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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on October 2, 2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
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.
Claim(s) 1, 5, 8-9 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by U.S. Publication No. 2022/0026516 to Guidon et al. (hereinafter Guidon).
Regarding independent claim 1, Guidon discloses A method of machine training for magnetic resonance (MR) reconstruction in medical imaging (abstract, "A computer-implemented method of correcting phase and reducing noise in magnetic resonance (MR) phase images is provided;" "The method includes executing a neural network model for analyzing MR images, wherein the neural network model is trained with a pair of pristine images and corrupted images,"), the method comprising:
acquiring MR training data including ground truth representations (abstract, "wherein the neural network model is trained with a pair of pristine images and corrupted images, wherein the corrupted images include corrupted phase information, the pristine images are the corrupted images with the corrupted phase information reduced, and target output images of the neural network model are the pristine images");
machine training a neural network for the MR reconstruction using the MR training data (abstract, "wherein the neural network model is trained with a pair of pristine images and corrupted images, wherein the corrupted images include corrupted phase information, the pristine images are the corrupted images with the corrupted phase information reduced, and target output images of the neural network model are the pristine images"), wherein an output of the neural network and/or the ground truth representations are phase corrected (note: based on the "and/or" the neural network is chosen as evaluated (i.e. an output of the neural network representations are phase corrected;" paragraph 0056, "In some embodiment, output phase images are computed based on the output images from the neural network model 204. In other embodiment, pristine phase images are directly output from the neural network model 204. Compared to the corrupted phase images of the received MR images, the derived pristine phase images include reduced corrupted phase information, i.e., with corrupted phase information reduced. The method 250 also includes outputting 260 images based on the pristine phase images"); and
storing the neural network as machine trained (Figure 2B, element 252, "execute a neural network model;" paragraph 0055, "In the exemplary embodiment, the method includes executing 252 a neural network model for analyzing MR images. The neural network model is trained with training images;" the neural network was previously trained, and in order to call the model to be implemented it must be stored as trained so that it is used as the trained model).
Regarding dependent claim 5, the rejection of claim 1 is incorporated herein. Additionally, Guidon further discloses wherein machine training comprises machine training where the phase correction is derived from the output (abstract, "The method includes executing a neural network model for analyzing MR images, wherein the neural network model is trained with a pair of pristine images and corrupted images, wherein the corrupted images include corrupted phase information, the pristine images are the corrupted images with the corrupted phase information reduced, and target output images of the neural network model are the pristine images;" the output are the pristine images, which have been phase corrected, and the model learns based on how the output and input relate to eachother).
Regarding independent claim 8, Guidon discloses A method for reconstruction of a medical image in a medical imaging system (abstract, "A computer-implemented method of correcting phase and reducing noise in magnetic resonance (MR) phase images is provided.".. "outputting MR images based on the derived pristine phase images."), the method comprising:
scanning, by the medical imaging system, a patient, the scanning resulting in scan data (Figure 2A, element 254, "receive MR images including corrupted phase information;" paragraph 0056, "The method 250 further includes receiving 254 MR images including corrupted phase information. The received MR images may be in any format that includes phase information, such as complex MR images, real and imaginary image pairs, or images in a phasor representation”);
reconstructing, by an image processor applying a machine-learned model, a scan image, the machine-learned model having been trained with application of phase correction (Figure 2B; as seen in figure 2B, the initial images are input (i.e. at 254) and are corrected at step 258 using the trained neural network; abstract, "wherein the neural network model is trained with a pair of pristine images and corrupted images;" paragraph 0056, "In some embodiment, output phase images are computed based on the output images from the neural network model 204. In other embodiment, pristine phase images are directly output from the neural network model 204. Compared to the corrupted phase images of the received MR images, the derived pristine phase images include reduced corrupted phase information, i.e., with corrupted phase information reduced. The method 250 also includes outputting 260 images based on the pristine phase images"); and
displaying the medical image based on the scan image (Figure 2B, element 260, "output images based on the derived pristine phase image;" paragraph 0089, "Moreover, in the exemplary embodiment, computing device 800 includes a display interface 817 that presents information").
Regarding dependent claim 9, the rejection of claim 8 is incorporated herein. Additionally, Guidon further discloses wherein the scan data comprises measurements over a series of scans of an imaging protocol (paragraph 0041, “the workstation 12 provides an operator interface that allows scan prescriptions to be entered into the MRI system 10;" the scan prescription is read as the imaging protocol; further MRI is a series of slices (i.e. multiple scans) made in one imaging protocol), wherein reconstructing comprises reconstructing the scan image for each of the scans of the series (paragraph 0040, "A Fourier relationship exists between the acquired MR signals and an image of the subject, and therefore the image of the subject can be derived by reconstructing the MR signals;" further multiple slices are generated from one MRI protocol), the machine-learned model having been trained for use for each scan of the imaging protocol based on a loss function from a combination of training images from different scans for the imaging protocol (paragraph 0069, "The neural network 302 may trained with a loss function, which is a function measuring the inference error by the neural network 302. The loss function may be expressed as nin(f1(input)-f2(output)), where f1 and f2 are functions of the input and the output to the neural network 302, respectively. In some embodiment, the loss function includes constraints based on prior knowledge of the phase information;" paragraph 0069, "Inputs and outputs to the neural network 302 may also be complex images, magnitude and phase image pairs, or real or imaginary image pairs;" note that the images can be plural (i.e. images) which means that the loss function can be based on the combination of the input/output in training from different scans); and
further comprising combining the scan images into the medical image (MRI signals are reconstructed to form a MRI volume; paragraph 0040, "A Fourier relationship exists between the acquired MR signals and an image of the subject, and therefore the image of the subject can be derived by reconstructing the MR signals;" i.e. each slice combined forms the volume).
Double Patenting
Non-statutory
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-13 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-3, 4-8, 11, 13-15 and 17 of U.S. Patent No. 12,205,279 to Arberet et al. (hereinafter US ‘279). Although the claims at issue are not identical, they are not patentably distinct from each other because the instant application is more broad in scope.
Claim 1: Regarding claim 1, claim 1 compares to claim 1 of the US ‘279 patent as indicated below:
Instant Application 18/904,590
U.S. Patent No. 12,205,279
Notes
A method of machine training for magnetic resonance (MR) reconstruction in medical imaging, the method comprising:
A method of machine training for magnetic resonance (MR) reconstruction in medical imaging, the method comprising:
Verbatim the same
acquiring MR training data including ground truth representations;
acquiring MR training data including ground truth representations;
Verbatim the same
machine training a neural network for the MR reconstruction using the MR training data, wherein an output of the neural network and/or the ground truth representations are phase corrected; and
machine training a neural network for the MR reconstruction using the MR training data, wherein an output of the neural network and/or the ground truth representations are phase corrected;
Verbatim the same
extracting a phase map from low pass filtering of the output or one of the ground truth representations, wherein the phase correction multiplies complex values with the phase map; and
Instant application more broad
storing the neural network as machine trained.
storing the neural network as machine trained.
Verbatim the same
As can be seen above, claim 1 of the current application is more broad in scope than claim 1 of the US ‘279 patent. Therefore, any patent granted on the current application would result in the unjustifiable timewise extension of the monopoly granted on claim 2 of the U.S. Patent No. 12,205,279.
Claim 2:
Regarding claim 2, claim 2 compares to claim 2 of the US ‘279 patent as indicated below:
Instant Application 18/904,590
U.S. Patent No. 12,205,279
Notes
The method of claim 1 wherein acquiring comprises acquiring the MR training data for an MR protocol using multiple repetitions and wherein machine training comprises training the neural network to output an image for each one of the multiple repetitions,
The method of claim 1 wherein acquiring comprises acquiring the MR training data for an MR protocol using multiple repetitions and wherein machine training comprises training the neural network to output an image for each one of the multiple repetitions,
Verbatim the same
a first loss used in the training being based on an aggregation of the images from the multiple repetitions.
a first loss used in the training being based on an aggregation of the images from the multiple repetitions.
Verbatim the same
As can be seen above, claim 2 of the current application is more broad in scope when considering the dependency than claim 2 of the US ‘279 patent. Therefore, any patent granted on the current application would result in the unjustifiable timewise extension of the monopoly granted on claim 2 of the U.S. Patent No. 12,205,279.
Claim 3
Regarding claim 3, claim 3 compares to claim 3 of the US ‘279 patent as indicated below:
Instant Application 18/904,590
U.S. Patent No. 12,205,279
Notes
The method of claim 2 wherein the aggregation is an average in a complex-value domain where the first loss comprises a combination of a complex-value loss and a magnitude-based loss.
The method of claim 2 wherein the aggregation is an average in a complex-value domain where the first loss comprises a combination of a complex-value loss and a magnitude-based loss.
Verbatim the same
As can be seen above, claim 3 of the current application is more broad in scope when considering claim dependency than claim 3 of the US ‘279 patent. Therefore, any patent granted on the current application would result in the unjustifiable timewise extension of the monopoly granted on claim 3 of the U.S. Patent No. 12,205,279.
Claim 4:
Regarding claim 4, claim 4 compares to claim 5 of the US ‘279 patent as indicated below:
Instant Application 18/904,590
U.S. Patent No. 12,205,279
Notes
The method of claim 1 wherein machine training comprises machine training where the phase correction is derived from the MR training data and applied to the output.
The method of claim 1 wherein machine training comprises machine training where the phase correction is derived from the MR training data and applied to the output.
Verbatim the same
As can be seen above, claim 4 of the current application is broader in scope (when incorporating dependency) than claim 5 of the US ‘279 patent. Therefore, any patent granted on the current application would result in the unjustifiable timewise extension of the monopoly granted on claim 5 of the U.S. Patent No. 12,205,279.
Claim 5:
Regarding claim 5, claim 5 compares to claim 6 of the US ‘279 patent as indicated below:
Instant Application 18/904,590
U.S. Patent No. 12,205,279
Notes
The method of claim 1 wherein machine training comprises machine training where the phase correction is derived from the output.
The method of claim 1 wherein machine training comprises machine training where the phase correction is derived from the output.
Verbatim the same
As can be seen above, claim 5 of the current application is broader in scope (when incorporating dependency) than claim 6 of the US ‘279 patent. Therefore, any patent granted on the current application would result in the unjustifiable timewise extension of the monopoly granted on claim 6 of the U.S. Patent No. 12,205,279.
Claim 6:
Regarding claim 6, claim 6 compares to claim 7 of the US ‘279 patent as indicated below:
Instant Application 18/904,590
U.S. Patent No. 12,205,279
Notes
The method of claim 1 wherein machine training comprises machine training where the phase correction is derived from the MR training data and applied to the ground truth representations
The method of claim 1 wherein machine training comprises machine training where the phase correction is derived from the MR training data and applied to the ground truth representations
Verbatim the same
As can be seen above, claim 6 of the current application is more broad in scope when considering the dependency than claim 7 of the US ‘279 patent. Therefore, any patent granted on the current application would result in the unjustifiable timewise extension of the monopoly granted on claim 7 of the U.S. Patent No. 12,205,279.
Claim 7:
Regarding claim 7, claim 7 compares to claim 8 of the US ‘279 patent as indicated below:
Instant Application 18/904,590
U.S. Patent No. 12,205,279
Notes
The method of claim 1 wherein machine training comprises applying the phase correction to the output and the ground truth representations.
The method of claim 1 wherein machine training comprises applying the phase correction to the output and the ground truth representations.
Verbatim the same
As can be seen above, claim 7 of the current application is more broad in scope when considering the claim dependency than claim 8 of the US ‘279 patent. Therefore, any patent granted on the current application would result in the unjustifiable timewise extension of the monopoly granted on claim 8 of the U.S. Patent No. 12,205,279.
Claim 8:
Regarding claim 8, claim 8 compares to claim 11 of the US ‘279 patent as indicated below:
Instant Application 18/904,590
U.S. Patent No. 12,205,279
Notes
A method for reconstruction of a medical image in a medical imaging system, the method comprising:
A method for reconstruction of a medical image in a medical imaging system, the method comprising:
Verbatim the same
scanning, by the medical imaging system, a patient, the scanning resulting in scan data;
scanning, by the medical imaging system, a patient, the scanning resulting in scan data, wherein the scan data comprises measurements over a series of scans of an imaging protocol;
Instant application more broad
reconstructing, by an image processor applying a machine-learned model, a scan image, the machine-learned model having been trained with application of phase correction; and
reconstructing, by an image processor applying a machine-learned model, a scan image, the machine-learned model having been trained with application of phase correction,
Verbatim the same
wherein reconstructing comprises reconstructing the scan image for each of the scans of the series, the machine-learned model having been trained for use for each scan of the imaging protocol based on a loss function from a combination of training images from different scans for the imaging protocol, wherein the phase correction was separately calculated for each ground truth image for each of the scans of the imaging protocol, an averaged ground truth was generated from the phase corrected ground truths and applied for a complex-valued loss;
Instant application more broad
combining the scan images into the medical image; and
Instant application more broad
displaying the medical image based on the scan image.
displaying the medical image based on the scan image.
Verbatim the same
As can be seen above, claim 8 of the current application is more broad in scope than claim 11 of the US ‘279 patent. Therefore, any patent granted on the current application would result in the unjustifiable timewise extension of the monopoly granted on claim 11 of the U.S. Patent No. 12,205,279.
Claim 9:
Regarding claim 9, claim 9 compares to claim 11 of the US ‘279 patent as indicated below:
Instant Application 18/904,590
U.S. Patent No. 12,205,279
Notes
The method of claim 8 wherein the scan data comprises measurements over a series of scans of an imaging protocol
wherein the scan data comprises measurements over a series of scans of an imaging protocol;
Verbatim the same
wherein reconstructing comprises reconstructing the scan image for each of the scans of the series,
wherein reconstructing comprises reconstructing the scan image for each of the scans of the series,
Verbatim the same
the machine-learned model having been trained for use for each scan of the imaging protocol based on a loss function from a combination of training images from different scans for the imaging protocol; and
the machine-learned model having been trained for use for each scan of the imaging protocol based on a loss function from a combination of training images from different scans for the imaging protocol,
Verbatim the same
further comprising combining the scan images into the medical image.
combining the scan images into the medical image; and
Verbatim the same
As can be seen above, claim 9 of the current application is more broad when incorporating dependency in scope than claim 11 of the US ‘279 patent. Therefore, any patent granted on the current application would result in the unjustifiable timewise extension of the monopoly granted on claim 11 of the U.S. Patent No. 12,205,279.
Claim 10:
Regarding claim 10, claim 10 compares to claim 13 of the US ‘279 patent as indicated below:
Instant Application 18/904,590
U.S. Patent No. 12,205,279
Notes
A system for reconstruction in medical imaging, the system comprising:
A system for reconstruction in medical imaging, the system comprising:
Verbatim the same
a medical scanner configured to repetitively scan a region of a patient pursuant to a protocol, the scan providing scan data in repetitions of the protocol;
a medical scanner configured to repetitively scan a region of a patient pursuant to a protocol, the scan providing scan data in repetitions of the protocol;
Verbatim the same
an image processor configured to reconstruct, for each of the repetitions, a representation of the region, the image processor configured to reconstruct by application of a machine-learned model having been trained for the reconstruction for each of the repetitions based on a loss function between an aggregate of outputs from the repetitions of the protocol and a ground truth
an image processor configured to reconstruct, for each of the repetitions, a representation of the region, the image processor configured to reconstruct by application of a machine-learned model having been trained for the reconstruction for each of the repetitions based on a loss function between an aggregate of outputs from the repetitions of the protocol and a ground truth,
Verbatim the same
the loss function having been a complex-valued loss based on the output for each of the repetitions or component images of the ground truth being phase corrected,
the loss function having been a complex-valued loss based on the output for each of the repetitions and component images of the ground truth being phase corrected,
Instant application more broad (or vs and)
the image processor further configured to combine the representations from the repetitions; and
the image processor further configured to combine the representations from the repetitions; and
Verbatim the same
a display configured to display an image of the region from the combined representations.
a display configured to display an image of the region from the combined representations.
Verbatim the same
As can be seen above, claim 10 of the current application is more broad in scope than claim 13 of the US ‘279 patent. Therefore, any patent granted on the current application would result in the unjustifiable timewise extension of the monopoly granted on claim 13 of the U.S. Patent No. 12,205,279.
Claim 11:
Regarding claim 11, claim 11 compares to claim 14 of the US ‘279 patent as indicated below:
Instant Application 18/904,590
U.S. Patent No. 12,205,279
Notes
The system of claim 10 wherein the machine-learned model was trained with the phase corrections for the outputs having been derived from the component images of the ground truth.
The system of claim 13 wherein the machine-learned model was trained with the phase corrections for the outputs having been derived from the component images of the ground truth.
Verbatim the same
As can be seen above, claim 11 of the current application is more broad in scope (when incorporating dependency) than claim 14 of the US ‘279 patent. Therefore, any patent granted on the current application would result in the unjustifiable timewise extension of the monopoly granted on claim 14 of the U.S. Patent No. 12,205,279.
Claim 12:
Regarding claim 12, claim 12 compares to claim 15 of the US ‘279 patent as indicated below:
Instant Application 18/904,590
U.S. Patent No. 12,205,279
Notes
The system of claim 11 wherein the machine-learned model was trained with the phase corrections having been derived from the component images by low pass filtering and extraction from results of the low pass filtering.
The system of claim 14 wherein the machine-learned model was trained with the phase corrections having been derived from the component images by low pass filtering and extraction from results of the low pass filtering.
Verbatim the same
As can be seen above, claim 12 of the current application is more broad in scope (when incorporating dependency) than claim 15 of the US ‘279 patent. Therefore, any patent granted on the current application would result in the unjustifiable timewise extension of the monopoly granted on claim 15 of the U.S. Patent No. 12,205,279.
Claim 13:
Regarding claim 13, claim 13 compares to claim 17 of the US ‘279 patent as indicated below:
Instant Application 18/904,590
U.S. Patent No. 12,205,279
Notes
The system of claim 10 wherein the ground truth comprised an aggregated ground truth.
The system of claim 13 wherein the ground truth comprised an aggregated ground truth.
Verbatim the same
As can be seen above, claim 13 of the current application is more broad in scope (when incorporating dependency) than claim 17 of the US ‘279 patent. Therefore, any patent granted on the current application would result in the unjustifiable timewise extension of the monopoly granted on claim 17 of the U.S. Patent No. 12,205,279.
Allowable Subject Matter
Claims 2-4 and 6-7 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims, and the double patenting rejection was overcome.
Claims 10-13 would allowed if the double patenting rejection was overcame.
Claims 2-3:
The following is a statement of reasons for the indication of allowable subject matter: the closest prior arts of record teach methods of using machine learning techniques to perform phase correction on MRI images. However, none of them alone or in any combination teaches outputting an image for each iteration of acquiring data where a first loss used for training is based on aggregating the images from the iterations.
The closest prior art Guidon discloses training a machine learning model to perform phase correction of MRI images (abstract). The training is performed based on pairs of clean images and corrupt images, thus determining the relationship between the two (abstract). Further, Guidon does implement loss functions within the neural network training (see paragraph 0069).
However, Guidon fails to disclose outputting an image for each iteration of acquiring data where a first loss used for training is based on aggregating the images from the iterations.
Claim 4:
The following is a statement of reasons for the indication of allowable subject matter: the closest prior arts of record teach methods of using machine learning techniques to perform phase correction on MRI images. However, none of them alone or in any combination teaches applying phase correction to the output of the neural network.
The closest prior art Guidon discloses training a machine learning model to perform phase correction of MRI images (abstract). The training is performed based on pairs of clean images and corrupt images, thus determining the relationship between the two (abstract). Further, Guidon applies the phase correction to the images to generate an output, but doesn't apply the phase correction to the output once the output itself is generated (see figure 2B; the phase correction occurs before output generation).
Thus, Guidon fails to disclose applying phase correction to the output of the neural network
Claim 6:
The following is a statement of reasons for the indication of allowable subject matter: the closest prior arts of record teach methods of using machine learning techniques to perform phase correction on MRI images. However, none of them alone or in any combination teaches applying phase correction to the ground truths of the neural network.
The closest prior art Guidon discloses training a machine learning model to perform phase correction of MRI images (abstract). The training is performed based on pairs of clean images and corrupt images, thus determining the relationship between the two (abstract). Further, Guidon applies the phase correction to the images to generate an output, but doesn't apply the phase correction to the output once the output itself is generated or to the ground truths (see figure 2B; the phase correction occurs before output generation; and ground truths are used for training as targets, the phase correction is derived from the ground truths, not applied to it).
Thus, Guidon fails to disclose applying phase correction to the ground truths of the neural network.
Claim 7:
The following is a statement of reasons for the indication of allowable subject matter: the closest prior arts of record teach methods of using machine learning techniques to perform phase correction on MRI images. However, none of them alone or in any combination teaches applying phase correction to the output and the ground truths of the neural network.
The closest prior art Guidon discloses training a machine learning model to perform phase correction of MRI images (abstract). The training is performed based on pairs of clean images and corrupt images, thus determining the relationship between the two (abstract). Further, Guidon applies the phase correction to the images to generate an output, but doesn't apply the phase correction to the output once the output itself is generated or to the ground truths (see figure 2B; the phase correction occurs before output generation; and ground truths are used for training as targets, the phase correction is derived from the ground truths, not applied to it).
Thus, Guidon fails to disclose applying phase correction to the output and the ground truths of the neural network.
Claims 10-13:
The following is a statement of reasons for the indication of allowable subject matter: the closest prior arts of record teach methods of using machine learning techniques to perform phase correction on MRI images. However, none of them alone or in any combination teaches reconstruction of medical scan images using a machine learning model which was trained based on a loss function between an aggregate of outputs from the repetitions of the protocol and a ground truth, further the loss function is a complex-valued loss based on the output for each of the repetitions and component images of the ground truth being phase corrected.
The closest prior art Guidon discloses training a machine learning model to perform phase correction of MRI images (abstract). The training is performed based on pairs of clean images and corrupt images, thus determining the relationship between the two (abstract). Further, Guidon applies the phase correction to the images to generate an output, but doesn't apply the phase correction to the ground truths (see figure 2B; the phase correction occurs before output generation; and ground truths are used for training as targets, the phase correction is derived from the ground truths, not applied to it).
Thus, Guidon fails to disclose reconstruction of medical scan images using a machine learning model which was trained based on a loss function between an aggregate of outputs from the repetitions of the protocol and a ground truth, further the loss function is a complex-valued loss based on the output for each of the repetitions and component images of the ground truth being phase corrected.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
U.S. Publication No. 2021/0150783 to Arberet et al. discloses, “For magnetic resonance imaging reconstruction, using a cost function independent of the ground truth and many samples of k-space measurements, machine learning is used to train a model with unsupervised learning (abstract).”
U.S. Publication No. 2021/0123999 to An et al. discloses, “A computer-implemented method of reconstructing magnetic resonance (MR) images of a subject is provided. The method includes executing a neural network model for analyzing MR images, wherein the neural network model is trained with a first subset of training MR images as inputs and a second subset of the training MR images as outputs, wherein each image in the first subset is acquired during a neighboring respiratory phase of at least one of the images in the second subset (abstract).”
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Courtney J. Windsor whose telephone number is (571)272-3956. The examiner can normally be reached Monday - Friday 8:00 - 4:00.
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, John Villecco can be reached at 571-272-7319. 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.
/COURTNEY JOAN NELSON/Primary Examiner, Art Unit 2661
Prosecution Insights