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 .
Response to Arguments
Priority
Applicant's arguments filed 1/31/2026 have been fully considered but they are not persuasive. Applicant argues that the Applicant need not provide a response to the Office’s finding that Applicant has not complied with one or more conditions for receiving the benefit of an earlier filing date under 35 U.S.C. 119(e). Remarks at 7. Applicant’s argument is improper and not responsive. The finding that claim 11 lacks written description in the disclosure of the prior filed provisional application 63/539,176 (the “‘176 App”) is maintained. Further, as detailed in infra rejection, amended claim 9 lacks written description in the disclosure of the ‘176 App. Further, as detailed in infra rejection, amended independent claims 1, 14, and 16 lack written description in the disclosure of the ‘176 App.
Claim Interpretation
Applicant's arguments filed 1/31/2026 have been fully considered but they are not persuasive. Applicant argues that the Office failed to establish a prima facie case that Applicant has invoked 35 U.S.C. 112(f). Remarks at 7=8. Applicant’s argument is improper and not responsive. As set forth in the Non-Final Rejection mailed 10/1/2025 (“NF”) at 3-5 the modules recited in claims 14 and 15 use a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. It is clear from the claim language that there is no structural support for the recited modules. The word module is a nonce term that is only given meaning by the functional language coupled thereto, i.e., “feature extraction,” “functional connectivity analysis,” and “data collection.” The Office made a finding that no structural support can be found in the claim language. This provides ample evidence of a prima facie case under the preponderance of evidence standard that the claims do not provide sufficient structure to perform the recited function.
Applicant appears to assert that the Office must show evidence of the lack of structural support; however, under the analysis implied by the Applicant, it is unclear how the Office can satisfy the Applicant’s demand for a showing of structural support when the claim does not recite any structural support and, therefore, the structural support is nonexistent. The Office cannot produce something that does not exist. Thus, Applicant’s argument and analysis is improper.
Moreover, the Office provided the Applicant with corresponding structure from Applicant’s specification that is not recited in the claims, “appear to correspond to components of a computer system or processor as disclosed in applicant’s specification P.15, lines 1-12 and P.33, lines 22-27.” NF at 5. None of a computer system, processor, or equivalents thereof are recited in the claims. This provides ample evidence of a prima facie case under the preponderance of evidence standard that the claims do not provide sufficient structure to perform the recited function.
Thus, the interpretation of claims 14 and 15 under 35 U.S.C. 112(f) is maintained.
112(a) Rejections
With regard to, Applicant's arguments filed 1/31/2026 have been fully considered but they are not persuasive. Applicant argues that “claim 9 has been revised to overcome the limitations.” Remarks at 8. Applicant points to no support in the Applicant’s originally filed disclosure for the alleged claim features of amended claim 9 and, therefore, claim 9 is rejected as detailed in infra rejection.
With regard to claim 11, Applicant’s arguments, see arguments filed 1/31/2026, have been fully considered and are persuasive. The rejection of claim 11 under 35 U.S.C. 112(a) has been withdrawn. Applicant argues that “[c]laim 11 has support in the originally-filed application, which includes claim 11.” Taking Applicant’s assertion to be true, as detailed in infra objection, Applicant’s specification is objected to for failing to include the claimed subject matter.
112(b) Rejections
With regard to claim 9, Applicant's arguments filed 1/31/2026 have been fully considered but they are not persuasive. Applicant argues that “claim 9 has been revised to overcome the limitations.” Remarks at 8. Claim 9, lines 1-3 recites “the functional connectivity analysis indicates functional connectivity distributions which represent typical or atypical neural connectivity neural expressions related to conditions and clinical progression of the patient, not only analyzed at the original data but also analyzed with the generated fMRI synthetic data from the CVAE outputs.” It is unclear what “functional connectivity distributions which represent typical or atypical neural connectivity neural expressions” means in the context of functional connectivity analysis. The specification and drawings of the present application do not disclose the scope or meaning of this limitation. Furthermore, it is unclear what “conditions and clinical progression of the patient” means in the context of functional connectivity analysis. The specification and drawings of the present application do not disclose the scope or meaning of this limitation.
101 Rejections
Applicant's arguments filed 1/31/2026 have been fully considered but they are not persuasive. Applicant argues
that claim 1 recites a number of features that cannot practically be performed in the human mind, including for example: applying a conditional variational encoder model, generating neurodivergent and non-neurodivergent synthetic fMRI data, and conducting a functional connectivity analysis. The Examiner fails to provide any support for the conclusion, for example, that the CVAE and fMRI data encompasses a mental process that is practically performed in the human mind. Remarks at 8-9.
The Applicant fails to engage with or respond to the analysis of the mental process detailed in NF at 7-9. On this ground alone Applicant’s argument is not persuasive, improper, and non-responsive.
In arguendo, Applicant provides no arguments or evidence to support that “applying a conditional variation encoder model” cannot be practically performed in the human mind. As stated in the NF at 7
This encompasses application and training of a CVAE model using selected conditions. When given their broadest reasonable interpretation in light of the background, the conditioning of the CVAE model encompasses the mental process of the user making a determination of which conditions/covariates to input into the model to perform application/training of the model. See MPEP 2106.04(a)(2), subsection III.
Further, Applicant provides no arguments or evidence to support that “generating neurodivergent and non-neurodivergent synthetic fMRI data” cannot be practically performed in the human mind. As stated in the NF at 7
This encompasses performing evaluation, judgment, and opinion to make a determination about neurodivergent features in the input patient fMRI data. Under its broadest reasonable interpretation when read in light of the specification, the generating of neurodivergent synthetic fMRI data encompasses mental processes practically performed in the human mind by observation, evaluation, judgment, and opinion. See MPEP 2106.04(a)(2), subsection III.
…
This encompasses performing evaluation, judgment, and opinion to make a determination about non-neurodivergent features in the input patient fMRI data. Under its broadest reasonable interpretation when read in light of the specification, the generating of non-neurodivergent synthetic fMRI data encompasses mental processes practically performed in the human mind by observation, evaluation, judgment, and opinion. See MPEP 2106.04(a)(2), subsection III.
Further, Applicant provides no arguments or evidence to support that “conducting a functional connectivity analysis” cannot be practically performed in the human mind. As stated in the NF at 8
This may be practically performed in the human mind using observation, evaluation, judgment, and opinion. For example, under the broadest reasonable interpretation, the claimed functional connectivity analysis encompasses a user observing the labeled brain regions and calculating the Pearson’s correlation coefficient between at least a pair of labeled brain regions to calculate the functional connectivity matrix for each of the neurodivergent features and the non-neurodivergent features, and comparing the correlation coefficient of the neurodivergent features with the non-neurodivergent features. Further, under the broadest reasonable interpretation, the claimed identification encompasses making a determination using the calculated correlation coefficients and the comparison between the neurodivergent and non-neurodivergent features to determine neurodivergence in the patient fMRI data. See MPEP 2106.04(a)(2), subsection III. The broadest reasonable interpretation of claim 1, lines 13-15 also encompasses mathematical concepts (e.g., calculating the Pearson’s correlation coefficient). See MPEP 2106.04(a)(2), subsection I.
Further, Applicant asserts that the Office concluded “that the CVAE and fMRI data encompasses a mental process that is practically performed in the human mind.”
As set forth in the NF at 7-9, claim 1 recites applying the CVAE model. Again, as stated in the NF at 7
This encompasses application and training of a CVAE model using selected conditions. When given their broadest reasonable interpretation in light of the background, the conditioning of the CVAE model encompasses the mental process of the user making a determination of which conditions/covariates to input into the model to perform application/training of the model. See MPEP 2106.04(a)(2), subsection III.
Applicant provides no arguments or evidence to support that applying the CVAE model cannot be practically performed in the human mind. It is not the CVAE model itself that is being performed in the human mind, but rather the mental process of the user making a determination of which conditions/covariates to input into the model to perform application/training of the model as disclosed in Applicant’s specification.
As set forth in the NF at 7-9, claim 1 recites mapping the fMRI data, applying the CVAE model to the fMRI data, and generating synthetic neurodivergent and non-neurodivergent fMRI data. Again, as set forth in the NF at 7
This encompasses application and training of a CVAE model using selected conditions. When given their broadest reasonable interpretation in light of the background, the conditioning of the CVAE model encompasses the mental process of the user making a determination of which conditions/covariates to input into the model to perform application/training of the model. See MPEP 2106.04(a)(2), subsection III.
…
This encompasses performing evaluation, judgment, and opinion to make a determination about neurodivergent features in the input patient fMRI data. Under its broadest reasonable interpretation when read in light of the specification, the generating of neurodivergent synthetic fMRI data encompasses mental processes practically performed in the human mind by observation, evaluation, judgment, and opinion. See MPEP 2106.04(a)(2), subsection III.
…
This encompasses performing evaluation, judgment, and opinion to make a determination about non-neurodivergent features in the input patient fMRI data. Under its broadest reasonable interpretation when read in light of the specification, the generating of non-neurodivergent synthetic fMRI data encompasses mental processes practically performed in the human mind by observation, evaluation, judgment, and opinion. See MPEP 2106.04(a)(2), subsection III.
Applicant provides no arguments or evidence to support that applying the CVAE model to the fMRI data, and generating synthetic neurodivergent and non-neurodivergent fMRI data cannot be practically performed in the human mind. It is not the CVAE model itself that is being performed in the human mind, but rather the mental process of the user making a determination of which conditions/covariates to input into the model to perform application/training of the model as disclosed in Applicant’s specification. It is also not the fMRI data itself being performed in the human mind but rather the mental process of encompasses performing evaluation, judgment, and opinion to make a determination about neurodivergent or non-neurodivergent features in the input patient fMRI data
Additionally, it is noted that claim 1 encompasses patient fMRI data and synthetic fMRI data of any size including a single pixel/voxel or a single 2D image. It is readily contemplated that a clinician/technician may, with the aid of pen and paper, perform the recited method steps as part of a mental process including mapping/matching the image to an atlas, inputting the image to a CVAE model including conditioning the model, and analyzing the neurodivergent and non-neurodivergent images output from the CVAE model to identify neurodivergences in the fMRI image.
Applicant further argues that the recitation in claim 4 of “optimizes” does not recite a mathematical concept as it does not recite a specific mathematical relationship. Remarks at 9. As set forth in the NF at 15
When given their broadest reasonable interpretation in light of the background, the optimization is a mathematical calculation. The plain meaning of this term is an optimization algorithm, which compute neural network parameters using a series of mathematical calculations. Thus, claim 4 requires mathematical calculations (an optimization algorithm) to perform the training of the CVAE model and therefore encompasses mathematical concepts. See MPEP 2106.04(a)(2), subsection I.
Applicant provides no arguments or evidence to support that the optimization claimed in claim 4 merely involves an exception. Again, the plain meaning of this term is an optimization algorithm, which compute neural network parameters using a series of mathematical calculations. The claim expressly recites the mathematical optimization calculation and therefore recites a mathematical concept.
Applicant further restates that in evaluating claims under 35 U.S.C. 101 that the preponderance of the evidence standard applies. Remarks at 9. In the NF and in infra rejections, the Office has applied the preponderance of the evidence standard in finding that it is more likely than not that claims 1-16 are ineligible under 35 U.S.C. 101.
Therefore, Applicant’s arguments are not persuasive.
Furthermore, as detailed in infra rejection, amended claim 14 is rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
103 Rejections
Applicant's arguments filed 1/31/2026 have been fully considered but they are not persuasive.
First, Applicant argues
that Pijar uses the raw data to compute functional connectivity, with 51 by 51 functional connectivity format (page 8), and their data is "preprocessed" (page 8) and not from their own network. In contrast, the claimed invention requires CV AE to generate a synthetic brain model to produce a generalized synthetic brain signal outcomes, which can produce both typical and atypical ±MRI signals based on the subject, and then compute the functional connectivity. The functional connectivity is based on more generalized synthetic brain model outcomes. Remarks at 10.
Applicant's arguments fail to comply with 37 CFR 1.111(b) because they amount to a general allegation that the claims define a patentable invention without specifically pointing out how the language of the claims patentably distinguishes them from the references. Applicant's arguments do not comply with 37 CFR 1.111(c) because they do not clearly point out the patentable novelty which he or she thinks the claims present in view of the state of the art disclosed by the references cited or the objections made. Further, they do not show how the amendments avoid such references or objections.
The relevance of Applicant’s statement of the teachings of Pijar from page 8 to applicant’s attempt to distinguish from the claimed invention is unclear. Applicant does not provide any arguments or explanation of how the asserted teachings of Pijar differ from the claimed invention aside from a restatement of the claimed invention. On this ground alone Applicant’s argument is unpersuasive.
In arguendo, as best the Office can ascertain, Applicant appears to be arguing that the functional connectivity analysis as taught by Pijar does not identify neurodivergences in the patient fMRI data. This contention is not supported by the record. As detailed in NF at 19-20, Pijar, P.8, ¶1 – P.9, ¶2 teaches that the functional connections altered by Autism Spectrum Disorder (ASD) in the patient fMRI data, fMRI blood-oxygen-level-dependent (BOLD) scans of each patient/participant/subject, are identified using functional connectivity analysis to identify differences between the neurodivergent synthetic fMRI data, ASD specific reconstructed fMRI data output from a contrastive variational autoencoder (CVAE) model, and the non-neurodivergent synthetic fMRI data, TD twin without ASD reconstructed fMRI data output from a contrastive variational autoencoder (CVAE) model.
Thus, as Pijar teaches the asserted claim features, Applicant’s arguments are not persuasive.
Second, Applicant argues that
Milana is a thesis, composing dense literature review of techniques until 2017-18. But the technology Milana used to make conclusion (or connect sMRI images and AD classes) is only a traditional support vector machine (SVM) algorithm. Remarks at 11.
In response to applicant's argument that Milana is nonanalogous art, it has been held that a prior art reference must either be in the field of the inventor’s endeavor or, if not, then be reasonably pertinent to the particular problem with which the inventor was concerned, in order to be relied upon as a basis for rejection of the claimed invention. See In re Oetiker, 977 F.2d 1443, 24 USPQ2d 1443 (Fed. Cir. 1992). In this case, as stated in the NF at 20 Milana is “in the same field of endeavor of brain studies of neurological disorders.” Applicant provides no arguments or evidence to the contrary or to establish that a PHOSITA (a researcher/clinician with significant postdoctoral experience in the field of MRI imaging, including fMRI/BOLD imaging, and neurological disorders, including ASD and AD, such as the inventors of the present application and the inventors, authors, editors, and advisors of the prior art cited in the rejections and pertinent art) would not refer to prior art such as Milana.
Applicant appears to assert that because Milana is a thesis paper that the teachings therein should be accorded lesser or no weight. Applicant provides no basis in law or fact for such a contention.
Applicant appears to assert that to be accorded weight, Milana’s conclusion must alone teach the use of an algorithm other than support vector machine (SVM). First, in response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). Milana is not relied upon to teach any alleged claim features other than that the CVAE model is conditioned on sex, age, and neurodivergence subgroup label. Pijar is relied upon to teach the remaining alleged claim features of claim 1. Therefore, Applicant’s arguments are improper, irrelevant, and not persuasive.
Furthermore, a prior art printed publication may be cited “concerning obviousness, a disclosure may be cited for all that it would reasonably have made known to a person of ordinary skill in the art.” MPEP 2152.02(b). See also MPEP 2158 “while a disclosure must enable those skilled in the art to make the invention in order to anticipate under 35 U.S.C. 102, a non-enabling disclosure is prior art for all it teaches for purposes of determining obviousness under 35 U.S.C. 103. Symbol Techs. Inc. v. Opticon Inc., 935 F.2d 1569, 1578, 19 USPQ2d 1241, 1247 (Fed. Cir. 1991); Beckman Instruments v. LKB Produkter AB, 892 F.2d 1547, 1551, 13 USPQ2d 1301, 1304 (Fed. Cir. 1989) ("Even if a reference discloses an inoperative device, it is prior art for all that it teaches."). Therefore, contrary to Applicant’;s contention, in finding a prima facie case of obviousness, the Office properly relied upon teachings from Milana.
Further, Applicant's arguments fail to comply with 37 CFR 1.111(b) because they amount to a general allegation that the claims define a patentable invention without specifically pointing out how the language of the claims patentably distinguishes them from the references. Applicant's arguments do not comply with 37 CFR 1.111(c) because they do not clearly point out the patentable novelty which he or she thinks the claims present in view of the state of the art disclosed by the references cited or the objections made. Further, they do not show how the amendments avoid such references or objections.
Further, Applicant provides no evidence that Milana is limited to “a traditional support vector machine (SVM) algorithm.” Applicant provides no citations or other evidence in the record that Milana’s teachings are limited to a SVM and makes no attempt to address the citations in the NF from Milana that teach CVAE models and conditioning the CVAE model with labels for age, diagnosis/classification (class), and gender.
Thus, Applicant’s arguments are not persuasive.
Third, Applicant argues
it is respectfully submitted that the Examiner is confusing AD (Alzheimer's disease) and ASD (Autism spectrum disorder), and MRI and fMRI. The claimed invention requires fMRI data from ASD population, with typical and epilepsy patients' data used together during training. Remarks at 11.
In response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., fMRI data from ASD population) are not recited in the rejected independent claims. Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
Furthermore, there is no confusion by the Office between autism spectrum disorder and Alzheimer’s disease as contended by the Applicant. For example, in the rejection of claim 2 in the NF at 21, Pijar, P.9, ¶1-2 is cited as teaching that the population in question is autism spectrum disorder.
Furthermore, there is no confusion by the Office between MRI and fMRI data as contended by the Applicant. For example, in the rejection of claim 1 in the NF at 20, Pijar, P.7, ¶3 – P.8, ¶2 is cited as teaching that the data is fMRI data, e.g., fMRI blood-oxygen-level-dependent (BOLD) data.
Applicant appears to contend that the prior art must be limited to references that individually teach autism spectrum disorder and fMRI data. This contention has no basis in law. In response to applicant's argument that references that do not teach ASD and fMRI data are nonanalogous art, it has been held that a prior art reference must either be in the field of the inventor’s endeavor or, if not, then be reasonably pertinent to the particular problem with which the inventor was concerned, in order to be relied upon as a basis for rejection of the claimed invention. See In re Oetiker, 977 F.2d 1443, 24 USPQ2d 1443 (Fed. Cir. 1992). Applicant has provided no arguments or evidence to rebut the findings and conclusions that each of the references are either in the field of the inventor’s endeavor or, if not, then be reasonably pertinent to the particular problem with which the inventor was concerned. For example, Applicant has not addressed that as set forth in the NF at 20 that Milana is “in the same field of endeavor of brain studies of neurological disorders.” Applicant appears to limit the inventor’s field of endeavor to autism spectrum disorder and fMRI data, excluding the relevance of all other neurological disorders and brain studies. Applicant provides no support in law or fact for such a narrow field of endeavor, let alone address that the independent claims do not recite ASD. Even if the independent claims recited ASD as well as fMRI data, that alone would not suffice to limit the field of endeavor to only ASD and fMRI data as contended.
Further, in response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). Milana alone is not relied upon to teach ASD and fMRI data. Rather the combination of Pijar in further view of Milana is relied upon to teach the asserted features. As addressed above, Pijar teaches ASD and fMRI data.
Further, in response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., “typical and epilepsy patient’s data used together during training”) are not recited in the rejected independent claims. Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). In arguendo, as addressed with regard to the rejection of claim 11 over Pijar in further view of Milana in further view of Aglinskas in NF at 28-29, the combination of these references teaches that the CVAE model conditioning can include feature labels for normal, autism, and epilepsy.
Thus, Applicant’s argument is not persuasive.
Fourth, Applicant argues that as amended “[t]he cited art fails to teach a neural network used in the claimed manner.” As detailed in infra rejection, the independent claims as amended are taught by the combination of Pijar in further view of Milana. In addition, claims 1-14 are rejected under 35 U.S.C. 112(a) as lacking written description.
Thus, Applicant’s argument is not persuasive.
Fifth, Applicant argues that
As to claim 3, Aguila is in line of similar research trends, while Aguila only used the latent space in CV AE to study the distribution of AD and MCI patients, while our work used "Sex" as a conditional variable and then produced gender-specific brain signals that explains the gender differences in Autism, followed by the FC analysis.
In response to applicant's argument that Aguila is nonanalogous art, it has been held that a prior art reference must either be in the field of the inventor’s endeavor or, if not, then be reasonably pertinent to the particular problem with which the inventor was concerned, in order to be relied upon as a basis for rejection of the claimed invention. See In re Oetiker, 977 F.2d 1443, 24 USPQ2d 1443 (Fed. Cir. 1992). In this case, as stated in the NF at 25 Aguila is “in the same field of endeavor of brain studies of neurological disorders.” Applicant provides no arguments or evidence to the contrary. Note that Applicant states that “Aguila is in line of similar research trends” which appears to be an admission that Aguila is in the same field of endeavor as the claimed invention.
Applicant appears to assert that to be accorded weight, Aguila must alone teach “’Sex’ as a conditional variable and then produced gender-specific brain signals that explains the gender differences in Autism, followed by the FC analysis.” In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). Aguila is not relied upon to teach any alleged claim features other than applying Welch t-test to identify differences between reconstructed/synthesized disease and control MRI data. As stated in NF at 25, Aguila, P.437, ¶1-2 and Fig. 4 teaches Welch’s t-test per brain region to identify the significance of separation/deviation between CVAE model reconstructed/synthesized neurodivergent, late mild cognitive impairment and Alzheimer’s disease, and healthy control MRI data. Pijar in further view of Milana in further view of Bhavna is relied upon to teach the remaining alleged claim features of claim 3. Aguila’s known technique of using Welch’s t-test to identify differences is applied to Pijar in further view of Milana in further view of Bhavna’s known process of using t-test to identify differences. Applicant provides no arguments or evidence to address the motivation to combine the references.
Therefore, Applicant’s arguments are improper, irrelevant, and not persuasive.
Furthermore, a prior art printed publication may be cited “concerning obviousness, a disclosure may be cited for all that it would reasonably have made known to a person of ordinary skill in the art.” MPEP 2152.02(b). See also MPEP 2158 “while a disclosure must enable those skilled in the art to make the invention in order to anticipate under 35 U.S.C. 102, a non-enabling disclosure is prior art for all it teaches for purposes of determining obviousness under 35 U.S.C. 103 . Symbol Techs. Inc. v. Opticon Inc., 935 F.2d 1569, 1578, 19 USPQ2d 1241, 1247 (Fed. Cir. 1991); Beckman Instruments v. LKB Produkter AB, 892 F.2d 1547, 1551, 13 USPQ2d 1301, 1304 (Fed. Cir. 1989) ("Even if a reference discloses an inoperative device, it is prior art for all that it teaches."). Therefore, contrary to Applicant’;s contention, in finding a prima facie case of obviousness, the Office properly relied upon teachings from Aguila.
Further, Applicant's arguments fail to comply with 37 CFR 1.111(b) because they amount to a general allegation that the claims define a patentable invention without specifically pointing out how the language of the claims patentably distinguishes them from the references. Applicant's arguments do not comply with 37 CFR 1.111(c) because they do not clearly point out the patentable novelty which he or she thinks the claims present in view of the state of the art disclosed by the references cited or the objections made. Further, they do not show how the amendments avoid such references or objections.
Thus, Applicant’s arguments are not persuasive.
Priority
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged. Applicant has not complied with one or more conditions for receiving the benefit of an earlier filing date under 35 U.S.C. 119(e) as follows:
The later-filed application must be an application for a patent for an invention which is also disclosed in the prior application (the parent or original nonprovisional application or provisional application). The disclosure of the invention in the parent application and in the later-filed application must be sufficient to comply with the requirements of 35 U.S.C. 112(a) or the first paragraph of pre-AIA 35 U.S.C. 112, except for the best mode requirement. See Transco Products, Inc. v. Performance Contracting, Inc., 38 F.3d 551, 32 USPQ2d 1077 (Fed. Cir. 1994).
The disclosure of the prior filed provisional application 63/539,176 (the “‘176 App”) fails to provide adequate support or enablement in the manner provided by 35 U.S.C. 112(a) for one or more claims of this application. Claims 1-14 recite subject matter not disclosed in the application from which priority is claimed. Specifically:
Claim 1, lines 4-5 recites “mapping at a neural network, the patient fMRI data of the patient to a predefined brain atlas.” There does not appear to be written description in the ‘176 App for these limitations. Particularly, there is no disclosure that a neural network is involved in the mapping step as claimed. Claim 1, lines 14-16 recites “conducting at the neural network, functional connectivity analysis to identify differences between the neurodivergent synthetic fMRI data and the non-neurodivergent synthetic fMRI data to identify neurodivergences in the patient fMRI data.” There does not appear to be written description in the ‘176 App for these limitations. Particularly, there is no disclosure that a neural network is involved in the functional connectivity analysis as claimed.
Claim 9, lines 1-5 recites “the functional connectivity analysis indicates functional connectivity distributions which represent typical or atypical neural connectivity neural expressions related to conditions and clinical progression of the patient, not only analyzed at the original data but also analyzed with the generated fMRI synthetic data from the CVAE outputs.” There does not appear to be written description in the ‘176 App for these limitations.
Claim 11, lines 1-2 recites “the subgroup neurodivergence label including: normal, autism, and epilepsy.” There does not appear to be written description in the ‘176 App for these limitations.
Claim 14, lines 1-4 and 7-8 recites “a neural network configured to identify neurodivergences in a patient, the system comprising: a feature extraction module configured to receive patient fMRI data and extract features from the patient fMRI data… a functional connectivity analysis module configured to perform functional connectivity analysis on the synthetic fMRI data to identify neurodivergences in individuals.” There does not appear to be written description in the ‘176 App for these limitations. Particularly there is no disclosure that a neural network is involved in the feature extraction as claimed and there is no disclosure that a neural network is involved in the functional connectivity analysis.
Claim 16, lines 4-6 and 11-12 recites “a neural network having layers configured to execute instructions from the one or more non-transitory memory devices to cause the system to:
map fMRI data to a predefined brain atlas;
perform functional connectivity analysis on the synthetic fMRI data to identify neurodivergences in the fMRI data.” There does not appear to be written description in the ‘176 App for these limitations. Particularly there is no disclosure that a neural network is involved in the mapping as claimed and there is no disclosure that a neural network is involved in the functional connectivity analysis.
Claims 2-13 and 15 fail to comply with one or more conditions for receiving the benefit of an earlier filing date under 35 U.S.C. 119(e) as depending from independent claims 1 and 14, respectively.
Specification
The specification is objected to as failing to provide proper antecedent basis for the claimed subject matter. See 37 CFR 1.75(d)(1) and MPEP § 608.01(o). Correction of the following is required: Claim 11 as field 9/19/2024 recites “the subgroup neurodivergence label including: normal, autism, and epilepsy” There is no corresponding disclosure in the Applicant’s Specification as filed 9/19/2024.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are:
Claim 14, line 3 recites “a feature extraction module”
Claim 14, line 7 recites “a functional connectivity analysis module”
Claim 15, line 1 recites “a data collection module”
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof. “[F]eature extraction module,” “functional connectivity analysis module,” and “a data collection module” appear to correspond to components of a computer system or processor as disclosed in applicant’s specification P.15, lines 1-12 and P.33, lines 22-27.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-16 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claim 1, lines 4-5 recites “mapping at a neural network, the patient fMRI data of the patient to a predefined brain atlas.” There does not appear to be written description in the present application for these limitations. Particularly, there is no disclosure that a neural network is involved in the mapping step as claimed. Claim 1, lines 14-16 recites “conducting at the neural network, functional connectivity analysis to identify differences between the neurodivergent synthetic fMRI data and the non-neurodivergent synthetic fMRI data to identify neurodivergences in the patient fMRI data.” There does not appear to be written description in the present application for these limitations. Particularly, there is no disclosure that a neural network is involved in the functional connectivity analysis as claimed.
Claim 9, lines 1-5 recites “the functional connectivity analysis indicates functional connectivity distributions which represent typical or atypical neural connectivity neural expressions related to conditions and clinical progression of the patient, not only analyzed at the original data but also analyzed with the generated fMRI synthetic data from the CVAE outputs.” There does not appear to be written description in the present application for these limitations.
Claim 14, lines 1-4 and 7-8 recites “a neural network configured to identify neurodivergences in a patient, the system comprising: a feature extraction module configured to receive patient fMRI data and extract features from the patient fMRI data… a functional connectivity analysis module configured to perform functional connectivity analysis on the synthetic fMRI data to identify neurodivergences in individuals.” There does not appear to be written description in the present application for these limitations. Particularly there is no disclosure that a neural network is involved in the feature extraction as claimed and there is no disclosure that a neural network is involved in the functional connectivity analysis.
Claim 16, lines 4-6 and 11-12 recites “a neural network having layers configured to execute instructions from the one or more non-transitory memory devices to cause the system to:
map fMRI data to a predefined brain atlas;
perform functional connectivity analysis on the synthetic fMRI data to identify neurodivergences in the fMRI data.” There does not appear to be written description in the present application for these limitations. Particularly there is no disclosure that a neural network is involved in the mapping as claimed and there is no disclosure that a neural network is involved in the functional connectivity analysis.
Claims 2-13 and 15 are rejected as depending from rejected independent claims 1 and 14, respectively.
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 9 and 14-15 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 9, lines 1-3 recites “the functional connectivity analysis indicates functional connectivity distributions which represent typical or atypical neural connectivity neural expressions related to conditions and clinical progression of the patient, not only analyzed at the original data but also analyzed with the generated fMRI synthetic data from the CVAE outputs.” It is unclear what “functional connectivity distributions which represent typical or atypical neural connectivity neural expressions” means in the context of functional connectivity analysis. The specification and drawings of the present application do not disclose the scope or meaning of this limitation. Furthermore, it is unclear what “conditions and clinical progression of the patient” means in the context of functional connectivity analysis. The specification and drawings of the present application do not disclose the scope or meaning of this limitation.
Claim 14, lines 1-2 recites “a neural network configured to identify neurodivergences in a patient, the system comprising:”. It is unclear whether the claim is directed to “a neural network” or to a “system.”
Claim 15 is rejected as being dependent from rejected independent claim 14.
Claim Rejections - 35 USC § 101
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claims 1-16 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Independent claim 1 is illustrative:
Step 1: This part of the eligibility analysis evaluates whether the claim falls within any statutory category. See MPEP 2106.03. The claim recites at least one step or act, including receiving continuous training data. Thus, the claim is to a process, which is one of the statutory categories of invention. (Step 1: YES).
Step 2A, Prong One: This part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP 2106.04, subsection II, a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim.
Claim 1, lines 4-5 recites “mapping at a neural network, the patient fMRI data of the patient to a predefined brain atlas.” This may be practically performed in the human mind using observation, evaluation, judgment, and opinion. For example, under the broadest reasonable interpretation, the claimed mapping encompasses a user observing the patient fMRI data and labeling one or more regions of the brain according to their anatomy or functional group as informed by a predefined brain atlas. See MPEP 2106.04(a)(2), subsection III.
Claim 1, lines 6-8 recites “applying at the neural network, a conditional variational autoencoder (CVAE) model to the mapped fMRI data, wherein the CVAE model is conditioned on sex, age, and neurodivergence subgroup label.” This encompasses application and training of a CVAE model using selected conditions. When given their broadest reasonable interpretation in light of the background, the conditioning of the CVAE model encompasses the mental process of the user making a determination of which conditions/covariates to input into the model to perform application/training of the model. See MPEP 2106.04(a)(2), subsection III.
Claim 1, lines 9-10 recites “generating at the neural network, neurodivergent synthetic fMRI data corresponding to the conditions of sex, age and neurodivergence subgroup label using the CVAE model.” This encompasses performing evaluation, judgment, and opinion to make a determination about neurodivergent features in the input patient fMRI data. Under its broadest reasonable interpretation when read in light of the specification, the generating of neurodivergent synthetic fMRI data encompasses mental processes practically performed in the human mind by observation, evaluation, judgment, and opinion. See MPEP 2106.04(a)(2), subsection III.
Claim 1, lines 11-12 recites “generating at the neural network, non-neurodivergent synthetic fMRI data corresponding to the conditions of sex and age conditions using the CVAE model.” This encompasses performing evaluation, judgment, and opinion to make a determination about non-neurodivergent features in the input patient fMRI data. Under its broadest reasonable interpretation when read in light of the specification, the generating of non-neurodivergent synthetic fMRI data encompasses mental processes practically performed in the human mind by observation, evaluation, judgment, and opinion. See MPEP 2106.04(a)(2), subsection III.
Claim 1, lines 13-15 recites “conducting at the neural network, functional connectivity analysis to identify differences between the neurodivergent synthetic fMRI data and the non-neurodivergent synthetic fMRI data to identify neurodivergences in the patient fMRI data.” This may be practically performed in the human mind using observation, evaluation, judgment, and opinion. For example, under the broadest reasonable interpretation, the claimed functional connectivity analysis encompasses a user observing the labeled brain regions and calculating the Pearson’s correlation coefficient between at least a pair of labeled brain regions to calculate the functional connectivity matrix for each of the neurodivergent features and the non-neurodivergent features, and comparing the correlation coefficient of the neurodivergent features with the non-neurodivergent features. Further, under the broadest reasonable interpretation, the claimed identification encompasses making a determination using the calculated correlation coefficients and the comparison between the neurodivergent and non-neurodivergent features to determine neurodivergence in the patient fMRI data. See MPEP 2106.04(a)(2), subsection III. The broadest reasonable interpretation of claim 1, lines 13-15 also encompasses mathematical concepts (e.g., calculating the Pearson’s correlation coefficient). See MPEP 2106.04(a)(2), subsection I.
Additionally, it is noted that claim 1 encompasses patient fMRI data and synthetic fMRI data of any size including a single pixel/voxel or a single 2D image. It is readily contemplated that a clinician/technician may, with the aid of pen and paper, perform the recited method steps as part of a mental process including mapping/matching the image to an atlas, inputting the image to a CVAE model including conditioning the model, and analyzing the neurodivergent and non-neurodivergent images output from the CVAE model to identify neurodivergences in the fMRI image.
“Unless it is clear that a claim recites distinct exceptions, such as a law of nature and an abstract idea, care should be taken not to parse the claim into multiple exceptions, particularly in claims involving abstract ideas.” MPEP 2106.04, subsection II.B. However, if possible, the examiner should consider the limitations together as a single abstract idea rather than as a plurality of separate abstract ideas to be analyzed individually. “For example, in a claim that includes a series of steps that recite mental steps as well as a mathematical calculation, an examiner should identify the claim as reciting both a mental process and a mathematical concept for Step 2A, Prong One to make the analysis clear on the record.” MPEP 2106.04, subsection II.B. Under such circumstances, however, the Supreme Court has treated such claims in the same manner as claims reciting a single judicial exception. Id. (discussing Bilski v. Kappos, 561 U.S. 593 (2010)). Here, steps (b), (d), and (e) fall within the mental process grouping of abstract ideas, and steps (b) and (c) fall within the mathematical concepts grouping of abstract ideas. Limitations (b)-(e) are considered together as a single abstract idea for further analysis. (Step 2A, Prong One: YES).
Step 2A, Prong Two: This part of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception into a practical application of the exception or whether the claim is “directed to” the judicial exception. This evaluation is performed by (1) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (2) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application. See MPEP 2106.04(d).
The claim recites the additional elements of “a computer-implemented method for identifying neurodivergences in a patient using functional Magnetic Resonance Imaging (fMRI) data of a patient” in claim 1, lines 1-2, and “at a neural network” in claim 1, line 4, and “at the neural network” in claim 1, lines 6, 9, 11, and 13.
The limitations “for identifying neurodivergences in a patient using functional Magnetic Resonance Imaging (fMRI) data of a patient” are mere data gathering recited at a high level of generality, and are insignificant extra-solution activity. See MPEP 2106.05(g) (“whether the limitation is significant”). In addition, all uses of the recited judicial exceptions require such data gathering, and, as such, these limitations do not impose any meaningful limits on the claim. These limitations amount to necessary data gathering. See MPEP 2106.05.
The recitation of “for identifying neurodivergences in a patient” in claim 1, lines 1-2 also merely indicates a field of use or technological environment in which the judicial exception is performed. Although the additional element limits the identified judicial exceptions, this type of limitation merely confines the use of the abstract idea to a particular technological environment (neurodivergence identification) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
Further, the limitations of claim 1 are recited as being performed by a computer and neural network. The computer and neural network are recited at a high level of generality. The “computer-implemented method” of claim 1, line 1 recites a computer used as a tool to perform the generic computer function of performing the method, such that it amounts to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f). In the limitations of claim 1, lines 4-15 the abstract idea is performed “at a neural network,” as discussed above in Step 2A, Prong One, such that it amounts to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f). Further, it is unclear whether the neural network itself is performing the method steps of the abstract idea or if the method steps of the abstract idea merely occur as part of the computer-implemented method that contain a neural network/CVAE model. For example, the “mapping” of lines 4-5 and functional connectivity analysis of lines 14-16 are not performed by the neural network/CVAE model but rather involve the pre-processing of the input to the neural network/CVAE model and the analysis of the output of the neural network/CVAE model, respectively. For example, the conditioning of the CVAE model of lines 6-8 is not performed by the neural network/CVAE model, but instead involves labels selected by the user. Moreover, the neural network/CVAE model itself is recited at a high level of generality.
The limitations in claim 1, lines 6-7 of “applying… a conditional variational autoencoder (CVAE) model” and claim 1, lines 10 and 12 of “using the CVAE model” provide nothing more than mere instructions to implement an abstract idea on a generic computer. See MPEP 2106.05(f). MPEP 2106.05(f) provides the following considerations for determining whether a claim simply recites a judicial exception with the words “apply it” (or an equivalent), such as mere instructions to implement an abstract idea on a computer: (1) whether the claim recites only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished; (2) whether the claim invokes computers or other machinery merely as a tool to perform an existing process; and (3) the particularity or generality of the application of the judicial exception.
The judicial exception of “generating… neurodivergent synthetic fMRI data corresponding to the conditions of sex, age and neurodivergence subgroup label” and “generating… non-neurodivergent synthetic fMRI data corresponding to sex and age conditions using the CVAE model” is performed “using the CVAE model.” The trained CVAE model is used to generally apply the abstract idea without placing any limits on how the trained CVAE model functions. Rather, these limitations only recite the outcome of “generating… neurodivergent synthetic fMRI data” and “generating… non-neurodivergent synthetic fMRI data” and do not include any details about how the “generating” is accomplished. See MPEP 2106.05(f).
The recitation of “applying… a conditional variational autoencoder (CVAE) model” in claim 1, lines 6-8 and “using the CVAE model” in claim 1, lines 9-10 and 11-12 also merely indicates a field of use or technological environment in which the judicial exception is performed. Although the additional elements “applying… a conditional variational autoencoder (CVAE) model” and “using the CVAE model” limits the identified judicial exceptions, this type of limitation merely confines the use of the abstract idea to a particular technological environment (CVAE models) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application (Step 2A, Prong Two: NO), and the claim is directed to the judicial exception. (Step 2A: YES).
Step 2B: This part of the eligibility analysis evaluates whether the claim as a whole amounts to significantly more than the recited exception i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim. See MPEP 2106.05.
As explained with respect to Step 2A, Prong Two, there are four additional elements.
The additional elements of “applying… a conditional variational autoencoder (CVAE) model” in claim 1, lines 6-8 and “using the CVAE model” in claim 1, lines 9-10 and 11 are at best mere instructions to “apply” the abstract ideas, which cannot provide an inventive concept. See MPEP 2106.05(f).
The additional element of “for identifying neurodivergences in a patient using functional Magnetic Resonance Imaging (fMRI) data of a patient” was found to be insignificant extra-solution activity in Step 2A, Prong Two, because it was determined to be an insignificant limitation as necessary data gathering. However, a conclusion that an additional element is insignificant extra-solution activity in Step 2A, Prong Two should be re-evaluated in Step 2B. See MPEP 2106.05, subsection I.A. At Step 2B, the evaluation of the insignificant extra-solution activity consideration takes into account whether or not the extra-solution activity is well understood, routine, and conventional in the field. See MPEP 2106.05(g).
As discussed in Step 2A, Prong Two above, the recitation of “using functional Magnetic Resonance Imaging (fMRI) data of a patient” is recited at a high level of generality. This element amounts to receiving fMRI data that is well-understood, routine, conventional activity. See MPEP 2106.05(d), subsection II.
As discussed in Step 2A, Prong Two above, the recitation of a computer to perform the method of claim 1 and a neural network to perform the limitations of claim 1, lines 4-15 amounts to no more than mere instructions to apply the exception using a generic computer component.
Even when considered in combination, these additional elements represent mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept. (Step 2B: NO).
Thus, independent claim 1 is ineligible.
Turning to the additional limitations in the remaining independent claims:
Independent claim 13, lines 1-3 additionally recites “a non-transitory computer-readable storage medium comprising instructions that, when executed by a computer, cause the computer to perform the method of claim 1.” The recitation of a non-transitory computer-readable storage medium, instructions, and a computer to perform the method of claim 1 amounts to no more than mere instructions to apply the exception using a generic computer component. See MPEP 2106.05(f).
Independent claim 14, lines 1-2 additionally recites “a neural network” and “system” comprising “a feature extraction module” (lines 3-4) and “a functional connectivity analysis module” (lines 7-8). The recitation of a computer system comprising computer modules configured to perform the judicial exception amounts to no more than mere instructions to apply the exception using a generic computer component. The neural network and system are recited at a high level of generality. That the “neural network” is “configured to identify neurodivergences in a patient” amounts to no more than mere instructions to apply the exception using a generic computer in that the abstract idea is performed involving a neural network. See MPEP 2106.05(f). Further, it is unclear whether the neural network itself is performing the method steps of the abstract idea or if the method steps of the abstract idea merely occur as part of the computer system that contain a neural network/CVAE model. For example, the “feature extraction” of lines 3-4 and “functional connectivity analysis” of lines 6-7 are not performed by the neural network/CVAE model but rather involve the pre-processing of the input to the neural network/CVAE model and the analysis of the output of the neural network/CVAE model, respectively. For example, the conditioning of the CVAE model of lines 5-6 is not performed by the neural network/CVAE model, but instead involves labels selected by the user. Moreover, the neural network/CVAE model itself is recited at a high level of generality.
Furthermore, the limitation “configured to identify neurodivergences in a patient” in claim 14, line 1 merely indicates a field of use or technological environment in which the judicial exception is performed. Although the additional element limits the identified judicial exceptions, this type of limitation merely confines the use of the abstract idea to a particular technological environment (neurodivergence identification) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h). Further, the limitation “to receive patient fMRI data” in claim 14, line 3 are mere data gathering recited at a high level of generality, and are insignificant extra-solution activity. See MPEP 2106.05(g) (“whether the limitation is significant”). In addition, all uses of the recited judicial exceptions require such data gathering and output, and, as such, these limitations do not impose any meaningful limits on the claim. These limitations amount to necessary data gathering. See MPEP 2106.05. Further, the limitation “to… extract features from the patient fMRI data” in claim 1, lines 3-4 may be practically performed in the human mind using observation, evaluation, judgment, and opinion. For example, under the broadest reasonable interpretation, the claimed mapping encompasses a user observing the patient fMRI data and labeling one or more regions of the brain according to their anatomy or functional group as informed by a predefined brain atlas. See MPEP 2106.04(a)(2), subsection III.
Independent claim 16, lines 1-2 additionally recites “a system” comprising “one or more non-transitory memory devices” (line 3) and “a neural network having layers configured to execute instructions from the one or more non-transitory memory devices to cause the system to” perform method steps. The recitation of a system comprising one or more non-transitory memory device, instructions, and a neural network having layers configured to perform the judicial exceptions amounts to no more than mere instructions to apply the exception using a generic computer component. See MPEP 2106.05(f). The system, memory devices, and neural network are recited at a high level of generality. That the “neural network” is “configured to execute instructions” amounts to no more than mere instructions to apply the exception using a generic computer in that the abstract idea is performed involving a neural network. See MPEP 2106.05(f). Further, it is unclear whether the neural network itself is performing the method steps of the abstract idea or if the method steps of the abstract idea merely occur as part of the system that contain a neural network/CVAE model. For example, the mapping of line 6 and functional connectivity analysis of lines 11-12 are not performed by the neural network/CVAE model but rather involve the pre-processing of the input to the neural network/CVAE model and the analysis of the output of the neural network/CVAE model, respectively. For example, the conditioning of the CVAE model of lines 7-9 is not performed by the neural network/CVAE model, but instead involves labels selected by the user. Moreover, the neural network/CVAE model itself is recited at a high level of generality.
Furthermore, the limitation “for image classification and inventory management” in claim 14, line 1 merely indicates a field of use or technological environment in which the judicial exception is performed. Although the additional element limits the identified judicial exceptions, this type of limitation merely confines the use of the abstract idea to a particular technological environment (image classification and inventory management) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
Thus, independent claims 13, 14, and 16 are ineligible.
Turning to the dependent claims:
Claim 2 merely specifies that the neurodivergence comprises Autism Spectrum Disorder (ASD). This merely indicates a field of use or technological environment in which the judicial exception is performed. Although the additional element limits the identified judicial exceptions, this type of limitation merely confines the use of the abstract idea to a particular technological environment (autism spectrum disorder) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
Claim 3, lines 3-4 recites “calculating correlation matrices based on the neurodivergent synthetic fMRI data and the non-neurodivergent synthetic fMRI data.” This may be practically performed in the human mind using observation, evaluation, judgment, and opinion. For example, under the broadest reasonable interpretation, the claimed functional connectivity analysis encompasses a user observing the labeled brain regions and calculating the Pearson’s correlation coefficient between at least a pair of labeled brain regions to calculate the functional connectivity matrix for each of the neurodivergent features and the non-neurodivergent features, and comparing the correlation coefficient of the neurodivergent features with the non-neurodivergent features. See MPEP 2106.04(a)(2), subsection III. The broadest reasonable interpretation of claim 3, lines 3-4 also encompasses mathematical concepts (e.g., calculating the Pearson’s correlation coefficient). See MPEP 2106.04(a)(2), subsection I.
Claim 3, lines 5-6 recites “applying Welch t-test to the correlation matrices to identify the differences in functional connectivity patterns between patient fMRI data.” This may be practically performed in the human mind using observation, evaluation, judgment, and opinion. For example, under the broadest reasonable interpretation, the claimed functional connectivity analysis encompasses a user observing the calculated functional connectivity matrix for each of the neurodivergent features and the non-neurodivergent features, and calculating the Welch’s t-test p-value between the functional connectivity matrices. Further, under the broadest reasonable interpretation, the claimed identification encompasses making a determination using the calculated p-values to identify differences between the functional connectivity matrices of the neurodivergent and non-neurodivergent features to determine neurodivergence in the patient fMRI data. See MPEP 2106.04(a)(2), subsection III. The broadest reasonable interpretation of claim 1, lines 13-15 also encompasses mathematical concepts (e.g., calculating the Welch’s t-test p-values). See MPEP 2106.04(a)(2), subsection I.
Claim 4 recites “optimizes the latent space representations of the fMRI data” that encompasses any known optimization algorithm. When given their broadest reasonable interpretation in light of the background, the optimization is a mathematical calculation. The plain meaning of this term is an optimization algorithm, which compute neural network parameters using a series of mathematical calculations. Thus, claim 4 requires mathematical calculations (an optimization algorithm) to perform the training of the CVAE model and therefore encompasses mathematical concepts. See MPEP 2106.04(a)(2), subsection I. The limitation “to enhance the separability of individuals with ASD and healthy individuals” merely indicates a field of use or technological environment in which the judicial exception is performed. Although the additional element limits the identified judicial exceptions, this type of limitation merely confines the use of the abstract idea to a particular technological environment (separate autism spectrum disorder and healthy individuals) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
Claim 5 recites “the CVAE model is trained using a deep learning architecture having multiple layers of neural networks.” When given their broadest reasonable interpretation in light of the background, “the deep learning architecture having multiple layer of neural networks” is a mathematical calculation. The plain meaning of this term is a training algorithm, which compute neural network parameters using a series of mathematical calculations. Thus, claim 5 requires mathematical calculations (a training algorithm) to perform the training of the CVAE model and therefore encompasses mathematical concepts. See MPEP 2106.04(a)(2), subsection I.
Claim 6 recites “displaying at a display device a chord diagram indicating connectivity between networks.” The limitation “a chord diagram indicating connectivity between networks” may be practically performed in the human mind using observation, evaluation, judgment, and opinion. For example, under the broadest reasonable interpretation, the claimed chord diagram encompasses a user observing the calculated functional connectivity matrix for each of the neurodivergent features and the non-neurodivergent features, calculating the Welch’s t-test p-value between the functional connectivity matrices, and drawing lines with colors or thickness corresponding to the pairs of regions that have a p-value above a user selected or predefined threshold value. See MPEP 2106.04(a)(2), subsection III. The broadest reasonable interpretation of claim 6 also encompasses mathematical concepts (e.g., calculating the Welch’s t-test p-values and threshold comparison). See MPEP 2106.04(a)(2), subsection I. The limitation “displaying at a display device a chord diagram” merely requires a generic output of the result of the p-value threshold comparison using a generic display device that comprise mere instructions to apply an exception and insignificant extra-solution activity. See MPEP 2106.05(f) and 2106.05(g).
Claim 7 recites “the fMRI data is a 3-dimensional volumetric image of the patient’s brain taken over time and represent brain activity of the patient’s brain.” This merely indicates a field of use or technological environment in which the judicial exception is performed. Although the additional element limits the identified judicial exceptions, this type of limitation merely confines the use of the abstract idea to a particular technological environment (3D functional MRI data of the brain) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
Claim 8 recites “the fMRI data is captured by a Magnetic Resonance Imaging (MRI) device.” This is mere data gathering recited at a high level of generality, and are insignificant extra-solution activity. See MPEP 2106.05(g) (“whether the limitation is significant”). In addition, all uses of the recited judicial exceptions require such data gathering, and, as such, these limitations do not impose any meaningful limits on the claim. These limitations amount to necessary data gathering. See MPEP 2106.05.
Claim 9 recites “the functional connectivity analysis indicates functional connectivity distributions which represent typical or atypical neural connectivity neural expressions related to conditions and clinical progression of the patient, not only analyzed at the original data but also analyzed with generated fMRI synthetic data from the CVAE outputs.” This may be practically performed in the human mind using observation, evaluation, judgment, and opinion. For example, under the broadest reasonable interpretation, the claimed functional connectivity analysis encompasses a user observing the labeled brain regions and calculating the Pearson’s correlation coefficient between at least a pair of labeled brain regions to calculate the functional connectivity matrix for each of the neurodivergent features and the non-neurodivergent features, and comparing the correlation coefficient of the neurodivergent features with the non-neurodivergent features, i.e., atypical or typical. Further, under the broadest reasonable interpretation, the claimed identification encompasses making a determination using the calculated correlation coefficients and the comparison between the neurodivergent and non-neurodivergent features to determine different neural expressions with conditions and clinical progression. See MPEP 2106.04(a)(2), subsection III. The broadest reasonable interpretation of claim 9 also encompasses mathematical concepts (e.g., calculating the Pearson’s correlation coefficient). See MPEP 2106.04(a)(2), subsection I.
Claim 10 recites “said mapping determines a brain region of the fMRI data to identify an area of interest and functional differences.” This may be practically performed in the human mind using observation, evaluation, judgment, and opinion. For example, under the broadest reasonable interpretation, the claimed mapping encompasses a user observing the patient fMRI data and labeling one or more regions of the brain as areas of interest according to their functional differences as informed by a predefined brain atlas. See MPEP 2106.04(a)(2), subsection III.
Claim 11 recites “the subgroup neurodivergence label including: normal, autism, and epilepsy.” This encompasses application and training of a CVAE model using selected conditions. When given their broadest reasonable interpretation in light of the background, the conditioning of the CVAE model encompasses the mental process of the user making a determination of which conditions/covariates to input into the model to perform application/training of the model. See MPEP 2106.04(a)(2), subsection III. Further, these limitation merely indicate a field of use or technological environment in which the judicial exception is performed. Although the additional element limits the identified judicial exceptions, this type of limitation merely confines the use of the abstract idea to a particular technological environment (normal, autism, and epilepsy) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
Claim 12 recites “said CVAE model comprises a neural network architecture.” When given their broadest reasonable interpretation in light of the background, “the neural network architecture” is a mathematical calculation. The plain meaning of this term is a training algorithm, which compute neural network parameters using a series of mathematical calculations. Thus, claim 12 requires mathematical calculations (a neural network) to perform the training of the CVAE model and therefore encompasses mathematical concepts. See MPEP 2106.04(a)(2), subsection I.
Claim 15 recites “a data collection module configured to collect fMRI data from individuals.” The limitation “to collect fMRI data from individuals” is mere data gathering recited at a high level of generality, and are insignificant extra-solution activity. See MPEP 2106.05(g) (“whether the limitation is significant”). In addition, all uses of the recited judicial exceptions require such data gathering, and, as such, these limitations do not impose any meaningful limits on the claim. These limitations amount to necessary data gathering. See MPEP 2106.05.
Thus, dependent claims 2-12 and 15 are ineligible.
Claim 14 is rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter because it is directed to a product that does not have aa physical or tangible form, such as information or a computer program per se when claimed as a product without any structural recitations. Claim 14, lines 1-2 recites “[a] neural network configured to identify neurodivergences in a patient.” A neural network does not have a physical or tangible form and the claim is without any structural recitations. See MPEP 2106.03 I.
Claim Rejections - 35 USC § 103
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 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-2, 4-5, 7-8, 10, and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Pijar (“Investigating individual differences in autism spectrum disorder through genetic and functional connectivity variability” 2023), hereinafter “Pijar,” in further view of Milana (“Deep generative models for predicting Alzheimer’s disease progression from MR data” 2018), hereinafter “Milana.”
Regarding claim 1, Pijar discloses a computer-implemented (computer processing is used to process fMRI scans for input into a CVAE model and to analyze the output of the CVAE model, P.8, ¶1 – P.9, ¶2) method for identifying neurodivergences in a patient (reconstructed and typically developed (TD) twin functional matrices are analyzed to identify the differences between them to identify functional connections altered by autism spectrum disorder (ASD) in the input fMRI data, P.9, ¶1-2) using functional Magnetic Resonance Imaging (fMRI) data of a patient (fMRI data of a patient using blood oxygen level dependent (BOLD) fMRI imaging, P.7, ¶3 – P.8, ¶2), the method comprising:
mapping at a neural network (computer processing of fMRI scans for input into CVAE model, P.8, ¶1 – P.9, ¶2), the patient fMRI data of the patient to a predefined brain atlas (patient fMRI data is mapped to an atlas, P.8, ¶2);
applying at the neural network (computer processing of fMRI scans for input into CVAE model, P.8, ¶1 – P.9, ¶2), a conditional variational autoencoder (CVAE) model to the mapped fMRI data (CVAE model is applied to mapped fMRI data, P.9, ¶2);
generating at the neural network (fMRI scans input into CVAE model to generate output from CVAE model, P.8, ¶1 – P.9, ¶2), neurodivergent synthetic fMRI data corresponding to the conditions of sex, age and neurodivergence subgroup label using the CVAE model (CVAE model outputs reconstructed functional connectivity matrices that corresponds to shared (age and gender) and ASD specific features, P.9, ¶1-2);
generating at the neural network (fMRI scans input into CVAE model to generate output from CVAE model, P.8, ¶1 – P.9, ¶2), non-neurodivergent synthetic fMRI data corresponding to sex and age conditions using the CVAE model (CVAE model outputs typically developed (TD) twin functional connectivity matrices that corresponds to shared (age and gender) features, P.9, ¶1-2); and
conducting at the neural network (CVAE model outputs and input fMRI data are analyzed using computer processing, P.8, ¶1 – P.9, ¶2), functional connectivity analysis to identify differences between the neurodivergent synthetic fMRI data and the non-neurodivergent synthetic fMRI data to identify neurodivergences in the patient fMRI data (reconstructed and typically developed (TD) twin functional matrices are analyzed to identify the differences between them to identify functional connections altered by autism spectrum disorder (ASD) in the input fMRI data, P.9, ¶1-2).
However, Pijar does not appear to disclose the CVAE model is conditioned on sex, age, and neurodivergence subgroup label.
However, in the same field of endeavor of brain studies of neurological disorders, Milana teaches the CVAE model is conditioned on sex, age, and neurodivergence subgroup label (MRI data is labeled with age, diagnosis/classification (class), and gender, P.59, ¶1; CVAE model conditioned on age and class is applied to the preprocessed MRI data, P.67, ¶7 – P.68, ¶1, P.86, ¶1, P.89, ¶1; CVAE model can be further conditioned using gender, P.104, ¶4; method implemented using a combination of computer hardware and software, P.81, ¶2).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Milana’s known technique of conditioning the training of the CVAE model using labels for age, class, and gender to Pijar’s known process of training a CVAE model to achieve the predictable result that “includ[ing] more information in the conditioning part of the network” provides “for a more accurate prediction” Milana, P.104, ¶4.
Regarding claim 2, Pijar discloses the neurodivergence comprises Autism Spectrum Disorder (ASD) (reconstructed and typically developed (TD) twin functional matrices are analyzed to identify the differences between them to identify functional connections altered by autism spectrum disorder (ASD) in the input fMRI data, P.9, ¶1-2).
Regarding claim 4, PIjar discloses the CVAE model optimizes latent space representations of the fMRI data to enhance the separability of individuals with ASD and healthy individuals (CVAE model separates features shared between autism spectrum disorder (ASD) and typically developed (TD) individuals, noting that a CVAE model operates by encoding latent space features and decoding from the latent space features to output a synthetic reconstruction of the input, P.9, ¶1-2).
Additionally, or, in the alternative, Pijar does not appear to explictly disclose the CVAE model optimizes latent space representations.
However, in the same field of endeavor of brain studies of neurological disorders, Milana teaches the CVAE model optimizes latent space representations (CVAE model optimizes latent space representations of the MRI data to enhance the separability of individuals with alzheimer’s disease (AD) and normal control (NC), P.16, ¶6 – P.17, ¶1, P.41, ¶2, P.63, ¶1, P.66, ¶1, 3, P.77, ¶1-2, P.92, ¶4-P.93, ¶1, Figs. 6.2, 6.22).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Milana’s known technique of a CVAE model that optimizes latent space representations between a neurodivergent condition and normal control to Pijar’s known process of training a CVAE model to enhance the separability between autism spectrum disorder (ASD) and typically developed (TD) individuals to achieve the predictable result that by optimizing the latent space representations using a CVAE model the encoding “radically reduc[es] the dimensionality of the inputs but still keep[s] the most important features” Milana, P.66, ¶1.
Regarding claim 5, Pijar discloses the CVAE model is trained (CVAE model is applied to separate shared features from autism spectrum disorder specific ones in individuals, P.9, ¶1-2).
However, Pijar does not appear to explictly disclose the CVAE model is trained using a deep learning architecture having multiple layers of neural networks.
However, in the same field of endeavor of brain studies of neurological disorders, Milana teaches the CVAE model is trained using a deep learning architecture having multiple layers of neural networks (CVAE model is trained using a deep learning architecture having multiple layers of neural networks for the encoder and the decoder, P.81, ¶4 – P.82, ¶1, P.92, ¶3 – P.93, ¶ 1, Figs. 6.2, 6.22).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Milana’s known technique of a CVAE model that optimizes latent space representations to Pijar’s known process of training a CVAE model to achieve the predictable result that by optimizing the latent space representations using a CVAE model the encoding “radically reduc[es] the dimensionality of the inputs but still keep[s] the most important features” Milana, P.66, ¶1.
Regarding claim 7, Pijar discloses the fMRI data is a 3-dimensional volumetric image of the patient's brain taken over time and represents brain activity of the patient's brain (fMRI data from the Autism Brain Imaging Data Exchange (ABIDE) and Simons Foundation Autism Research Initiative (SFARI) are 3D volumetric images of patient’s brains taken over time in the resting state and represents functional brain activity, P.7, ¶3 – P.8, ¶2).
Regarding claim 8, Pijar discloses the fMRI data is captured by a Magnetic Resonance Imaging (MRI) device (fMRI data from the Autism Brain Imaging Data Exchange (ABIDE) and Simons Foundation Autism Research Initiative (SFARI) are captured by a MRI scan of the brain using a magnetic resonance imaging (MRI) device, P.7, ¶3 – P.8, ¶2).
Regarding claim 10, Pijar discloses said mapping determines a brain region of the fMRI data to identify an area of interest and functional differences (mapping the fMRI data using an atlas identifies 51 regions and pairwise correlation is used to generate a functional connectivity matrix between the regions, P.8, ¶2).
Regarding claim 12, Pijar does not appear to explictly disclose said CVAE model comprises a neural network architecture.
However, in the same field of endeavor of brain studies of neurological disorders, Milana teaches said CVAE model comprises a neural network architecture (CVAE model is trained using a deep learning architecture having multiple layers of neural networks for the encoder and the decoder, P.81, ¶4 – P.82, ¶1, P.92, ¶3 – P.93, ¶ 1, Figs. 6.2, 6.22).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Milana’s known technique of a CVAE model that optimizes latent space representations to Pijar’s known process of training a CVAE model to achieve the predictable result that by optimizing the latent space representations using a CVAE model the encoding “radically reduc[es] the dimensionality of the inputs but still keep[s] the most important features” Milana, P.66, ¶1.
Claim 3 is rejected over Pijar in further view of Milana as in claim 1 above, and further in view of Bhavna et al. (“End-to-End explainable AI: Derived theory-of-mind fingerprints to distinguish between autistic and typically developing and social symptom severity” January 2023), hereinafter “Bhavna,” in further view of Aguila et al. (“Conditional VAEs for confound removal and normative modelling of neurodegenerative diseases” 2022), hereinafter “Aguila” as evidenced by Delacre et al. (“Why psychologists should by default use Welch’s t-test instead of Student’s t-test” 2017), hereinafter “Delacre.”
Regarding claim 3, PIjar discloses the functional connectivity analysis comprises:
calculating correlation matrices based on the neurodivergent synthetic fMRI data and the non-neurodivergent synthetic fMRI data (calculate reconstructed functional connectivity matrices based on the autism spectrum disorder (ASD) specific fMRI data and typically developed (TD) twin functional connectivity matrices based on the subject without autism spectrum disorder (ASD), shared fMRI data, P.9, ¶1-2); and
to identify the differences in functional connectivity patterns between patient fMRI data (reconstructed and typically developed (TD) twin functional matrices are analyzed to identify the differences between them to identify functional connections altered by autism spectrum disorder (ASD in the input fMRI data), P.9, ¶1-2).
However, while Pijar discloses to identify the differences in functional connectivity patterns between patient fMRI data, Pijar does not appear to disclose applying Welch t-test to the correlation matrices to identify the differences in functional connectivity patterns between patient fMRI data.
However, in the same field of endeavor of brain studies of autism spectrum disorder, Bhavna teaches applying t-test to the correlation matrices to identify the differences in functional connectivity patterns between patient fMRI data (functional connectivity matrices of the ASD samples, the reconstructed/synthetic fMRI data from the trained CVAE model, are calculated and a t-test between the functional connectivity matrix and the corresponding input patient fMRI images is performed to identify differences in the functional connectivity patterns between the input patient fMRI images and the ASD samples, P.7, ¶7 – P.9, ¶1, Fig. 5; see also CVAE model to separate ASD-specific and shared characteristics, P.4, ¶6 – P.5, ¶2, Fig. 1).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Bhavna’s known technique of performing functional connectivity analysis of the functional connectivity matrix of the CVAE model reconstructed/synthetic fMRI data with patient fMRI data using t-test to Pijar in further view of Milana’s known process of performing functional connectivity analysis of the functional connectivity matrix of the CVAE model reconstructed/synthetic fMRI data with patient fMRI data to achieve the predictable result that this allowed verification that the CVAE model produced synthetic fMRI data corresponding to features specific to typically developing individuals, and distinct autism symptoms. See, e.g., Bhavna, P.7, ¶7 – P.9, ¶1, Fig. 5 and P.11, ¶3.
However, while Bhavna teaches applying t-test, Bhavna does not appear to teach applying Welch t-test.
However, in the same field of endeavor of brain studies of neurological disorders, Aguila teaches applying Welch t-test to identify differences between reconstructed/synthesized disease and control MRI data (Welch’s t-test per brain region to identify the significance of separation/deviation between CVAE model reconstructed/synthesized neurodivergent, late mild cognitive impairment and Alzheimer’s disease, and healthy control MRI data, P.437, ¶1-2, Fig. 4).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Aguila’s known technique of using Welch’s t-test to identify differences to Pijar in further view of Milana in further view of Bhavna’s known process of using t-test to identify differences to achieve the predictable result that applying “Welch’s t-test provides a better control of Type 1 error rates when the assumption of homogeneity of variance is not met, and it loses little robustness compared to Student’s t-test when the assumptions are met” Delacre, P.92, ¶1; see also Delacre, P.99, ¶3-4.
Claim 6 is rejected over Pijar in further view of Milana as in claim 1 above, and further in view of Bhavna in further view of Besson et al. (U.S. Pub. No. 2022/0122250), hereinafter “Besson.”
Regarding claim 6, Pijar in further view of Milana does not appear to disclose displaying at a display device a chord diagram indicating connectivity between networks.
However, in the same field of endeavor of brain studies of autism spectrum disorder, Bhavna teaches displaying a chord diagram indicating connectivity between networks (Figure 5 shows display of a chord diagram indicating connectivity between the networks).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Bhavna’s known technique of performing functional connectivity analysis of the functional connectivity matrix of the CVAE model reconstructed/synthetic fMRI data with patient fMRI data using t-test to Pijar in further view of Milana’s known process of performing functional connectivity analysis of the functional connectivity matrix of the CVAE model reconstructed/synthetic fMRI data with patient fMRI data to achieve the predictable result that this allowed verification that the CVAE model produced synthetic fMRI data corresponding to features specific to typically developing individuals, and distinct autism symptoms. See, e.g., Bhavna, P.7, ¶7 – P.9, ¶1, Fig. 5 and P.11, ¶3.
However, Pijar in further view of Milana in further view of Bhavna does not appear to disclose displaying at a display device.
However, in the same field of endeavor of brain studies of brain disorders such as autism, Besson teaches displaying at a display device (display, [0209], presenting data/content on a display, [0052], [0211], [0214], [0218]).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Besson’s known technique of displaying content on a display to Pijar in further view of Milana in further view of Bhavna’s known process for displaying a chord diagram indicating connectivity between networks to achieve the predictable result that displaying brain feature data can allow a user to view the feature data to predict or otherwise characterize a condition of a subject’s brain. See, e.g., Besson, [0052]-[0053].
Claim 9 is rejected under 35 U.S.C 103 as being unpatentable over Pijar in further view of Milana as in claim 1 above, and further in view of Bhavna.
Regarding claim 9, Pijar discloses the functional connectivity analysis indicates functional connectivity distributions which represent typical or atypical neural connectivity neural expressions related to conditions of the patient, not only analyzed at the original data but also analyzed with the generated fMRI synthetic data from the CVAE outputs (CVAE model outputs reconstructed functional connectivity matrices that corresponds to shared (age and gender) and ASD specific features, P.9, ¶1-2; CVAE model outputs typically developed (TD) twin functional connectivity matrices that corresponds to shared (age and gender) features, P.9, ¶1-2; reconstructed and typically developed (TD) twin functional matrices are analyzed to identify the differences between them to identify functional connections altered by autism spectrum disorder (ASD) in the input fMRI data, P.9, ¶1-2; see also P.10, ¶1 – P.11, ¶2).
However, Pijar does not appear to disclose the functional connectivity analysis indicates functional connectivity distributions which represent typical or atypical neural connectivity neural expressions related to clinical progression.
However, in the same field of endeavor of brain studies of autism spectrum disorder, Bhavna teaches the functional connectivity analysis indicates functional connectivity distributions which represent typical or atypical neural connectivity neural expressions related to clinical progression (functional connectivity analysis of the ASD samples output by the CVAE model allows for identification of symptom severity score predictions using the functional connectivity distributions which represent typically developing and ASD neural connectivity neural expressions, P.1, ¶1, P.3, ¶3 – P.4, ¶2, P.6, ¶2 – P.7, ¶1, P.7, ¶7 – P.9, ¶1, P.11, ¶3 – P.12, ¶1).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Bhavna’s known technique of performing functional connectivity analysis to estimate the symptom severity score to Pijar in further view of Milana’s known process of performing functional connectivity analysis to achieve the predictable result that using a trained CVAE model for functional connectivity analysis allows “identifying neurobiologically interpretable and meaningful features rather than requiring feature engineering for predicting ASD social and communication deficits with heterogeneous manifestations in ASD children arising from atypicality of TOM and DMN regions functional connectivity patterns” Bhavna, P.3, ¶6. Additionally, or, in the alternative, it achieve the predictable result that “accurate[] predict[ion] of each individual’s mild to severe social symptom severity [] open[s] up future possibilities of individual fingerprinting” Bhavna, P.12, ¶2.
Claim 11 is rejected over Pijar in further view of Milana as in claim 1 above, and further in view of Aglinskas et al. (“Disentangling disorder-specific variation is key for precision psychiatry in autism” March 2023), hereinafter “Aglinskas.”
Regarding claim 11, while Pijar discloses training a CVAE model to separate autism spectrum disorder (ASD) from typically developed (TD) individuals (CVAE model is trained to separate features shared between autism spectrum disorder (ASD) and typically developed (TD) from ASD specific ones in individuals, P.9, ¶1-2) Pijar does not appear to disclose the subgroup neurodivergence label including: normal, autism, and epilepsy.
However, in the same field of endeavor of brain studies of neurological disorders, Milana teaches the subgroup neurodivergence label including: normal and neurodivergent (MRI data is labeled with age, diagnosis/classification (class), and gender, P.59, ¶1; CVAE model conditioned on age and class is applied to the preprocessed MRI data, P.67, ¶7 – P.68, ¶1, P.86, ¶1, P.89, ¶1; class label includes neurodivergence, Alzheimer’s disease (AD) and/or mild cognitive impairment (MCI), and normal control (NC), P.59, ¶1).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Milana’s known technique of training a CVAE model using a subgroup neurodivergence label including normal control and neurodivergence to Pijar’s known process of training a CVAE model to enhance the separability between autism spectrum disorder (ASD) and typically developed (TD) individuals to achieve the predictable result that by optimizing the latent space representations using a CVAE model the encoding “radically reduc[es] the dimensionality of the inputs but still keep[s] the most important features” Milana, P.66, ¶1.
However, Pijar in further view of Milana does not appear to disclose the subgroup neurodivergence label includes epilepsy.
However, in the same field of endeavor of brain studies of autism, Aglinskas teaches the subgroup neurodivergence label includes epilepsy (CVAE architecture to isolate autism spectrum disorder (ASD)- specific features from features that are shared between ASDs and typically developing (TD) participants, P.02, ¶2-3, Fig. 1; CVAE architecture can be modified to identify features specific to the presence of each disorder, autism spectrum disorder (ASD) and comorbid neurological conditions such as epilepsy, as well as features that are uniquely associated with comorbidity, P.03, ¶1 – P.04, ¶1).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Aglinskas known technique of modifying a CVAE architecture for identifying features specific to autism spectrum disorder (ASD) and typically developing (TD) individuals to also identify features specific to epilepsy individuals to Pijar in further view of Milana’s known process of training a CVAE model to enhance separability between neurodivergence, autism spectrum disorder (ASD), and typically developed (TD) individuals conditioned using a subgroup neurodivergence label including normal control/typically developed and one or more neurodivergence labels to achieve the predictable result that modifying the CVAE architecture to identify comorbidities for autism spectrum disorder (ASD) such as epilepsy better informs the etiology of ASD including whether individuals with both ASD and epilepsy have a set of features distinct from individuals having only ASD and having only epilepsy. See, e.g., Aglinskas, P.03, ¶1-2.
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Pijar in further view of Milana.
Regarding claim 13, while Pijar discloses a computer-implemented method (computer processing of fMRI scans, P.8, ¶1 – P.9, ¶2), Pijar does not appear to explictly disclose a non-transitory computer-readable storage medium comprising instructions that, when executed by a computer, cause the computer to perform the method of claim 1.
However, in the same field of endeavor of brain studies of neurological disorders, Milana teaches a non-transitory computer-readable storage medium comprising instructions that, when executed by a computer, cause the computer to perform the method (software instructions implemented using memory in processing hardware including the memory and processor of a Tesla k40 GPU, P.81, ¶2) of claim 1 (see rejection of claim 1 above).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Milana’s known technique of conditioning the training of the CVAE model using labels for age, class, and gender to Pijar’s known apparatus for training a CVAE model to achieve the predictable result that “includ[ing] more information in the conditioning part of the network” provides “for a more accurate prediction” Milana, P.104, ¶4.
Claims 14 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Pijar in further view of Milana.
Regarding claim 14, Pijar discloses a neural network (computer processing is used to process fMRI scans for input into a CVAE model and to analyze the output of the CVAE model, P.8, ¶1 – P.9, ¶2) configured to identify neurodivergences in a patient (reconstructed and typically developed (TD) twin functional matrices are analyzed to identify the differences between them to identify functional connections altered by autism spectrum disorder (ASD) in the fMRI data, P.9, ¶1-2), the system (computer processing and CVAE model P.8, ¶1 – P.9, ¶2), comprising:
a feature extraction module (computer processing of fMRI scans for input into CVAE model, P.8, ¶1 – P.9, ¶2) configured to receive patient fMRI data (acquire fMRI data from the Autism Brain Imaging Data Exchange (ABIDE) and Simons Foundation Autism Research Initiative (SFARI) datasets, P.7, ¶3 – P.8, ¶2) and extract features from the patient fMRI data (patient fMRI data is mapped to an atlas, P.8, ¶2);
a conditional variational autoencoder (CVAE) model, to generate synthetic patient fMRI data based on the patient fMRI data (CVAE model outputs reconstructed functional connectivity matrices that corresponds to shared (age and gender) and ASD specific features, P.9, ¶1-2; CVAE model outputs typically developed (TD) twin functional connectivity matrices that corresponds to shared (age and gender) features, P.9, ¶1-2); and
a functional connectivity analysis module (CVAE model outputs and input fMRI data are analyzed using computer processing, P.8, ¶1 – P.9, ¶2) configured to perform functional connectivity analysis on the synthetic fMRI data to identify neurodivergences in individuals (reconstructed and typically developed (TD) twin functional matrices are analyzed to identify the differences between them to identify functional connections altered by autism spectrum disorder (ASD) in the input fMRI data, P.9, ¶1-2).
However, Pijar does not appear to disclose the CVAE model is conditioned on sex, age, and diagnosis.
However, in the same field of endeavor of brain studies of neurological disorders, Milana teaches the CVAE model is conditioned on sex, age, and diagnosis (MRI data is labeled with age, diagnosis/classification (class), and gender, P.59, ¶1; CVAE model conditioned on age and class is applied to the preprocessed MRI data, P.67, ¶7 – P.68, ¶1, P.86, ¶1, P.89, ¶1; CVAE model can be further conditioned using gender, P.104, ¶4; method implemented using a combination of computer hardware and software, P.81, ¶2).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Milana’s known technique of conditioning the training of the CVAE model using labels for age, class, and gender to Pijar’s known apparatus for training a CVAE model to achieve the predictable result that “includ[ing] more information in the conditioning part of the network” provides “for a more accurate prediction” Milana, P.104, ¶4.
Regarding claim 15, Pijar discloses further comprising a data collection module (computer processing of fMRI scans, P.8, ¶1 – P.9, ¶2) configured to collect fMRI data from individuals (fMRI data from the Autism Brain Imaging Data Exchange (ABIDE) and Simons Foundation Autism Research Initiative (SFARI) are captured by a MRI scan of the brain using a magnetic resonance imaging (MRI) device, P.7, ¶3 – P.8, ¶2).
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Pijar in further view of Milana.
Regarding claim 16, Pijar discloses a computer system (computer processing is used to process fMRI scans for input into a CVAE model and to analyze the output of the CVAE model, P.8, ¶1 – P.9, ¶2), the system comprising:
a neural network (CVAE model comprises a neural network, P.9, ¶2):
map fMRI data to a predefined brain atlas (patient fMRI data is mapped to an atlas, P.8, ¶2);
obtaining a trained conditional variational autoencoder (CVAE) model based on extracted features (CVAE model is applied to mapped fMRI data to separate shared features from autism spectrum disorder specific ones in individuals, P.9, ¶1-2);
generate synthetic fMRI data using the trained CVAE model (CVAE model outputs reconstructed functional connectivity matrices that corresponds to shared (age and gender) and ASD specific features, P.9, ¶1-2; CVAE model outputs typically developed (TD) twin functional connectivity matrices that corresponds to shared (age and gender) features, P.9, ¶1-2); and
perform functional connectivity analysis on the synthetic fMRI data to identify neurodivergences in the fMRI data (reconstructed and typically developed (TD) twin functional matrices are analyzed to identify the differences between them to identify functional connections altered by autism spectrum disorder (ASD) in the input fMRI data, P.9, ¶1-2).
However, while Pijar discloses a computer processing system comprising a neural network, Pijar does not appear to disclose a system for image classification and inventory management, the system comprising: one or more non-transitory memory devices; and a neural network having layers configured to execute instructions from the one or more non-transitory memory devices; and the CVAE model is conditioned on sex, age, and neurodivergence subgroup label.
However, in the same field of endeavor of brain studies of neurological disorders, Milana teaches a system for image classification and inventory management (a combination of software and hardware to perform training and image processing, P.81, ¶2), the system comprising:
one or more non-transitory memory devices (software instructions implemented using memory in hardware including the memory of a Tesla k40 GPU, P.81, ¶2); and
a neural network having layers (CVAE model having layers, P.66, ¶1 – P.68, ¶3, P.81, ¶3 – P.91, ¶1, P.92, ¶1 – P.101, Figs. 6.2-6.6.21) configured to execute instructions from the one or more non-transitory memory devices (software instructions implemented using memory in processing hardware including the memory and processor of a Tesla k40 GPU, P.81, ¶2); and
the CVAE model is conditioned on sex, age, and subgroup label (MRI data is labeled with age, diagnosis/classification (class), and gender, P.59, ¶1; CVAE model conditioned on age and class is applied to the preprocessed MRI data, P.67, ¶7 – P.68, ¶1, P.86, ¶1, P.89, ¶1; CVAE model can be further conditioned using gender, P.104, ¶4; method implemented using a combination of computer hardware and software, P.81, ¶2).
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to have applied Milana’s known technique of conditioning the training of the CVAE model, which comprises layers, using labels for age, class, and gender to Pijar’s known apparatus for training a CVAE model to achieve the predictable result that “includ[ing] more information in the conditioning part of the network” provides “for a more accurate prediction” Milana, P.104, ¶4.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Gao et al. (“Learning a phenotypic-attribute attentional brain connectivity embedding for ADHD classification using rs-fMRI” 2020) discloses training a CVAE model on atlas mapped fMRI data conditioned on age and gender/sex to generate synthetic data for neurodivergent ADHD and typical develop control individuals and performing functional connectivity analysis using the synthetic data.
Wang et al. (“Normative modeling via conditional variational autoencoder and adversarial learning to identify brain dysfunction in Alzheimer’s disease” September 1, 2023) discloses training a CVAE model on atlas mapped fMRI data conditioned on age and gender/sex to generate synthetic data for neurodivergent Alzheimer’s disease and healthy control individuals and performing functional connectivity analysis using the synthetic data.
Wu et al. (“Reconstruction of resting state fMRI using LSTM variational auto-encoder on subcortical surface to detect epilepsy” 2022) discloses training a graphical VAE model on atlas mapped fMRI data to generate synthetic data for neurodivergent epilepsy and healthy individuals and performing functional connectivity analysis using the synthetic data.
Choi et al. (“Functional connectivity patterns of autism spectrum disorder identified by deep feature learning” 2017) discloses training a VAE model on atlas mapped fMRI data to generate synthetic data for neurodivergent epilepsy and healthy individuals and performing functional connectivity analysis using the synthetic data.
Aglinskas et al. (“Contrastive machine learning reveals the structure of neuroanatomical variation within autism” 2022) discloses training a CVAE model on atlas mapped MRI data to generate synthetic data for autism spectrum disorder and typical control individuals.
Aglinskas et al. (“Precision psychiatry requires disentangling disorder-specific variation: The case of ASD” 2022) discloses training a CVAE model on atlas mapped MRI data to generate synthetic data for autism spectrum disorder and typical control individuals.
Nunes et al. (“Measuring heterogeneity in normative models as the effective number of deviation patterns” 2020) discloses training a CVAE model conditioned on sex and age on atlas mapped MRI data to generate synthetic data for autism spectrum disorder and typical control individuals.
Louiset et al. (“SepVAE: a contrastive VAE to separate pathological patterns from healthy ones” July 2023) discloses training a CVAE model on atlas mapped MRI data to generate synthetic data for autism spectrum disorder and typical control individuals.
Ma et al. (“Autism spectrum disorder classification in children based on structural MRI features extracted using contrastive variational autoencoder” July 2023) discloses training a CVAE model on atlas mapped MRI data to generate synthetic data for autism spectrum disorder and typical control individuals.
Bai et al. (“Discovering the neural correlate informed nosological relation among multiple neuropsychiatric disorders through dual utilization of diagnostic information” 2022) discloses training a CVAE model conditioned on diagnostic labels on atlas mapped MRI data to generate synthetic data for autism spectrum disorder and typical control individuals.
Abdulaal et al. (“Deep structural causal modelling of the clinical and radiological phenotype of Alzheimer’s disease” 2022) discloses training a CVAE model conditioned on sex and age on atlas mapped MRI data to generate synthetic data for autism spectrum disorder and typical control individuals.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 Johnathan Maynard whose telephone number is (571)272-7977. The examiner can normally be reached 10 AM - 6 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, Keith Raymond can be reached at 571-270-1790. 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.
/J.M./Examiner, Art Unit 3798
/KEITH M RAYMOND/Supervisory Patent Examiner, Art Unit 3798