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 Amendment
The amendment filed on November 5, 2025 has been entered.
The amendment filed of claims 1, 3, 13, and 15 has been acknowledged.
The cancelation of claims 2, and 14 has been acknowledged.
Response to Arguments
Applicant's arguments, see “Rejections Under 35 U.S.C § 102”, filed November 5, 2025, have been fully considered but they are not persuasive.
The applicant argues that the machine learning involved in Lauritsch is auxiliary and outside the iteration and not a part of the iterative parameter optimization handed by the Adam algorithm.
Additionally, applicant argues that Adam optimization algorithm for stochastic target functions based on gradients and not a form of machine learning as no training data is used and simply a “traditional parameter optimization tool” lacking the learning ability that a machine learning algorithm requires.
The examiner respectfully disagrees that this is enough to overcome rejection. The prior art Lauritsch, teaches a segmentation method that potentially takes projection data and segments them through machine learning for use in the iterative generation of a motion-compensated image. ([0038], "In a further advantageous embodiment, a segmentation of the projection images and/or of the images generated therefrom, that is, for example, of the differential images, the iterative images, the provisional motion-compensated images and/or of the final image is carried out. Other image processing methods, machine learning methods and/or suchlike may likewise be used. Ultimately, an image quality of the final motion-compensated image may be improved by excluding static regions, parts, or structures in the determination or application of the motion field.") The purpose of the prior art is to create motion-compensated images and the use of machine learning in this instance is to create motion-compensated images at each iteration. Those images might be subject to further processes and other optimization models, but at least one of the plurality of iterations would be based on a machine learning model even if only as part of the iterative process. Additionally, the first iteration of reference image used is explicitly embodied as potentially a fully automatic segmentation. ([0016], "The generation of the provisional motion-compensated image may likewise potentially include a manual, partly automatic, or fully automatic segmentation of the provisional motion-compensated image, a (e.g. intensity-based) thresholding, that is, threshold value filtering, and/or further image processing acts.")
The examiner does agree that the Adam optimization algorithm for stochastic target functions based on gradients and not a form of machine learning. However, the claim language, “at least one of the plurality of iterations being obtained based on a machine learning model” means that the Adam optimization does not need to be a machine learning algorithm for the prior art to map onto the claim. The prior art just has to demonstrate that at least one of its iterations is based on machine learning. The claim language “based on” also does not require that the iteration be formed singularly through machine learning, but only that it has some tangible influence or part of the process in the production of those iterations.
Allowable Subject Matter
Claims 7-11, and 17-19 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.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1, 3-6, 12-13, 15-16, and 20 is/are rejected under 35 U.S.C. 102(a) as being unpatentable by Lauritsch et al. (U.S. Patent Number 2020/0242783-A1, hereinafter “Lauritsch”).
Regarding claim 1, Lauritsch teaches: A method for image reconstruction, comprising: obtaining original scanning data of an object; ([0009], "As part of the method, a plurality of projection images of the target object are acquired, that is, for instance, of a predetermined acquisition or imaging region or volume, the projection images having been or being acquired during a motion of at least part of the target object, wherein the motion has a main point.")
obtaining an initial image and an initial motion vector field of the object; (Fig. 3; [0024], "To determine the motion field, a multi-dimensional motion model or a model, in particular, a three-dimensional model of the volume shown or of the target object may be specified with motion vectors for the individual projection images."; [0092], "FIG. 3 depicts in diagram form an initial reference image 13 of the or of a vascular tree 12, such as may be present in the iterative act 0. The vascular tree 12 shown here is still not sharp or blurred and incomplete.")
, wherein the initial reconstructed image and the initial motion vector field are determined based on the original scanning data; ([0024], "To determine the motion field, a multi-dimensional motion model or a model, in particular, a three-dimensional model of the volume shown or of the target object may be specified with motion vectors for the individual projection images.")
and determining a target reconstructed image of the object by a plurality of iterations ([0014], "For this purpose, in a further process act of the method, a motion field that characterizes the motion of the target object is determined iteratively from the projection images, which field encompasses motion vectors for the individual projection images with respect to the respective current reference image. This may be formulated as an optimization problem, in which, for instance, one or a plurality of parameters for a predetermined motion model for the target object is adjusted or varied in an iterative manner.")
an iterative result of at least one of the plurality of iterations being obtained based on a machine learning model. ([0038], "In a further advantageous embodiment, a segmentation of the projection images and/or of the images generated therefrom, that is, for example, of the differential images, the iterative images, the provisional motion-compensated images and/or of the final image is carried out. … Other image processing methods, machine learning methods and/or suchlike may likewise be used. Ultimately, an image quality of the final motion-compensated image may be improved by excluding static regions, parts, or structures in the determination or application of the motion field.")
wherein the determining the target reconstructed image of the object by the plurality of iterations based on the original scanning data, the initial reconstructed image and the initial motion vector field comprises performing the plurality of iterations on the initial reconstructed image and the initial motion vector field using energy functions ([0017], "Provision may be made for a corresponding iterative image to be generated in the context of the iteration to determine the motion field in each iterative act, in order to carry out an evaluation of, for example, a predetermined target function for the iteration and/or an adjustment or variation of at least one parameter for the respective next iterative act"; [0024], "These motion vectors may then form the parameters to be adjusted, varied, or optimized.")
until a preset iteration stop condition is met to ([0020], "The predetermined termination condition may include a predetermined number of iterative acts, the elapsing of a predetermined computation time since the beginning of the iteration, a fulfilment of a convergence criterion for the target function of the iteration or optimization, attainment of a predetermined image characteristic, e.g., of a minimum image definition, size, length, width, or suchlike from reconstructed details, for instance an anatomical structure, such as a blood vessel or vascular tree, or suchlike."; Examiner Note- Motion vectors being used in the parameters of the target function maps it to an energy function.)
determine the target reconstructed image of the object, ([0014], "For this purpose, in a further process act of the method, a motion field that characterizes the motion of the target object is determined iteratively from the projection images, which field encompasses motion vectors for the individual projection images with respect to the respective current reference image. This may be formulated as an optimization problem, in which, for instance, one or a plurality of parameters for a predetermined motion model for the target object is adjusted or varied in an iterative manner.")
the energy function corresponding to the at least one of the plurality of iterations being constructed based on the machine learning model. ([0017], "Provision may be made for a corresponding iterative image to be generated in the context of the iteration to determine the motion field in each iterative act, in order to carry out an evaluation of, for example, a predetermined target function for the iteration and/or an adjustment or variation of at least one parameter for the respective next iterative act"; [0024], "These motion vectors may then form the parameters to be adjusted, varied, or optimized.")
Regarding claim 3, Lauritsch teaches: The method of claim 1, wherein the determining the target reconstructed image of the object by the plurality of iterations based on the original scanning data, the initial reconstructed image and the initial motion vector field further comprises: determining the target reconstructed image of the object based on an iterated reconstructed image corresponding to a target iteration meeting the preset iteration stop condition. ([0014], "For this purpose, in a further process act of the method, a motion field that characterizes the motion of the target object is determined iteratively from the projection images, which field encompasses motion vectors for the individual projection images with respect to the respective current reference image. This may be formulated as an optimization problem, in which, for instance, one or a plurality of parameters for a predetermined motion model for the target object is adjusted or varied in an iterative manner.")
Regarding claim 4, Lauritsch teaches: The method of claim 3, wherein the plurality of iterations each comprise: obtaining an iterated reconstructed image based on a starting reconstructed image and a starting motion vector field in a current iteration;
and/or obtaining an iterated motion vector field based on a starting reconstructed image and a starting motion vector field in a current iteration. ([0024], "To determine the motion field, a multi-dimensional motion model or a model, in particular, a three-dimensional model of the volume shown or of the target object may be specified with motion vectors for the individual projection images."; [0092], "FIG. 3 depicts in diagram form an initial reference image 13 of the or of a vascular tree 12, such as may be present in the iterative act 0. The vascular tree 12 shown here is still not sharp or blurred and incomplete.")
Regarding claim 5, Lauritsch teaches: The method of claim 3, wherein the plurality of iterations each comprise :obtaining an iterated reconstructed image based on a starting reconstructed image and a starting motion vector field in a current iteration, and obtaining an iterated motion vector field based on the iterated reconstructed image and the starting motion vector field;
or obtaining an iterated motion vector field based on a starting reconstructed image and a starting motion vector field in a current iteration, and obtaining an iterated reconstructed image based on the starting reconstructed image and the iterated motion vector field. ([0024], "To determine the motion field, a multi-dimensional motion model or a model, in particular, a three-dimensional model of the volume shown or of the target object may be specified with motion vectors for the individual projection images."; [0092], "FIG. 3 depicts in diagram form an initial reference image 13 of the or of a vascular tree 12, such as may be present in the iterative act 0. The vascular tree 12 shown here is still not sharp or blurred and incomplete."; [0014], "For this purpose, in a further process act of the method, a motion field that characterizes the motion of the target object is determined iteratively from the projection images, which field encompasses motion vectors for the individual projection images with respect to the respective current reference image. This may be formulated as an optimization problem, in which, for instance, one or a plurality of parameters for a predetermined motion model for the target object is adjusted or varied in an iterative manner.")
Regarding claim 6, Lauritsch teaches: The method of claim 3, wherein the preset iteration stop condition comprises a preset number of iterations and/or a preset threshold, the preset threshold being related to at least one of a quality of the reconstructed image, a quality variation amount of the reconstructed image, a quality of the motion vector field, a quality variation amount of the motion vector field, or a value of the energy function. ([0020], "The predetermined termination condition may include a predetermined number of iterative acts, the elapsing of a predetermined computation time since the beginning of the iteration, a fulfilment of a convergence criterion for the target function of the iteration or optimization, attainment of a predetermined image characteristic, e.g., of a minimum image definition, size, length, width, or suchlike from reconstructed details, for instance an anatomical structure, such as a blood vessel or vascular tree, or suchlike.")
Regarding claim 12, Lauritsch teaches: The method of claim 1, wherein the target reconstructed image comprises one of a CT image, an MR image, a PET image, and a PET-CT image. ([0027], "The present disclosure is therefore suited in particular to thinly or sparsely populated target objects or corresponding projection images with a relatively high contrast, because even when the target object is moving, a tomographic reconstruction is possible in a particularly reliable manner.")
Regarding claim 13, claim 13 has been analyzed with regard to claim 1 and is rejected for the same reasons of obviousness as used above as well as in accordance with Lauritsch further teaching on: A computer device, comprises a memory and a processor, the memory including a computer program stored therein, wherein the processor, when executing the computer program, performs a method for image reconstruction ([0009], "The present disclosure may also be (e.g., fully or partially) computer implemented."; [0045], "A further aspect is a computer program or computer program product that includes commands or control instructions which, when the computer programs is run by a computer, in particular by the data processing facility or the imaging device, cause the relevant computer to carry out at least one embodiment or variant of the method, in particular automatically or semi-automatically. The computer program therefore encodes or represents in other words the process acts of the method."; [0046], "A further aspect is a computer-readable storage medium, on which a computer program is stored.")
Regarding claim 15, claim 15 has been analyzed with regard to claim 3 and is rejected for the same reasons of obviousness as used above as well as in accordance with Lauritsch further teaching on: A computer device, comprises a memory and a processor, the memory including a computer program stored therein, wherein the processor, when executing the computer program, performs a method for image reconstruction ([0009], "The present disclosure may also be (e.g., fully or partially) computer implemented."; [0045], "A further aspect is a computer program or computer program product that includes commands or control instructions which, when the computer programs is run by a computer, in particular by the data processing facility or the imaging device, cause the relevant computer to carry out at least one embodiment or variant of the method, in particular automatically or semi-automatically. The computer program therefore encodes or represents in other words the process acts of the method."; [0046], "A further aspect is a computer-readable storage medium, on which a computer program is stored.")
Regarding claim 16, claim 16 has been analyzed with regard to claim 5 and is rejected for the same reasons of obviousness as used above as well as in accordance with Lauritsch further teaching on: A computer device, comprises a memory and a processor, the memory including a computer program stored therein, wherein the processor, when executing the computer program, performs a method for image reconstruction ([0009], "The present disclosure may also be (e.g., fully or partially) computer implemented."; [0045], "A further aspect is a computer program or computer program product that includes commands or control instructions which, when the computer programs is run by a computer, in particular by the data processing facility or the imaging device, cause the relevant computer to carry out at least one embodiment or variant of the method, in particular automatically or semi-automatically. The computer program therefore encodes or represents in other words the process acts of the method."; [0046], "A further aspect is a computer-readable storage medium, on which a computer program is stored.")
Regarding claim 20, Lauritsch teaches: A non-transitory computer-readable storage medium having a computer program stored therein, wherein the computer program, when executed by a processor, causes the processor to perform a method for image reconstruction of claim 1. ([0009], "The present disclosure may also be (e.g., fully or partially) computer implemented."; [0045], "A further aspect is a computer program or computer program product that includes commands or control instructions which, when the computer programs is run by a computer, in particular by the data processing facility or the imaging device, cause the relevant computer to carry out at least one embodiment or variant of the method, in particular automatically or semi-automatically. The computer program therefore encodes or represents in other words the process acts of the method."; [0046], "A further aspect is a computer-readable storage medium, on which a computer program is stored.")
Conclusion
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 Jinsu Hwang whose telephone number is (703)756-1370. The examiner can normally be reached Mon 6am-8am, 3pm-9pm EST; Thu 12pm - 8pm EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Matthew Bella can be reached at (571) 272-7778. 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.
/JINSU HWANG/Examiner, Art Unit 2667
/MATTHEW C BELLA/Supervisory Patent Examiner, Art Unit 2667