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
The reply filed on 8 July 2026 has been entered. Applicant’s arguments with respect to claims 1-14 and 16-21 have been considered but are moot in view of new ground(s) of rejection. Applicant was correct in that the applied primary reference was not prior art, therefore the finality of the last rejection has been withdrawn.
Claims 1-14 and 16-21 are pending in this application and have been considered below. Claim 15 is canceled by the applicant.
Priority
Receipt is acknowledged that application is a National Stage application of PCT EP2023/085985. Priority to EP22214132.7 with a priority date of 16 December 2022 is acknowledged under 35 USC 119(e) and 37 CFR 1.78.
Information Disclosure Statement
The IDSs dated 1 August 2024 and 19 January 2024 that have been previously considered remain placed in the application file.
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.
Claims 5 and 13 are rejected under 35 U.S.C. § 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Claim 5 and claim 13 recite “and/or.” Applicants argue that “the plain language A and/or B means A or B, and both A and B. Since claims set out the legal boundaries of infringement, the examiner accepts the broadest interpretation as argued by applicants that “or” is the intended term. However, MPEP 2143.03 (I), “If a claim is subject to more than one interpretation, at least one of which would render the claim unpatentable over the prior art, the examiner should reject the claim as indefinite under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph (see MPEP § 2175) and should reject the claim over the prior art based on the interpretation of the claim that renders the prior art applicable. (Ex parte Ionescu, 222 USPQ 537 (Bd. Pat. App. & Inter. 1984)” and thus the rejection is maintained.
Claim Interpretation
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification.
The following terms in the claims have been given the following interpretations in light of the specification:
creating raw data, Claim 17: Page 3, lines 32-35, “In some embodiments, the attenuation coefficients can be used for the forward projection to create the raw data. The representation of the raw data itself can be in different units (e.g., attenuation / line integral space). The units for the representation of the raw data depend on the type of noise that is desired to be added in subsequent step(s).”
Thus, creating raw data is creating new image data. This definition is used for purposes of searching for prior art, but cannot be incorporated into the claims.
attenuation coefficients, Claim 1: page 3, lines 25-27, “This attenuation coefficient may be given as a function of the energy of the X- ray radiation.”
Thus, attenuation coefficients are numerical values that relate received radiation to expected radiation. This definition is used for purposes of searching for prior art, but cannot be incorporated into the claims.
Scanner parameters, Claim 1 and 3: Page 3, Lines 30-34, “These scanner parameters may comprise a location of the scanner with respect to the patent, a rotation angle, scatter properties, beam-hardening effects, or detector deficiencies, for example.”
Thus, a Scanner parameters are physical characteristics of a scanner. This definition is used for purposes of searching for prior art, but cannot be incorporated into the claims.
Should applicant wish different definitions, Applicant should point to the portions of the specification that clearly show a different definition.
Claim Interpretation
Under MPEP 2143.03, "All words in a claim must be considered in judging the patentability of that claim against the prior art." In re Wilson, 424 F.2d 1382, 1385, 165 USPQ 494, 496 (CCPA 1970). As a general matter, the grammar and ordinary meaning of terms as understood by one having ordinary skill in the art used in a claim will dictate whether, and to what extent, the language limits the claim scope. Language that suggests or makes a feature or step optional but does not require that feature or step does not limit the scope of a claim under the broadest reasonable claim interpretation. In addition, when a claim requires selection of an element from a list of alternatives, the prior art teaches the element if one of the alternatives is taught by the prior art. See, e.g., Fresenius USA, Inc. v. Baxter Int’l, Inc., 582 F.3d 1288, 1298, 92 USPQ2d 1163, 1171 (Fed. Cir. 2009).
Claims 4, 8 and 14 state “or.” Claim 5 recites “one of the first computed tomography image and the second computed tomography image, the other one of the first computed tomography image and the second computed tomography image, and data representing the transformation.” Claim 5 further recites, “one of the first computed tomography image and the second computed tomography image according to the method of claim 1.” Since “one of” and “or” are disjunctive, any one of the elements found in the prior art is sufficient to reject the claim. While citations have been provided for completeness and rapid prosecution, only one element is required. Because, on balance, it appears the disjunctive interpretation enjoys the most specification support and for that reason the disjunctive interpretation (one of A, B OR C) is being adopted for the purposes of this Office Action. Applicant’s comments and/or amendments relating to this issue are invited to clarify the claim language and the prosecution history.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(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.
Claims 1, 4-11, 14, 16-17 and 19 (all claims except 2-3, 12-13, 15, 18 and 20-21) are rejected under 35 U.S.C. 102(a)(1) and/or (a)(2) as being anticipated by US Patent Publication 2025 0191252 A1, (Moriakov et al.) (with a priority date of 17 Feb 2022). References are listed in the Notice of Cited References when they were first cited. If a reference is not identifiable (e.g., due to a typo), it can be identified by searching for the quoted text.
PNG
media_image1.png
567
509
media_image1.png
Greyscale
Claim 1
[AltContent: textbox (Moriakov et al. Fig. 9, showing CT images of a thorax converted to a CBCT image and then back through intermediate images.)] Regarding Claim 1, Moriakov et al. disclose a computer-implemented method for generating a simulated cone-beam computed tomography (CBCT) image based on a computed tomography image ("One of the possible ways to apply deep learning to CT or CBCT reconstruction problems is to use a neural network as a learned post-processing operator for a classical reconstruction method," paragraph [0006]), the method comprising:
receiving data representing a CT image comprising a volume of a subject ("set of X-ray projections is first acquired for varying positions of the source and the detector and where X-rays from the source typically form a narrow fan beam. Subsequently, this projection data is processed by a reconstruction algorithm yielding either a two-dimensional slice or a three-dimensional volume," paragraph [0002]), wherein the volume is divided into voxels ("Additionally, we measured the performance of LIRE and PDHG on the test set of thorax CT data for the small FOY setting in the region where Yf=0, YP=l, consisting of the voxels in the partial field of view which do not belong to the full field of view," paragraph [0176]), wherein the voxels comprise a representation of a tissue property of a tissue of the subject in a Hounsfield Unit ("To simulate noisy projection data for the CT scans, Hounsfield units were converted into attenuation coefficients using μ=0.2 cm-1 as the water linear attenuation coefficient," paragraph [0159]);
converting the Hounsfield Unit of the CT image into attenuation coefficients ("To simulate noisy projection data for the CT scans, Hounsfield units were converted into attenuation coefficients using μ=0.2 cm-1 as the water linear attenuation coefficient," paragraph [0159]);
receiving scanner parameters of a simulated CBCT scanner ("the updating of the dual parameters is performed using a model ( e.g. a learned model) that is dependent on further calculated parameters, called auxiliary dual parameters herein. Therefore, in step 205a, these auxiliary dual parameters may be calculated before updating the dual parameters. For example, the auxiliary dual parameters may include one or more forward projected channels of the primal parameters (e.g. the forward-projection of the second primal channels) and/or the forward-projected latest updated reconstruction," paragraph [0125] where the model is the simulated CBCT scanner, also "Different models may be trained for clinical CBCT geometries with differently sized field-of-view. For example, two models may be trained for large and small field of view, respectively," paragraph [0068] where CBCT geometries are parameters),
forward-projecting the CT image to a projection image based on the scanner parameters of the simulated CBCT scanner ("The subset of the dual space may comprise an area of a two-dimensional projection image, as well as one or more projection directions. For example, the subset of the dual space may comprise an area of a two-dimensional projection image and an angular range of projection directions, thus forming a rectangular region in dual space," paragraph [0028]);
adding artificial noise to the projection image, the artificial noise is a representation of noise detected by the simulated CBCT scanner ("Attenuated projection data was corrupted by Poisson noise with I0=30000 photons in Eq. (2)," paragraph [0160] where Poisson noise is artificial noise with a Poisson distribution);
back-projecting the projection image with a reconstruction algorithm, thereby generating a simulated CBCT image of the subject ("reconstructions of acquired data for a related imaging modality, such as CT volumes being used to train a CBCT reconstruction algorithm," paragraph [0141]); and
providing the simulated CBCT image of the subject ("Imaging apparatus 150 may be a CBCT scanner or another type of scanner, such as an MRI scanner or a helical-type CT scanner, for example. The communications unit 103 may further be configured to communicate with a user input/output interface 151, such as an output device such as a display, and/or an input device such as a keyboard, mouse, or touch screen," paragraph [0115]).
Claim 4
Regarding Claim 4, Moriakov et al. disclose the method of claims 1, wherein the computed tomography image is a fan-beam computed tomography image or a CBCT image ("Indeed, the techniques may be applied to a broader range of computed tomography systems, such as fan-beam CT and spiral CT," paragraph [0064]).
Claim 5
Regarding Claim 5, Moriakov et al. disclose a computer-implemented method for generating training data for training of an artificial intelligence module to register a CBCT image to a computed tomography image, the method comprising:
receiving data representing a first computed tomography image of a subject ("The thorax CT dataset was used to train, validate and test the models, while the additional head & neck dataset was used exclusively for testing the models on out-of distribution data," paragraph [0158]);
generating data representing a second computed tomography image of the subject, wherein the second computed tomography image differs from the first computed tomography image in that a transformation is applied to the second computed tomography image, the transformation comprising a deformation, and/or distortion, and/or rotation, and/or translation of the subject, and/or a cropped field of view ("Artificial processing steps can include adding noise and/or applying operations such as rotations, mirroring or other deformations to existing acquired samples," paragraph [0141] and "During the sampling, augmentations that flip patient left-right and top-bottom are randomly applied, both with probability 50%." paragraph [0109]);
generating data representing the transformation ("Also, the train set can contain processed samples of artificially generated acquired data, together with the gold standard reconstruction and/or digital phantoms that were used to generate the acquired data," paragraph [0141]);
generating a simulated CBCT image based on one of the first computed tomography image and the second computed tomography image according to the method of claim 1, wherein the data representing the computed tomography image comprises the first and/or the second computed tomography image ("In step 403, a reconstruction is performed for the measured data of a sample in the train set. This reconstruction may be done using one of the methods disclosed herein, for example the method described with reference to FIG. 2 or FIG. 3," paragraph [0144]);
generating a set of training data, the set of training data comprising the simulated CBCT image based on one of the first computed tomography image and the second computed tomography image, the other one of the first computed tomography image and the second computed tomography image, and data representing the transformation ("For example, the processor system may be further configured to control training the dual-space learned invertible operator and the primal-space learned invertible operator, based on a train set," paragraph [0190]); and
providing the set of training data ("the blocks are connected by projection and back projection operators, enabling end-to-end training. Such architecture allows to filter noise efficiently, since raw projection data is provided to the dual blocks," paragraph [0009]).
Claim 6
Regarding Claim 6, Moriakov et al. disclose the method of claim 5, wherein the generating data representing a second computed tomography image of the subject comprises receiving data representing the second computed tomography image of the subject acquired by a computed tomography scanner ("a set of X-ray projections is first acquired for varying positions of the source and the detector and where X-rays from the source typically form a narrow fan beam. Subsequently, this projection data is processed by a reconstruction algorithm yielding either a two-dimensional slice or a three-dimensional volume," paragraph [0002]).
Claim 7
Regarding Claim 7, Moriakov et al. disclose the method of claim 6, wherein the generating data representing the transformation comprises registering the first computed tomography image to the second computed tomography image ("For the small field of view setting, our method is able to reconstruct certain anatomy details outside the full field of view much better than the iterative baseline, which can be interesting for applications in radiotherapy, e.g., by allowing for a better registration of the planning CT scan to the CBCT reconstruction," paragraph [0177]).
Claim 8
Regarding Claim 8, Moriakov et al. disclose the method of claim 7, wherein the registering of the first computed tomography image to the second computed tomography image is performed with a registering algorithm or an AI- based registering algorithm ("The test results show that the method outperforms the classical and deep learning baselines on the test set of thorax CT scans and the out-of distribution test set of head & neck CT scans, where additionally better generalization of our method was observed compared to the U-net baseline," paragraph [0177]).
Claim 9
Regarding Claim 9, Moriakov et al. disclose the method of claim 5, wherein the generating data representing a second computed tomography image of the subject comprises applying an artificial transformation to the data representing the first computed tomography image of the subject thereby generating data representing the second computed tomography image of the subject ("Artificial processing steps can include adding noise and/or applying operations such as rotations, mirroring or other deformations to existing acquired samples," paragraph [0141]).
Claim 10
Regarding Claim 10, Moriakov et al. disclose the method of claim 9, wherein the step of generating data representing the transformation comprises receiving data representing the artificial transformation ("Artificial processing steps can include adding noise and/or applying operations such as rotations, mirroring or other deformations to existing acquired samples," paragraph [0141] where receiving data includes receiving data to do a rotation or mirroring).
Claim 11
Regarding Claim 11, Moriakov et al. disclose a computer-implemented method for registering a computed tomography image to a CBCT image("One of the possible ways to apply deep learning to CT or CBCT reconstruction problems is to use a neural network as a learned post-processing operator for a classical reconstruction method," paragraph [0006]), the method comprising:
receiving data representing a computed tomography image of a subject ("set of X-ray projections is first acquired for varying positions of the source and the detector and where X-rays from the source typically form a narrow fan beam. Subsequently, this projection data is processed by a reconstruction algorithm yielding either a two-dimensional slice or a three-dimensional volume," paragraph [0002]);
receiving data representing a CBCT image of the subject ("Imaging apparatus 150 may be a CBCT scanner or another type of scanner, such as an MRI scanner or a helical-type CT scanner, for example. The communications unit 103 may further be configured to communicate with a user input/output interface 151, such as an output device such as a display, and/or an input device such as a keyboard, mouse, or touch screen," paragraph [0115]);
determining a transformation necessary for registering the computed tomography image to the CBCT image using an artificial intelligence module, wherein the artificial intelligence module is trained with training data generated with the method of claim 5 ("One of the possible ways to apply deep learning to CT or CBCT reconstruction problems is to use a neural network as a learned post-processing operator for a classical reconstruction method," paragraph [0006]);
registering the computed tomography image to the CBCT image according to the determined transformation ("For the small field of view setting, our method is able to reconstruct certain anatomy details outside the full field of view much better than the iterative baseline, which can be interesting for applications in radiotherapy, e.g., by allowing for a better registration of the planning CT scan to the CBCT reconstruction," paragraph [0177]); and
providing the computed tomography image registered to the CBCT ("Imaging apparatus 150 may be a CBCT scanner or another type of scanner, such as an MRI scanner or a helical-type CT scanner, for example. The communications unit 103 may further be configured to communicate with a user input/output interface 151, such as an output device such as a display, and/or an input device such as a keyboard, mouse, or touch screen," paragraph [0115]).
Claim 14
Regarding Claim 14, Moriakov et al. disclose the method of claim 11, wherein the artificial intelligence module is trained with the training data using a supervised or a semi-supervised training algorithm ("Moreover, an algorithm to implement a suitable training procedure is disclosed in Algorithm 3. The training according to algorithm 3 is supervised, and the training set (of e.g. CT volumes) is denoted by 'D train," paragraph [0105]).
Claim 16
Regarding Claim 16, Moriakov et al. disclose the method of claim 1, wherein the forward projecting is based on the attenuation coefficients ("CBCT reconstruction can be viewed as an inverse problem. Let x:zf-+ x(z) be a function specifying the attenuation coefficient for every point zE.Qx in the spatial domain," paragraph [00]).
Claim 17
Regarding Claim 17, Moriakov et al. disclose the method of claim 1, wherein the forward projecting includes creating raw data based on the attenuation coefficients ("A list of intermediate reconstructions may be created, this list may be extended during the procedure by adding newly created reconstructions to the list. In general, the image is defined in a primal space," paragraph [0118] where intermediate constructions are raw data).
Claim 19
Regarding Claim 19, Moriakov et al. disclose a tangible, non-transitory computer readable medium that stores instructions for generating a simulated cone-beam computed tomography (CBCT) image based on a computed tomography image, wherein when executed by a processor ("One of the possible ways to apply deep learning to CT or CBCT reconstruction problems is to use a neural network as a learned post-processing operator for a classical reconstruction method," paragraph [0006]), the instructions cause the processor to:
receive data representing a CT image comprising a volume of a subject ("set of X-ray projections is first acquired for varying positions of the source and the detector and where X-rays from the source typically form a narrow fan beam. Subsequently, this projection data is processed by a reconstruction algorithm yielding either a two-dimensional slice or a three-dimensional volume," paragraph [0002]), wherein the volume is divided into voxels ("Additionally, we measured the performance of LIRE and PDHG on the test set of thorax CT data for the small FOY setting in the region where Yf=0, YP=l, consisting of the voxels in the partial field of view which do not belong to the full field of view," paragraph [0176]), wherein the voxels comprise a representation of a tissue property of a tissue of the subject in a Hounsfield Unit ("To simulate noisy projection data for the CT scans, Hounsfield units were converted into attenuation coefficients using μ=0.2 cm-1 as the water linear attenuation coefficient," paragraph [0159]);
convert the Hounsfield Unit of the CT image into attenuation coefficients ("To simulate noisy projection data for the CT scans, Hounsfield units were converted into attenuation coefficients using μ=0.2 cm-1 as the water linear attenuation coefficient," paragraph [0159]);
receive scanner parameters of a simulated CBCT scanner ("the updating of the dual parameters is performed using a model ( e.g. a learned model) that is dependent on further calculated parameters, called auxiliary dual parameters herein. Therefore, in step 205a, these auxiliary dual parameters may be calculated before updating the dual parameters. For example, the auxiliary dual parameters may include one or more forward projected channels of the primal parameters (e.g. the forward-projection of the second primal channels) and/or the forward-projected latest updated reconstruction," paragraph [0125] where the model is the simulated CBCT scanner, also "Different models may be trained for clinical CBCT geometries with differently sized field-of-view. For example, two models may be trained for large and small field of view, respectively," paragraph [0068] where CBCT geometries are parameters);
forward-project the CT image to a projection image based on the scanner parameters of the simulated CBCT scanner ("The subset of the dual space may comprise an area of a two-dimensional projection image, as well as one or more projection directions. For example, the subset of the dual space may comprise an area of a two-dimensional projection image and an angular range of projection directions, thus forming a rectangular region in dual space," paragraph [0028]);
add artificial noise to the projection image, the artificial noise is a representation of noise detected by the simulated CBCT scanner ("," paragraph [00]);
back-project the projection image with a reconstruction algorithm, thereby generating a simulated CBCT image of the subject ("Attenuated projection data was corrupted by Poisson noise with I0=30000 photons in Eq. (2)," paragraph [0160] where Poisson noise is artificial noise with a Poisson distribution); and
provide the simulated CBCT image of the subject ("Imaging apparatus 150 may be a CBCT scanner or another type of scanner, such as an MRI scanner or a helical-type CT scanner, for example. The communications unit 103 may further be configured to communicate with a user input/output interface 151, such as an output device such as a display, and/or an input device such as a keyboard, mouse, or touch screen," paragraph [0115]).
1st 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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 2-3, 12-13 and 20 (all remaining claims except 18 and 21) are rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2025 0191252 A1, (Moriakov et al.) in view of US Patent Publication 2018 0232944 A1, (Barski et al.) (Priority date of 26 Mar 2014). The references are listed in a PTO-892 from the Office Action in which they are first used. If a reference is not identifiable (e.g., due to a typo), it can be identified by searching for the quoted text.
Claim 2
Regarding Claim 2, Moriakov et al. teach the method of claim 1, as noted above.
Moriakov et al. is not relied upon to explicitly teach all of modifying the tissue property of the tissue of the subject.
[AltContent: textbox (Barski et al. Fig. 2B, showing a system for modifying tissue data based on bone/soft tissue identification.)]
PNG
media_image2.png
490
685
media_image2.png
Greyscale
However, Barski et al. teach wherein the method further comprises the step of modifying the tissue property of the tissue of the subject ("Frequency decomposition is applied to the bone content and tissue detail slices prior to combination and executes according to the segmentation results," paragraph [0035]).
Therefore, taking the teachings of Moriakov et al. and Barski et al. as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify “Learned Invertible Reconstruction” of CT and CBCT images as taught by Moriakov et al. to use “Enhanced Display of Image Slices from 3D volume Image” as taught by Barski et al., showing that Moriakov et al. and Barski et al. are analogous art because both are manipulating medical radiation images. The suggestion/motivation for combination is that, “Among the most common methods for reconstructing the 3-D volume image are filtered back projection approaches.” as noted by the Barski et al. disclosure in paragraph [0003], which also motivates combination because the combination would predictably have a higher quality as there is a reasonable expectation that different materials in x-ray images need different image procedures for best display quality; and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Claim 3
Regarding claim 3, Moriakov et al. teach the method of claim 1, as noted above.
Moriakov et al. is not relied upon to explicitly teach all of two tube peak voltages.
However, Barski et al. teach wherein the scanner parameters comprise at least two tube peak voltages of the simulated CBCT scanner ("According to an embodiment of the present invention, the procedure in FIG. 2A obtains and modifies a displayed first image slice from the volume image by segmenting bone and soft tissue content in the first image slice data, defining two or more spatial frequency bands, such as non-overlapping spatial frequency bands," paragraph [0050] where tube peak voltage is used to create frequency bands, thus two frequency bands teaches two tube peak voltages).
Moriakov et al. and Barski et al. are combined as per claim 2.
Claim 12
Regarding claim 12, Moriakov et al. teach a computer-implemented method for segmenting a CBCT image, the method comprising the steps of:
receiving data representing a CBCT image of a subject acquired by a CBCT scanner ("Imaging apparatus 150 may be a CBCT scanner or another type of scanner, such as an MRI scanner or a helical-type CT scanner, for example. The communications unit 103 may further be configured to communicate with a user input/output interface 151, such as an output device such as a display, and/or an input device such as a keyboard, mouse, or touch screen," paragraph [0115]);
wherein the artificial intelligence module is trained with training data comprising a plurality of simulated CBCT images generated with the method according to claim 1 ("One of the possible ways to apply deep learning to CT or CBCT reconstruction problems is to use a neural network as a learned post-processing operator for a classical reconstruction method," paragraph [0006]); and
providing the segmented CBCT image ("Imaging apparatus 150 may be a CBCT scanner or another type of scanner, such as an MRI scanner or a helical-type CT scanner, for example. The communications unit 103 may further be configured to communicate with a user input/output interface 151, such as an output device such as a display, and/or an input device such as a keyboard, mouse, or touch screen," paragraph [0115]).
Moriakov et al. is not relied upon to explicitly teach all of segmenting the CBCT image.
However, Barski et al. teach segmenting the CBCT image using an artificial intelligence module ("Segmentation of the image and anatomical features (e.g. bone and other features) in step S130 then provides the information on volume image content that is needed for subsequent processing," paragraph [0055]),
Moriakov et al. and Barski et al. are combined as per claim 2.
Claim 13
Regarding claim 13, Moriakov et al. teach the method of claim 12, wherein the training data comprises a plurality of CT images acquired with a computed tomography scanner and/or a plurality of CBCT images acquired with a CBCT scanner ("The test results show that the method outperforms the classical and deep learning baselines on the test set of thorax CT scans and the out-of distribution test set of head & neck CT scans, where additionally better generalization of our method was observed compared to the U-net baseline," paragraph [0177]).
Claim 20
Regarding claim 20, Moriakov et al. teach the computer readable medium of claim 19, as noted above.
Moriakov et al. is not relied upon to explicitly teach all of modify the tissue property of the tissue of the subject.
However, Barski et al. teach wherein the instructions further cause the processor to modify the tissue property of the tissue of the subject ("Frequency decomposition is applied to the bone content and tissue detail slices prior to combination and executes according to the segmentation results," paragraph [0035]).
Moriakov et al. and Barski et al. are combined as per claim 2.
2nd Claim Rejections - 35 USC § 103
Claims 18 and 21 (all remaining claims) are rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2025 0191252 A1, (Moriakov et al.) in view of US Patent 12,579,718 B1 (Holt) (Priority date 6 Sep 2019). The references are listed in a PTO-892 from the Office Action in which they are first used. If a reference is not identifiable (e.g., due to a typo), it can be identified by searching for the quoted text.
Claim 18
Regarding Claim 18, Moriakov et al. teach the method of claim 1, as noted above.
Moriakov et al. is not relied upon to explicitly teach all of cropping.
[AltContent: textbox (Holt Fig. 10, showing a system for CT to CBCT conversion using cropping/truncation.)]
PNG
media_image3.png
668
495
media_image3.png
Greyscale
However, Holt teaches wherein the back-projecting comprises CBCT reconstruction with a cropped field of view corresponding to the cone-beam geometry of the simulated CBCT scanner ("Iterative reconstruction (IR) techniques are especially susceptible to truncation artifacts that can be difficult to mitigate. Iterative reconstruction refers to iterative algorithms used to reconstruct images (typically two-dimensional (2D or 2-D) or 3D images) using certain imaging techniques, and generally feature iteratively improving a guess or estimate (or set of guesses or estimates) for the reconstruction until an acceptable image is found. For example, in computed tomography (CT), such as cone beam computed tomography (CBCT), an image is reconstructed from projections of an object," Col. 2, lines 51-61, and "Additionally, some individual projection frames may appear cropped, whether or not the entire object is truncated relative to the entire scan field of view. For example: Half-fan (or HalfFan, also sometimes referred to as asymmetric or offset scanning) data is cropped on one side, where the edge 234 of the detector 230 falls within the scan object (vertically from the x-ray imaging source 210)." Col. 5, lines 23-29).
Therefore, taking the teachings of Moriakov et al. and Holt as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify “learned invertible reconstruction” of CT to CPCT images as taught by Moriakov et al. to use “Handling truncated data in Iterative reconstruction” as taught by Holt, showing that Moriakov et al. and Holt are analogous art because both are iterative reconstruction of medical images. The suggestion/motivation for combination is that, “Some challenges with reconstruction can occur when the complete scan FOY is truncated relative to the scanned object, which can violate typical data sufficiency conditions (DSC) required for proper reconstruction.” as noted by the Holt disclosure in Column 1, Lines 19-23, which also motivates combination because the combination would predictably have a higher flexibility as there is a reasonable expectation that different CT and CBCT machines will have different resolutions and produce different resolutions of data; and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Claim 21
Regarding claim 21, Moriakov et al. teach the computer readable medium of claim 19, as noted above.
Moriakov et al. is not relied upon to explicitly teach all of cropping.
However, Holt teaches wherein the back-projection comprises CBCT reconstruction with a cropped field of view corresponding to the cone- beam geometry of the simulated CBCT scanner ("Iterative reconstruction (IR) techniques are especially susceptible to truncation artifacts that can be difficult to mitigate. Iterative reconstruction refers to iterative algorithms used to reconstruct images (typically two-dimensional (2D or 2-D) or 3D images) using certain imaging techniques, and generally feature iteratively improving a guess or estimate (or set of guesses or estimates) for the reconstruction until an acceptable image is found. For example, in computed tomography (CT), such as cone beam computed tomography (CBCT), an image is reconstructed from projections of an object," Col. 2, lines 51-61, and "Additionally, some individual projection frames may appear cropped, whether or not the entire object is truncated relative to the entire scan field of view. For example: Half-fan (or Half Fan, also sometimes referred to as asymmetric or offset scanning) data is cropped on one side, where the edge 234 of the detector 230 falls within the scan object (vertically from the x-ray imaging source 210)." Col. 5, lines 23-29).
Moriakov et al. and Holt are combined as per claim 18.
Reference Cited
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure.
US Patent Publication 2003 0007601 A1 to Jaffray et al. discloses a cone-beam computer tomography system includes an x-ray source that emits an x-ray beam in a cone-beam form towards an object to be imaged and an amorphous silicon flat-panel imager receiving x-rays after they pass through the object, the imager providing an image of the object. A computer is connected to the radiation source and the cone beam computerized tomography system, wherein the computer receives the image of the object and based on the image sends a signal to the radiation source that controls the path of the radiation source.
US Patent Publication 2020 0027264 A1 to Chen et al. discloses creating a registered image that integrates the information of CT and CBCT images. With the present method and system, medical practitioners can precisely transform the information of CT image-based treatment plan into the CBCT image so as to accurately control the dosage and location of a radiation therapy.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HEATH E WELLS whose telephone number is (703)756-4696. The examiner can normally be reached Monday-Friday 8:00-4:00.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Ms. Jennifer Mehmood can be reached on 571-272-2976. 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.
/Heath E. Wells/Examiner, Art Unit 2664
Date: 25 July 2026
Prosecution Insights