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 .
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.
Claim(s) 1, 13-14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Botnar (US 20190346522 A1) in view of Huang (US 20200096587 A1).
Regarding claim 1, Botnar discloses a computer implemented method for magnetic resonance (MR) image reconstruction ([0018] a method of reconstructing MR image data from undersampled k-space data; [0063] a magnetic resonance apparatus comprising a computing system), comprising:
obtaining MR measurement data representing an imaged object ([0072] the original acquired k-space data is transformed into MR image data (e.g. a MR image); [0079] step 101 comprises obtaining k-space data of an image region of a subject (see also Fig. 1)); and
generating a reconstructed MR image based on the MR measurement data, wherein the generation of the reconstructed MR image includes performing at least two reconstruction iterations (Fig. 4; [0097] the optimization problem iterates between a data consistency step which reconstructs a high-resolution isotropic MR volume x and a low-complexity 3D patch-based denoising step which provides a reconstructed volume as prior for the next step),
for each iteration of the at least two reconstruction iterations: a) receiving a prior MR image for the respective iteration (Fig. 4, [0101] MR reconstruction is performed using a conjugate gradient descent and uses the 3D denoised volume obtained from stage 2 as prior knowledge);
b) optimizing a predefined first loss function, which depends on the MR measurement data and on the prior MR image, to generate an optimized MR image ([0101] MR reconstruction (Fig. 4: Stage 1) is performed using a conjugate gradient descent and uses the 3D denoised volume obtained from stage 2 as prior knowledge, the data consistency iteration step is of the form of an Augmented Lagrangian (see equation)); and
c) applying a model for image enhancement to the optimized MR image to generate an enhanced MR image ([0102] a 3D block-matching 2,5 algorithm is used to exploit redundancies in the volume x…the de-noised 3D blocks are then placed back to their original positions by averaging),
wherein the prior MR image of the respective iteration corresponds to the enhanced MR image of a preceding iteration unless the respective iteration corresponds to an initial iteration of the at least two iterations, and wherein the prior MR image of the initial iteration corresponds to a predefined initial image ([0101] MR reconstruction is performed using a conjugate gradient descent and uses the 3D denoised volume obtained from stage 2 as prior knowledge (x=b=0 initially, then updated by stage 2)).
Botnar fails to disclose a trained machine learning model.
Huang, in a related system from the same field of endeavor of performing enhancement and reconstruction on magnetic resonance images including iterating on a previous image (Abstract), discloses applying a trained machine learning model for image enhancement ([0060] the image enhancement algorithm may be a total variation model of a deep neural network; [0127] in the magnetic resonance imaging method provided by examples of the present disclosure, the obtained third image is subject to repeated enhancement processing and constrained reconstruction, in this way the quality of the magnetic resonance image is further improved).
It would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to combine Huang with Botnar and apply a trained machine learning model, as disclosed by Huang, as part of a computer implemented method for magnetic resonance image reconstruction, as disclosed by Botnar, for the purpose of improving magnetic resonance image quality (see Huang: [0092], [0095], [0127]).
Regarding claim 13, Botnar in view of Huang discloses the method of claim 1 as applied above. Botnar further discloses a data processing apparatus comprising: one or more processors; and memory storing instructions that, when executed by the one or more processors, cause the apparatus to perform the method ([0141] the described elements may be configured to reside on a tangible, persistent, addressable storage medium and may be configured to execute on one or more processors; [0001] present disclosure relates to a method of reconstructing magnetic resonance (MR) image data, a computer readable medium, and a MR imaging apparatus).
Regarding claim 14, Botnar in view of Huang discloses the method of claim 1 as applied above. Botnar further discloses one or more non-transitory media storing instructions that, when executed by one or more processors, cause the one or more processors to perform the method ([0141] the described elements may be configured to reside on a tangible, persistent, addressable storage medium and may be configured to execute on one or more processors; [0001] present disclosure relates to a method of reconstructing magnetic resonance (MR) image data, a computer readable medium, and a MR imaging apparatus).
Claim(s) 10, 15, 17-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Botnar (US 20190346522 A1) in view of Huang (US 20200096587 A1) in further view of Tamir (Tamir, Jonathan I., X. Yu Stella, and Michael Lustig. "Unsupervised deep basis pursuit: Learning reconstruction without ground-truth data." Proceedings of the 27th Annual Meeting of ISMRM. 2019.).
Regarding claim 10, Botnar in view of Huang discloses the computer implemented method according to claim 1 as applied above. Botnar further discloses receiving magnetic resonance data and a ground truth reconstructed MR image ([0072] the original acquired k-space data is transformed into MR image data (e.g. a MR image); [0079] step 101 comprises obtaining k-space data of an image region of a subject (see also Fig. 1)); and performing at least two iterations (Fig. 4; [0097] the optimization problem iterates between a data consistency step which reconstructs a high-resolution isotropic MR volume x and a low-complexity 3D patch-based denoising step which provides a reconstructed volume as prior for the next step), wherein, for each iteration of the at least two iterations: receiving a prior MR image for the respective iteration ((Fig. 4, [0101] MR reconstruction is performed using a conjugate gradient descent and uses the 3D denoised volume obtained from stage 2 as prior knowledge); generating an optimized MR image by optimizing a predefined second loss function, which depends on the MR data and on the prior MR image ([0101] MR reconstruction (Fig. 4: Stage 1) is performed using a conjugate gradient descent and uses the 3D denoised volume obtained from stage 2 as prior knowledge, the data consistency iteration step is of the form of an Augmented Lagrangian (see equation)); and generating an enhanced MR image by applying a model to the optimized MR image, wherein the prior MR image of the respective iteration corresponds to the enhanced MR image of a preceding iteration, unless the respective iteration corresponds to an initial iteration of the at least two iterations, and the prior MR image of the initial iteration corresponds to a predefined initial image ([0101] MR reconstruction is performed using a conjugate gradient descent and uses the 3D denoised volume obtained from stage 2 as prior knowledge (x=b=0 initially, then updated by stage 2)).
Botnar fails to disclose a method for training a machine learning model, receiving training MR data and the ground truth data corresponding to the training data, the iterations being training iterations, applying a trained machine learning model, evaluating a predefined third loss function depending on the enhanced training MR image of a final training iteration of the at least two training iterations and the ground truth reconstructed MR image; and updating the MLM depending on a result of the evaluation of the third loss function.
Huang, in a related system from the same field of endeavor of performing enhancement and reconstruction on magnetic resonance images including iterating on a previous image (Abstract), discloses applying a trained machine learning model for image enhancement ([0060] the image enhancement algorithm may be a total variation model of a deep neural network; [0127] in the magnetic resonance imaging method provided by examples of the present disclosure, the obtained third image is subject to repeated enhancement processing and constrained reconstruction, in this way the quality of the magnetic resonance image is further improved).
It would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to combine Huang with Botnar and apply a trained machine learning model, as disclosed by Huang, as part of a computer implemented method for magnetic resonance image reconstruction, as disclosed by Botnar, for the purpose of improving magnetic resonance image quality (see Huang: [0092], [0095], [0127]).
Tamir, in a related system from the same field of endeavor of using a trained machine learning model to reconstruct magnetic resonance images (pg. 1, Synopsis), discloses a method for training a machine learning model ([pg. 1, Introduction] we present an approach to model-based deep learning…during training, we jointly solve for the CNN weights and the reconstructed training set images), receiving training MR data and the ground truth data corresponding to the training data ([pg. 1, Introduction] the training data usually consist of pairs of under-sampled k-space and the desire ground-truth image…we compare the deep basis pursuit (DBP) with and without supervised learning; [pg. 1, Theory] when both input and ground truth training data are available, the network weights can be trained in a traditional end-to-end fashion; [pg. 2, Methods] DBP was separately trained with and without ground-truth data), the iterations being training iterations ([pg. 1, Theory] for the k-th training iteration…), evaluating a predefined third loss function depending on the enhanced training MR image of a final training iteration of the at least two training iterations and the ground truth reconstructed MR image; and updating the MLM depending on a result of the evaluation of the third loss function ([pg. 2, Results and Discussion] Figure 2 shows the training loss curves and box plots of testing error, indicating a small performance gap between supervised and unsupervised learning…jointly optimizing over the images and weights can be seen as a non-linear extension to dictionary learning...highlighting the importance of a large training data set; see also Fig. 3).
It would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to combine Tamir with Botnar in view of wherein the method includes training a machine learning model, receiving training MR data and ground truth data, training iterations, and evaluating a third loss function, as disclosed by Tamir, as part of a computer implemented method for magnetic resonance image reconstruction, as disclosed by Botnar, in view of Huang, for the purpose of improving denoising and reconstruction of under-sampled MR image data (See Tamir: Synopsis, Introduction, Conclusion).
Regarding claim 15, Botnar discloses a computer implemented training method for image enhancement for use in a computer implemented method ([0018] a method of reconstructing MR image data from undersampled k-space data; [0063] a magnetic resonance apparatus comprising a computing system), the method for training comprises: receiving magnetic resonance data and a ground truth reconstructed MR image ([0072] the original acquired k-space data is transformed into MR image data (e.g. a MR image); [0079] step 101 comprises obtaining k-space data of an image region of a subject (see also Fig. 1)); and performing at least two iterations (Fig. 4; [0097] the optimization problem iterates between a data consistency step which reconstructs a high-resolution isotropic MR volume x and a low-complexity 3D patch-based denoising step which provides a reconstructed volume as prior for the next step), wherein, for each iteration of the at least two iterations: receiving a prior MR image for the respective iteration ((Fig. 4, [0101] MR reconstruction is performed using a conjugate gradient descent and uses the 3D denoised volume obtained from stage 2 as prior knowledge); generating an optimized MR image by optimizing a predefined second loss function, which depends on the MR data and on the prior MR image ([0101] MR reconstruction (Fig. 4: Stage 1) is performed using a conjugate gradient descent and uses the 3D denoised volume obtained from stage 2 as prior knowledge, the data consistency iteration step is of the form of an Augmented Lagrangian (see equation)); and generating an enhanced MR image by applying a model to the optimized MR image, wherein the prior MR image of the respective iteration corresponds to the enhanced MR image of a preceding iteration, unless the respective iteration corresponds to an initial iteration of the at least two iterations, and the prior MR image of the initial iteration corresponds to a predefined initial image ([0101] MR reconstruction is performed using a conjugate gradient descent and uses the 3D denoised volume obtained from stage 2 as prior knowledge (x=b=0 initially, then updated by stage 2)).
Botnar fails to disclose a method for training a machine learning model, receiving training MR data and the ground truth data corresponding to the training data, the iterations being training iterations, applying a trained machine learning model, evaluating a predefined third loss function depending on the enhanced training MR image of a final training iteration of the at least two training iterations and the ground truth reconstructed MR image; and updating the MLM depending on a result of the evaluation of the third loss function.
Huang, in a related system from the same field of endeavor of performing enhancement and reconstruction on magnetic resonance images including iterating on a previous image (Abstract), discloses applying a trained machine learning model for image enhancement ([0060] the image enhancement algorithm may be a total variation model of a deep neural network; [0127] in the magnetic resonance imaging method provided by examples of the present disclosure, the obtained third image is subject to repeated enhancement processing and constrained reconstruction, in this way the quality of the magnetic resonance image is further improved).
It would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to combine Huang with Botnar and apply a trained machine learning model, as disclosed by Huang, as part of a computer implemented method for magnetic resonance image reconstruction, as disclosed by Botnar, for the purpose of improving magnetic resonance image quality (see Huang: [0092], [0095], [0127]).
Tamir, in a related system from the same field of endeavor of using a trained machine learning model to reconstruct magnetic resonance images (pg. 1, Synopsis), discloses a method for training a machine learning model ([pg. 1, Introduction] we present an approach to model-based deep learning…during training, we jointly solve for the CNN weights and the reconstructed training set images), receiving training MR data and the ground truth data corresponding to the training data ([pg. 1, Introduction] the training data usually consist of pairs of under-sampled k-space and the desire ground-truth image…we compare the deep basis pursuit (DBP) with and without supervised learning; [pg. 1, Theory] when both input and ground truth training data are available, the network weights can be trained in a traditional end-to-end fashion; [pg. 2, Methods] DBP was separately trained with and without ground-truth data), the iterations being training iterations ([pg. 1, Theory] for the k-th training iteration…), evaluating a predefined third loss function depending on the enhanced training MR image of a final training iteration of the at least two training iterations and the ground truth reconstructed MR image; and updating the MLM depending on a result of the evaluation of the third loss function ([pg. 2, Results and Discussion] Figure 2 shows the training loss curves and box plots of testing error, indicating a small performance gap between supervised and unsupervised learning…jointly optimizing over the images and weights can be seen as a non-linear extension to dictionary learning...highlighting the importance of a large training data set; see also Fig. 3).
It would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to combine Tamir with Botnar in view of wherein the method includes training a machine learning model, receiving training MR data and ground truth data, training iterations, and evaluating a third loss function, as disclosed by Tamir, as part of a computer implemented method for magnetic resonance image reconstruction, as disclosed by Botnar, in view of Huang, for the purpose of improving denoising and reconstruction of under-sampled MR image data (See Tamir: Synopsis, Introduction, Conclusion).
Regarding claim 17, Botnar in view of Huang and Tamir discloses the method of claim 15 as applied above. Botnar further discloses a data processing apparatus comprising: one or more processors; and memory storing instructions that, when executed by the one or more processors, cause the apparatus to perform the method ([0141] the described elements may be configured to reside on a tangible, persistent, addressable storage medium and may be configured to execute on one or more processors; [0001] present disclosure relates to a method of reconstructing magnetic resonance (MR) image data, a computer readable medium, and a MR imaging apparatus).
Regarding claim 18, Botnar in view of Huang and Tamir discloses the method of claim 15 as applied above. Botnar further discloses one or more non-transitory media storing instructions that, when executed by one or more processors, cause the one or more processors to perform the method ([0141] the described elements may be configured to reside on a tangible, persistent, addressable storage medium and may be configured to execute on one or more processors; [0001] present disclosure relates to a method of reconstructing magnetic resonance (MR) image data, a computer readable medium, and a MR imaging apparatus).
Allowable Subject Matter
Claims 2-9, 11-12, 16 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.
The following is a statement of reasons for the indication of allowable subject matter:
Regarding claim 2, Botnar in view of Huang discloses the computer implemented method of claim 1 as applied above. Botnar fails to disclose wherein the optimization of the first loss function is carried out under variation of a variable MR image, while the prior MR image is kept constant during the optimization.
Similar reasoning applies to claims 3-9 which are dependent on claim 2.
Regarding claim 11, Botnar in view of Huang and Tamir discloses the computer implemented method of claim 10 as applied above. Botnar fails to disclose wherein: the optimization of the second loss function is carried out under variation of a variable MR image, while the training prior MR image is kept constant during the optimization; and the second loss function comprises a data term, which depends on the training MR data and on further encoded data, which is given by a predefined further MR signal model matrix applied to the variable MR image.
Similar reasoning applies to claim 12 which is dependent on claim 11. Similar reasoning applies to claim 16 which is directed to similar subject matter to claim 11.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Kamilov (US 20230122658 A1) discloses MR image reconstruction including training a deep learning neural network without ground truth data, resulting in enhanced image quality.
Nickel-87 (US 20220067987 A1) discloses MRI reconstruction including iterative optimization including multiple iterations and a predefined ground image and adjusting weights based on a loss function.
Nickel-54 (US 20220051454 A1) discloses training a CNN for performing MRI reconstruction including iterative optimization based on a loss function.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CAROLINE DEPALMA whose telephone number is (571)270-0769. The examiner can normally be reached Mon-Thurs 9:00am-4pm Eastern Time.
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, Emily Terrell can be reached at (571) 270-3717. 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.
/CAROLINE E. DEPALMA/Examiner, Art Unit 2675
/SJ Park/Primary Examiner, Art Unit 2675
Prosecution Insights