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 Amendment
This Office Action is responsive to Applicant’s remarks received on January 28, 2026. Claims 1-4 and 6-16 are pending.
Claim Rejections - 35 USC § 101
The previous 101 rejection has been withdrawn in light of Applicant’s amendment.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1, 4, 6, 8, 9, 11 and 13-16 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Shim et al. (WO2020106896).
Regarding claim 1, Shim et al. discloses a data generation apparatus comprising:
processing circuitry configured to:
receive a first relative value of molecules in a first region as input data (“A total of 102,005 spectra were obtained and separated into three data subsets: 85,661 for training” at paragraph 0070, last sentence);
apply the input data to a function, the function having predetermined coefficients to be learned (“In each epoch of training, spectra in the training data set were run through CEMD to produce fitted spectra, RMSE for each spectrum was calculated, and gradient backpropagation was performed to update the encoder weights” at paragraph 0086, line 1; “The central 2p elements of y′.sub.low were used as the input for the next level of wavelet reconstruction. The CEMD encoder therefore needed to calculate 42 coefficients, 10 for the metabolite resonances and 32 for the baseline, which are passed to the decoder to create the fitted spectrum” at paragraph 0081; the training process learns the wavelet coefficients and weights to be utilized post-training);
compute a second relative value of the molecules in a second region as output data from the function (the test spectra are applied to the trained CEMD; “Once training of the CEMD encoder weights was complete, the encoder can be applied to spectra to compute the relative concentration of each metabolite resonance based on the parameters in the encoder output, θ.sub.p” at paragraph 0086, last sentence), wherein the first and second relative values each represent a density estimate of a first molecule divided by density estimate of a second molecule among the molecules (“In some embodiments, the one or more measurements may include quantification of a concentration of one or more metabolites, among others, or a combination thereof. By way of example, the concentration may include concentration of one metabolite, a concentration ratio of two or more metabolites” at paragraph 0058, line 1); and
output the output data (see Figures 8, 10 and 11 for examples of the output CEMD metabolite concentrations).
Regarding claim 4, Shim et al. discloses an apparatus wherein the first and second relative values each represent a relationship between the molecules in a chemical shift band (“For each metabolite, m, the metabolite model required six parameters: peak amplitude A.sub.m, resonance frequency ω.sub.m, zero and first order phases (ϕ.sub.0 and ϕ.sub.1), and Gaussian and Lorentzian decay constants (T.sub.a and T.sub.b). The three major singlet resonances at TE=50 ms were modeled: Cho, Cr, and NAA. Note that this formulation returned the relative concentrations of each metabolite” at paragraph 0078, line 1).
Regarding claim 6, Shim et al. discloses an apparatus wherein the first relative value of the molecules is obtained by using any of magnetic resonance spectroscopy, magnetic resonance spectroscopic imaging (“By way of example, the data may be acquired using magnetic resonance spectroscopy protocols for imaging multiple-voxels within a region of interest (rather than measuring metabolite signal in a single voxel), such as proton spectroscopic magnetic resonance imaging (e.g., MRS or MRSI) that can enable multi-voxel volumes of metabolite levels to be obtained in vivo without contrast agents or radioactive tracers” at paragraph 0045, line 1), and chemical exchange saturation transfer (CEST) imaging.
Regarding claim 8, Shim et al. discloses an apparatus wherein the second region includes a region different from the first region (the testing spectra comprise a different set from the training spectra, and therefore correspond to different regions).
Regarding claim 9, Shim et al. discloses an apparatus wherein the first region and the second region are set on different slices (the testing spectra comprise a different set from the training spectra, and therefore correspond to different image slice data).
Regarding claim 11, Shim et al. discloses an apparatus wherein the coefficients are determined in such a manner that a loss function decreases, the loss function representing a difference between a result of applying the function to known training data and answer data relative to the known training data (“In each epoch of training, spectra in the training data set were run through CEMD to produce fitted spectra, RMSE for each spectrum was calculated, and gradient backpropagation was performed to update the encoder weights. Then, the spectra in the validation set were run through the CEMD and the validation loss was calculated as the sum of RMSEs. Training continued through multiple epochs until the validation loss converged” at paragraph 0086, line 1).
Regarding claim 13, Shim et al. discloses an apparatus wherein the first and second relative values each represent a ratio between an integral signal value of a first molecule in a first chemical shift band and an integral signal value of a second molecule in a second chemical shift band among the molecules (“In some embodiments, the one or more measurements may include quantification of a concentration of one or more metabolites, among others, or a combination thereof. By way of example, the concentration may include concentration of one metabolite, a concentration ratio of two or more metabolites” at paragraph 0058, line 1).
Regarding claim 14, Shim et al. discloses an apparatus wherein the known training data and the answer data include a relative value of the molecules, the relative value being prepared prior to computation of the loss function (“In each epoch of training, spectra in the training data set were run through CEMD to produce fitted spectra, RMSE for each spectrum was calculated, and gradient backpropagation was performed to update the encoder weights. Then, the spectra in the validation set were run through the CEMD and the validation loss was calculated as the sum of RMSEs. Training continued through multiple epochs until the validation loss converged” at paragraph 0086, line 1).
Regarding claim 15, Shim et al. discloses a data generation method comprising:
receiving a first relative value of molecules in a first region as input data (“A total of 102,005 spectra were obtained and separated into three data subsets: 85,661 for training” at paragraph 0070, last sentence);
applying the input data to a function, the function having predetermined coefficients to be learned (“In each epoch of training, spectra in the training data set were run through CEMD to produce fitted spectra, RMSE for each spectrum was calculated, and gradient backpropagation was performed to update the encoder weights” at paragraph 0086, line 1; “The central 2p elements of y′.sub.low were used as the input for the next level of wavelet reconstruction. The CEMD encoder therefore needed to calculate 42 coefficients, 10 for the metabolite resonances and 32 for the baseline, which are passed to the decoder to create the fitted spectrum” at paragraph 0081; the training process learns the wavelet coefficients and weights to be utilized post-training);
computing a second relative value of the molecules in a second region as output data from the function (the test spectra are applied to the trained CEMD;“Once training of the CEMD encoder weights was complete, the encoder can be applied to spectra to compute the relative concentration of each metabolite resonance based on the parameters in the encoder output, θ.sub.p” at paragraph 0086, last sentence), wherein the first and second relative values each represent a density estimate of a first molecule divided by density estimate of a second molecule among the molecules (“In some embodiments, the one or more measurements may include quantification of a concentration of one or more metabolites, among others, or a combination thereof. By way of example, the concentration may include concentration of one metabolite, a concentration ratio of two or more metabolites” at paragraph 0058, line 1); and
outputting the output data (see Figures 8, 10 and 11 for examples of the output CEMD metabolite concentrations).
Regarding claim 16, Shim et al. discloses a non-transitory computer-readable storage medium storing a data generation program which causes a computer to execute:
receiving a first relative value of molecules in a first region as input data (“A total of 102,005 spectra were obtained and separated into three data subsets: 85,661 for training” at paragraph 0070, last sentence);
applying the input data to a function, the function having predetermined coefficients to be learned (“In each epoch of training, spectra in the training data set were run through CEMD to produce fitted spectra, RMSE for each spectrum was calculated, and gradient backpropagation was performed to update the encoder weights” at paragraph 0086, line 1; “The central 2p elements of y′.sub.low were used as the input for the next level of wavelet reconstruction. The CEMD encoder therefore needed to calculate 42 coefficients, 10 for the metabolite resonances and 32 for the baseline, which are passed to the decoder to create the fitted spectrum” at paragraph 0081; the training process learns the wavelet coefficients and weights to be utilized post-training);
computing a second relative value of the molecules in a second region as output data from the function (the test spectra are applied to the trained CEMD;“Once training of the CEMD encoder weights was complete, the encoder can be applied to spectra to compute the relative concentration of each metabolite resonance based on the parameters in the encoder output, θ.sub.p” at paragraph 0086, last sentence), wherein the first and second relative values each represent a density estimate of a first molecule divided by density estimate of a second molecule among the molecules (“In some embodiments, the one or more measurements may include quantification of a concentration of one or more metabolites, among others, or a combination thereof. By way of example, the concentration may include concentration of one metabolite, a concentration ratio of two or more metabolites” at paragraph 0058, line 1); and
outputting the output data (see Figures 8, 10 and 11 for examples of the output CEMD metabolite concentrations).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 10 is rejected under 35 U.S.C. 103 as being unpatentable over Shim et al.
Shim et al. discloses the elements of claim 1 as described in claim 1 above.
Shim et al. does not explicitly disclose that the second region is a same size as or larger than the first region.
However, it is feasible that the second region is larger or equal to the first region given the large amount of images provided to the training and testing. As such, this is an obvious scenario as supported by the disclosure of Shim et al.
Claim(s) 2, 3 and 7 are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Shim et al. and Su et al. (“Predicting cancer malignancy and proliferation in glioma patients: intra-subject inter-metabolite correlation analyses using MRI and MRSI contrast scans”).
Regarding claim 2, Shim et al. discloses an apparatus wherein the processing circuitry is further configured to:
receive a morphological image including the first region and the second region as input data (“Briefly, T1-weighted (T1w) magnetization-prepared rapid gradient echo pulse (TR=1900 ms, TE=3.52 ms, 256×256×160 matrix, flip angle (FA)=9°) and whole-brain 3D EPSI (TR=1551 ms, TE=50 ms, 64×64×32 matrix, FA=71°) sequences with generalized autocalibrating partially parallel acquisitions (GRAPPA) acceleration were obtained during the same scanning session” at paragraph 0070, line 8), and
compute the second relative value of the molecules in the second region by using the first relative value of the molecules in the first region (“Once training of the CEMD encoder weights was complete, the encoder can be applied to spectra to compute the relative concentration of each metabolite resonance based on the parameters in the encoder output, θ.sub.p” at paragraph 0086, last sentence).
Shim et al. does not explicitly disclose computing the second relative value of the molecules in the second region by using the morphological image as input data.
Su et al. teaches an apparatus in the same field of endeavor of MRI spectroscopy and metabolic analysis, wherein the processing circuitry is further configured to:
receive a morphological image including the first region and the second region as input data (“Anatomical MRI scans included T2 fluid-attenuated inversion recovery imaging (T2FLAIR), T1 fluidattenuated inversion recovery imaging (T1FLAIR), T2-weighted fast spin-echo (T2FSE), and T1 post-contrast (T1C)” at page 2723, Scanning protocols, line 2), and
compute the second relative value of the molecules in the second region by using the first relative value of the molecules in the first region and the morphological image as input data (“Using the AW4.6 workstation, anatomical MRIs were automatically matched with MRSI scanning slabs, and quantitative parameters were reconstructed according to the acquisition matrix. MRSI voxels that fell completely within the tumor solid parts were included, and voxel-wise quantitative parameters were obtained. After that, voxel positions were recorded concerning anatomical images, based on which corresponding APT and MTC in each voxel were produced” at page 2724, Multi-voxel segmentation and quantification of metabolites, line 1).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to utilize the inter-metabolite correlation as taught by Su et al. in the analysis of Shim et al. as “combining multiple IMCCs further improved cancer characterization” (page 2730, Conclusions, line 3).
Regarding claim 3, Shim et al. discloses an apparatus as described in claim 1 above.
Shim et al. does not explicitly disclose that the input data includes data acquired by measuring a same subject.
Su et al. teaches an apparatus in the same field of endeavor of MRI spectroscopy and metabolic analysis wherein the input data includes data acquired by measuring a same subject (“Anatomical MRI, CEST, and MRSI were conducted. Anatomical MRI scans included T2 fluid-attenuated inversion recovery imaging (T2FLAIR), T1 fluidattenuated inversion recovery imaging (T1FLAIR), T2-weighted fast spin-echo (T2FSE), and T1 post-contrast (T1C). All anatomical MRI scans were collected with the same field of view (FOV, 240×240 mm2), slice thickness (5.0 mm), slice spacing (1.5 mm), and a total of 20 slices covering the whole brain. Both CEST and MRSI were scanned on the same slices:” at page 2723, Scanning protocols, line 1).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to utilize the inter-metabolite correlation as taught by Su et al. in the analysis of Shim et al. as “combining multiple IMCCs further improved cancer characterization” (page 2730, Conclusions, line 3).
Regarding claim 7, Shim et al. discloses an apparatus wherein the processing circuitry is further configured to:
receive a morphological image including a two-dimensional or three-dimensional Ti weighted image (“Briefly, T1-weighted (T1w) magnetization-prepared rapid gradient echo pulse (TR=1900 ms, TE=3.52 ms, 256×256×160 matrix, flip angle (FA)=9°) and whole-brain 3D EPSI (TR=1551 ms, TE=50 ms, 64×64×32 matrix, FA=71°) sequences with generalized autocalibrating partially parallel acquisitions (GRAPPA) acceleration were obtained during the same scanning session” at paragraph 0070, line 8), a T2 weighted image, a fluid attenuated inversion recovery (FLAIR) image, a T2* weighted image, a diffusive weighted image, or a proton density weighted image and
compute the output data by applying the first relative value of the molecules in the first region to the function (“Once training of the CEMD encoder weights was complete, the encoder can be applied to spectra to compute the relative concentration of each metabolite resonance based on the parameters in the encoder output, θ.sub.p” at paragraph 0086, last sentence).
Shim et al. does not explicitly disclose computing the output data by applying the first relative value of the molecules in the first region and the morphological image to the function.
Su et al. teaches an apparatus in the same field of endeavor of MRI spectroscopy and metabolic analysis, wherein the processing circuitry is further configured to:
receive a morphological image including a two-dimensional or three-dimensional Ti weighted image, T2 weighted image, fluid attenuated inversion recovery (FLAIR) image (“Anatomical MRI scans included T2 fluid-attenuated inversion recovery imaging (T2FLAIR), T1 fluidattenuated inversion recovery imaging (T1FLAIR), T2-weighted fast spin-echo (T2FSE), and T1 post-contrast (T1C)” at page 2723, Scanning protocols, line 2), T2* weighted image, diffusive weighted image, or proton density weighted image and
compute the output data by applying the first relative value of the molecules in the first region and the morphological image to the function (“Using the AW4.6 workstation, anatomical MRIs were automatically matched with MRSI scanning slabs, and quantitative parameters were reconstructed according to the acquisition matrix. MRSI voxels that fell completely within the tumor solid parts were included, and voxel-wise quantitative parameters were obtained. After that, voxel positions were recorded concerning anatomical images, based on which corresponding APT and MTC in each voxel were produced” at page 2724, Multi-voxel segmentation and quantification of metabolites, line 1).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to utilize the inter-metabolite correlation as taught by Su et al. in the analysis of Shim et al. as “combining multiple IMCCs further improved cancer characterization” (page 2730, Conclusions, line 3).
Claim(s) 12 is rejected under 35 U.S.C. 103 as being unpatentable over the combination of Shim et al. and Weigand-Whittier et al. (“Accelerated and Quantitative 3D Semisolid MT/CEST Imaging using a Generative Adversarial Network (GANCEST)”, hereinafter Weigand et al.).
Shim et al. discloses an apparatus as described in claim 11 above.
Shim et al. does not explicitly disclose that the function is a data generative function trained by using a conditional generative adversarial network or a conditional variational autoencoder.
Weigand et al. teaches an apparatus in the same field of endeavor of MR metabolic analysis, wherein the function is a data generative function trained by using a conditional generative adversarial network (“A supervised learning framework Figure 1 was designed based on the conditional GAN architecture.12 The generator was a U-Net convolutional network aiming to synthesize two proton exchange parameter maps (volume fraction and exchange rate), for either the semisolid MT or the CEST compound exchangeable protons. The discriminator aimed to predict whether the images are the ‘real’ corresponding quantitative images, or a ‘fake’ (generator synthesized maps)” at section 2.1, line 1) or a conditional variational autoencoder.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to utilize a conditional GAN as taught by Weigand et al. for the function of Shim et al. to “accelerate 3D acquisitions of semisolid MT and CEST mapping by 70% while maintaining excellent agreement with full-length CEST-MRF based reference maps and retaining performance across unseen pathologies and scanner models.” (Weigand et al. at section 5, line 1).
Response to Arguments
Summary of Remarks (@ response page labeled 7): “However, Applicant respectfully submits that the '896 application fails to disclose processing circuitry configured to compute a second relative value of the molecules in a second region as output data from the function, wherein the first and second relative values each represent a density estimate of a first molecule divided by a density estimate of a second molecule among the molecules, as recited in amended Claim 1.
Applicant respectfully submits that the '896 application is silent regarding applying input data to a function, the input data being a first relative value of molecules in a first region, and outputting a second relative value of the molecules in a second region as output data from the function, wherein the first relative values of molecules in a first region is the input data to the function, as recited in Claim 1.”
Examiner’s Response: The test data is applied to CEMD, which takes on the role as a convolutional encoder-model decoder function to determine the metabolite concentration in a region. This is the second relative value. As disclosed by Shim et al., the system is able to determine the concentration ratio between two or more metabolites, which is a density estimate of one metabolite divided by a density estimate of another metabolite. The training data as input to the CEMD produces an estimated metabolite concentration ratio, which represents the first relative value.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KATRINA R FUJITA whose telephone number is (571)270-1574. The examiner can normally be reached Monday - Friday 9:30-5:30 pm ET.
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, Sumati Lefkowitz can be reached at 5712723638. 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.
/KATRINA R FUJITA/ Primary Examiner, Art Unit 2672