein the seizure-generating tissues are modelled as a source patch of brain tissue through the combination of references as it would have yielded the predictable result of evaluating signals in patients suffering from epilepsy (He (Figure 3, Page 180)).
Regarding claim 13, modified Cui fails to explicitly disclose the limitations of the claim.
However, He further teaches wherein the entire source patch shares a temporal waveform (He (Fig. 3, Page 180, “Electrophysiological source imaging of seizure. Seizure onset zones (SOZs) and the source time–frequency representations (TFRs) estimated from a typical seizure in (top) patient 1 with frontal lobe epilepsy and (bottom) patient 2 with temporal lobe epilepsy.”)).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Cui, Ardizzone, and He with that of He to include wherein the entire source patch shares a temporal waveform through the combination of references as it would have yielded the predictable result of evaluating signals in patients suffering from epilepsy (He (Figure 3, Page 180)).
Regarding claim 15, modified Cui fails to explicitly disclose the limitations of the claim.
Cui does disclose wherein source of differing sizes, shapes, locations, and temporal dynamics are generated as part of the training data (Cui (Page 135, “In training phase, traditional forward model is used for the generation of simulated signal and the head model is obtained from the segmentation of MRI data. The electrodes position is aligned and matched in the head model.”)(Page 137, “We have generated 15000 and 1000 simulated single source signals with different positions for training and testing, respectively. Each signal is a one-second segment with 250 Hz sampling rate and 128 channels located by the standard BIOSEMI-128 EEG system”)).
However, He further teaches source patch (He (Fig. 3, Page 180, “Electrophysiological source imaging of seizure. Seizure onset zones (SOZs) and the source time–frequency representations (TFRs) estimated from a typical seizure in (top) patient 1 with frontal lobe epilepsy and (bottom) patient 2 with temporal lobe epilepsy.”)).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Cui, Ardizzone, He with that of He to include wherein source patches of differing sizes, shapes, locations, and temporal dynamics are generated as part of the training data through the combination of references as it would have yielded the predictable result of evaluating signals in patients suffering from epilepsy (He (Figure 3, Page 180)) and improve overall model quality through the use of additional training data.
Regarding claim 17, modified Cui fails to explicitly disclose the limitations of the claim.
However, Cui does disclose wherein the neural network model is trained to model ictal neural oscillations based on an input of EEG or MEG data (Cui (Page 135, “The network contains two pathways to model combination of information from sEEG and source signal. For sEEG encoding, an LSTM is used to learn the spatial and temporal information from sEEG signal. For source decoding, the source location is decoded from implicit location in hidden layers of LSTM. The network structure is given in figure 2….”)(Page 137, “We have generated 15000 and 1000 simulated single source signals with different positions for training and testing, respectively. Each signal is a one-second segment with 250 Hz sampling rate and 128 channels located by the standard BIOSEMI-128 EEG system”)).
He further teaches ictal neural oscillations and Ictal EEG (He (Page 178 (EEG and MEG recordings))(Fig. 3, Page 180, “Electrophysiological source imaging of seizure. Seizure onset zones (SOZs) and the source time–frequency representations (TFRs) estimated from a typical seizure in (top) patient 1 with frontal lobe epilepsy and (bottom) patient 2 with temporal lobe epilepsy.”)).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Cui, Ardizzone, He with that of He to include wherein the inverse neural network model of Ardizzone is trained to model ictal neural oscillations based on an input of ictal EEG or MEG data through the combination of references as it would have yielded the predictable result of evaluating signals in patients suffering from epilepsy (He (Figure 3, Page 180)) and improve overall model quality through the use of additional training data.
Regarding claim 25, modified Cui fails to explicitly disclose the limitations of the claim.
However, Cui does disclose wherein the neural network model is trained to localize and image sources from oscillations in an EEG, MEG or iEEG trace of a patient (Cui (Fig. 2, Page 135, “The network contains two pathways to model combination of information from sEEG and source signal. For sEEG encoding, an LSTM is used to learn the spatial and temporal information from sEEG signal. For source decoding, the source location is decoded from implicit location in hidden layers of LSTM. The network structure is given in figure 2….”) (Page 135-136 (source decoding based on output)).
He teaches ictal oscillations in an EEG, MEG or iEEG trace of an epilepsy patient (He (Fig. 3, Page 180, “Electrophysiological source imaging of seizure. Seizure onset zones (SOZs) and the source time–frequency representations (TFRs) estimated from a typical seizure in (top) patient 1 with frontal lobe epilepsy and (bottom) patient 2 with temporal lobe epilepsy.”) (Page 178, section 4.2, Fig. 3 (seizure source imaging))).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Cui and Ardizzone with that of He to include wherein the inverse neural network model of Ardizzone is trained to localize and image sources from ictal oscillations in an EEG, MEG or iEEG trace of an epilepsy patient through the combination of references as it would have yielded the predictable result of monitoring signals in patients suffering from epilepsy (He (Figure 3, Page 180)) and improve the overall model quality.
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cui in view of Ardizzone as applied to claim 1 above, and further in view of Kunze (“Transcranial direct current stimulation changes resting state functional connectivity: A large-scale brain network modeling study.”, 2016) hereinafter Kunze.
Cui and Ardizzone teach the method of claim 1 above.
Regarding claim 3, modified Cui fails to explicitly disclose the limitations of the claim.
However, Kunze teaches wherein the forward source model comprises one or more neural mass models (Page 175, Col. 1 (Par. 2-3) – Col. 2 (Par. 1-2) (Jansen Rit model to simulate and characterize brain dynamics)) (Page 176, Col. 2, Par. 2 (Jansen-Rit model for determination of temporal dynamics of cortical areas)).
Cui, Ardizzone, and Kunze are considered to be analogous art to the claimed invention as they are involved with data modeling.
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Cui and Ardizzone with that of Kunze to include wherein the forward source model comprises one or more neural mass models through the combination of reference as it would have yielded the predictable result of providing improved modeling connectivity between the source and sensor space (Kunze (Page 175)).
Claim(s) 8, 9, and 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cui in view of Ardizzone and He as applied to claim 2 above, and further in view of Kunze.
Cui, Ardizzone, and He teach the method of claim 2 above.
Regarding claim 8, modified Cui fails to explicitly disclose the limitations of the claim.
Cui does disclose wherein the forward source model comprises a model modified to generate training data with vArdizzoneous spatio-temporal-spectral features indicative of ictal oscillatory activity (Cui (Fig. 1, Page 135, “traditional forward model is used for the generation of simulated signal and the head model is obtained from the segmentation of MRI data.”, “With simulated sEEG signal and source position, the networks are trained to locate the source position.” (sEEG data generated)) (Fig. 3, Page 137, “The flow chart of the simulated sEEG signal generation is shown in figure 3.” (sEEG signal generation))).
However, Kunze teaches a Jansen-Rit model (Page 175, Col. 1 (Par. 2-3) – Col. 2 (Par. 1-2) (Jansen Rit model to simulate and characterize brain dynamics)) (Page 176, Col. 2, Par. 2 (Jansen-Rit model for determination of temporal dynamics of cortical areas)).
Cui, Ardizzone, He, and Kunze are considered to be analogous art to the claimed invention as they are involved with data modeling.
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Cui, Ardizzone, and He with that of Kunze to include wherein the forward source model comprises a Jansen-Rit model of Kunze modified to generate training data with vArdizzoneous spatio-temporal-spectral features indicative of ictal oscillatory activity through the combination of reference as it would have yielded the predictable result of providing improved modeling connectivity between the source and sensor space (Kunze (Page 175)) and improved the overall model accuracy with additional training data.
Regarding claim 9, modified Cui further discloses fails to explicitly disclose the limitations of the claim.
However, Cui does disclose wherein the forward source model models different types of oscillations (Cui (Fig. 1, Page 135, “traditional forward model is used for the generation of simulated signal and the head model is obtained from the segmentation of MRI data.”, “With simulated sEEG signal and source position, the networks are trained to locate the source position.” (generating signals for different locations)) (Fig. 3, Page 137, “The flow chart of the simulated sEEG signal generation is shown in figure 3.” (sEEG signal generation))).
He further teaches different types of ictal oscillations (He (Page 178, section 4.2, Fig. 3 (seizure source imaging))).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Cui, Ardizzone, He, and Kunze with that of He to include wherein the forward source model models different types of ictal oscillations of He through the combination of references as it would have yielded the predictable result of improving the overall model quality by using additional data types and for evaluating patients with epilepsy (He (Page 178-180, section 4.2)).
Regarding claim 11, modified Cui fails to explicitly disclose the limitations of the claim.
However, Kunze further teaches the modified Jansen-Rit model (Page 175, Col. 1 (Par. 2-3) – Col. 2 (Par. 1-2) (Jansen Rit model to simulate and characterize brain dynamics)) (Page 176, Col. 2, Par. 2 (Jansen-Rit model for determination of temporal dynamics of cortical areas)).
Kunze does teach modeling for epileptic sources and defects (Kunze (Page 184, Col. 2, Par. 1-2 (modeling for epileptic sources and defects))).
He further teaches different types of ictal oscillations (He (Page 178, section 4.2, Fig. 3 (seizure source imaging))).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Cui, Ardizzone, He, and Kunze with that of Kunze to include wherein the modified Jansen-Rit model is caused to produce ictal oscillations of He based on a selection of input parameters through the combination of reference as it would have yielded the predictable result of providing improved modeling connectivity between the source and sensor space (Kunze (Page 175)) and improved the overall model accuracy with additional training data.
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cui in view of Ardizzone, He, and Kunze as applied to claim 8 above, and further in view of Shayegh et al. “A Brief Survey of Computational Models of Normal and Epileptic EEG Signals: A Guideline to Model-based Seizure Prediction.”, 2011) hereinafter Shayegh.
Cui, Ardizzone, He, and Kunze teach the method of claim 8 above.
Regarding claim 10, modified Cui fails to explicitly disclose the limitations of the claim.
However, Kunze further teaches wherein the modified Jansen-Rit model models signals (Kunze (Page 175, Col. 1 (Par. 2-3) – Col. 2 (Par. 1-2) (Jansen Rit model to simulate and characterize brain dynamics)) (Page 176, Col. 2, Par. 2 (Jansen-Rit model for determination of temporal dynamics of cortical areas))).
Shayegh teaches signals comprising normal activity, sporadic spikes, sustained discharge of spikes, rhythmic activity, low voltage rapid activity and quasi- sinusoidal activity (Page 68, Col. 1-2, “Normal background, sustained discharge of spikes, low voltage rapid activity, slow quasi-sinusoidal activity, sporadic spikes, and slow rhythmic activity. Each of these type of signals can be met in the real world (normal and pathological) during different activities of the brain…”)(Abstract (seizure models)).
Cui, Ardizzone, He, Kunze, and Shayegh are considered to be analogous art to the claimed invention as they are involved with data modeling.
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Cui, He, and Kunze with that of Kunze and Shayegh to include wherein the modified Jansen-Rit model of Kunze models signals comprising normal activity, sporadic spikes, sustained discharge of spikes, rhythmic activity, low voltage rapid activity and quasi-sinusoidal activity through the combination of references as differing seizure models are known (Shayegh (Page 67, Col. 2)) and it would have yielded the predictable result of explicitly modeling different signal types that are met in real world situations by the brain (Shayegh (Page 68, Col. 1-2)).
Claim(s) 24 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cui in view of Ardizzone as applied to claims 23 and 1 above, and further in view of He and Kunze.
Cui and Ardizzone teach the method of claim 23 above.
Regarding claim 24, modified Cui fails to explicitly disclose the limitations of the claim.
However, Cui does disclose wherein the synthetic EEG, MEG or iEEG traces are modeled using a model modified to produce oscillation (Cui (Fig. 1, Page 135, “traditional forward model is used for the generation of simulated signal and the head model is obtained from the segmentation of MRI data.”, “With simulated sEEG signal and source position, the networks are trained to locate the source position.” (generating signals for different locations)) (Fig. 3, Page 137, “The flow chart of the simulated sEEG signal generation is shown in figure 3.” (sEEG signal generation))).
He teaches ictal oscillation (He (Page 178, section 4.2, Fig. 3 (seizure source imaging))).
However, Kunze teaches Jansen-Rit model (Page 175, Col. 1 (Par. 2-3) – Col. 2 (Par. 1-2) (Jansen Rit model to simulate and characterize brain dynamics)) (Page 176, Col. 2, Par. 2 (Jansen-Rit model for determination of temporal dynamics of cortical areas)).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Cui and Ardizzone with that of He and Kunze to include wherein the synthetic EEG, MEG or iEEG traces are modeled using a Jansen-Rit model modified to produce ictal oscillation through the combination of reference as it would have yielded the predictable result of providing improved modeling connectivity between the source and sensor space (Kunze (Page 175)), and yielded the predictable result of monitoring signals in patients suffering from seizures (He (Figure 3, Page 180)).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ARI SINGH KANE PADDA whose telephone number is (571)272-7228. The examiner can normally be reached Monday - Friday 8:00 am - 5:00 pm.
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, Jason Sims can be reached at (571) 272-7540. 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.
/ARI S PADDA/ Examiner, Art Unit 3791
/RENE T TOWA/ Primary Examiner, Art Unit 3791
