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
Claims 1, 4-11, 13-19, and 21 remain pending in the application in response to the applicant’s amendments to the rejections previously set forth in the Non-Final Office Action mailed 04/07/2026.
Response to Arguments
Applicant's arguments filed 07/06/2026 have been fully considered but they are not persuasive.
The applicant argues “in a distinct contrast from the instantly claimed inventions, Tapper uses two neural networks (one for frequency, one for phase) rather than a single, dual stream network” (see pg. 3, para. 2 of applicant’s remarks), and the examiner disagrees.
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).
In response to applicant’s argument that there is no teaching, suggestion, or motivation to combine the references, the examiner recognizes that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR International Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007). In this case, Tapper is used to teach inputting the spectrum data to a trained machine learning model to estimate frequency corrections and phase corrections for the spectrum data, while Zhang is used to teach a dual stream convolutional neural network.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 4-11, 13-19, and 21 are rejected under35 U.S.C. 103 as being unpatentable over S. Tapper et al, "Frequency and phase correction of J-difference edited MR spectra using deep learning", Magnetic Resonance in Medicine, vol. 85, pp. 1755-1765, Aug.2020 in view of Zhang et al, "Automatic Modulation Classification Using CNN-LSTM Based Dual-Stream Structure", IEEE Transactions on Vehicular Technology, vol. 69, no. 11, pp. 13521-13531, Nov. 2020, hereinafter referred to as Tapper and Zhang, respectively.
Regarding claim 1, and similarly for claims 19 and 21, Tapper teaches a method for performing frequency and phase correction of magnetic resonance spectroscopy (MRS) data to quantify one or more metabolites, the method comprising:
receiving spectrum data related to a plurality of metabolites generated using magnetic resonance spectroscopy of a subject's brain (see pg. 1756, col. 1, para. 5 "Networks for FPC [frequency-and-phase correction] were trained and validated using simulated data and further tested using in vivo MEGA-edited MRS [magnetic resonance spectroscopy]data from the openly available Big GABA repository [plurality of metabolites in the brain].");
inputting the spectrum data to a trained machine learning model, wherein the trained machine learning model estimates frequency corrections and phase corrections for the spectrum data, generating corrected on-spectrum data and corrected off-spectrum data thereby (see pg. 1758 " then, central 1024 samples of the magnitude spectra were extracted and used as input to the trained frequency offset network. The resulting predicted frequency offset (Δf) was then applied to frequency-correct the original transient in the time domain. Second, this frequency-corrected validation transient was then Fourier transformed and normalized, and then the central 1024 samples of the real spectrum were extracted and used as input to the trained phase offset network. The resulting predicted phase offset (Δϕ) was then used to phase-correct the frequency-corrected transient. Finally, all fully corrected FIDs were used to compute an average difference spectrum by subtracting the corrected OFF spectra from the corrected ON spectra."); and
quantifying one or more of the metabolites according to the corrected on-spectrum data and corrected off-spectrum data (see pg. 1756, col. 1, para. 1 "Appropriate FPC [frequency-and-phase correction] is even more crucial when using J difference-edited MRS methods such as MEGA-PRESS, which relies on the subtraction of 2 spectra containing strong signals (OFF and ON) in order to reveal a much smaller targeted signal (eg, gamma aminobutyric acid [GABA]) [metabolite] in the resulting difference spectrum." Where it is inherent and known in the art to quantify metabolites via J-difference MRS).
Tapper teaches a trained machine learning model, but does not explicitly teach wherein the trained machine learning model comprises a dual stream convolutional neural network.
Whereas, Zhang, in an analogous field of endeavor, teaches wherein the trained machine learning model comprises a dual stream convolutional neural network (see Fig. 1 "The CNN-LSTM based dual stream architecture."; see pg. 13524, col. 2, para. 4 "In our implementation, the dataset is split into training set and testing set.").
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified a trained machine learning model, as disclosed in Tapper, by having a dual stream convolutional neural network as the trained machine learning model, as disclosed in Zhang. One of ordinary skill in the art would have been motivated to make this modification in order to efficiently explores the feature interaction, and the spatial-temporal properties of raw complex temporal signals, as taught in Zhang (see Abstract).
Furthermore, regarding claim 4, Tapper further teaches wherein the dual stream convolutional neural network comprises a first stream for frequency correction and a second stream for phase correction (see Fig. 1 "Both the frequency (A) [first stream] and phase (B) [second stream] offset networks have the same basic structure with 3 FC [fully connected] layers (1024, 512, 1 node(s)).").
Furthermore, regarding claim 5, Tapper further teaches wherein the first stream comprises a plurality of convolutional layers and the second stream comprises a plurality of convolutional layers (see Fig. 1 "Both the frequency (A) [first stream] and phase (B) [second stream] offset networks have the same basic structure with 3 FC [fully connected] layers (1024, 512, 1 node(s)).").
Furthermore, regarding claim 6, Tapper further teaches wherein the first stream comprises a same architecture as the second stream (see Fig. 1 "Both the frequency (A) [first stream] and phase (B) [second stream] offset networks have the same basic structure with 3 FC [fully connected] layers (1024, 512, 1 node(s)).").
Furthermore, regarding claim 7, Tapper further teaches wherein input to the first stream comprises magnitude spectrum data (see pg. 1758, col. 1, para. 1 "...then, central 1024 samples of the magnitude spectra were extracted and used as input to the trained frequency offset network [first stream].") and input to the second stream comprises real spectrum data (see pg. 1758, col. 1, para. 1 - " Page 6 then the central 1024 samples of the real spectrum were extracted and used as input to the trained phase offset network [second stream].").
Furthermore, regarding claim 8, Tapper further teaches wherein the trained machine learning model comprises a transformer network with a plurality of multi-head attention blocks (see Fig. 1- "The hidden FC [fully connected] layers were each followed by a rectified linear unit (ReLU) activation function, and the output FC layer was followed by a linear activation function that generated the output offset as a continuous variable." Where a transformer model with multi-head attention blocks is a machine learning model that is inherent and known in the art).
Furthermore, regarding claim 9, Tapper further teaches wherein the trained machine learning model comprises an encoder comprising a multi-head attention block and a decoder comprising at least two multi-head attention blocks (see Fig. "The 2 hidden FC [fully connected] layers were each followed by a rectified linear unit (ReLU) activation function, and the output FC layer was followed by a linear activation function that generated the output offset as a continuous variable." where it is inherent and known in the art that CNNs includes an encoder and a decoder).
Furthermore, regarding claim 10, Tapper further teaches wherein the spectrum data comprises on-spectrum data and off-spectrum data (see pg. 1758, col. 1, para. 1 "Finally, all fully corrected FIDs were used to compute an average difference spectrum by subtracting the corrected OFF spectra from the corrected ON spectra." Where on-spectrum and off-spectrum data is inherent and known in the art).
Furthermore, regarding claim 11, Tapper further teaches wherein generating the corrected on spectrum data and the corrected off-spectrum comprises:
applying estimated frequency corrections to the on-spectrum data and the off-spectrum data (see Fig. 2 "The predicted Δf [frequency offset/correction] was applied to each FID [includes on spectrum and off spectrum]."); and
applying estimated phase corrections to the on-spectrum data and the off-spectrum data (see Fig. 2 "The predicted Δϕ [phase offset/correction] for each FID was subsequently used to phase correct the frequency-corrected FIDs [includes on spectrum and off spectrum].").
Furthermore, regarding claim 13, Tapper further teaches wherein the spectrum data comprises single voxel MEGA-PRESS MRS data (see pg. 1756, col. 2, para. 1 "In order to establish in vivo-like levels of SNR and residual water signal, data from the publicly available Big GABA repository were used, which includes a total of 101 Philips (Philips Healthcare, Best, Netherlands) MEGA-edited [MEGA- PRESS] datasets collected from 9 different sites...").
Furthermore, regarding claim 14, Tapper further teaches wherein the one or more of the metabolites is quantified over at least a portion of the subject's brain (see pg. 1756, col. 1, para. 1 "Appropriate FPC [frequency-and-phase correction] is even more crucial when using J-difference-edited MRS methods such as MEGA-PRESS, which relies on the subtraction of2 spectra containing strong signals (OFF and ON) in order to reveal a much smaller targeted signal (eg, gamma aminobutyric acid [GABA]) [known metabolite in Page 9 brain] in the resulting difference spectrum." Where it is inherent and known in the art to quantify metabolites via J difference MRS).
Furthermore, regarding claim 15, Tapper further teaches wherein the one or more of the metabolites comprises GABA (see pg. 1756, col. 1, para. 1- "Appropriate FPC [frequency-and-phase correction] is even more crucial when using J-difference-edited MRS methods such as MEGA-PRESS, which relies on the subtraction of 2 spectra containing strong signals (OFF and ON) in order to reveal a much smaller targeted signal (eg, gamma aminobutyric acid [GABA]) [metabolite] in the resulting difference spectrum." Where it is inherent and known in the art to quantify metabolites via J-difference MRS).
Furthermore, regarding claim 16, Tapper further teaches wherein the one or more of the metabolites comprises glutamate or glutamine (see pg. 1756, col. 1, para. 1 "Appropriate FPC [frequency-and-phase correction] is even more crucial when using J-difference-edited MRS methods such as MEGA-PRESS, which relies on the subtraction of 2 spectra containing strong signals (OFF and ON) in order to reveal a much smaller targeted signal (eg, gamma aminobutyric acid [GABA]) [metabolite] in the resulting difference spectrum." Where it is inherent and known in the art to quantify metabolites, including glutamate and glutamine, via J-difference MRS).
Furthermore, regarding claim 17, Tapper further teaches wherein a therapeutic agent is administered to the subject based on the glutamate or glutamine that is quantified, wherein the therapeutic agent reduces, decreases or inhibits glutamate or glutamine levels the subject's brain after administration (see pg. 1756, col. 1, para. 1 "Appropriate FPC [frequency-and-phase correction] is even more crucial when using J-difference-edited MRS methods such as MEGA-PRESS, which relies on the subtraction of 2 spectra containing strong signals (OFF and ON) in order to reveal a much smaller targeted signal (eg, gamma aminobutyric acid [GABA]) [metabolite] in the resulting difference spectrum." Where it is inherent and known in the art to quantify metabolites via J-difference MRS, and it is inherent and known in the art to reduce glutamate (metabolites in the brain) levels to treat neurological disorders with known higher levels of glutamate).
Furthermore, regarding claim 18, Tapper further teaches wherein the quantifying one or more of the metabolites according to the corrected on-spectrum data and corrected off-spectrum data comprises calculating a difference between the off-spectrum data and the on-spectrum data (see Fig. 2 "An average difference spectrum was computed by subtracting the averaged OFF spectrum from the average ON spectrum.").
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Cheng et al. (US 20200105031 A1, published April 2, 2020) discloses a set of neural network channels for processing in parallel the slices in the applied training batch, where each of the channels produces the image output from the deep neural network from applying the slice in the applied training batch, where each channel comprises a sequence of block pairs, where each of the block pairs comprises a data consistency block and a neural network block (Fig. 2).
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 Nyrobi Celestine whose telephone number is 571-272-0129. The examiner can normally be reached on Monday - Thursday, 7:00AM - 5:00PM EST.
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, Pascal Bui-Pho can be reached on 571-272-2714. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/N.C./Examiner, Art Unit 3798
/PASCAL M BUI PHO/Supervisory Patent Examiner, Art Unit 3798
Prosecution Insights