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 .
Status of the Claims
Claims 1-15 are currently pending in the present application, with claims 1 and 15 being independent.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 03/13/2025 have been considered by the examiner.
Claim Objections
Claims 2, 8, 11, and 13 is/are objected to because of the following informalities:
The recitation of “and/or” in claim 2 should be amended to “and, “or”, or otherwise clarify the intended scope
The recitation of “colour” in claim 8 should be amended to “color” to conform to U.S. spelling conventions.
The recitation of “e.g., a portion of a heart” in claims 11 and 13 is exemplary language and does not positively recite a claim limitation. Examiner suggests amending the claims to remove the exemplary language or otherwise positively recite the intended subject matter, rather than including examples.
Appropriate correction is required.
Claims 13 is objected to under 37 CFR 1.75 as being a substantial duplicate of claim 11. When two claims in an application are duplicates or else are so close in content that they both cover the same thing, despite a slight difference in wording, it is proper after allowing one claim to object to the other as being a substantial duplicate of the allowed claim. See MPEP § 608.01(m).
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.
Claims 1-15 is/are 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.
The term “approximate” in claim 1 is a relative term which renders the claim indefinite. The term “approximate” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. The claims do not specify whether approximation is based on geometric similarity, contour correspondence, voxel intensity, registration error, or another objective criterion, nor does it define when the estimated 3D shape is sufficiently “approximate”. Therefore, the metes and bounds of the claimed subject matter cannot be determined with reasonable certainty.
The recitation of “the optimal 3D shift in the 3D image space that minimizes a discrepancy between the extracted contour and the estimated 3D shape…” in claim 1 renders the claim indefinite. The claim fails to define what constitutes the recites “discrepancy,” or according to what objective criterion the claimed 3D shift is determined to be “optimal.” Different optimization criteria or discrepancy metrics may produce different 3D shifts, and the metes and bounds of the claim therefore cannot be determined with reasonable certainty.
Claim 15 recites substantially similar subject matter as to that of claim 1 and is rejected using substantially similar rationale as to that which was set forth with respect to claim 1.
Claims depending thereon are also rejected for substantially similar reasons as that set forth for the claims from which they depend on.
Claim 5 recite that “a breathing pattern is used as a regularizer when determining the 3D shift.” However, neither the claims nor the specification identifies what quantity or optimization is being regularized, how the breathing pattern is incorporated into the regularization, or the meaning of “regularizer” in the context of the claimed invention. Accordingly, the scope of the claims cannot be determined with reasonable certainty.
Claims depending thereon are also rejected for substantially similar reasons as that set forth for the claims from which they depend on.
The examiner respectfully requests the applicant to clarify the scope of the claimed invention.
Claims 1-15 will be examined as best understood by the examiner.
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.
Claim(s) 1, 4, 8, 14-15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Jiang et al., "MRI of moving subjects using multislice snapshot images with volume reconstruction (SVR): application to fetal, neonatal, and adult brain studies," IEEE Transactions on Medical Imaging, Vol. 26, No. 7, 2007, pp. 967-980. hereinafter referred to as “Jiang”. From IDS.
Regarding claim 1, Jiang discloses A free-breathing system for reconstructing a super-resolution volume of a 3D portion of a breathing body (Abstract; Snapshot magnetic resonance imaging (MRI) with Volume Reconstruction (SVR) has been developed for imaging moving subjects at high resolution and high signal-to-noise ratio (SNR)…Multilevel scattered interpolation has been used to obtain high-fidelity reconstruction…Section III.A; Images were acquired using a 4 channel torso array coil with the mother free breathing and without sedation), the system comprising:
a medical imaging device comprising (Section III.A; Fetal brain images were acquired on a Philips 1.5 T Intera system. Test data and images of the brains of neonates, children, and adults were acquired at 3T):
a snapshot module arranged to move or to be moved relative to the 3D portion in a direction perpendicular to a set of K parallel snapshot planes, generating at least two snapshots for each plane within the set of K parallel planes transverse to the 3D portion, K being a non-null and positive integer number (Section II.A; the target volume in Ωo is repeatedly imaged by simply looping through all slice positions so that in the absence of motion each location is sampled multiple times…Section III.A; The imaging was performed as dynamic loops with the scanner operating continuously to acquire parallel slices at a rate of about 1/s. The scans were specified as loops of continuous and overlapping slices…either four or eight basic loops of dynamic scans were acquired in a transverse orientation), while the body is freely breathing (Section III.A; Images were acquired using a 4 channel torso array coil with the mother free breathing and without sedation), wherein each snapshot contains a 2D cross-section of the 3D portion (Section II; The acquired slices consist of voxels which have a mesured intensity I(X, Y, Z) at prescribed positions in the scanner frame of reference, Ωo(X, Y, Z));
an iterative 3D shift estimation module arranged for iteratively estimating a 3D shift in a 3D image space of the extracted contours (Section II.B; Determine the mapping from Ωo(X, Y, Z) to Ω(x, y, z) for each sample. A multitime scale registration and combination approach is employed to determine the transformation from laboratory coordinates Ωo(X, Y, Z) to anatomy coordinates Ω(x, y, z) for each slice…), by using two iterative sub-steps:
a forward step, in which the iterative 3D shift estimation module is arranged to
use the extracted contours to estimate an approximate 3D shape of the 3D portion (Section II.B; The data is first divided into temporally contiguous blocks each containing multiple slices that together provide coverage of the volume of Ωo(X, Y, Z) of interest (i.e., 1 loop…these slice blocks are treated as 3-D volumes and registered together using rigid bod transformations. One block is chosen as the target for these registrations…Once the data is aligned, it is combined to form an average data set),
a backward step, in which the iterative 3D shift estimation module is arranged to determine, for each extracted contour, the optimal 3D shift in the 3D image space that minimizes a discrepancy between the extracted contour and the estimated 3D shape (Section II.B; These subpackages are registered to the average brain…the registration process involves moving the subpackage with the average brain held fixed in space. When the transformation (T(Ωo --> Ω)) of all subpackages have been determined, an updated average brain is calculated. The time scale is then reduced again and the process repeated until each slice is treated in isolation and registered to the latest estimate of the brain composed of all the other slices); and
a super-resolution reconstruction module arranged for:
repositioning in the image 3D space all snapshots according to the computed 3D shift (Section II.B; ; Determine the mapping from Ωo(X, Y, Z) to Ω(x, y, z) for each sample…Section II.C; Having determined the correct spatial alignment of the slice data it must be combined into a single 3-D space (Ω). Each acquired slice pixel is a valid sample of the brain being imaged and its location is known as a consequence of the image registration process…),
sampling the repositioned snapshots in the image 3D space with a super-resolution factor (Section I; Repeated sampling of slice planes makes it highly probable that every part of the fetal brain is sampled even when there is significant motion...Section II.C; To convert from this scattered data to a regular Cartesian grid of samples requires interpolation…), and
computing voxel intensities in the sampled image 3D space by averaging voxel
values from the snapshots, so as to reconstruct the super-resolution volume of the 3D portion (Section I; Having determined the correct location of each image in a self-consistent anatomical space of the fetal brain, we regard the measured voxel intensities from all the valid slices as valid samples at known although irregularly spaced locations and use a scattered interpolation approach to reconstruct an optimal estimate of the 3-D fetal brain. The final result is a 3-D image dataset on a Cartesian voxel lattice…a weighted mean of signal values within a local neighborhood was calculated as the intensity on a regular grid using a Gaussian kernel. Section II.B; Once the data is aligned, it is combined together to form an average data set).
Jiang does not appear to explicitly disclose a contour extraction module, arranged for extracting from the snapshot at least part of the contour of the 2D cross-section for the snapshots of each snapshot plane, however, Jiang discloses a semi-automated segmentation method for extracting the fetal brain from the surrounding images (Section II; Working in the image domain it is possible to segment the anatomy of interest and separate it from the rest of the field of view. Section III.B; The fetal brain images were preprocessed to isolate the region containing the head from the womb using ImageJ' by roughly tracing the edge of the head manually. Section V; Semi-automated segmentation method for extracting the fetal brain from the rest of the maternal images has been explored. We first roughly segment one loop of the fetal brain, typically the on that initially considered as the target, and then run a registration-based segmentation to segment slices from the other loops. This will be interleaved with the current registration process allowing both registration and segmentation to be iteratively improved), and further discloses iteratively reconstructing an estimated 3D brain volume from the acquired slices and registering each individual 2D slice to the current estimate of the 3D volume by determining an optimized spatial transformation (Jiang Fig. 2 and Pg. 969-970, Sections II-III).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to identify and use at least part of the boundary of Jiang’s segmented fetal-brain cross-section as the contour employed during Jiang’s iterative slice-to-volume registration. Doing so defines a boundary between the segmented and non-segmented regions, reduces the influence of surrounding maternal tissue or intensity variation, and focus the alignment on the anatomy of interest. The modification merely uses geometric information already produced by Jiang’s semi-automated segmentation method in Jiang’s existing iterative registration and reconstruction framework, without altering the underlying operation of Jiang’s functions of segmentation or volume reconstruction, yielding predictable results of optimizing the alignment of segmented fetal-brain cross-sections with the reconstructed 3D brain volume.
Regarding claim 2, Jiang discloses the free-breathing system of claim 1, and further discloses a mask computing module, arranged to compute for the snapshots of each snapshot plane a mask for an inner and/or outer contour of the 3D portion, the mask representing a segmentation of the 3D portion in each snapshot, wherein the contour extraction module is arranged for extracting from the computed masks at least part of the contour (Section II; Working in the image domain it is possible to segment the anatomy of interest and separate it from the rest of the field of view. Section III.B; The fetal brain images were preprocessed to isolate the region containing the head from the womb using ImageJ' by roughly tracing the edge of the head manually. Section V; Semi-automated segmentation method for extracting the fetal brain from the rest of the maternal images has been explored. We first roughly segment one loop of the fetal brain, typically the on that initially considered as the target, and then run a registration-based segmentation to segment slices from the other loops. This will be interleaved with the current registration process allowing both registration and segmentation to be iteratively improved. Examiner’s note: Jiang teaches initially segmenting the fetal brain in one acquisition loop and performing registration-based segmentation of slices from the other loops. The resulting identification of fetal-brain pixels relative to surrounding maternal-image pixels reasonably constitutes a segmentation mask representing the fetal-brain cross-section and defining its outer contour).
Jiang’s semi-automated segmentation (Section V) and SVR technique (Section II-III) are combined for the reasons set forth above with respect to claim 1.
Regarding claim 4, Jiang discloses the free-breathing system of claim 2, and further discloses wherein after the extraction of the masks,
the contour extraction module is also arranged to place the contours back into their corresponding original locations in the image 3D space (Fig. 2 and Section II.B; Determine the mapping from Ωo(X, Y, Z) to Ω(x, y, z) for each sample. Section II.C).
Jiang’s semi-automated segmentation (Section V) and SVR technique (Section II-III) are combined for the reasons set forth above with respect to claim 1.
Regarding claim 8, Jiang discloses the free-breathing system of claim 1, and further discloses comprising a colour normalization module arranged to perform a snapshot colour normalization of the snapshots (Section III.A; Images were automatically intensity corrected using knowledge of the coil sensitivity profile).
Jiang’s semi-automated segmentation (Section V) and SVR technique (Section II-III) are combined for the reasons set forth above with respect to claim 1.
Regarding claim 14, Jiang discloses the free-breathing system of claim 1, and further discloses wherein the medical imaging device is an MRI imaging device or a CT imaging device (Section III.A; Fetal brain images were acquired on a Philips 1.5 T Intera system. Test data and images of the brains of neonates, children, and adults were acquired at 3T).
Jiang’s semi-automated segmentation (Section V) and SVR technique (Section II-III) are combined for the reasons set forth above with respect to claim 1.
Regarding claim 15, claim 15 is the method claim of system claim 1, and is accordingly rejected using substantially similar rationale as to that which is set for with respect to claim 1.
Claim(s) 3, and 5-7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Jiang et al., "MRI of moving subjects using multislice snapshot images with volume reconstruction (SVR): application to fetal, neonatal, and adult brain studies," IEEE Transactions on Medical Imaging, Vol. 26, No. 7, 2007, pp. 967-980. hereinafter referred to as “Jiang”, in view of Kiely (US 10650585 B2).
Regarding claim 3, Jiang discloses the free-breathing system of claim 2, but does not disclose wherein the contour extraction module is also arranged to perform post processing on the masks, thereby generating cleaned masks.
In the same art of respiratory motion estimation and correction of 3D medical image reconstruction, Kiely discloses wherein the contour extraction module is also arranged to perform post processing on the masks, thereby generating cleaned masks (Fig. 1; post-processing software 106. Fig. 23 and Col. 28, lines 15-21; the body mask images are simulated with the optimal x-ray unit settings, thereby removing forms of noise and potential sources of artifacts from the body mask. The body mask and the segmented lungs could then recombine to form artifact- and noise-free x-ray images with global enhancement for clinical applications like structure contouring).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to apply Kiely’s mask post-processing and filtering techniques to the fetal-brain segmentation masks in Jiang. Applying such filtering techniques would have removed isolated noise, segmentation artifacts, and unnecessary anatomical regions before contour extraction, yielding predictable results in providing cleaner anatomical boundaries and improving segmentation and alignment accuracy during slice registration and volumetric reconstruction.
Regarding claim 5, Jiang discloses the free-breathing system of claim 1, but does not disclose wherein a breathing pattern is used as a regularizer when determining the 3D shift.
In the same art of respiratory motion estimation and correction of 3D medical image reconstruction, Kiely discloses wherein a breathing pattern is used as a regularizer when determining the 3D shift (Fig. 28A; sort planar images according to breathing phase, Select 2 adjacent planar images…update respiratory stimuli…update displacement vectors…).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to use the measured breathing phases taught by Kiely as a regularizing constraint in Jiang’s estimation of the spatial shift of each snapshot. Doing so allows constrained candidate shifts to positions consistent with the patient’s respiratory motion, and yields predictable results in reduced noise-driven registration solutions and improved physiological accuracy and stability of the reconstructed volume.
Regarding claim 6, Jiang in view of Kiely discloses the free-breathing system of claim 5, but Jiang does not disclose wherein the breathing pattern is obtained from an external sensor attached to the patient, or from a motion analysis from the snapshots themselves.
In the same art of respiratory motion estimation and correction of 3D medical image reconstruction, Kiely discloses wherein the breathing pattern is obtained
from an external sensor attached to the patient, or from a motion analysis from the snapshots themselves (Col. 5, lines 29-41; one or more sensors are used for measuring biometric signals of the patient as one or more sequences of time series, including one or more of a 3D spatial position localizer, a breathing phase sensor, and a cardiac phase sensor…the breathing phase sensor is configured for measuring one or more physiologic metrics related to the patient's breathing…).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to obtain the breathing phase from an external respiratory sensor as taught by Kiely for Jiang’s motion correction techniques. Doing so would allow synchronization of external respiratory measurements with snapshots and providing an independent indication of breathing state and movement, yielding predictable results in facilitating a more reliable estimation of breathing-induced displacement.
Regarding claim 7, Jiang discloses the free-breathing system of claim 1, but does not disclose comprising a local deformation field module arranged to compute a local deformation field, by applying local deformations to the contours.
In the same art of respiratory motion estimation and correction of 3D medical image reconstruction, Kiely discloses comprising a local deformation field module arranged to compute a local deformation field, by applying local deformations to the contours (Fig. 25, 27 and Col. 29-30; 3D multi-resolution optical flow algorithm performs deformable image registration…).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to apply Kiely’s local deformation field to Jiang’s fetal-brain segmentation masks for shift correction. Doing so allows different portions of an anatomical contour to move by different amounts, therefore compensating for local tissue deformation that cannot be represented by a single global 3D shift, yielding predictable results in improving local boundary correspondence and reconstruction fidelity.
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Jiang et al., "MRI of moving subjects using multislice snapshot images with volume reconstruction (SVR): application to fetal, neonatal, and adult brain studies," IEEE Transactions on Medical Imaging, Vol. 26, No. 7, 2007, pp. 967-980. hereinafter referred to as “Jiang”, in view of Mahmoudzadeh et al. "Interpolation-based super-resolution reconstruction: effects of slice thickness." Journal of Medical Imaging 1, no. 3 (2014): 034007-034007, hereinafter referred to as “Mahmoudzadeh”.
Regarding claim 9, Jiang discloses the free-breathing system of claim 1, but does not disclose wherein sampling the repositioned snapshots in the image 3D space with a super-resolution factor comprises dividing the distance d between a location of a snapshot and the consecutive or adjacent location by an integer number.
In the same art of super-resolution volumetric MRI reconstruction, Mahmoudzadeh discloses wherein sampling the repositioned snapshots in the image 3D space with a super-resolution factor comprises dividing the distance d between a location of a snapshot and the consecutive or adjacent location by an integer number (Fig. 3 and Section 2.1.1; we simulated the new 3-D HR images…with a resolution 256 × 256 × 120, a voxel size of 1×1×1.3 mm3 and with slice thickness and spacing between the slices of 1.3 mm. The first LR images were generated…and the resolution was decreased (256 × 256 × 60 with a voxel size of 1 × 1 × 2.6 mm3) along the slice direction by subsampling by factor of 2 (axial plane)…They were upsampled and changed back to their original dimensions (256 x 256 x 120). Examiner's note: HR volume voxel spacing = 1 × 1 × 2.6 mm3, LR volume = 1 × 1 × 2.6 mm3. It then reconstructs the LR data back onto the HR grid, so mathematically 2.6/2 = 1.3, divided by integer 2).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Jiang’s super-resolution reconstruction to perform the sampling using the integer-factor sampling technique taught by Mahmoudzadeh. Doing so improves the quality of the reconstructed super-resolution volume by mapping the acquired image data onto a higher-resolution grid and sampling at a finer spacing, yielding predictable results in improved reconstruction accuracy using a known super-resolution sampling technique in the same field of medical image reconstruction.
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Jiang et al., "MRI of moving subjects using multislice snapshot images with volume reconstruction (SVR): application to fetal, neonatal, and adult brain studies," IEEE Transactions on Medical Imaging, Vol. 26, No. 7, 2007, pp. 967-980. hereinafter referred to as “Jiang”, in view of Zhong et al. (US 20200249304 A1), hereinafter referred to as Zhong.
Regarding claim 10, Jiang discloses the free-breathing system of claim 1, but does not disclose wherein the snapshot module is arranged for generating 24 to 32 snapshots of the 3D portion in each snapshot plane.
In the same art of free-breathing MRI acquisition techniques for motion compensation, Zhong discloses wherein the snapshot module is arranged for generating 24 to 32 snapshots of the 3D portion in each snapshot plane (Par. 0073; The method described herein worked well for a clinically relevant range of number of slices and number of radial views, i.e., 22, 30, 36 and 44 slices and 404 and 800 radial views. Fig. 11; 30 slices).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to acquire 30 snapshots, as taught by Zhong, at each of Jiang’s slice planes. Repeated frame acquisition at a fixed anatomical plane is a known parameter selected to provide sufficient temporal sampling of moving anatomy and multiple observations for motion estimation and reconstruction. Using a number within the disclosed range would have increased the likelihood of sampling the anatomy at different motion states and supply the necessary amount of image registration and averaging to avoid redundant image information, yielding predictable results in reduced scan time, data volume, and computational burden when acquiring a number of frames.
Claim(s) 11 and 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Jiang et al., "MRI of moving subjects using multislice snapshot images with volume reconstruction (SVR): application to fetal, neonatal, and adult brain studies," IEEE Transactions on Medical Imaging, Vol. 26, No. 7, 2007, pp. 967-980. hereinafter referred to as “Jiang”, in view of van Amerom et al., "Fetal Whole-heart 4D imaging using motion-corrected multi-planar real-time MRI," Magnetic Resonance in Medicine, 2019, Vol. 82, pages 1055-1072, hereinafter referred to as “van Amerom”, From IDS.
Regarding claim 11, Jiang discloses the free-breathing system of claim 1, and further discloses wherein the 3D portion of the breathing body is at least a portion of an organ (Section III.A; Fetal brain images were acquired on a Philips 1.5 T Intera system. Test data and images of the brains of neonates, children, and adults were acquired at 3T).
Jiang does not disclose e.g., a portion of a heart.
In the same art of super-resolution volumetric MRI reconstruction, e.g., a portion of a heart (Fig. 1; 4D whole-heart reconstruction).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to apply Jiang’s motion-corrected snapshot volume-reconstruction method to a portion of the heart, as taught by van Amerom. Applying Jiang’s established reconstruction process to cardiac anatomy would have been a predictable use of the same technique for the same purpose of compensating for motion and producing a volumetric representation of the imaged organ.
Regarding claim 13, Jiang discloses the free-breathing system of claim 1, and further discloses wherein the 3D portion of the breathing body is at least a portion of an organ (Section III.A; Fetal brain images were acquired on a Philips 1.5 T Intera system. Test data and images of the brains of neonates, children, and adults were acquired at 3T).
Jiang does not disclose e.g., a portion of a heart.
In the same art of super-resolution volumetric MRI reconstruction, e.g., a portion of a heart (Fig. 1; 4D whole-heart reconstruction).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to apply Jiang’s motion-corrected snapshot volume-reconstruction method to a portion of the heart, as taught by van Amerom. Applying Jiang’s established reconstruction process to cardiac anatomy would have been a predictable use of the same technique for the same purpose of compensating for motion and producing a volumetric representation of the imaged organ.
Claim(s) 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Jiang et al., "MRI of moving subjects using multislice snapshot images with volume reconstruction (SVR): application to fetal, neonatal, and adult brain studies," IEEE Transactions on Medical Imaging, Vol. 26, No. 7, 2007, pp. 967-980. hereinafter referred to as “Jiang”, in view of Ebner et al., "An automated framework for localization, segmentation an super-resolution reconstruction of fetal brain MRI," Neuro Image, Vol. 206, 2020, 116324, hereinafter referred to as “Ebner”, from IDS.
Regarding claim 12, Jiang discloses the free-breathing system of claim 1, but does not disclose wherein at least one module of the modules is a machine learning-based module (Fig. 3 and Pg. 3, Section 3; fully automated framework for fetal brain reconstruction…first use a CNN to automatically localize the fetal brain region in each input low-resolution stack and obtain a 3D bounding box of the fetal brain. Within the bounding box we use another CNN to automatically generate a fine segmentation of the fetal brain…).
In the same art of super-resolution reconstruction of fetal brain MRI, Ebner discloses wherein at least one module of the modules is a machine learning-based module (Fig. 3 and Pg. 3, Section 3; fully automated framework for fetal brain reconstruction…first use a CNN to automatically localize the fetal brain region in each input low-resolution stack and obtain a 3D bounding box of the fetal brain. Within the bounding box we use another CNN to automatically generate a fine segmentation of the fetal brain…).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Jiang’s system to implement at least one of image-processing modules using machine learning-based modules, as taught by Ebner. Machine learning techniques automate image-processing tasks, reduce manual processing, and provide more robust and efficient image reconstruction while applying a known technique in the same field of medical image reconstruction.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JENNY NGAN TRAN whose telephone number is (571)272-6888. The examiner can normally be reached Mon-Thurs 8am-5pm.
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, Alicia Harrington can be reached at (571) 272-2330. 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.
/JENNY N TRAN/Examiner, Art Unit 2615
/YANNA WU/Primary Examiner, Art Unit 2615
Prosecution Insights