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/Amendments
The amendment, filed 03/12/2026 in response to the Non-Final Office Action mailed on 11/03/2025 has been entered.
Claims 1, 4-17, and 20-24 are currently pending in U.S. Patent Application No. 18/494,737.
Applicant’s remarks filed 03/12/2026 have been fully considered and responded to below.
Regarding the objection to the specification, the objection is removed in view of the amended specification.
Regarding the prior art rejections under 35 U.S.C. 102(a)(1) and/or 35 U.S.C. 103, the Applicant’s remarks have been fully considered but are moot because the new grounds of rejection regarding the amended limitation no longer relies on the combination of references presented in the Non-Final Rejection. A change in scope necessitated by the Applicant’s amendments has led to an updated search revealing new art.
However, the Examiner will make note of the assertion made by the Applicant on page 15 of the Applicant remarks. The Applicant asserts that Jeong’s low-pass filtering does not teach or disclose “performing low-pass filtering on the restoration data corresponding to the metal portion”. The Examiner respectfully disagrees with this assertion. In Jeong’s disclosure, Jeong references the work by Kalendar et al. (“Reduction of CT artifact caused by metallic implants”,
PNG
media_image1.png
471
305
media_image1.png
Greyscale
DOI: 10.1148/radiology.164.2.3602406; shown below and also attached to this office action) in relation to performing low-pass filtering on data
P
L
I
(
u
,
ϕ
)
. The Examiner notes from the Kalendar disclosure that the linear interpolation is only performed in the region associated with the metal implant, and therefore is analogous to the claimed “restoration data corresponding to the metal portion”.
PNG
media_image2.png
148
290
media_image2.png
Greyscale
[AltContent: textbox (Excerpts from Kalendar et al.)]
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 16-17, and 20 are rejected as being unpatentable over Jeong et al. (“Metal artifact reduction based on sinogram correction in CT”, DOI: 10.1109/NSSMIC.2009.5401793; hereinafter “Jeong”) in view of Bal and Spies (“Metal artifact reduction in CT using tissue-class modeling and adaptive prefiltering”, DOI: 10.1118/1.2218062, Publication Year: 2006; hereinafter “Bal”).
Regarding Claim 1, Jeong discloses a system for metal artifacts correction, comprising: at least one storage medium including a set of instructions; and at least one processor in communication with the at least one storage medium, wherein when executing the set of instructions, the at least one processor is directed to cause the system to perform operations including (Section III. Results, Figs. 3-4, Jeong discloses metal-artifact-reduction algorithm, which involves various image processing techniques (see Section II. Method) and consequently outputting a resultant modified image. The Examiner asserts that the computation and processes performed by Jeong are performed using a computing machine using programs which can perform image processing and output a resultant image, in which the computing machine includes the claimed “processor” and “storage medium”.):
obtaining an image to be processed including a metal portion (Fig. 3(a), Section I. Introduction, Section II. Method, Jeong discloses a process of reducing metal artifacts precent in CT images.);
determining initial projection data by performing data restoration on the metal portion of the image to be processed (Section II. Method, B. Reprojection after filtering the CT image Jeong discloses obtaining reprojection data
P
r
e
p
r
o
j
u
,
ϕ
. Notably
P
r
e
p
r
o
j
u
,
ϕ
is only computed for metal-trance portions which were obtained from an interpolation (i.e., data restoration) process (see Fig. 6).);
determining target projection data by filtering the initial projection data, including:
obtaining restoration data corresponding to the metal portion in the initial projection data (Section II. Method, B. Reprojection after filtering the CT image, Jeong discloses obtaining data
P
r
e
p
r
o
j
(
u
,
ϕ
) (i.e., initial projection data) representing the metal segments of a CT image by interpolating surrounding non-metallic pixels.);
performing low-pass filtering on the restoration data corresponding to the metal portion (D. Merging the projection data, Jeong discloses obtaining low-pass filter data
P
^
L
I
(
u
,
ϕ
) based on linear interpolation data. The Examiner notes the Kalender et al. reference cited by Jeong (noted by [1], which is what inspires the filtering step performed by Jeong, along with the Examiner remarks made above), wherein Kalender performs linear interpolation on the metal/implant region of the image, which is analogous to “restoration data corresponding to the metal portion”.); and
determining the target projection data by combining the low-pass filtered restoration data corresponding to the metal portion (The Examiner notes D. Merging the projection data, wherein Jeong discloses obtaining target projection data
P
c
o
r
r
u
,
ϕ
which is based on low pass filtered data
P
^
L
I
(
u
,
ϕ
) and
P
~
r
e
p
r
o
j
(
u
,
ϕ
)
. However,
P
~
r
e
p
r
o
j
(
u
,
ϕ
)
has been processed by a high pass filter.); and
determining a target image based on the target projection data (D. Merging the projection data, Jeong produces a final image
I
M
A
R
(
x
,
y
)
where
I
M
A
R
(
x
,
y
)
consists of the corrected image
I
c
o
r
r
(
x
,
y
)
superimposed with the metal portions of the original image
I
r
. Note that the corrected image
I
c
o
r
r
(
x
,
y
)
is the image where artifacts are removed/suppressed, and is based on the corrected projection data
P
c
o
r
r
u
,
ϕ
(i.e., target projection data).).
Jeong does not explicitly disclose determining the target projection data by combining the low-pass filtered restoration data corresponding to the metal portion (italicized for context) with raw projection data of the image to be processed corresponding to other portion other than the metal portion.
Bal discloses determining the target projection data by combining the low-pass filtered restoration data corresponding to the metal portion (italicized for context) with raw projection data of the image to be processed corresponding to other portion other than the metal portion (Fig. 1, II.C. Sinogram completion, Bal discloses a method for reducing metal artifacts in CT images, wherein the process involves a sinogram completion step where the metal segments found in the original sinogram are replaced by the corresponding portion from a model sinogram (i.e., target projection data). This process is equivalent to merging/combining the non-metal portions from the original sinogram with the modified/processed portions from the model sinogram which correspond to the metal portion in the image.).
Jeong and Bal are considered to be analogous to the claimed invention as they are in the same field of artifact reduction in radiographic images. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Jeong such that the target projection data disclosed by Jeong is obtained by combining the low-pass filtered restoration data (disclosed by Jeong) along with the original projection data (as disclosed by Bal). The motivation for this combination being the ability to retain characteristics of the original projection data in the modified projection data without the need for a computationally intensive algorithm.
Claims 17 and 20 are the method and non-transitory computer readable medium claims corresponding to claim 1, and are similarly rejected (see Section II. Method regarding the method. Regarding the non-transitory computer readable medium, the Examiner asserts (similarly to the assertion made above) that the processes and methods taught by Jeong are performed using a computing machine which includes the claimed “non-transitory computer readable medium”.).
Regarding Claim 16, Jeong in view of Bal teaches the system of claim 1, wherein the image to be processed includes a radiographic image (Fig. 3(a), Section I. Introduction, Section II. Method, Jeong discloses a process of reducing metal artifacts precent in CT images.).
Claim 4 is rejected as being unpatentable over Jeong in view of Bal in view of De Man et al. (US 2005/0286749; hereinafter “De Man”).
Regarding Claim 4, Jeong in view of Bal teaches the system of claim 1, wherein the determining the target projection data by filtering the initial projection data includes: (D. Merging the projection data, Jeong discloses obtaining
P
^
L
I
(
u
,
ϕ
)
by applying a low-pass filter to the interpolated data.).
Jeong in view of Bal does not teach determining a target filter based on the initial projection data.
De Man discloses determining a target filter based on the initial projection data ([0024-0025], De Man teaches applying an adaptive filter onto projection data, wherein the adaptive filter is computed based on attenuation values of the projection data.).
Jeong, Bal, and De Man are considered to be analogous to the claimed invention as they are in the same field of improving image quality of radiograph images. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Jeong in view of Bal such that it incorporated De Man’s method of using an adaptive filter to filter projection data. The motivation for this combination being the ability to use a specific adaptive filter which is appropriate for the projection data compared to a more generic filter that is applied to all types of projection data.
Claim 5 is rejected as being unpatentable over Jeong in view of Bal in view of De Man in view of Lee et al. (US 2020/0311490; hereinafter “Lee”).
Regarding Claim 5, Jeong in view of Bal in view of De Man teaches the system of claim 4.
Jeong in view of Bal in view of De Man does not teach determining the target filter based on the initial projection data using a trained first model.
Lee discloses determining the target filter based on the initial projection data using a trained first model ([0051], Fig. 2, Lee teaches using a trained DL network to determine filter parameters, which are used to filter sinogram data.).
Jeong, Bal, De Man, and Lee are considered to be analogous to the claimed invention as they are in the same field of improving image quality of radiograph images. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Jeong in view of Bal in view of De Man such that it further incorporated the trained DL model taught by Lee as a way to determine a filter to be applied to projection data. The motivation for this combination being the ability to train a model such that it is fine-tuned to the context of the image to be restored.
Claim 6 is rejected as being unpatentable over Jeong in view of Bal in view of Gao et al. (US 2016/0012615; hereinafter “Gao”).
Regarding Claim 6, Jeong in view of Bal teaches the system of claim 1.
Jeong in view of Bal does not teach wherein the determining the target projection data by filtering the initial projection data includes: obtaining object information of an object corresponding to the image to be processed, the object information including at least one of personal information, a scanning position, a scanning parameter, or historical scanning data; determining a target filter based on the object information; and determining the target projection data by filtering the initial projection data using the target filter.
Gao discloses wherein the determining the target projection data by filtering the initial projection data includes: obtaining object information of an object corresponding to the image to be processed, the object information including at least one of personal information, a scanning position, a scanning parameter, or historical scanning data; determining a target filter based on the object information; and determining the target projection data by filtering the initial projection data using the target filter ([0040], [0055-0056], Fig. 8, Gao teaches obtaining an imaging input which includes scanning operational parameters such as tube voltage (i.e., scanning parameter) and information regarding the imaged body part (i.e., scanning position – in that knowing which body part is imaged gives information regarding where the scanner was positioned in respect to the body to obtain an image). The information is then used to select a filter based on the imaging input.).
Jeong, Bal, and Gao are considered to be analogous to the claimed invention as they are in the same field of improving image quality of radiograph images. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Jeong in view of Bal such that the filtering process (taught by Jeong in view of Bal) incorporated the methods taught by Gao such that the filter is based on scanning parameters or scanning position associated with the motivation. The motivation for this combination being the ability to select a filter which is specific to the context of the image which is being analyzed.
Claim 7 is rejected as being unpatentable over Jeong in view of Bal in view of Gao in view of Lee.
Regarding Claim 7, Jeong in view of Bal in view of Gao teaches the system of claim 6.
Jeong in view of Bal in view of Gao does not teach wherein the determining the target filter based on the object information includes: determining the target filter based on the object information using a trained second model.
Lee discloses wherein the determining the target filter based on the object information includes: determining the target filter based on the object information using a trained second model ([0051], Fig. 2, Lee teaches using a trained DL network to determine filter parameters, which are used to filter sinogram data. The Examiner notes here that this limitation is interpreted as a target filter (specifically, “the target filter based on the object information” as defined in claim 6) is obtained based on a trained model. The limitation as presented, does not specifically require that object information is utilized by the training model in order to make the filter determination (i.e., “determining the target filter based on the object information using a trained second model, wherein the trained second model utilizes object information to determine the target filter based on the object information” as supported by Applicant’s Fig. 9.), but rather that a trained model is used to determine a target filter.).
Jeong, Bal, Gao, and Lee are considered to be analogous to the claimed invention as they are in the same field of improving image quality of radiograph images. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Jeong in view of Bal in view of Gao such that the target filter based on object information, as taught by Jeong in view of Bal in view of Gao, is obtained by Lee’s process of using a trained model to determine filter parameters in order to generate the claimed “second model”. The motivation for this combination being the ability to use a trained model that can learn optimal filtering strategies based on input data (see [0025-0026], Lee).
Claim 8 is rejected as being unpatentable over Jeong in view of Bal in view of Batenburg et al. (US 2014/0219417; hereinafter “Batenburg”).
Regarding Claim 8, Jeong in view of Bal teaches the system of claim 1, wherein the determining the target projection data by filtering the initial projection data includes: C. Reprojection data modification, D. Merging the projection data, Jeong discloses obtaining
P
^
L
I
(
u
,
ϕ
)
by applying a low-pass filter to the interpolated data, which is used to obtain the corrected projection data
P
c
o
r
r
(
u
,
ϕ
) (i.e., target projection data).).
Jeong in view of Bal does not teach determining a target filter based on a data restoration process corresponding to the initial projection data.
Batenburg discloses determining a target filter based on a data restoration process corresponding to the initial projection data ([0074], Batenburg teaches determining a filter based on a set of virtual projection data sets which have been reconstructed based on an algebraic reconstruction algorithm (i.e., data restoration process). The Examiner notes that the virtual projection dataset is reconstructed based on the algebraic reconstruction algorithm, and as the filter is determined based on the virtual projection dataset, the filter is furthermore also then based on the algebraic reconstruction algorithm.).
Jeong, Bal, and Batenburg are considered to be analogous to the claimed invention as they are in the same field of improving image quality of radiograph images. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Jeong in view of Bal such that it incorporated Batenburg’s methods of determining a filter based on the restoration algorithm. The motivation for this combination being the ability to calculate a filter which is specifically based on (i.e., influenced by) the reconstruction method applied to the projection data.
Claim 9 is rejected as being unpatentable over Jeong in view of Bal in view of Batenburg in view of Lee.
Regarding Claim 9, Jeong in view of Bal in view of Batenburg teaches the system of claim 8.
Jeong in view of Bal in view of Batenburg does not teach wherein the determining the target filter based on the data restoration process corresponding to the initial projection data includes: determining the target filter based on the data restoration process corresponding to the initial projection data using a trained third model.
Lee discloses wherein the determining the target filter based on the data restoration process corresponding to the initial projection data includes: determining the target filter based on the data restoration process corresponding to the initial projection data using a trained third model ([0051], Fig. 2, Lee teaches using a trained DL network to determine filter parameters, which are used to filter sinogram data. The Examiner notes here (similarly to the interpretation applied to claim 7) that this limitation is interpreted as a target filter (specifically, “the target filter based on the data restoration process” as defined in claim 8) is obtained based on a trained model. The limitation as presented, does not specifically require that restoration process information is utilized by the training model in order to make the filter determination (i.e., “determining the target filter based on the data restoration process using a trained third model, wherein the trained third model utilizes data restoration process information to determine the target filter based on the data restoration process” as supported by Applicant’s Fig. 10.), but rather that a trained model is used to determine a target filter.).
Jeong, Bal, Batenburg, and Lee are considered to be analogous to the claimed invention as they are in the same field of improving image quality of radiograph images. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Jeong in view of Bal in view of Batenburg such that the target filter based on a data restoration process, as taught by Jeong in view of Bal in view of Batenburg, is obtained by Lee’s process of using a trained model to determine filter parameters in order to generate the claimed “third model”. The motivation for this combination being the ability to use a trained model that can learn optimal filtering strategies based on input data (see [0025-0026], Lee).
Claim 10 is rejected as being unpatentable over Jeong in view of Bal in view of Gao in view of Yue et al. (US 2021/0272336; hereinafter “Yue”).
Regarding Claim 10, Jeong in view of Bal teaches the system of claim 1.
Jeong in view of Bal does not teach wherein the determining the target projection data by filtering the initial projection data includes: determining a target frequency band based on at least one of object information of an object corresponding to the image to be processed, or a data restoration process corresponding to the initial projection data; wherein the object information includes at least one of personal information, a scanning position, a scanning parameter, or historical scanning data; and obtaining the target projection data by filtering out data higher than the target frequency band from the initial projection data.
Gao discloses wherein the determining the target projection data by filtering the initial projection data includes: determining a filter parameter based on at least one of object information of an object corresponding to the image to be processed, or a data restoration process corresponding to the initial projection data; wherein the object information includes at least one of personal information, a scanning position, a scanning parameter, or historical scanning data; and obtaining the target projection data by filtering out data higher than the ([0023], [0040], [0062], Gao discloses performing filtering to remove artifacts, wherein the filter is a low pass filter (i.e., filters out high frequencies). Specifically, the filter configuration (which includes selecting a filter parameter) can be selected based on the portion of the body image.).
Jeong, Bal, and Gao are considered to be analogous to the claimed invention as they are in the same field of improving image quality of radiograph images. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Jeong in view of Bal such that the filtering methods taught by Jeong in view of Bal incorporate the logic disclosed by Gao such that a filter configuration is selected based on the portion of the body being imaged. The motivation for this combination being the ability to specify which filter is used increasing the performance of the overall correction system.
Jeong in view of Bal in view of Gao does not explicitly teach a target frequency band used to filter out data.
Yue discloses a target frequency band used to filter out data ([0051-0052], Yue discloses using a filter (selected based on a clinical task) which is able to filter/remove frequencies higher than a given threshold.).
Jeong, Bal, Gao, and Yue are considered to be analogous to the claimed invention as they are in the same field of improving image quality of radiograph images. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Jeong in view of Bal in view of Gao such that the filter parameter taught by Jeong in view of Bal in view of Gao is specifically a threshold used to filter out frequencies, as disclosed by Yue. The motivation for this combination being the ability to specify the exact parameter which can define the filtering ability of the filter.
Claims 14-15 are rejected as being unpatentable over Jeong in view of Bal in view of Wang and Cao (WO 2017/111997; hereinafter “Wang”).
Regarding Claim 14, Jeong in view of Bal teaches the system of claim 1, wherein the determining the initial projection data by performing the data restoration on the metal portion of the image to be processed includes: determining a metal image based on the image to be processed (Fig. 3(a), Section I. Introduction, Section II. Method, Jeong discloses a process of reducing metal artifacts precent in CT images.);
Jeong in view of Bal does not teach determining a metal trajectory based on the metal image; and obtaining the initial projection data by performing the data restoration based on the metal trajectory.
Wang discloses determining a metal trajectory based on the metal image (Fig. 1, [0030], [0034], Wang teaches obtaining a metal projection trace of a region of interest, wherein the region of interest is a region of low reliability due to metal presence.); and obtaining the initial projection data by performing the data restoration based on the metal trajectory (Fig. 1, [0034], Wang teaches performing data recovery (i.e., data restoration) along the metal projection trace.).
Jeong, Bal, and Wang are considered to be analogous to the claimed invention as they are in the same field of improving image quality of radiograph images. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Jeong in view of Bal such that it incorporates Wang’s methods of obtaining a metal projection trace, which is used to recover data along the metal projection trace. The motivation for this combination being the ability to account for radiograph data present in both horizontal and vertical axis of a detector channel.
Regarding Claim 15, Jeong in view of Bal in view of Wang teaches the system of claim 14, wherein the metal trajectory includes a metal trajectory sinogram (See Fig. 13, [00139], Wang teaches obtaining a CT projection trace of a metal portion.).
Allowable Subject Matter
Claims 11-13 and 21-24 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 PROMOTTO TAJRIAN ISLAM whose telephone number is (703)756-5584. The examiner can normally be reached Monday - Friday 8:30 am - 5:00 pm 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, Chan Park can be reached at (571) 272-7409. 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.
/PROMOTTO TAJRIAN ISLAM/Examiner, Art Unit 2669 /CHAN S PARK/Supervisory Patent Examiner, Art Unit 2669
Prosecution Insights