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 .
Acknowledgement of Amendment
The following office action is in response to the applicant’s amendment filed on 02/13/2026. Claims 1, 3-15 and are pending. Claim 2 has been cancelled. Claims 1, 3, 4, 14 and 15 are amended. Claims 1, and 3-15 are rejected under 35 U.S.C. 102/103 for the reasons stated in the Response to Arguments and 35 U.S.C. 102/103 sections below.
Response to Arguments
Applicant’s arguments, see Remarks page 24, filed 02/13/2026, with respect to the objections to the specification and drawings have been fully considered and are partially persuasive given the amendments made thereto.
The examiner respectfully refers the Applicant to the page 46 of the specification (See Specification section below) with respect to its objection. Furthermore, the examiner notes that the objections to FIGS. 40, 48, and 49 (see Drawings section below) have not been addressed in the response filed 02/13/2026.
The other objections to the specification and drawings in the non-final rejection of 08/14/2025 have been withdrawn.
Applicant’s arguments, see Remarks page 24, filed 02/13/2026, with respect to the objection to claim 2 have been fully considered and are persuasive. The examiner acknowledges that the Applicant has canceled claim 2, thus rendering the objection moot. The objection to claim 2 in the non-final rejection of 08/14/2025 has been withdrawn.
Applicant’s arguments, see Remarks page 24-25, filed 02/13/2026, with respect to the rejection of claims 1-10 and 12-15 under 35 U.S.C. 102(a)(1) have been fully considered and are not persuasive.
Regarding claim 1, the claim has been amended to recite that the machine learning model includes “a first convolutional network and a second convolutional network” and that the system provides “first input generated from the CBFV measurement to the first convolutional neural network […] and second input generated from the ABP measurement to the second convolutional neural network”.
The Applicant argues that Mourad does not disclose two convolutional networks, and providing first input generated to the first convolutional neural network to obtain a first output, and providing second input generated to the second convolutional neural network to obtain a second output and determining the ICP measurement using the first and second outputs.
The examiner respectfully disagrees that Mourad does not disclose two convolutional neural networks, providing first input generated from the CBFV measurement to the first convolutional neural network to obtain a first output, providing second input generated from the ABP measurement to the second convolutional neural network to obtain a second output or determining the ICP measurement using the first and second outputs.
Specifically, the examiner refers the Applicant to paragraphs [0112] and [0091] of Mourad. Paragraph [0112] describes an algorithm utilizing an ANN was chosen for deriving ICP (i.e. intracranial pressure) predictions based on variable inputs of V_mca (i.e. flow velocity in the middle cerebral artery) and ABP (i.e. arterial blood pressure) and exemplary techniques such as a multiple circular path convolutional neural network (see Lo S C, Li H, Wang Y, Kinnard L, Freedman M T, A multiple circular path convolution neural network system for detection of mammographic masses, IEEE Trans Med Imaging 2002 February;21(2):150-8 “Lo”). FIG. 4 of Lo shows three types of network paths (i.e. convolutional neural networks) which are used in the multiple circular path convolutional neural network to provide an output.
Furthermore, paragraph [0091] discloses that “ICP may be represented as a sum and/or the convolutional product of one or more samples of ABP and V_mca”. In order to derive a sum and/or convolutional product of one or more samples of ABP and V_mca (i.e. flow velocity in the middle cerebral artery), these values had to have been provided to the machine learning model (i.e. ANN containing the first and second convolutional neural networks, see discussion of paragraph [0112] above) to generate the first and second outputs.
The examiner respectfully maintains that since the ANN derives ICP predictions based on variable inputs of V_mca and ABP and the multiple circular path convolutional neural network of Lo is one such ANN (i.e. a convolutional neural network being a type of artificial neural network) that Mourad discloses the use of two convolutional neural networks, providing first input generated from the CBFV measurement (i.e. V_mca) to the first convolutional neural network to obtain a first output, providing second input generated from the ABP measurement to the second convolutional neural network to obtain a second output and determining the ICP measurement using the first and second outputs.
Therefore, the rejection of claim 1 and its corresponding dependent claims (i.e. claims 3-13) under 35 U.S.C. 102(a)(1) are respectfully maintained.
The rejection of claim 1 has been updated to reflect the newly added limitations as stated in the 35 U.S.C. 102 section below.
Regarding claims 14 and 15, these claims have been amended similarly to claim 1. Therefore, these claims are subject to the reasoning provided therein. Thus, the examiner respectfully maintains the rejection of claims 14 and 15 under 35 U.S.C. 102(a)(1) for the reasons stated above.
Applicant’s arguments, see Remarks page 25, filed 02/13/2026, with respect to the rejection of claims 11 under 35 U.S.C. 103 have been fully considered and are not persuasive.
Regarding claim 11, this claim was rejected under 35 U.S.C. 103 as being unpatentable over Mourad as applied to claim 1 and further in view of Kashif et al. US 2010/0063405 “Kashif”.
The Applicant argues that Kashif does not cure the deficiencies of Mourad. It is thus submitted that claim 11 is patentable at least by virtue of its dependency for the above reasons, and because of the additional features recited therein.
Since claim 11 is dependent on claim 1, this claim is subject to the reasoning provided above with respect to the teaching of Mourad. Furthermore, the examiner notes that Kashif was not incorporated to teach the limitations of claim 1, particularly with respect to the limitations: “wherein the machine learning model includes a first convolutional network and a second convolutional network”; and “wherein providing the input comprises: providing first input generated from the CBFV measurement to the first convolutional neural network to obtain a first output; providing second input generated from the ABP measurement to the second convolutional neural network to obtain a second output; and determining the ICP measurement of the subject’s brain using the first and second outputs”. Rather, Kashif was incorporated to teach the limitations of claim 11.
Therefore, the rejection of claim 11 under 35 U.S.C. 103 is respectfully maintained for the reasons stated in the Response to Arguments section above and the 35 U.S.C. 103 section below.
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they do not include the following reference sign(s) mentioned in the description:
FIG. 48: Although the specification states “The overlays 4802 and inside circle 4806 shows where a beating motion is occurring in the brain. Lines 4804 indicates a decreasing pixel intensity whereas a coloration inside circle 4804 indicates increasing pixel intensity with time. The trace plotted at the bottom of each frame shows the variations of the pixel intensity in the circle 4802” [Page 80, Lines 1-4], this figure does not include the labels 4802, 4806 or 4804. Additionally, it seems as though the label 4804 is intended to correspond to lines and a circle. The examiner recommends utilizing two different labels if these are in fact different entities.
FIG. 49: Although the specification states “The process 4900 may begin at act 4902” [Page 80, Signal Decomposition, Line 4], this figure does not include the label 4900. Rather this figure includes the label 1400. The examiner recommends updating either the figure or the specification accordingly.
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they include the following reference character(s) not mentioned in the description:
FIG. 40: Although this figure includes the labels “4058” and “4056” these labels do not appear within the specification.
Corrected drawing sheets in compliance with 37 CFR 1.121(d), or amendment to the specification to add the reference character(s) in the description in compliance with 37 CFR 1.121(b) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Specification
The disclosure is objected to because of the following informalities:
[Page 46, Lines 30-31]: As written it reads “the arterial deformation measurement component 2100A2100A-1 may be configured to determine the arterial wall deformation measurement 2100A-1”. However, to correct the typos “2100A2100A-1” should be “2100A/2100A-1”.
Appropriate correction is required.
Claim Objections
Claims 1, 14 and 15 are objected to because of the following informalities:
Regarding claims 1, 14 and 15, the claim reads “the machine learning model includes a first convolutional network and a second convolutional network […] providing first input generated from the CBFV measurement to the first convolutional neural network to obtain a first output; providing second input generated from the ABP measurement to the second convolutional neural network to obtain a second output”. The examiner believes that “a first convolutional network” is the same as “the first convolutional neural network” and that “a second convolutional network” is the same as “the second convolutional neural network”. Therefore, the examiner would recommend amending “a first convolutional network” to be “a first convolutional neural network” and amending “a second convolutional network” to be “a second convolutional neural network” to avoid antecedent basis issues.
Appropriate correction is required.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1, 3-10, and 12-15 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Mourad et al. US 2005/0015009 A1 “Mourad”.
Regarding claims 1, 14 and 15, Mourad teaches “A method of determining intracranial pressure (ICP) of a subject’s brain, the method comprising:” (Claim 1) (“Systems and methods for determining ICP based on parameters that can be measured using non-invasive or minimally invasive techniques are provided, wherein a non-linear relationship is used to determine ICP based on one or more variable inputs. The first variable input relates to one or more properties of a cranial blood vessel and/or blood flow, such as acoustic backscatter from an acoustic transducer having a focus trained on a cranial blood vessel, flow velocity in a cranial blood vessel, and the like. Additional variables, such as arterial blood pressure (ABP), may be used in combination with a first variable input relating to one or more properties of a cranial blood vessel, such as flow velocity of the middle cerebral artery (MCA) to derive ICP using a non-linear relationship” [Abstract]. In this case, the intracranial pressure (ICP) is determined based on one or more variable inputs including one or more properties of a cranial blood vessel (i.e. within a subject’s brain). Therefore, Mourad describes a method for determining intracranial pressure of a subject’s brain.);
“An ICP measurement system comprising: one or more probes configured to obtain acoustic measurement data by detecting acoustic signals in a subject’s brain; and at least one computer hardware processor configured to” (Claim 14) (See [Abstract] above, and “For assessment of CNS tissue and determination of ICP, for example, one or more acoustic transducer(s) is placed in contact with or in proximity to a subject's skull” [0048]; “An acoustic transducer/receiver array may be employed in a scanning mode, for example, to acquire acoustic data from numerous sites within a larger target area. Based on the acoustic data collected in the scanning mode, localized sites within the target area may be selected as target sites for focused acoustic illumination and/or probing” [0221]; “Methods and systems of the present invention are preferably integrated in a controller component having data processing, storage and display features that provide meaningful information to professional clinicians. The controller component may be integrated with other clinical devices, or may be programmed to receive additional data inputs relating to other clinical parameters” [0066]. These one or more acoustic transducers represent one or more probes configured to obtain acoustic measurement data (i.e. acoustic data) by detecting acoustic signals in a subject’s brain (i.e. within the subject’s skull). In this case, since the controller component has a data processing feature and may be integrated with other clinical devices, the controller component represents a computer hardware processor. Therefore, Mourad describes an ICP measurement system comprising: one or more probes (i.e. one of more acoustic transducers) configured to obtain acoustic measurement data by detecting acoustic signals (i.e. acoustic data) in a subject’s brain; and at least one computer hardware processor (i.e. controller component) configured to perform specific tasks.);
“At least one non-transitory computer-readable storage medium storing instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor to perform:” (Claim 15) (See [0066]. In order for the computer component to perform data processing, it must access instructions. Therefore, Mourad includes at least one non-transitory computer-readable storage medium storing instructions that, when executed by at least one computer hardware processor (i.e. computer component), cause the at least one computer hardware processor to perform specific tasks.);
“using at least one computer hardware processor to perform: obtaining acoustic measurement data obtained from measuring acoustic signals from the subject’s brain” (Claim 1); “obtaining acoustic measurement data obtained from measuring acoustic signals from the subject’s brain” (Claim 15) (See [0048], [0221] and [0066] above. Therefore, the method carried out by the system involves using at least one computer hardware processor (i.e. computer component) to perform the step of obtaining acoustic measurement data (i.e. acoustic data) obtained from measuring acoustic signals from the subject’s brain (i.e. within the subject’s skull).);
“determine(ing) a cerebral blood flow velocity (CBFV) measurement of the subject’s brain using the acoustic measurement data” (Claims 1, 14 and 15); “obtain(ing) an arterial blood pressure (ABP) measurement of the subject’s brain” (Claims 1, 14 and 15); (“One of the variable physiological parameters may relate to intracranial blood flow and may, for example, be quantified as an acoustic property of tissue or blood that is related to intracranial blood flow or intracranial flow velocity, such as cerebral blood flow or flow velocity. In one embodiment, ICP is determined based on an acoustic property of cerebral tissue, or on blood flow or cerebral blood flow velocity, and/or arterial blood pressure (ABP)” [0037] and “In an exemplary embodiment described in detail below, patient ICP is determined based on at least two variable parameters: (1) acoustic scatter or flow velocity in the middle cerebral artery (V_mca) measured, for example, using a TCD device; and (2) ABP measured invasively or non-invasively. ABP may be measured using conventional techniques, or using ultrasound techniques as described herein. In one embodiment, ABP is measured non-invasively, using "active" and/or "passive" ultrasound techniques, in a cranial blood vessel such as the MCA or a carotid or vertebral artery. In this embodiment, V_mca may be determined simultaneously or alternatively with ABP using an ultrasound device of the present invention” [0038]. In this case, TCD represents transcranial doppler. Therefore, the method carried out by the system involves determining a cerebral blood flow velocity (CBFV) measurement (i.e. flow velocity in the middle cerebral artery V_mca) of the subject’s brain using the acoustic measurement data (i.e. obtained using a TCD device); and obtaining an arterial blood pressure (ABP) measurement of the subject’s brain (i.e. non-invasively using “active” and/or “passive” ultrasound techniques).);
“generate(ing), using the CBFV measurement and the ABP measurement, input to a machine learning model trained to output an ICP measurement” (Claims 1, 14 and 15); and “provide(ing) the input to the machine learning model to obtain an ICP measurement of the subject’s brain” (Claims 1, 14 and 15) (See [0037] and [0038] above and “For various reasons, an algorithm utilizing an ANN was chosen for deriving ICP predictions based on variable inputs of V_mca and ABP. Neural network analysis is a well-described and important signal-processing technique that has found a number of uses in the medical field, including voice recognition, radiologic image analysis, and physiologic signal processing. Exemplary techniques are described in the following articles: Boone JM, Sigillito VG, Shaber GS, Neural networks in radiology: an introduction and evaluation in a signal detection task, Med Phys 1990 March-April;17(2):234-41; Lo S C, Li H, Wang Y, Kinnard L, Freedman M T, A multiple circular path convolution neural network system for detection of mammographic masses, IEEE Trans Med Imaging 2002 February;21(2):150-8; and Sepulveda F, Cliquet Junior A, An artificial neural system for closed loop control of locomotion produced via neuromuscular electrical stimulation, Artif Organs 1995 March; 19(3):231-7” [0112].
In this case, ANN represents an artificial neural network which is an example of a machine learning model. Therefore, since the ANN derives ICP predictions (i.e. measurements) based on variable inputs of V_mca (i.e. flow velocity in the middle cerebral artery) and ABP (i.e. arterial blood pressure), the method carried out by the system involves generating, using the CBFV measurement and the ABP measurement, input to a machine learning model (i.e. ANN) trained to output an ICP measurement; and providing the input to the machine learning model to obtain an ICP measurement of the subject’s brain.).
“wherein: the machine learning model includes a first convolutional network and a second convolutional network” (See [0112] as discussed in claim 1 above. Therefore, since the ANN (i.e. of which a convolutional neural network is a specific type) for deriving ICP predictions based on variable inputs of V_mca (i.e. flow velocity in the middle cerebral artery) and ABP (i.e. arterial blood pressure) and may utilize the technique of a multiple circular path convolutional neural network (i.e. containing more than one convolutional network, see Lo S C, Li H, Wang Y, Kinnard L, Freedman M T, A multiple circular path convolution neural network system for detection of mammographic masses, IEEE Trans Med Imaging 2002 February;21(2):150-8, specifically FIG. 4), the machine learning model includes a first convolutional network and a second convolutional network.);and
“providing the input to the machine learning model to obtain the ICP measurement of the subject’s brain, wherein providing the input comprises: providing first input generated from the CBFV measurement to the first convolutional neural network to obtain a first output; providing second input generated from the ABP measurement to the second convolutional neural network to obtain a second output; and determining the ICP measurement of the subject’s brain using the first and second outputs” (“As the output of a linear filter, ICP may be represented as a sum and/or the convolution product of one or more samples of ABP and V_mca, or other TCD-derived measurement(s) such as a tapped delay line in which two or more samples of data, usually with fixed sample interval, are considered simultaneously, with an impulse response vector” [0091]. Therefore, since the ICP is represented as a sum and/or convolution product of one or more samples of ABP and V_mca, the step of providing the input to the machine learning model to obtain the ICP measurement of the subject’s brain comprises: providing first input generated from the CBFV measurement (i.e. V_mca) to the first convolutional neural network to obtain a first output; providing second input generated from the ABP measurement to the second convolutional neural network to obtain a second output; and determining the ICP measurement of the subject’s brain using the first and second outputs.).
Regarding claim 3, Mourad discloses all features of the claimed invention as discussed with respect to claim 1 above, and Mourad further teaches “wherein determining the ICP measurement of the subject’s brain using the first and second outputs comprises: generating a combined input for an ICP predictor of the machine learning model using the first and second outputs” (See [0038] and [0112] as discussed in claim 1 above, [0091] as discussed in claim 2 above, and “A neural network, set up and trained as described below, was used to derive a non-linear relationship, which is further characterized below, and which provided accurate determinations of ICP in experimental protocols based on two variable parameters: V_mca measurements taken using TCD techniques; and ABP measured using an arterial line” [0064]; “A non-linear multilayer perceptron (a 2-layer feed-forward ANN) was chosen as the experimental prototype architecture for its well-known characteristics and relatively straight-forward training process. […] The hidden neuron layer utilizes an approximation of the hyperbolic tangent function as a transfer function, which allows the network to model non-linear input-target relationships; the output neuron layer uses a linear transfer function so that network outputs can be linearly scaled. Network inputs consist of normalized, arbitrary-duration tapped delay-lines of invasive ABP and Doppler ultrasound V_mca data in which each input contains pulse-contour data from one or more cardiac cycles. Network output represents a continuous ICP pulse contour normalized to the duration of one cardiac cycle” [0125] and “Using an ANN, as described above, is a convenient and reliable technique for deriving an accurate non-linear relationship between patient input variables, such as V_mca and ABP and the determined output, ICP” [0170].
Therefore, the step of determining the ICP measurement of the subject’s brain using the first and second outputs comprises: generating a combined input (i.e. sum and/or the convolution product of one or more samples of ABP and V_mca, see [0091]) for an ICP predictor (i.e. output neuron layer, see [0125]) of the machine learning model (i.e. ANN) using the first and second outputs (i.e. corresponding to the V_mca and ABP data).); and
“providing the combined input to the ICP predictor to obtain the ICP measurement of the subject’s brain” (See [0112] as discussed in claim 1 above. Since the ANN derives ICP predictions (i.e. measurements) based on the variable inputs of V_mca and ABP, the method carried out by the system involves providing the combined input (sum and/or the convolution product of one or more samples of ABP and V_mca, see [0091])) to the ICP predictor (i.e. output neuron layer, see [0125]) to obtain the ICP measurement of the subject’s brain.).
Regarding claim 4, Mourad discloses all features of the claimed invention as discussed with respect to claim 1 above, and Mourad further teaches “wherein the first output is a first ICP measurement and the second output is a second ICP measurement” (“A second stage is through the relatively straightforward step of input space mapping, in which thousands of canonical inputs encompassing the input set likely to be encountered in clinical practice (e.g. ABP waveforms throughout the physiologic range in increments of 1 mm Hg, each with V_mca waveforms throughout the physiologic range in increments of 1 cm/s) are presented to the validated network, and the resultant ICP outputs recorded” [0155]. Therefore, since thousands of canonical inputs (i.e. ABP waveforms and V_mca waveforms) are presented to the validated network and resultant ICP outputs are recorded, the first output is a first ICP measurement and the second output is a second ICP measurement.); and
“determining the ICP measurement of the subject’s brain using the first and second outputs comprises: performing a comparison between the first and second outputs to determine the ICP measurement of the subject’s brain” (“FIGS. 12A and 12B show comparisons of instantaneous traces of invasively measured (generally, lower trace) and non-invasively determined ICP (generally, upper trace) for an exemplary patient described in Example 1” [0079] and “Point-by-point comparisons of time series for each patient demonstrates our successful prediction of invasively measured ICP, using only invasively measured ABP and acoustic measurement of the blood flow rate in the middle cerebral artery (V_mca), and a properly determined algorithm” [0266]. Therefore, the step of determining the ICP measurement of the subject’s brain using the first and second outputs comprises: performing a comparison (i.e. point-by-point comparison) between the first and second outputs (i.e. corresponding to the lower and upper traces shown in FIG. 12A/12B, for example) to determine the ICP measurement of the subject’s brain.).
Regarding claim 5, Mourad discloses all features of the claimed invention as discussed with respect to claim 1 above, and Mourad further teaches “wherein the acoustic measurement data is obtained by: guiding an acoustic beam towards a region of the subject’s brain; and detecting a signal from the region of interest of the subject’s brain” (See [0048] and [0221] as discussed in claim 1 above and “In one embodiment, methods and systems of the present invention employ a confocal acoustic system comprising at least two acoustic transducers, driven at different frequencies, or a focal acoustic system comprising a single acoustic transducer driven at a given pulse repetition frequency (PRF), to induce an oscillatory radiation force in the target tissue, such as brain tissue” […] Diagnostic ultrasound techniques may be used to measure the frequency or other properties of the emitted acoustic signal, which are empirically related to tissue properties” [0054], “In one aspect, ICP is determined by measuring an acoustic property relating to a cranial blood vessel, such as acoustic backscatter produced when an ultrasound beam is focused on a cranial blood vessel, or blood flow velocity measured, for example, using TCD techniques, and then using a non-linear relationship to relate the acoustic property and/or blood flow velocity to ICP” [0062] and “The two, crossed linear cMUT arrays alternatively transmit and receive ultrasound beams while steering the sending and listening beams, to identify and focus on acoustic signals having the desired property” [0240]. Therefore, the acoustic measurement data is obtained by: guiding an acoustic beam towards a region of the subject’s brain (i.e. via the confocal acoustic system comprising at least two acoustic transducers); and detecting a signal from the region of interest of the subject’s brain (i.e. acoustic backscatter produced when an ultrasound beam is focused on a cranial blood vessel).).
Regarding claim 6, Mourad discloses all features of the claimed invention as discussed with respect to claim 1 above, and Mourad further teaches “wherein the machine learning model comprises a contrastive convolutional network” (See [0091] as discussed in claim 2 above and [0112] as discussed in claim 1 above. Therefore, since the ANN derives the ICP predictions (i.e. measurements) utilizing a sum and/or the convolutional product of one or more samples of ABP and V_mca, the ANN represents a machine learning model which comprises a contrastive convolutional network.).
Regarding claim 7, Mourad discloses all features of the claimed invention as discussed with respect to claim 1 above, and Mourad further teaches “wherein the machine learning model comprises a decision tree model” (“With limited computing resources, a simplified "average" vascular tree, with an arbitrary number of vascular bifurcations, could be used as the basis for a model for specific subtypes of patients and used to calculate ICP from other measured physiologic parameters” [0185]. Therefore, the machine learning model comprises a decision tree model (i.e. simplified “average” vascular tree used to calculate ICP).).
Regarding claim 8, Mourad discloses all features of the claimed invention as discussed with respect to claim 1 above, and Mourad further teaches “wherein generating, using the CBFV measurement and the ABP measurement, the input to the machine learning model comprises: determining, using the CBFV measurement, a mean CBFV value as an input” (“CPP is determined from the displacement or emission data and ABP data. Specifically, correlation coefficient indices between time averaged mean flow velocity (FVm) and CPP (Mx), and between the flow velocity during systole and CPP (Sx), are calculated during several minute epochs and averaged for each investigation” [0206]. In this case, CPP represents cerebral perfusion pressure. Since the mean (i.e. average) flow velocity is calculated, the step of generating, using the CBFV measurement and the ABP measurement, the input to the machine learning model comprises: determining, using the CBFV measurement, a mean CBFV value as an input.); and
“determining, using the ABP measurement, a mean ABP value as an input” (“Alternative input data formats include non-invasive blood pressure (derived through cuff, tonometric, or other means) which is represented as systolic, mean, and diastolic pressure values that are updated intermittently” [0126]. Therefore, the step of generating, using the CBFV measurement and the ABP measurement, the input to the machine learning model comprises: determining, using the ABP measurement, a mean ABP value as an input.).
Regarding claim 9, Mourad discloses all features of the claimed invention as discussed with respect to claim 1 above, and Mourad further teaches “wherein: the CBFV measurement comprises a time series of CBFV values” (See [0266] as discussed in claim 4 above. Therefore, since point-by-point comparisons of time series are used to successfully predict the intracranial pressure (ICP) using invasively measured ABP and the acoustic measurement of the blood flow rate in the middle cerebral artery (i.e. V_mca), the CBFV measurement comprises a time series of CBFV values and the ABP measurement comprises a time series of ABP values.); and
“generating, using the CBFV measurement and the ABP measurement, the input to the machine learning model comprises: identifying one or more characteristics of the time series of CBFV values and/or one or more characteristics of the time series of the ABP values” (See [0266] as discussed with respect to claim 4 above. In order to perform a point-by-point comparison of time series for each patient using invasively measured ABP and acoustic measurement of the blood flow rate in the middle cerebral artery (V_mca), one or more characteristics of the time series of CBFV values (i.e. blood flow rate in V_mca) must be identified. Therefore, the step of generating, using the CBFV measurement and the ABP measurement, the input to the machine learning model comprises: identifying one or more characteristics of the time series of BCFV values and/or one or more characteristics of the time series of the ABP values.); and
“generating, using the one or more characteristics of the time series of CBFV values and/or the one or more characteristics of the time series of ABP values, the input to the machine learning model” (See [0266] as discussed with respect to claim 4 above and “FIG. 15 shows the mean values for invasively measured ICP plotted against mean values for non-invasively determined ICP with data collected over a 10 minute period and subjected to a one minute running average” [0082]; “FIG. 16 shows application of an algorithm formulated using a neural network and a 29 patient training set to determine ICP for each of the 29 patient members of the training set using acoustic scatter and ABP data” [0083]. Therefore, the method carried out by the system involves generating, using the one or more characteristics of the time series of CBFV values and/or the one or more characteristics of the time series of ABP values, the input to the machine learning model (i.e. ANN).).
Regarding claim 10, Mourad discloses all features of the claimed invention as discussed with respect to claim 1 above, and Mourad further teaches “wherein generating, using the CBFV measurement and the ABP measurement, the input to the learning model comprises: determining frequency domain CBFV values using the CBFV measurement; determining frequency domain ABP values using the ABP measurement”” (See [0266] as discussed with respect to claim 4 above, and “Sensor time series data are divided into frames, often overlapped, multiplied by the transmitted waveform replica and then transformed into the frequency domain via the Fast Fourier Transform (FFT) algorithm” [0225]. Therefore, since the sensor time series data is transformed into the frequency domain via the FFT algorithm, the step of generating, using the CBFV measurement and the ABP measurement, the input to the learning model comprises: determining frequency domain CBFV values using the CBFV measurement and determining frequency domain ABP values using the ABP measurement.);
“determining a mean CBFV value using the frequency domain CBFV values”; “determining a mean ABP value using the frequency domain ABP values” (See [0206] and [0126] as discussed with respect to claim 8 above. Therefore, the method involves determining a mean CBFV value using the frequency domain CBFV values (i.e. see [0225] and [0206]) and determining a mean ABP value using the frequency domain ABP values (i.e. see [0225] and [0126].); and
“generating the input using the mean CBFV value and the mean ABP value” (“Exemplary acoustic data that may be used to determine ICP according to the present invention include: values for or changes in acoustic scatter, including values of and changes in the amplitude, phase and/or frequency of acoustic signals, values for or changes in length of scattered signals relative to the interrogation signal, values for or changes in the primary and/or other maxima and/or minima amplitudes of an acoustic signal within a cardiac and/or respiratory cycle; values for or changes in ratios of the maximum and/or minimum amplitude to that of the mean or variance or distribution of subsequent signals within a cardiac cycle” [0057]. Therefore, since exemplary acoustic data that may be used to determine ICP may be the mean or variance or distribution of subsequent signals within a cardiac cycle, the method involves generating the input using the mean CBFV value and the mean ABP value.).
Regarding claim 12, Mourad discloses all features of the claimed invention as discussed with respect to claim 1 above, and Mourad further teaches “wherein the ICP measurement of the subject’s brain is a mean ICP value” (“FIG. 14 shows the mean values for invasively measured ICP plotted against mean values for non-invasively determined ICP with data collected over a 10 minute period and subjected to a one minute running average” [0081]. Therefore, the ICP measurement of the subject’s brain is a mean ICP value (see plot in FIG. 14).).
Regarding claim 13, Mourad discloses all features of the claimed invention as discussed with respect to claim 1 above, and Mourad further teaches “wherein the ICP measurement of the subject’s brain is a time series of ICP values” (See [0266] as discussed in claim 4 above and “FIGS. 12A and 12B show a comparison of the instantaneous time traces of measured and predicted ICP from one of the core eight patients, reduced down from an initial data acquisition rate of 250 Hz to 20 Hz (i.e., there are twenty data points per second for each data set, or roughly twenty points per cardiac cycle)” [0265]. Therefore, the ICP measurement of the subject’s brain is a time series of ICP values (i.e. point-by-point time series data including ABP and V_mca values.).).
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) 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Mourad et al. US 2005/0015009 A1 “Mourad” as applied to claim 1 above, and further in view of Kashif et al. US 2010/0063405 A1 “Kashif”.
Regarding claim 11, Mourad discloses all features of the claimed invention as discussed with respect to claim 1 above, however Mourad does not teach “wherein the machine learning model includes a model based on a resistor capacitor (RC) circuit model of the subject’s brain”.
Kashif is within the same field of endeavor as the claimed invention because it involves systems, devices and methods for estimation and monitoring of cerebrovascular system properties and intracranial pressure (ICP) from one or more measurements or measured signals (See [Abstract]).
Kashif teaches “wherein the machine learning model includes a model based on a resistor capacitor (RC) circuit model of the subject’s brain” (“In this application, embodiments will be described in reference to the estimation of one or more cerebrovascular parameters or variables using one or more computational models that represent physiological relationships among cerebrovascular flows and pressures” [0025]; “FIGS. 4A and 4B illustrate computational circuit-analog models 400 and 450 of cerebrovascular dynamics, according to an illustrative embodiment […] Computational model 400 is relatively simple, yet captures the key dynamics of the cerebrovascular system. Computational model 400 is drawn in terms of an electrical circuit analog, in which current represents blood flow, and voltage represents pressure. The resistance to flow and compliance of the blood vessels are represented by their respective electrical analogs, resistors and capacitors. CSF formation/outflow pathways are similarly represented by resistors. […] The autoregulatory mechanism is indicated by the controlled (and time-varying) cerebrovascular compliance C.sub.a and cerebrovascular resistance R.sub.a. Finally, intracranial compliance represents the capacity of the intracranial space to accommodate CSF volume, mainly due to elasticity of the brain tissue and compression of the blood vessels” [0058]; “ In some embodiments, CBFV may be used as an input to the computational model 400 instead of, or in addition to, CBF q(t)” [0059]; “The processor may compute estimates of a cerebrovascular compliance in a first stage of the two-stage algorithm, and may compute estimates of at least one of a cerebrovascular resistance and ICP in a second stage of a two-stage algorithm” [0017].
As shown in FIGS. 4A and 4B the circuit-analog models 400 and 450 represent cerebrovascular dynamics (i.e. within a subject’s brain) an include both resistors and capacitors. Therefore, the machine learning model (i.e. computational model) includes a model based on a resistor capacitor (RC) circuit model of the subject’s brain.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the machine learning model of Mourad such that it includes a model based on a resistor capacitor (RC) circuit model of the subject’s brain as disclosed in Kashif in order to effectively model, and thus observe, the relationship between intracranial pressure (ICP), arterial blood pressure (i.e. ABP), and cerebral blood flow velocity (i.e. V_mca, for example). A computational model including at least one resistive element (i.e. corresponding to resistance to flow) and at least one compliant element (i.e. corresponding to compliance of blood vessels), specifically an RC circuit, is one of a finite number of models which can be used to represent cerebrovascular properties used in determining intracranial pressure (ICP) with a reasonable expectation of success. Thus, modifying the machine learning model of Mourad such that it is a model based on a resistor capacitor (RC) circuit model of the subject’s brain as disclosed in Kashif would yield the predictable result of effectively modeling the relationship between intracranial pressure (ICP), arterial blood pressure (i.e. ABP), and cerebral blood flow velocity (i.e. V_mca, for example).
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KAITLYN E SEBASTIAN whose telephone number is (571)272-6190. The examiner can normally be reached Mon.- Fri. 7:30-4:30 (Alternate Fridays Off).
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, Anne M Kozak can be reached at (571) 270-0552. 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.
/KAITLYN E SEBASTIAN/Examiner, Art Unit 3797