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 .
The following action is in response to the amendment of 12/03/2025.
By the amendment, claims 1, 11 and 20 have been amended. Claim 2 has been canceled.
Claims 1 and 3-20 are pending and have been considered below.
Response to Arguments
Applicant's arguments filed 12/03/2025 have been fully considered but they are not persuasive.
Regarding the 35 USC 101 rejections of claims 1-20, Applicant argues that (1) none of the amended claims recite limitations that are directed towards any of the categories of abstract idea (Remarks pages 7-8), (2) that the amended claims recite limitations which integrate any purported abstract idea into a practical application (Remarks pages 8-9) and that (3) the amended claims are directed towards a technological solution to a technological problem and therefore not abstract (Remarks pages 10-13). The Examiner respectfully disagrees and the 35 USC 101 rejections have been updated and maintained to reflect the amendment to the claims.
Regarding Applicant’s argument (1) that none of the amended claims recite limitations that are directed towards any of the categories of abstract idea, the Examiner respectfully disagrees. The intendent claims now recite modulating a set of data-dependent scale or shift parameters associated with a second model in order to generate a conditioned second model that represents the first medical item within the spectral domain and mapping a first set of positions to a first set of predicted values associated with both the first medical item and the spectral domain via the conditioned second model. Both the modulation and mapping steps are directed to the abstract idea of mathematical concepts such as mathematical relationships, formulas or equations, or calculations (MPEP 2106.04(a)(2)(I)). In both cases, a broadest reasonable interpretation of the corresponding claim language yields explicit recitation of corresponding mathematical calculations used. For modulation, Applicant’s specification discloses that to modulate is to apply mathematical calculations (Specification ¶104, Equation (5)). For mapping, Applicant’s specification discloses that mapping is a mathematical operation (Specification ¶94-95). The argument is not persuasive.
Regarding Applicant’s argument (2) that the amended claims recite limitations which integrate any purported abstract idea into a practical application, the Examiner respectfully disagrees. Each of the additional limitations not found in the abstract idea have been evaluated and found to be limitations recited at a high level amounting to generic computing functions for merely applying the abstract idea, mere data gathering input/outputs, or mere instructions for implementing the abstract idea in a field of use. The limitations of a computer-implemented method, executing a first trained machine learning model, and a second (conditioned) model are each recited at high granularity and are considered generic computing functions for merely applying the abstract idea. The limitations of a first set of data points associated with a both a first medical item and a spectral domain, a first set of positions and a constructed first image of the first medical item based on the first set of predicted values each represent mere data gathering steps of input selection and predicted outputs. The limitations of the first medical item and spectral domain and associated first set of predicted values represent merely implementing the abstract idea in a field of use. The argument is not persuasive.
Regarding Applicant’s argument (3) that the amended claims are directed towards a technological solution to a technological problem and therefore not abstract, the Examiner respectfully disagrees. While Applicant has highlighted potential technological improvements to accuracy of a conditioned model relative to the prior art, the claimed invention still only recites generic models for achieving a solution in medical imaging. Applicant is encouraged to amend the claims to further recite improvements to the models themselves rather than simply claiming results that the generic models provide. The argument is not persuasive.
Regarding the 35 USC 102 rejections of claims 1, 11 and 20 by Buchholz, Applicant argues that Buchholz does not disclose modulating any data-dependent shift or scale parameters of a model in order to generate a conditioned second model that represents the input image within the spectral domain (Remarks pages 14-15). The Examiner respectfully disagrees. The claim language in question remains broad. For example, Applicant has not provided further details as to how the modulation conditions a set of parameters. As interpreted, Buchholz discloses (page 4 3.4) an encoder, the machine learning model, which executes on the raw sinogram, the first set of data points, to create a latent space representation, broadly the conditioned second model, of the full input sinogram, broadly the pre-conditioned second model. The claim remains broad that the interpretation of the data model latent space representation anticipates the second model. To create the latent space representation, a set of scale parameters, the sinogram FDE, is modulated. The argument is not persuasive.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1 and 3-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding claims 1, 11 and 20, claim 1 recites:
“A computer-implemented method for constructing medical images, the method comprising:
executing a first trained machine learning model on a first set of data points associated with both a first medical item and a spectral domain to modulate a set of data-dependent scale or shift parameters associated with a second model in order to generate a conditioned second model that represents the first medical item within the spectral domain;
mapping a first set of positions to a first set of predicted values associated with both the first medical item and the spectral domain via the conditioned second model; and
constructing a first image of the first medical item based on the first set of predicted values.”
Step 1, MPEP 2106.03:
Claim 1 recites a method and is directed to a statutory category of invention.
Claim 11 recites one or more non-transitory computer readable media for performing steps similar to that of claim1 and is also drawn to a statutory category of invention.
Claim 20 recites a system comprising memory and processors for performing steps similar to that of claim 1 and is also drawn to a statutory category of invention.
Step 2A Prong One, MPEP 2106.04, 2016.04(a):
Claims 1, 11 and 20 recite at least the limitations of modulating a set of data-dependent scale or shift parameters associated with a second model to generate a conditioned second model and mapping a first set of positions to a first set of predicted values. These limitations are directed to the abstract idea of mathematical concepts such as mathematical relationships, mathematical formulas or equations, or mathematical calculations (Specification ¶94-95, ¶105). See MPEP 2106.04(a)(2)(I).
Step 2A Prong Two, MPEP 2106.04(d):
Claims 1, 11 and 20 further recite a first set of data points and a first set of predicted values both associated with a medical item and spectral domain. These additional element of the data being medically-associated indicates a field of use in which the judicial exception is performed and is considered mere instructions to implement the abstract idea in an indicated field of use or technological environment. See MPEP 2106.05(h).
Claims 1, 11 and 20 further recite the first set of data points, for executing, and a first image of the first medical item is constructed. These additional elements of the set of data points for execution and construction of the image represent mere data gathering and output and, as such, these limitations do not impose any meaningful limits on the claim. See MPEP 2106.05.
Claims 1, 11 and 20 further recite recites the methods steps performed by a generic computer; executing a first trained machine learning model to generate a conditioned second model and mapping via the conditioned second model. When a computer, such as a computer comprised of processors and/or memories or computer readable medium executed by a computer comprised of processors and/or memories, is recited at a high level of generality, it represents mere instructions to implement steps of the abstract idea using generic computing tools. Similarly, the first machine learning model and second model for execution and mapping are recited at a high level of generality and amount to generally applying the abstract idea without placing any limits on how the first trained machine learning model or second model functions. See MPEP 2106.05(f).
Step 2B, MPEP 2106.05:
As discussed above, the additional element of claims 1, 11 and 20, including the field of use of the item and image, does not amount to significantly more than the judicial exception as it amounts to mere instructions to apply the exception. See MPEP 2106.05(h).
Further, the additional elements of claims 1, 11 and 20, including the data gathering steps of the first set of data points and construction of a first image, do not amount to significantly more than the judicial exception due to being insignificant extra-solution activity of selecting a particular data source or data output. See MPEP 2106.05(g).
Further, the additional elements of claims 1, 11 and 20, including the computer elements and machine learning models, do not amount to significantly more than the judicial exception as they amount to mere instructions to apply the exception using generic computer components. See MPEP 2106.05(f).
Regarding claims 3 and 13, claim 3 recites:
“The computer-implemented method of claim 1, wherein mapping the first set of positions to the first set of predicted values comprises computing a first set of encodings based on the first set of positions.”
Step 1, MPEP 2106.03:
Claim 3 depends from the method of claim 1 and is similarly drawn to a statutory category.
Claim 13 depends from the non-transitory computer readable media of claim 11 and is similarly drawn to a statutory category.
Step 2A Prong One, MPEP 2106.04, 2016.04(a):
The analysis of the parent is incorporated.
Claims 3 and 13 further recite wherein mapping the first set of positions to the first set of predicted values comprises computing a first set of encodings based on the first set of positions. This computing limitation is directed to the abstract idea of mathematical concepts such as mathematical relationships, mathematical formulas or equations, or mathematical calculations. See MPEP 2106.04(a)(2)(I).
Step 2A Prong Two, MPEP 2106.04(d):
All elements are part of the abstract idea above.
Step 2B, MPEP 2106.05:
All elements are part of the abstract idea above.
Regarding claims 4 and 14, claim 4 recites:
“The computer-implemented method of claim 1, further comprising computing the first set of predicted values based on a plurality of parameter values that are derived from the first set of data points and associated with the second model, a plurality of learned parameter values that are associated with the second model, and the first set of positions.”
Step 1, MPEP 2106.03:
Claim 4 depends from the method of claim 1 and is similarly drawn to a statutory category.
Claim 14 depends from the non-transitory computer readable media of claim 11 and is similarly drawn to a statutory category.
Step 2A Prong One, MPEP 2106.04, 2016.04(a):
The analysis of the parent is incorporated.
Claims 4 and 14 further recite computing the first set of predicted values based on a plurality of parameter values that are derived from the first set of data points and associated with the second model, a plurality of learned parameter values that are associated with the second model, and the first set of positions. This computing limitation is directed to the abstract idea of mathematical concepts such as mathematical relationships, mathematical formulas or equations, or mathematical calculations. See MPEP 2106.04(a)(2)(I).
Step 2A Prong Two, MPEP 2106.04(d):
All elements are part of the abstract idea above.
Step 2B, MPEP 2106.05:
All elements are part of the abstract idea above.
Regarding claims 5 and 15, claim 5 recites:
“The computer-implemented method of claim 1, wherein constructing the first image comprises computing an inverse Fourier transform based on the first set of positions and the first set of predicted values to generate a set of pixel values associated with the first medical item.”
Step 1, MPEP 2106.03:
Claim 5 depends from the method of claim 1 and is similarly drawn to a statutory category.
Claim 15 depends from the non-transitory computer readable media of claim 11 and is similarly drawn to a statutory category.
Step 2A Prong One, MPEP 2106.04, 2016.04(a):
The analysis of the parent is incorporated.
Claims 5 and 15 further recite wherein constructing the first image comprises computing an inverse Fourier transform based on the first set of positions and the first set of predicted values. This computing limitation is directed to the abstract idea of mathematical concepts such as mathematical relationships, mathematical formulas or equations, or mathematical calculations. See MPEP 2106.04(a)(2)(I).
Step 2A Prong Two, MPEP 2106.04(d):
Claims 5 and 15 further recite wherein the inverse Fourier transform is computed to generate a set of pixel values associated with the first medical item. This additional element of solution/outcome of the computing amounts to reciting no more than an idea of the solution and does not, alone or in combination, integrate the judicial exception into a practical application. See MPEP 2106.05.
Step 2B, MPEP 2106.05:
As discussed above, the additional element of claims 5 and 16 including the solution/outcome are at best mere instructions to apply the abstract idea, which cannot provide an inventive concept. See MPEP 2106.05(f).
Regarding claim 6 and 16, claim 6 recites:
“The computer-implemented method of claim 1, further comprising generating a third model that represents a second medical item within the spectral domain based on a second set of data points associated with both the second medical item and the spectral domain.”
Step 1, MPEP 2106.03:
Claim 6 depends from the method of claim 1 and is similarly drawn to a statutory category.
Claim 16 depends from the non-transitory computer readable media of claim 11 and is similarly drawn to a statutory category.
Step 2A Prong One, MPEP 2106.04, 2016.04(a):
The analysis of the parent is incorporated.
Step 2A Prong Two, MPEP 2106.04(d):
Claims 6 and 16 further recite a second set of data points associated with both a medical item and a spectral domain and the third model represents a second medical item with the spectral domain. These additional element of the data being medically-associated indicates a field of use in which the judicial exception is performed and is considered mere instructions to implement the abstract idea in an indicated field of use or technological environment. See MPEP 2106.05(h).
Claims 6 and 16 further recite the methods steps generating a third model that represents a second medical item within the spectral domain. The generating the third model is recited at a high level of generality and amount to generally applying the abstract idea without placing any limits on how the generating is accomplished. See MPEP 2106.05(f).
Step 2B, MPEP 2106.05:
As discussed above, the additional element of claims 6 and 16 including the field of use does not amount to significantly more than the judicial exception as it amounts to mere instructions to apply the exception. See MPEP 2106.05(h).
Further, the additional element of claims 6 and 16, the generating a third model, does not amount to significantly more than the judicial exception as it amounts to mere instructions to apply the exception using generic computer components. See MPEP 2106.05(f).
Regarding claim 7, claim 7 recites:
“The computer-implemented method of claim 1, wherein the first medical item comprises at least one of an internal body organ, a portion of body tissue, a blood vessel, a muscle, or a bone.”
Step 1, MPEP 2106.03:
Claim 7 depends from the method of claim 1 and is similarly drawn to a statutory category.
Step 2A Prong One, MPEP 2106.04, 2016.04(a):
The analysis of the parent is incorporated.
Step 2A Prong Two, MPEP 2106.04(d):
Claim 7 further recites wherein the first medical item comprises at least one of an internal body organ, a portion of body tissue, a blood vessel, a muscle, or a bone. These additional element of what the first medical item comprises amounts to mere data gathering and does not, alone or in combination, integrate the judicial exception into a practical application. See MPEP 2106.05.
Step 2B, MPEP 2106.05:
As discussed above, the additional element of claim 7 including the what data the first media item comprises does not amount to significantly more than the judicial exception as it amounts to an insignificant extra-solution activity of selecting a particular data/type of data. See MPEP 2106.05(g).
Regarding claim 8, claim 8 recites:
“The computer-implemented method of claim 1, wherein the first set of data points comprises a set of magnetic resonance imaging measurements or a sequence of projections associated with a computed tomography scan.”
Step 1, MPEP 2106.03:
Claim 8 depends from the method of claim 1 and is similarly drawn to a statutory category.
Step 2A Prong One, MPEP 2106.04, 2016.04(a):
The analysis of the parent is incorporated.
Step 2A Prong Two, MPEP 2106.04(d):
Claim 8 further recites wherein the first set of data points comprises a set of magnetic resonance imaging measurements or a sequence of projections associated with a computed tomography scan. These additional element of what the first set of data points comprises amounts to mere data gathering and does not, alone or in combination, integrate the judicial exception into a practical application. See MPEP 2106.05.
Step 2B, MPEP 2106.05:
As discussed above, the additional element of claim 8 including the what data points comprise does not amount to significantly more than the judicial exception as it amounts to an insignificant extra-solution activity of selecting a particular data/type of data. See MPEP 2106.05(g).
Regarding claim 9, claim 9 recites:
“The computer-implemented method of claim 1, further comprising performing one or more machine learning operations on an untrained machine learning model based on a plurality of ground-truth values that are associated with both a training medical item and the spectral domain to generate the first trained machine learning model.”
Step 1, MPEP 2106.03:
Claim 9 depends from the method of claim 1 and is similarly drawn to a statutory category.
Step 2A Prong One, MPEP 2106.04, 2016.04(a):
The analysis of the parent is incorporated.
Claim 9 recites performing one or more machine learning operations on an untrained machine learning model based on a plurality of ground-truth values to generate the first trained machine learning model. Training the first machine learning model by performing operations based on a plurality of ground-truth values is directed to the abstract idea of mathematical concepts such as mathematical relationships, mathematical formulas or equations, or mathematical calculations. See MPEP 2106.04(a)(2)(I).
Step 2A Prong Two, MPEP 2106.04(d):
Claim 9 further recites that the ground-truth values are associated with both a training medical item and the spectral domain. This additional element of with what the ground truth values are associated comprises amounts to mere data gathering and does not, alone or in combination, integrate the judicial exception into a practical application. See MPEP 2106.05.
Step 2B, MPEP 2106.05:
As discussed above, the additional element of claim 9 including the with what ground-truth data is associated does not amount to significantly more than the judicial exception as it amounts to an insignificant extra-solution activity of selecting a particular data/type of data. See MPEP 2106.05(g).
Regarding claim 10, claim 10 recites:
“The computer-implemented method of claim 1, further comprising modifying one or more learnable parameter values associated with an untrained machine learning model based on a reconstruction error associated with both a training medical item and the spectral domain to generate the first trained machine learning model.”
Step 1, MPEP 2106.03:
Claim 10 depends from the method of claim 1 and is similarly drawn to a statutory category.
Step 2A Prong One, MPEP 2106.04, 2016.04(a):
The analysis of the parent is incorporated.
Claim 10 recites modifying one or more learnable parameter values associated with an untrained machine learning model based on a reconstruction error to generate the first trained machine learning model. Training the first machine learning model by performing modifying learning parameters based on a reconstruction error is directed to the abstract idea of mathematical concepts such as mathematical relationships, mathematical formulas or equations, or mathematical calculations. See MPEP 2106.04(a)(2)(I).
Step 2A Prong Two, MPEP 2106.04(d):
Claim 10 further recites that the reconstruction error is associated with both a training medical item and the spectral domain. This additional element of with what the reconstruction error is associated comprises amounts to mere data gathering and does not, alone or in combination, integrate the judicial exception into a practical application. See MPEP 2106.05.
Step 2B, MPEP 2106.05:
As discussed above, the additional element of claim 10 including the with what the reconstruction error is associated does not amount to significantly more than the judicial exception as it amounts to an insignificant extra-solution activity of selecting a particular data/type of data. See MPEP 2106.05(g).
Regarding claim 12, claim 12 recites:
“The one or more non-transitory computer readable media of claim 11, wherein executing the first trained machine learning model on the first set of data points comprises computing at least one of a shifting coefficient or a scaling coefficient associated with the second model.”
Step 1, MPEP 2106.03:
Claim 12 depends from the non-transitory computer readable medium of claim 11 and is similarly drawn to a statutory category.
Step 2A Prong One, MPEP 2106.04, 2016.04(a):
The analysis of the parent is incorporated.
Claim 12 recites executing the first trained machine learning model on the first set of data points comprises computing at least one of a shifting coefficient or a scaling coefficient associated with the second model. Computing a shifting or scaling coefficient associated with the second model is directed to the abstract idea of mathematical concepts such as mathematical relationships, mathematical formulas or equations, or mathematical calculations. See MPEP 2106.04(a)(2)(I).
Step 2A Prong Two, MPEP 2106.04(d):
All elements are part of the abstract idea above.
Step 2B, MPEP 2106.05:
All elements are part of the abstract idea above.
Regarding claim 17, claim 17 recites:
“The one or more non-transitory computer readable media of claim 16, wherein a first plurality of learned parameter values associated with the second model is equal to a second plurality of learned parameter values associated with the third model.”
Step 1, MPEP 2106.03:
Claim 17 depends from the non-transitory computer readable medium of claim 16 and is similarly drawn to a statutory category.
Step 2A Prong One, MPEP 2106.04, 2016.04(a):
The analysis of the parent is incorporated.
Step 2A Prong Two, MPEP 2106.04(d):
Claim 17 further recites wherein a first plurality of learned parameter values associated with the second model is equal to a second plurality of learned parameter values associated with the third model. This additional element of solution/outcome of the equal learned parameters recites no more than an idea of the solution and does not, alone or in combination, integrate the judicial exception into a practical application. See MPEP 2106.05.
Step 2B, MPEP 2106.05:
As discussed above, the additional element of claim 17 including the solution/outcome are at best mere instructions to apply the abstract idea, which cannot provide an inventive concept. See MPEP 2106.05(f).
Regarding claim 18, claim 18 recites:
“The one or more non-transitory computer readable media of claim 11, wherein the first set of data points comprises a set of magnetic resonance imaging measurements, and the spectral domain comprises a k-space.”
Step 1, MPEP 2106.03:
Claim 18 depends from the non-transitory computer readable medium of claim 11 and is similarly drawn to a statutory category.
Step 2A Prong One, MPEP 2106.04, 2016.04(a):
The analysis of the parent is incorporated.
Step 2A Prong Two, MPEP 2106.04(d):
Claim 18 further recites wherein the first set of data points comprises a set of magnetic resonance imaging measurements and the spectral domain comprises a k-space. These additional elements of what the first set of data points and spectral domain comprise amounts to mere data gathering and does not, alone or in combination, integrate the judicial exception into a practical application. See MPEP 2106.05.
Step 2B, MPEP 2106.05:
As discussed above, the additional elements of claim 18 including the what data points and spectral domain comprise do not amount to significantly more than the judicial exception as it amounts to an insignificant extra-solution activity of selecting a particular data/type of data. See MPEP 2106.05(g).
Regarding claim 19, claim 19 recites:
“The one or more non-transitory computer readable media of claim 11, further comprising performing one or more machine learning operations on an untrained machine learning model based on a plurality of sets of ground-truth values and a plurality of sets of input values to generate the first trained machine learning model, wherein the plurality of sets of ground-truth values and the plurality of sets of input values are associated with the spectral domain and a plurality of medical images.”
Step 1, MPEP 2106.03:
Claim 19 depends from the non-transitory computer readable medium of claim 11 and is similarly drawn to a statutory category.
Step 2A Prong One, MPEP 2106.04, 2016.04(a):
Claim 19 recites comprising performing one or more machine learning operations on an untrained machine learning model based on a plurality of sets of ground-truth values and a plurality of sets of input values to generate the first trained machine learning model. Training the first machine learning model by performing operations based on ground-truth value sets and input value sets is directed to the abstract idea of mathematical concepts such as mathematical relationships, mathematical formulas or equations, or mathematical calculations. See MPEP 2106.04(a)(2)(I).
Step 2A Prong Two, MPEP 2106.04(d):
Claim 19 further recites that the plurality of sets of ground-truth values and input values are both associated the spectral domain and a plurality of medical images. This additional element of with what the ground-truth values and input values are associated comprises amounts to mere data gathering and does not, alone or in combination, integrate the judicial exception into a practical application. See MPEP 2106.05.
Step 2B, MPEP 2106.05:
As discussed above, the additional element of claim 19 including with what the ground-truth values and input values are associated does not amount to significantly more than the judicial exception as it amounts to an insignificant extra-solution activity of selecting a particular data/type of data. See MPEP 2106.05(g).
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 3-17 and 19-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by BUCHHOLZ, "Fourier Image Transformer." arXiv preprint arXiv:2104.02555v2 (2021), previously presented.
Regarding claim 1, BUCHHOLZ discloses computer-implemented method for constructing medical images (page 4 Section 3.4: “Fourier Image Transformer setup for tomographic reconstruction (“FIT: TRec”)”), the method comprising:
executing a first trained machine learning model on a first set of data points associated with both a first medical item and a spectral domain to modulate a set of data-dependent scale or shift parameters associated with a second model in order to generate a conditioned second model that represents the first medical item within the spectral domain (page 4 Section 3.4 FIT for Tomography: “As input to the encoder we use the Fourier Domain Encoding (FDE) of a raw sinogram
PNG
media_image2.png
11
11
media_image2.png
Greyscale
. As described above,
PNG
media_image2.png
11
11
media_image2.png
Greyscale
consists of
PNG
media_image3.png
19
15
media_image3.png
Greyscale
pixel columns
PNG
media_image4.png
22
91
media_image4.png
Greyscale
of 1D projections of
PNG
media_image5.png
11
13
media_image5.png
Greyscale
at angles
PNG
media_image6.png
25
94
media_image6.png
Greyscale
. The Fourier slice theorem states, see also Section 2.4, that the discrete 1D Fourier coefficients
PNG
media_image7.png
23
94
media_image7.png
Greyscale
coincide with the values of the 1D slice at
PNG
media_image8.png
16
23
media_image8.png
Greyscale
through the 2D Fourier spectrum
PNG
media_image9.png
21
42
media_image9.png
Greyscale
. To assemble the full FDE of a sinogram we need to combine all
PNG
media_image10.png
22
26
media_image10.png
Greyscale
with the adequate positional encoding (using polar coordinates) of all Fourier coefficients, as dictated by the Fourier slice theorem and sketched in Figure 3.”, “Hence, the encoder creates a latent space representation
PNG
media_image11.png
18
14
media_image11.png
Greyscale
that encodes the full input sinogram
PNG
media_image2.png
11
11
media_image2.png
Greyscale
.” – using Fourier Domain Encoding model to create modulated latent space representation data model);
mapping a first set of positions to a first set of predicted values associated with both the first medical item and the spectral domain via the conditioned second model (page 4 Section 3.4: “Hence, the encoder creates a latent space representation
PNG
media_image11.png
18
14
media_image11.png
Greyscale
that encodes the full input sinogram
PNG
media_image2.png
11
11
media_image2.png
Greyscale
. This latent space encoding is then given as input to the decoder. The decoder is then used to predict all Fourier coefficients
PNG
media_image12.png
21
17
media_image12.png
Greyscale
”, -mapping to predicted values); and
constructing a first image of the first medical item based on the first set of predicted values (page 4 Section 3.4: “..such that the predicted reconstruction
PNG
media_image13.png
16
14
media_image13.png
Greyscale
of
PNG
media_image5.png
11
13
media_image5.png
Greyscale
can be computed by
PNG
media_image14.png
24
146
media_image14.png
Greyscale
, where roll arranges the 1D sequence back into a discrete 2D Fourier spectrum. We call this setup “FIT: TRec”.” – predicted reconstruction of first image x).
Regarding claim 3, BUCHHOLZ discloses the computer-implemented method of claim 1, wherein mapping the first set of positions to the first set of predicted values comprises computing a first set of encodings based on the first set of positions (page 4 Section 3.4 - encoding).
Regarding claim 4, BUCHHOLZ discloses the computer-implemented method of claim 1, further comprising computing the first set of predicted values (page 5 Section 3.4: “We train “FIT: TRec” and “FIT: TRec + FBP” using the
PNG
media_image15.png
23
87
media_image15.png
Greyscale
of Eq.12.”) based on a plurality of parameter values that are derived from the first set of data points and associated with the second model (page 3 Section 3.1: “predicted amplitudes and phases
PNG
media_image16.png
24
97
media_image16.png
Greyscale
”), a plurality of learned parameter values that are associated with the second model (page 3-4 Section 3.2: a loss function consisting of two terms, (i) the amplitude loss” .. “and (ii) the phase loss”), and the first set of positions (page 4-5 Section 3.4: “encodes the full input sinogram
PNG
media_image2.png
11
11
media_image2.png
Greyscale
”).
Regarding claim 5, BUCHHOLZ discloses the computer-implemented method of claim 1, wherein constructing the first image comprises computing an inverse Fourier transform based on the first set of positions and the first set of predicted values to generate a set of pixel values associated with the first medical item (Fig. 4 Section 3.3: “All final prediction images
PNG
media_image13.png
16
14
media_image13.png
Greyscale
are generated by computing the inverse Fourier transform on predictions
PNG
media_image12.png
21
17
media_image12.png
Greyscale
”).
Regarding claim 6, BUCHHOLZ discloses the computer-implemented method of claim 1, further comprising generating a third model that represents a second medical item within the spectral domain based on a second set of data points associated with both the second medical item and the spectral domain (page 6 Section 4.6: “For each dataset, we show three input sinograms, the reconstruction baseline obtained via filtered backprojection (FBP), our results obtained via “FIT: TRec” and “FIT: TRec + FBP”, and the corresponding ground truth images.” – different inputs yield different reconstruction models).
Regarding claim 7, BUCHHOLZ discloses the computer-implemented method of claim 1, wherein the first medical item comprises at least one of an internal body organ, a portion of body tissue, a blood vessel, a muscle, or a bone (page 2 Section 2.4: “In computed tomography (CT), the radon transform (14, 15) of a 2D sample section is acquired by rotating a 1D detector array around the sample” .. “In practice, it is desirable to limit the number of projections/views in order to reduce overall acquisition times and total sample exposure.”, page 7 Section 5: “It is curious to see that eyes are the first high-resolution structures filled in by the trained FIT. We believe that this is a direct consequence of all training images being registered such that the eyes are consistently at the same location.”).
Regarding claim 8, BUCHHOLZ discloses the computer-implemented method of claim 1, wherein the first set of data points comprises a set of magnetic resonance imaging measurements or a sequence of projections associated with a computed tomography scan (page 1 Section 1: “Additionally, we show how an encoder-decoder based Fourier Image Transformer (“FIT: TRec”) can be trained on a set of Fourier measurements and then used to query arbitrary Fourier coefficients, which we use to improve sparse-view computed tomography (CT) image restoration1.”).
Regarding claim 9, BUCHHOLZ discloses the computer-implemented method of claim 1, further comprising performing one or more machine learning operations on an untrained machine learning model based on a plurality of ground-truth values that are associated with both a training medical item and the spectral domain to generate the first trained machine learning model (page 5 Section 3.4: “Additionally, we introduced a residual convolution block consisting of two convolutional layers (3×3 followed by 1×1) with
PNG
media_image17.png
16
39
media_image17.png
Greyscale
= 8 intermediate feature channels. This conv-block (conv) receives the inverse Fourier transform of the predicted Fourier coefficients
PNG
media_image14.png
24
146
media_image14.png
Greyscale
as input and is trained using the MSE-loss between the predicted real-space image
PNG
media_image18.png
19
64
media_image18.png
Greyscale
and the known ground truth image
PNG
media_image5.png
11
13
media_image5.png
Greyscale
. Hence, the full loss is the sum over LFC and the MSE-loss.”).
Regarding claim 10, BUCHHOLZ discloses the computer-implemented method of claim 1, further comprising modifying one or more learnable parameter values associated with an untrained machine learning model based on a reconstruction error associated with both a training medical item and the spectral domain to generate the first trained machine learning model (“page 5 Section 3.4: “Additionally, we introduced a residual convolution block consisting of two convolutional layers (3×3 followed by 1×1) with
PNG
media_image17.png
16
39
media_image17.png
Greyscale
= 8 intermediate feature channels. This conv-block (conv) receives the inverse Fourier transform of the predicted Fourier coefficients
PNG
media_image14.png
24
146
media_image14.png
Greyscale
as input and is trained using the MSE-loss between the predicted real-space image
PNG
media_image18.png
19
64
media_image18.png
Greyscale
and the known ground truth image
PNG
media_image5.png
11
13
media_image5.png
Greyscale
. Hence, the full loss is the sum over LFC and the MSE-loss.”).
Regarding claim 11, claim 11 recites limitations similar to claim 1 and is similarly rejected.
Regarding claim 12, BUCHHOLZ discloses the one or more non-transitory computer readable media of claim 11, wherein executing the first trained machine learning model on the first set of data points comprises computing at least one of a shifting coefficient or a scaling coefficient associated with the second model (page 3 Section 3.1: “predicted amplitudes and phases
PNG
media_image16.png
24
97
media_image16.png
Greyscale
”).
Regarding claims 13-16, claims 13-16 recite limitations similar to claims 3-6, respectively, and are similarly rejected.
Regarding claim 17, BUCHHOLZ discloses the one or more non-transitory computer readable media of claim 16, wherein a first plurality of learned parameter values associated with the second model is equal to a second plurality of learned parameter values associated with the third model (page 7 Section 5: “It is curious to see that eyes are the first high-resolution structures filled in by the trained FIT. We believe that this is a direct consequence of all training images being registered such that the eyes are consistently at the same location.”).
Regarding claim 19, BUCHHOLZ discloses the one or more non-transitory computer readable media of claim 11, further comprising performing one or more machine learning operations on an untrained machine learning model based on a plurality of sets of ground-truth values and a plurality of sets of input values to generate the first trained machine learning model (page 5 Section 3.4: “Additionally, we introduced a residual convolution block consisting of two convolutional layers (3×3 followed by 1×1) with
PNG
media_image17.png
16
39
media_image17.png
Greyscale
= 8 intermediate feature channels. This conv-block (conv) receives the inverse Fourier transform of the predicted Fourier coefficients
PNG
media_image14.png
24
146
media_image14.png
Greyscale
as input and is trained using the MSE-loss between the predicted real-space image
PNG
media_image18.png
19
64
media_image18.png
Greyscale
and the known ground truth image
PNG
media_image5.png
11
13
media_image5.png
Greyscale
. Hence, the full loss is the sum over LFC and the MSE-loss.), wherein the plurality of sets of ground-truth values and the plurality of sets of input values are associated with the spectral domain and a plurality of medical images (page 6 Section 4.6: “For each dataset, we show three input sinograms, the reconstruction baseline obtained via filtered backprojection (FBP), our results obtained via “FIT: TRec” and “FIT: TRec + FBP”, and the corresponding ground truth images.”).
Regarding claim 20, claim 20 recites limitation similar to claim 1 and is similarly rejected.
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:
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.
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.
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over BUCHHOLZ in view of HONG, "Accelerating compressed sensing reconstruction of subsampled radial k-space data using geometrically-derived density compensation." Physics in Medicine & Biology 66.21 (2021): 21NT01, previously presented.
Regarding claim 18, BUCHHOLZ discloses the one or more non-transitory computer readable media of claim 11, wherein the first set of data points comprises a set of medical imaging measurements (pages 2-3 Section 2.4: Tomographic Image Reconstruction), and the spectral domain comprises a k-space (page 3 Section 3.1: Fourier spectrum X).
BUCHHOLZ fails to explicitly disclose wherein the medical imaging measurements are a set of magnetic resonance imaging (MRI) measurements.
HONG discloses methods for reconstruction of medical image data using models (page 1 Abstract). In particular HONG discloses applying reconstruction models to 2D and 3D radial and other medical imaging (page 9 Discussion: “Our gDCF may apply to 2Dand 3D radial MRI and other medical (e.g. CT, SPECT, PET) and non-medical imaging modalities employing FBP and/or iterative reconstruction.”). Therefore it would have been obvious to one having ordinary skill in the art and the teachings of BUCHHOLZ and HONG before them before the effective filing of the claimed invention to combine the use of reconstruction models for medical images data derived from MRI or CT data, as suggested by HONG, with the use of the reconstruction model for medical image data of BUCHHOLZ. One would have been motivated to make this combination in order to provide use of the model across various well known tomographic imaging modalities, as suggested by HONG (page 1-2 Introduction: “Tomographic imaging modalities such as computed tomography (CT), single-photon emission computed tomography (SPECT), positron emission tomography (PET), and magnetic resonance imaging (MRI) are considered among the most important medical inventions in the last 50 years, with each modality having strengths and weaknesses. While their physics are vastly different, they share a digitalized image reconstruction pipeline including analytical and/or iterative algorithms (Gordon et al 1970, Shepp and Logan 1974, Lustig et al 2007, Geyer et al 2015).”).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Gottin et al.
US 20220237211 A1
OBJECT DETECTION
Rao et al.
US 20040136577 A1
OPTICAL FOURIER SYSTEM FOR MEDICAL IMAGE PROCESSING
Alvarez-Gila, Aitor, Joost Van De Weijer, and Estibaliz Garrote. "Adversarial networks for spatial context-aware spectral image reconstruction from RGB." Proceedings of the IEEE international conference on computer vision workshops. 2017.
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 ANDREW L TANK whose telephone number is (571)270-1692. The examiner can normally be reached Monday-Thursday 9a-6p.
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, Matthew Ell can be reached at 571-270-3264. 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.
/ANDREW L TANK/Primary Examiner, Art Unit 2141