DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
Applicant's arguments filed 13 August 2026 have been fully considered but they are not persuasive.
Regarding to 103 rejections, applicant argues that Li does not disclose “a set of parameters is generated, the pose parameters being an estimation of the pose of the subject during the acquisition time of the further set of additional k-space lines, because Li’s purpose is to produce images at a target resolution, and teaches determining a processed image with a target resolution level by processing the image using the target processing model, and does not teach applying the model specifically to a dataset including the low resolution image in k-space notation and a further set of additional k-space lines as claimed (pages 10-11). Li’s disclosure of acquiring k-space data is only used to generate low-resolution and high resolution sample images for training a model to generate higher resolution images, through k-space padding and weight matrices, thus, Li does not disclose claimed “further set of additional k-space lines.” The cited paragraph [0101] of Li teaches iterative image reconstruction where central k-space data remains unchanged across multiple processing cycles, thus iterative post-processing steps, not an acquisition of additional k-space lines (pages 11-12).
Moreover, applicant argues Chen does not applying neural network to a dataset including the low-resolution image in k-space notation and a further set of additional k-space lines as Chen does not teach the claimed “further set of additional k-space lines,” rather merely discloses an accelerated scan for acquiring cardiac positioning data and slice planning including compressed sensing, parallel imaging and fast spin echo, and does not disclose “Additional” k-space data (page 12). The applicant further argues that Chen does not teach applying NN to k-space, rather to image information, and thus, does not teach applying a trained machine learning model to a dataset including low resolution image in k-space notation and a further set of additional k-space lines as recited in claim 1, thus one or ordinary skill in the art would not combine Li with Chen as Li is directed to image resolution enhancement through trained models while Chen is directed to neural network based image plane planning and pose estimation from reconstructed image data, resulting in two fundamentally distinct purpose and foundations, combination would make inoperable for their intended purpose, leading to hindsight and compete redesign of the fundamental operation and purpose (pages 13-14).
Further regarding to claims 6 and 10, applicant argues that Splitthoff merely discloses protocol parameters such as field of view are modified before the acquisition process begins, thus does not disclose “pose parameters are used to adapt field of view during the imaging protocol” such as “in the same echo train” or “in the next echo train” as claimed (page 15), thus new claim 19 is allowable over cited references (page 15).
With regards to claim 18, applicant argues with same argument as set forth in claim 1 above. Applicant further argues that Polak discloses sampling a central region of k-space but does not disclose application of trained machine learning model to a dataset including an image in k-space notation and a further set of additional k-space lines to generate pose parameters as claimed, rather Polak estimates motion parameters by minimizing a data consistency error between acquired k-space data and the forward model, resulting in iterative numerical optimization and not a trained machine learning model (pages 17-18). Applicant concludes, for similar reasons for claim 1, one would not combine distinct and incompatible operational approaches of Li, Chen and Polak to generate pose parameters for motion correction of a dataset including in k-space notation and additional k-space lines acquired during an imaging protocol using a trained machine learning model, since purposes and foundations are fundamentally distinct, and modifying Polak to operate to use machine learning lack reasonable expectation of success and combining references would alter the core functionality and intended purpose of Polak (page 19). Claims 15-17 are allowable for the same reasons as set forth above.
However, the examiner respectfully disagrees.
Li teaches acquiring a low-resolution MRI image and further set of additional k-space lines at intervals through the imaging protocol, as Li teaches explicitly acquiring first data and second data and acquiring first set of k-space data and a second set of k-space data are generated by processing the image ([0100]). Li further teaches third k-space data may be generated using SENSE technology ([0174]). Li already teaches obtaining a plurality of sample images, which includes k-space data, which is MR signal data arranged according to spatial frequency.
With respect to incorporation of Chen, the examiner has stated as follows.
Li does not further disclose further limitations wherein a set of pose parameters is generated, the pose parameters being an estimation of the pose of the subject during the acquisition time of the further set of additional k-space lines.
However, in the analogous field of endeavor in MRI imaging method, Chen teaches an MRI imaging method using MRI image data to estimate a pose of heart ([0007] and [0013]), including limitations wherein a set of pose parameters is generated, the pose parameters being an estimation of the pose of the subject during the acquisition time of the further set of additional k-space lines (low resolution scout images are used to estimate pose of a patient’ heart using a neural network, and AI scout images including compressed sensing where data is undersampled in the K-space, acquired to compare heart pose to those of heart model from initial scouting [0040]-[0041]; Figure 4 shows step 412 and step 414 and using neural network (404 and 418]) to estimate a pose of a heart).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify MRI image data as taught by Li to incorporate teaching of Chen, since using neural network to estimate a pose of a heart using MRI data was well known in the art as taught by Chen. One of ordinary skill in the art could have combined the elements as claimed by Li with no change in their respective functions, implementing neural network of estimating a pose of a subject with existing MRI data of low resolution and k-space lines within a central region of k-space, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to provide automatic adjustment planned image planes to compensate for changes in a pose of a heart throughout an entire scanning process ([0006]), and there was reasonable expectation of success.
Accordingly, Chen was incorporated for teaching “set of pose parameters” based on AI estimation of pose pf a subject with existing MRI data of low-resolution and k-space lines within a central region of k-space.
The In response to applicant's argument that the examiner's conclusion of obviousness is based upon improper hindsight reasoning, it must be recognized that any judgment on obviousness is in a sense necessarily a reconstruction based upon hindsight reasoning. But so long as it takes into account only knowledge which was within the level of ordinary skill at the time the claimed invention was made, and does not include knowledge gleaned only from the applicant's disclosure, such a reconstruction is proper. See In re McLaughlin, 443 F.2d 1392, 170 USPQ 209 (CCPA 1971). Contrary to applicant’s argument that combination would alter core and functionality of invention, Li and Chen are analogous and concerning of MRI data acquisition and processing the data, and combination would provide automatic adjustment planned image planes to compensate for changes in a pose of a heart throughout an entire scanning process ([0006]) as set forth in previous office action.
With respect to argument for Splitthoff, the examiner submits that Splittoff teaches performing a scout scan and use for setting protocol parameters including field of view and modifying the parameters for optimal result and the steps provide immediate feedback and if reacquisition is suggested, the procedure may be repeated immediately ([0033]), thus, reads on limitations of “wherein the pose parameters are used to adapt a field-of-view of the magnetic resonance image dataset during the imaging protocol.”
With respect to argument for claim 18, specifically for Polak, the examiner submits that Polak was not cited for machine learning model, but rather was incorporated for teaching motion-corrected image dataset, forward model, and encoding matrix as well as further details.
However, in the analogous field of endeavor in ultrasound imaging method, Polak teaches following limitations:
a radio frequency (RF) controller configured to drive an RF-coil comprising a multi- channel coil array (radio frequency controller configured to drive an RF- coil comprising a multi-channel coil-array [0036]);
a gradient controller configured to control gradient coils (a gradient controller configured to control gradient coils [0036]); and
a control unit configured to control the radio frequency controller and the gradient controller to execute the imaging protocol (a control unit configured to control the radio frequency controller and the gradient controller to execute the imaging protocol [0036]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify MR imaging apparatus as taught by Li to incorporate teaching of Polak, since controller controlling RF coil and gradient coil for multi-channel coil array was well known in the art as taught by Polak. One of ordinary skill in the art could have combined the elements as claimed by Li with no change in their respective functions, configuring its MRI apparatus to acquire image using a multi-channel coil array and its controller, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to provide a multi-shot imaging protocol ([0036]), and there was reasonable expectation of success.
Thus, combining prior arts would not alter the operation of prior arts, rather provide controlling RF coil, gradient coil for multi-shot imaging protocol by modifying Li’s MRI with teaching of Polak.
Therefore, rejection is proper and maintained.
Applicant’s arguments with respect to new claims 19-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 20 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 20 recites the limitation "in the same echo train" in page 8. There is insufficient antecedent basis for this limitation in the claim, since “in same echo train” was not previously recited in claims 1 and 20.
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.
Claims 1, 13, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over “Li et al.,” US 2022/0092739 (hereinafter Li) and “Chen et al.,” US 2021/0161422 (hereinafter Chen).
Regarding to claim 1, Li teaches a method for acquiring a magnetic resonance image dataset of a body part of a subject (MRI [0041], [0044]), the method comprising:
acquiring the magnetic resonance image dataset using an imaging protocol (imaging device configured to scan a subject to acquire image data [0045]),
wherein spatial encoding is performed using phase encoding gradients along at least one phase encoding direction, and frequency encoding gradients along a frequency encoding direction (During the scan, spatial encoding within the slice may be implemented by spatial encoding coils along a phase encoding direction and a frequency encoding direction [0046]), and
wherein k-space is sampled during the imaging protocol by acquiring a plurality of imaging k-space lines oriented along the frequency encoding direction, and having different positions in the at least one phase encoding direction (phase encoding direction correspond to Y direction in the k-space, the frequency encoding direction correspond to X direction in the k-space, and phase and frequency encoding direction may be modified according to the actual needs [0046]),
acquiring or providing a low-resolution magnetic resonance image of the body part (acquire first data associated with the plurality of sample images with relatively low resolution levels [0070]);
acquiring further sets of additional k-space lines within a central region of k-space at intervals throughout the imaging protocol (image processed may only include k-space data in the central region of k space [0101]); and
applying a trained machine learning model (a machine learning algorithm [0095]) to a dataset comprising the low-resolution image in k-space notation and a further set of additional k-space lines (training models using a group of sample images with relatively low resolution levels and a corresponding group of sample images with relatively high resolution levels, training data is k-space data, central region of k space [0141], [0146])
Li does not further disclose further limitations wherein a set of pose parameters is generated, the pose parameters being an estimation of the pose of the subject during the acquisition time of the further set of additional k-space lines.
However, in the analogous field of endeavor in MRI imaging method, Chen teaches an MRI imaging method using MRI image data to estimate a pose of heart ([0007] and [0013]), including limitations wherein a set of pose parameters is generated, the pose parameters being an estimation of the pose of the subject during the acquisition time of the further set of additional k-space lines (low resolution scout images are used to estimate pose of a patient’ heart using a neural network, and AI scout images including compressed sensing where data is undersampled in the K-space, acquired to compare heart pose to those of heart model from initial scouting [0040]-[0041]; Figure 4 shows step 412 and step 414 and using neural network (404 and 418]) to estimate a pose of a heart).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify MRI image data as taught by Li to incorporate teaching of Chen, since using neural network to estimate a pose of a heart using MRI data was well known in the art as taught by Chen. One of ordinary skill in the art could have combined the elements as claimed by Li with no change in their respective functions, implementing neural network of estimating a pose of a subject with existing MRI data of low resolution and k-space lines within a central region of k-space, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to provide automatic adjustment planned image planes to compensate for changes in a pose of a heart throughout an entire scanning process ([0006]), and there was reasonable expectation of success.
Regarding to claim 13, Li and Chen together disclose all limitations of claim 1 as set forth above.
Li further teaches wherein the trained machine learning model comprises a convolutional neural network ( convolutional neural network [0095]).
Regarding to claim 17, Li teaches a computer-implemented method for providing a trained machine learning model (computer instructions including program [0059] and [0129]), the computer-implemented method comprising:
receiving input training data comprising a low-resolution magnetic resonance image of a body part in k-space notation and a set of additional k-space lines from a central region of k- space (training models using a group of sample images with relatively low resolution levels and a corresponding group of sample images with relatively high resolution levels, training data is k-space data, central region of k space [0141], [0146]),
wherein the low resolution image has been derived from an example magnetic resonance image (acquire first data associated with the plurality of sample images with relatively low resolution levels [0070]),
training a machine learning model based on the input training data and the output training data (training module configured to obtain a plurality of processing models by training group of images [0076]); and
providing the trained machine learning model (trained model [0097]).
Li does not further teach receiving output training data comprising the set of pose parameters and the set of additional k-space lines has been derived from the same example magnetic resonance image after the image has been rotated, translated, or rotated and translated by a set of pose parameters.
However, in the analogous field of endeavor in MRI imaging method, Chen teaches an MRI imaging method using MRI image data to estimate a pose of heart using a neural network ([0007] and [0013]), and the set of additional k-space lines has been derived from the same example magnetic resonance image after the image has been rotated, translated by a set of pose parameters (low resolution scout images are used to estimate pose of a patient’ heart using a neural network, and AI scout images including compressed sensing where data is undersampled in the K-space, acquired to compare heart pose to those of heart model from initial scouting [0040]-[0041]; Figure 4 shows step 412 and step 414 and using neural network (404 and 418]) to estimate a pose of a heart, reposition the imaging planes to correspond to the current location and pose of the patient’s heart and cause MRI scanner to use repositioned imaging planes to perform an acquisition scan and generate an image [0016]).
The examiner further notes that repositioning image plane involve any adjustment in imaging plane, would include either rotation or translation as claimed.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify MRI image data as taught by Li to incorporate teaching of Chen, since using neural network to estimate a pose of a heart using MRI data was well known in the art as taught by Chen. One of ordinary skill in the art could have combined the elements as claimed by Li with no change in their respective functions, implementing neural network of estimating a pose of a subject with existing MRI data of low resolution and k-space lines within a central region of k-space, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to provide automatic adjustment planned image planes to compensate for changes in a pose of a heart throughout an entire scanning process ([0006]), and there was reasonable expectation of success.
Claims 2-8 are rejected under 35 U.S.C. 103 as being unpatentable over Li and Chen as applied to claim 1 above, and further in view of “Splitthoff et al.,” US 2022/0342018 (hereinafter Splitthoff).
Regarding to claim 2, Li and Chen together teach all limitations of claim 1 as set forth above.
Li and Chen do not further explicitly disclose a reference image and its details.
However, in the analogous field of endeavor in MRI imaging method, Splitthoff teaches an MRI imaging method further comprising
Of claim 2, acquiring a reference set of additional k-space lines within a central region of k-space (motion free reference data is k-space data around the center [0030]).
Of claim 4, wherein the pose parameters are used for prospective, retrospective, or prospective and retrospective motion correction of the magnetic resonance image dataset (retrospective and prospective correction [0026]), for notifying an operator, for triggering further actions, or for notifying the operator and for triggering the further actions (generating a warning for physicians and operator so that the operator may elect or to redo the scan [0040]).
Of claim 6, wherein the pose parameters are used to adapt a field-of-view of the magnetic resonance image dataset during the imaging protocol (field-of-view [0033]).
Of claim 7, wherein the pose parameters are used for retrospective motion correction of the magnetic resonance image dataset (retrospective motion correction [0026]).
Of claim 8, wherein the pose parameters are further processed and, when the pose parameters indicate that subject motion has been above a certain threshold, the method further comprises triggering alerting a user supervising during the image acquisition, aborting or restarting the acquisition of the magnetic resonance image dataset, re-acquiring the magnetic resonance data affected by the subject motion, or any combination thereof (motion assessment generated by neural network to provide motion assessment to the operator, and motion score is compared to a threshold score that quantifies the extent of motion, indicating serious motion, a warning may be provided to the operator so that the operator may elect to redo the scan or the portion of the scan [0040]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify MRI imaging method as taught by Li and Chen to incorporate teaching of Splitthoff , since using reference data and motion correction adjustment based on motion assessment was well known in the art as taught by Splitthoff. One of ordinary skill in the art could have combined the elements as claimed by Li and Chen with no change in their respective functions, implementing motion correction and further actions based on motion, using a reference data, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to prospective and retrospective motion correction ([0026]), and to make sure the region of interest is included in the field of view, or to check the exposure techniques ([0030]), and there was reasonable expectation of success.
Regarding to claim 3, Li, Chen and Splitthoff together teach all limitations of claim 2 as set forth above.
Splitthoff further discloses wherein acquiring the reference set of additional k-space lines within the central region of k-space comprises acquiring the reference set of additional k-space lines within the central region of k-space at a beginning of the imaging protocol (motion free reference may be acquired during a scout scan or may be identified from a previous scan [0030]).
Regarding to claim 5, Li and Chen together teach all limitations of claim 1 as set forth above.
Li further teach wherein the trained machine learning model is applied to a dataset comprising the low-resolution image in k-space notation, and a further set of additional k-space lines (training models using a group of sample images with relatively low resolution levels and a corresponding group of sample images with relatively high resolution levels, training data is k-space data, central region of k space [0141], [0146]).
Li and Chen do not further disclose reference k-space lines.
However, In the analogous field of endeavor in MRI imaging method, Splitthoff teaches acquiring a reference set of additional k-space lines within a central region of k-space (motion free reference data is k-space data around the center [0030]), and a neural network with training data including a reference data ([0048]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify MRI imaging method as taught by Li and Chen to incorporate teaching of Splitthoff , since motion correction using a reference k-space data was well known in the art as taught by Splitthoff. One of ordinary skill in the art could have combined the elements as claimed by Li and Chen with no change in their respective functions, implementing motion correction using a reference data, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to estimate baseline, to make sure the region of interest is included in the field of view, or to check the exposure techniques ([0030]), and there was reasonable expectation of success.
Claims 9 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Li and Chen as applied to claim 1 above, and further in view of “Polak et al.,” US 2022/0326330 (hereinafter Polak).
Regarding to claims 9 and 12, Li and Chen together teach all limitations of claim 1 as set forth above.
Li and Chen do not further teach timing of acquisition and using a multi-channel coil array as claimed.
However, in the analogous field of endeavor in MRI imaging method, Polak teaches an MRI imaging with following details:
Of claim 9, wherein the low-resolution image has a different magnetic resonance contrast than the further sets of additional k-space lines, and is acquired in a calibration imaging scan performed before the imaging protocol (low resolution scout image acquired with same or different imaging protocol than high resolution image data set, having slightly differing contrast to the imaging protocol [0025]).
Of claim 12, wherein the magnetic resonance image dataset is acquired using a multi-channel coil array (imaging protocol uses a 3D parallel imaging technique where image data set is acquired using a multi-channel coil array [0028]), and wherein the low-resolution image in k-space notation and the further set of additional k-space lines are pre-processed by removing a peripheral region of k-space, by reducing a number of channels, or by removing the peripheral region of k-space and by reducing the number of channels (sub-sampling [0039] and coil compression that multi-channel k-space data was compressed to a lower number of coils [0078]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify MRI imaging acquisition as taught by Li to incorporate teaching of Polak, since multi-channel array and different contrast for low/high resolution image was well known in the art as taught by Polak. One of ordinary skill in the art could have combined the elements as claimed by Li and Chen with no change in their respective functions, configuring multi-channel array for MRI acquisition and imaging low resolution image with different contrast, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to (1) provide scout image (low resolution) with different imaging protocol from high resolution image ([0025]), and to (2) reduce computational footprint of the motion optimization ([0078]), and there was reasonable expectation of success.
Claims 10-11 are rejected under 35 U.S.C. 103 as being unpatentable over Li and Chen as applied to claim 1 above, and further in view of “Polak et al.,” US 2022/0326330 (hereinafter Polak), “Daniel et al.,” US 2019/0355157 (hereinafter Daniel), and “Splitthoff et al.,” US 2022/0342018 (hereinafter Splitthoff).
Regarding to claim 10, Li and Chen together teach all limitations of claim 1 as set forth above.
Li and Chen do not further teach echo trains and acquisition details of k-space line data as claimed.
However, in the analogous field of endeavor in MRI imaging method, Polak teaches
wherein the imaging protocol comprises acquiring a plurality of echo trains, each echo train of the plurality of echo trains comprising a plurality of echoes (echo train including several echoes [0014]), wherein one k-space line is sampled during one echo (one k-space line acquired during one echo [0014]), and wherein at least one further set of additional k-space lines is acquired in at least some echo trains of the plurality of echo trains (Figure 2 shows additional k-space lines acquired in echo trains [0061]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify k-space data acquisition as taught by Li and Chen to incorporate teaching of Polak, since acquiring echo trains and sampling k-pace line during echo train was well known in the art as taught by Polak. One of ordinary skill in the art could have combined the elements as claimed by Li with no change in their respective functions, configuring acquisition of k-space line to be in echo train, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to provide a fast imaging protocol ([0014]), and there was reasonable expectation of success.
Polak is silent in wherein at least one further set of additional k-space lines is acquired in at least some echo trains of the plurality of echo trains, preferably at the beginning of the echo train.
However, in MRI imaging method, Daniel teaches acquiring central k-space earlier in the echo train ([0043]). Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify k-space line acquisition in echo train as taught by Polak to incorporate teaching of Daniel, since k-space line acquisition in earlier part of the echo train was well known in the art as taught by Daniel. One of ordinary skill in the art could have combined the elements as claimed by Polak with no change in their respective functions, acquiring k-space line at earlier part of the echo train, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to avoid the estimation of the low- resolution phase from the central k-space data ([0043]), and there was reasonable expectation of success.
Polak does not further disclose wherein the pose parameters estimated from a further set of additional k-space lines is used to adapt a field-of-view of the magnetic resonance image dataset in the same echo train in which the further set of additional k-space lines is acquired, or in the next echo train.
However, in the analogous field of endeavor in MRI imaging method, Splitthoff teaches that based on scout can, position of the slices, protocol parameters such as field-of-view can be modified to optimize for particular patient’s anatomy, in acquiring MR data as k-space data in a series of echo trains ([0033]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify adjusting imaging parameters as taught by Li and Chen to incorporate teaching of Splitthoff, since adjusting field of view was well known in the art as taught by Splitthoff. One of ordinary skill in the art could have combined the elements as claimed by Li and Chen with no change in their respective functions, using a pose of a patient’s anatomy to provide adjustment for further imaging as disclosed by Chen to include a field of view adjustment in MR data acquisition as k-space data in echo train as taught by Splitthoff, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to provide a field of view optimization for particular patient’s anatomy ([0033]), and there was reasonable expectation of success.
Regarding to claim 11, Li, Chen, Polak, Daniel and Splitthoff together and collectively teach all limitations of claim 10 as set forth above.
Daniel further teaches wherein the at least one further set of additional k-space lines is acquired in the at least some echo trains at the beginning of the echo train ([0043]).
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Li and Chen as applied to claim 13 above, and further in view of “Braun et al.,” US 2019/0128989 (hereinafter Braun).
Regarding to claim 14, Li and Chen together teach all limitations of claim 13 as set forth above.
Li and Chen disclose convolutional neural network but does not specifically disclose it is a DenseNet.
However, in the analogous field of endeavor in MRI imaging method, Braun teaches correcting motion artifacts in MRI image data, using machine learning algorithm of convolutional network, a DenseNet ([0037]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify convolutional neural network as taught by Li to incorporate teaching of Braun, since DenseNet was well known in the art as taught by Braun. One of ordinary skill in the art could have combined the elements as claimed by Li with no change in their respective functions, configuring convolutional neural network to implement DenseNet, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to provide neural network with feed-forward connection of algorithms ([0037]), and there was reasonable expectation of success.
Claims 15-16 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over “Li et al.,” US 2022/0092739 (hereinafter Li) and “Chen et al.,” US 2021/0161422 (hereinafter Chen), and “Polak et al.,” US 2022/0326330 (hereinafter Polak).
Regarding to claim 15, Li teaches a method for generating a motion-corrected magnetic resonance image dataset of an object (motion artifact [0185]), the method comprising:
receiving k-space data acquired using an acquisition method (k-space data generated [0007]), the acquisition method comprising:
acquiring a magnetic resonance image dataset using an imaging protocol (imaging device configured to scan a subject to acquire image data [0045]), wherein spatial encoding is performed using phase encoding gradients along at least one phase encoding direction, and frequency encoding gradients along a frequency encoding direction (During the scan, spatial encoding within the slice may be implemented by spatial encoding coils along a phase encoding direction and a frequency encoding direction [0046]), and
wherein k-space is sampled during the imaging protocol by acquiring a plurality of imaging k-space lines oriented along the frequency encoding direction, and having different positions in the at least one phase encoding direction (phase encoding direction correspond to Y direction in the k-space, the frequency encoding direction correspond to X direction in the k-space, and phase and frequency encoding direction may be modified according to the actual needs [0046]),
acquiring or providing a low-resolution magnetic resonance image of a body part (acquire first data associated with the plurality of sample images with relatively low resolution levels [0070]);
acquiring further sets of additional k-space lines within a central region of k-space at intervals throughout the imaging protocol (image processed may only include k-space data in the central region of k space [0101]); and
applying a trained machine learning model (a machine learning algorithm [0095]) to a dataset comprising the low-resolution image in k-space notation and a further set of additional k-space lines (training models using a group of sample images with relatively low resolution levels and a corresponding group of sample images with relatively high resolution levels, training data is k-space data, central region of k space [0141], [0146])
Li does not teach estimating a pose from by machine learning model.
However, in the analogous field of endeavor in MRI imaging method, Chen teaches an MRI imaging method using MRI image data to estimate a pose of heart ([0007] and [0013]), including limitations wherein a set of pose parameters is generated, the pose parameters being an estimation of the pose of the subject during the acquisition time of the further set of additional k-space lines (low resolution scout images are used to estimate pose of a patient’ heart using a neural network, and AI scout images including compressed sensing where data is undersampled in the K-space, acquired to compare heart pose to those of heart model from initial scouting [0040]-[0041]; Figure 4 shows step 412 and step 414 and using neural network (404 and 418]) to estimate a pose of a heart).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify MRI image data as taught by Li to incorporate teaching of Chen, since using neural network to estimate a pose of a heart using MRI data was well known in the art as taught by Chen. One of ordinary skill in the art could have combined the elements as claimed by Li with no change in their respective functions, implementing neural network of estimating a pose of a subject with existing MRI data of low resolution and k-space lines within a central region of k-space, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to provide automatic adjustment planned image planes to compensate for changes in a pose of a heart throughout an entire scanning process ([0006]), and there was reasonable expectation of success.
Li and Chen do not further teach motion-corrected image dataset, forward model, and encoding matrix as well as further details.
However, in the analogous field of endeavor in ultrasound imaging method, Polak teaches following limitations:
receiving estimated pose parameters for each further set of additional k-space lines ( k-space data used to estimate motion [0091]);
estimating the motion-corrected magnetic resonance image dataset ( motion-corrected image data set [0029]), the estimating of the motion-corrected magnetic resonance image dataset comprising minimizing the data consistency error between the k-space data acquired in the imaging protocol and a forward model described by an encoding matrix (minimizing data consistency error of the forward model [0072]),
wherein the encoding matrix includes the pose parameters for each further set of additional k-space lines and Fourier encoding (encoding matrix includes the effects of rigid-body motion for each shot, Fourier encoding [0031] and [0039]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify MRI image data as taught by Li to incorporate teaching of Polak, since estimating motion of k-space data, minimizing error to forward model, and encoding matrix was well known in the art as taught by Polak. One of ordinary skill in the art could have combined the elements as claimed by Li with no change in their respective functions, estimating motion correction of MRI datasets using encoding matrix and forward model, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to estimate motion corrected image dataset ([0031]), and there was reasonable expectation of success.
Regarding to claim 16, Li, Chen, and Polka together teach all limitation of claim 15 as set forth above.
Polka further teaches wherein the encoding matrix further includes subsampling, coil sensitivities of a multi-channel coil array, or a combination thereof ( multi-channel k-space data acquired using a multi-channel coil array [0030]).
Regarding to claim 18, Li teaches a magnetic resonance imaging apparatus comprising:
a processor configured to acquire a magnetic resonance image dataset of a body part of a subject (processor process data obtained from the imaging device [0059]), the acquisition comprising:
acquisition of the magnetic resonance image dataset using an imaging protocol (imaging device configured to scan a subject to acquire image data [0045]),
wherein spatial encoding is performed using phase encoding gradients along at least one phase encoding direction, and frequency encoding gradients along a frequency encoding direction (During the scan, spatial encoding within the slice may be implemented by spatial encoding coils along a phase encoding direction and a frequency encoding direction [0046]), and
wherein k-space is sampled during the imaging protocol by acquiring a plurality of imaging k- space lines oriented along the frequency encoding direction, and having different positions in the at least one phase encoding direction (phase encoding direction correspond to Y direction in the k-space, the frequency encoding direction correspond to X direction in the k-space, and phase and frequency encoding direction may be modified according to the actual needs [0046]),
acquisition or provision of a low-resolution magnetic resonance image of the body part (acquire first data associated with the plurality of sample images with relatively low resolution levels [0070]);
acquisition of further sets of additional k-space lines within a central region of k- space at intervals throughout the imaging protocol (image processed may only include k-space data in the central region of k space [0101]); and
application of a trained machine learning model to a dataset comprising the low- resolution image in k-space notation and a further set of additional k-space lines (training models using a group of sample images with relatively low resolution levels and a corresponding group of sample images with relatively high resolution levels, training data is k-space data, central region of k space [0141], [0146]),
Li does not teach estimating a pose from by machine learning model.
However, in the analogous field of endeavor in MRI imaging method, Chen teaches an MRI imaging method using MRI image data to estimate a pose of heart ([0007] and [0013]), including limitations wherein a set of pose parameters is generated, the pose parameters being an estimation of the pose of the subject during the acquisition time of the further set of additional k-space lines (low resolution scout images are used to estimate pose of a patient’ heart using a neural network, and AI scout images including compressed sensing where data is undersampled in the K-space, acquired to compare heart pose to those of heart model from initial scouting [0040]-[0041]; Figure 4 shows step 412 and step 414 and using neural network (404 and 418]) to estimate a pose of a heart).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify MRI image data as taught by Li to incorporate teaching of Chen, since using neural network to estimate a pose of a heart using MRI data was well known in the art as taught by Chen. One of ordinary skill in the art could have combined the elements as claimed by Li with no change in their respective functions, implementing neural network of estimating a pose of a subject with existing MRI data of low resolution and k-space lines within a central region of k-space, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to provide automatic adjustment planned image planes to compensate for changes in a pose of a heart throughout an entire scanning process ([0006]), and there was reasonable expectation of success.
Li and Chen do not further teach following limitations:
a radio frequency (RF) controller configured to drive an RF-coil comprising a multi- channel coil array;
a gradient controller configured to control gradient coils; and
a control unit configured to control the radio frequency controller and the gradient controller to execute the imaging protocol.
However, in the analogous field of endeavor in ultrasound imaging method, Polak teaches following limitations:
a radio frequency (RF) controller configured to drive an RF-coil comprising a multi- channel coil array (radio frequency controller configured to drive an RF- coil comprising a multi-channel coil-array [0036]);
a gradient controller configured to control gradient coils (a gradient controller configured to control gradient coils [0036]); and
a control unit configured to control the radio frequency controller and the gradient controller to execute the imaging protocol (a control unit configured to control the radio frequency controller and the gradient controller to execute the imaging protocol [0036]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify MR imaging apparatus as taught by Li to incorporate teaching of Polak, since controller controlling RF coil and gradient coil for multi-channel coil array was well known in the art as taught by Polak. One of ordinary skill in the art could have combined the elements as claimed by Li with no change in their respective functions, configuring its MRI apparatus to acquire image using a multi-channel coil array and its controller, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to provide a multi-shot imaging protocol ([0036]), and there was reasonable expectation of success.
Claim 19 is rejected under 35 U.S.C. 103 as being unpatentable over Li and Chen as applied to claim 1 above, and further in view of “Chatterjee et al.,” US 2024/0410965 (hereinafter Chatterjee).
Regarding to claim 19, Li and Chen together teach all limitations of claim 1 as set forth above.
Li and Chen do not further teach wherein the trained machine learning model operates exclusively in k-space, the dataset being in k-space notation.
However, in the analogous field of endeavor in reducing motion artifact in MRI, Chatterjee teaches using machine learning model with training data includes k-space data ([0076] and [0107]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify MR imaging apparatus as taught by Li and machine learning algorithm taught by Chen to incorporate teaching of Chatterjee, since training machine learning model with dataset including k-space data was well known in the art as taught by Chatterjee. One of ordinary skill in the art could have combined the elements as claimed by Li and Chen with no change in their respective functions, configuring its training dataset to be k-space data, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to provide motion correction using training k-space data ([0017] and [0036]), and there was reasonable expectation of success.
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Li and Chen as applied to claim 1 above, and further in view of “Frost et al.,” “Markerless high-frequency prospective motion correction for neuroanatomical MRI,” Magn Reson Med. 2019 July; 82(1): 126-144.
Regarding to claim 20, Li and Chen together teach all limitations of claim 1 as set forth above.
Li and Chen do not further teach wherein the pose parameters estimated from a further set of additional k-space lines is used to adapt a field of view of the magnetic resonance image dataset in the same echo train in which the further set of additional k-space lines is acquired.
However, in analogous field of endeavor in a motion correction method in MRI, Forst teaches motion correction by quantifying motion during echo-trains and updates the FOV encoding within the echo-trains (Prospectively-corrected sequences page 5, Figure 2 FOV position and orientation updated every 6 lines of k-spaces).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify MR imaging apparatus as taught by Li to incorporate teaching of Frost, since prospectively correcting sequences within the echo train was well known in the art as taught by Frost. One of ordinary skill in the art could have combined the elements as claimed by Li with no change in their respective functions, configuring its MRI apparatus to adjust FOV within same echo train, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art before the effective filing date of the claimed invention. The motivation would have been to provide high frequency motion correction, resulting in improved image quality (conclusion, page 15), and there was reasonable expectation of success.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Daniel Polak et al. “Motion guidance lines for robust data-consistency based retrospective motion correction in 2D and 3D MRI,” Magn Reson Med. 2023 May; 89(5): 1777-1790
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 PATRICIA J PARK whose telephone number is (571)270-1788. The examiner can normally be reached Monday-Thursday 8 am - 3 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Pascal Bui-Pho can be reached at 571-272-2714. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of 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.
/PATRICIA J PARK/Primary Examiner, Art Unit 3798
Prosecution Insights