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 July 28, 2026 has been entered. Claims 1, 4–12, and 15–22 are currently pending. Claims 1, 4–12, and 15–19 have been amended, and claims 2–3 and 13–14 have been canceled. Examination remains directed to elected Species I.C and claims 1, 6, 11, 12, 17, and 22 readable thereon. Claims 4–5, 7–10, 15–16, and 18–21 remain withdrawn from further consideration.
Terminal Disclaimer
The electronic terminal disclaimer filed on July 28, 2026, expressly identifying U.S. Patent No. 12,591,072 B2, has been approved. Applicant’s request for reconsideration of the corresponding nonstatutory double-patenting rejection has been considered. Accordingly, the previous rejection of claims 1, 6, 11, 12, 17, and 22 on the ground of nonstatutory double patenting over claims 1, 5–6, and 10 of U.S. Patent No. 12,591,072 B2 in view of Gerlach is withdrawn. Previously rejected claims 2–3 and 13–14 is moot due to canceled claims.
Response to Arguments
Applicant's arguments filed July 28, 2026, on pages 8–12 of the Remarks, have been fully considered. Applicant’s amendments and arguments are persuasive with respect to the previous §112(f) interpretation, the rejection of claims 1, 6, 11, 12, 17, and 22 under 35 U.S.C. § 112(b). Arguments are also persuasive with respect to the previous rejection of claims 1–3, 6, 11–14, 17, and 22 under 35 U.S.C. § 103. Accordingly, the previous §112(f) interpretation of these limitations is not maintained, the previous rejections under 35 U.S.C. §112(b) and 35 U.S.C. §103 are withdrawn. However, new grounds of rejection under 35 U.S.C. §103 are made in this Office action. The revised rejections apply Ikeda in view of Wang and Sun to claims 1, 11, 12, and 22, and further in view of Brooks in the rejection of claims 6 and 17.
Applicant’s amendments to independent claims 1 and 12 have been fully considered. In addition to incorporating the previously dependent pixel-array, addition-processing, and trained-model limitations, Applicant has introduced the specific M×N rectangular scintillator units, one-to-one physical-pixel correspondence, and mesh-shaped separation structure. These substantive limitations narrow the claimed combination beyond the subject matter addressed by the previous action. Because Applicant’s substantive amendments necessitated the new grounds of rejection presented in this Office action, this action is properly made final in accordance with MPEP §706.07(a).
Based on these facts, this action is made FINAL.
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.
Claims 1, 11-12, and 22 are rejected under 35 U.S.C. §103 as being unpatentable over Ikeda (Ikeda et al, US 2020/0241150 A1, 2020), in view of Sun (Sun et al, US 2004/0251420 A1, 2004), further in view of Wang (Wang et al, US 2021/0097662 A1, 2021).
Regarding claim 1, Ikeda teaches a radiographic image acquiring device comprising:
an imaging device configured to scan radiation passing through a subject in one direction and capture an image of the radiation to acquire a radiographic image;
( [0005–0006], [0038–0043], [Fig. 1]: Ikeda teaches conveying inspection target W in the Y-axis direction while irradiating the target with X-rays and detecting the transmitted X-rays using detection means 130. Each detection element within a detection-element group sequentially detects radiation transmitted through the same target region as the target moves. The detected outputs determine image-pixel brightness; Ikeda further explains that sequential transmission-image lines are arranged in the scanning direction to generate a two-dimensional image. The Y-axis direction corresponds to the claimed one direction. )
a scintillator layer provided on the imaging device to convert the radiation into light; and
( [0044]: Ikeda teaches a conversion X-ray detection element in which a scintillator converts X-rays into visible light, which is then received by a photodiode to generate an output. )
an image processor configured to execute noise reducing processing of reducing noise from the radiographic image,
( [0025], [0045–0047], and [0051], [0054–0055]: Ikeda teaches shortening and appropriately routing the wiring between the detection elements and the reading means to reduce the influence of noise and suppress deterioration of detection sensitivity. The detection-element outputs are read and added to determine corresponding image-pixel brightness. Accordingly, Ikeda addresses noise reduction in the acquisition path used to form the radiographic image. )
wherein the imaging device includes
a detection element configured such that pixel lines each having M (M is an integer equal to or greater than 2) pixels arrayed in the one direction are arrayed in N columns (N is an integer equal to or greater than 2) in a direction orthogonal to the one direction to output a detection signal related to the light for each of the pixels, and
( [0043–0044], [0057], [Fig. 3]: Ikeda teaches detection means 130 comprising N detection-element groups arranged along the X-axis, each group containing M detection elements arranged along the Y-axis, where M and N are each integers of at least two and the X-axis is orthogonal to the Y-axis. Each element produces an output corresponding to detected intensity; in the indirect-conversion embodiment, the photodiode generates that output from the scintillator-produced light. Figure 3 illustrates M=4 elements per group and N=6 groups. Ikeda’s individual detection elements correspond to the claimed physical pixels, and each M-element group corresponds to a claimed pixel line. )
a readout circuit configured to output the radiographic image by performing addition processing on detection signals output from at least two of the M pixels for each of the pixel lines of N columns of the detection element and outputting the N detection signals on which the addition processing is performed, and
( [0039], [0043], [0045–0047], [Fig. 1]: Ikeda teaches reading means 140 that sequentially outputs electrical signals obtained from the detection elements and adding means 150 that adds those signals for each detection-element group. The added outputs determine the brightness of the image pixel corresponding to the target region detected by that group. Reading means 140 and adding means 150 collectively provide the claimed readout functions. Because each of the N groups contains M≥2 elements, adding the outputs within each group combines signals from at least two physical pixels and produces one added pixel result per group, corresponding to N added results across the N groups. Figure 1 shows the output of adding means 150 supplied to display means 151, tying the added detection signals to the radiographic-image output. )
Ikeda teaches reducing the influence of noise through detector-wiring arrangements. Thus, Ikeda recognizes the benefit of noise reduction in the acquisition path used to form the radiographic image. However, Ikeda does not expressly disclose neural-network-based removal of noise from the resulting image. Wang teaches that image-processing functionality:
an image processor configured to execute noise removal processing of removing noise from the radiographic image,
( [0004], [0036–0037], [0044], and [0062]: Wang teaches that CT uses X-ray radiation to produce images; computing device 104 includes processor 110 configured to perform the operations of MAP-NN apparatus 126. The neural-network modules receive an input low-dose CT image and generate progressively denoised output images. Paragraph [0062] expressly describes these operations as producing “noise removal from an image”. Therefore, processor 110 executing the MAP-NN operations provides the image-processing functionality for removing noise from the X-ray-derived input image. )
the image processor inputs the radiographic image to a trained model built in advance through machine learning using image data and executes the noise removal processing.
( Wang, [0031–0032], [0036–0037], and [0049– 0050]: teaches processor 110 executing the MAP-NN operations. The neural-network model is trained using low-dose CT images and corresponding normal-dose CT reference images, with network parameters adjusted during training. After training, the model receives an input low-dose CT image and processes it through trained neural-network modules to generate progressively denoised output images. Thus, Wang teaches processor-implemented denoising using a model previously trained through machine learning on image data. )
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Ikeda’s radiographic image acquiring device to include an image processor applying Wang’s trained neural-network denoising technique to the radiographic image produced after Ikeda’s readout and addition processing, with the model trained using image data representative of the intended acquisition conditions. The reason for this modification would have been to reduce noise remaining in the acquired image and thereby improve its quality for inspection. Ikeda already addresses the adverse influence of noise on detection performance, while its reading and adding means produce image-pixel values suitable for subsequent image processing [see Ikeda, 0045–0047 and 0051, 0054–0055]. The additional image-processing stage would complement, rather than replace, Ikeda’s noise-reducing wiring arrangement.
Ikeda [as modified by Wang] teaches an M×N detector arrangement and an indirect-conversion embodiment using a scintillator and photodiodes ( Ikeda > [0043–0044] ), but does not specify the claimed partitioning of the scintillator, one-to-one rectangular scintillator-unit arrangement and mesh-shaped separation unit. However, Sun teaches these features:
the scintillator layer includes
M×N rectangular scintillator units disposed separately to correspond one-to-one to the M×N pixels, and
( [0050], [0052], and [0058], [Fig. 4]: Sun teaches scintillator material 450 filling individual grid cells registered with corresponding photodiodes in a 1024×1024-pixel detector, with matching grid and detector pitch. Paragraph [0052] expressly permits square cells. The scintillator material within each separated cell corresponds to a scintillator unit. Under the interpretation that square cells are rectangular, this embodiment provides rectangular scintillator units in one-to-one correspondence with physical detector pixels, with M=N=1024 in the disclosed example. )
a separation unit disposed between adjacent ones of the scintillator units and formed in a mesh shape so as to partition the M×N scintillator units, and
( [0036], [0050–0052], and [0058], [Fig. 4]: Sun teaches a crosshatched grid whose cells contain scintillator material and whose intervening walls confine scintillation light within individual cells. Paragraph [0051] applies the previously described grid to the scintillator-filled plate. The intersecting walls of the square-cell grid correspond to the claimed mesh-shaped separation unit partitioning adjacent scintillator units. )
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the scintillator arrangement of Ikeda [as modified by Wang] according to Sun’s pixel-registered, grid-structured scintillator teaching, by providing a separate rectangular scintillator cell for each of Ikeda’s M×N physical detector pixels and intervening grid walls forming a mesh-shaped partition. The reason for the modification would have been to limit optical spread between neighboring physical pixels and thereby preserve spatial information in the detected signals before groupwise addition and subsequent image denoising. This reason is supported by Sun’s optical-confinement teaching in [0058].
Regarding claim 11, Ikeda [as modified by Wang and Sun] teaches a radiographic image acquiring system comprising: the radiographic image acquiring device according to claim 1;
a radiation source configured to irradiate the subject with radiation; and
( Ikeda > [0039], [0040], and [0042], [Fig. 1]: teaches nondestructive inspection apparatus 100 including electromagnetic wave irradiation means 110, which irradiates inspection target W with electromagnetic waves, expressly including X-rays. Electromagnetic wave detection means 130 detects the radiation transmitted through the irradiated target. Accordingly, irradiation means 110 in the disclosed X-ray implementation corresponds to the claimed radiation source, and inspection target W corresponds to the claimed subject. )
a transport device configured to transport the subject in the one direction with respect to the imaging device.
( Ikeda > [0041–0043], [Fig. 1]: teaches conveyance means 120, expressly exemplified as a belt conveyor, that transports inspection target W in the Y-axis direction at a predetermined speed. Detection means 130 is positioned to receive radiation transmitted through the target, and the detection elements arranged along the Y-axis sequentially detect radiation transmitted through the same target region as the target moves. Thus, conveyance means 120 transports the subject relative to detection means 130 along the Y-axis direction, corresponding to the claimed “one direction” identified in the claim 1 mapping. )
Regarding claims 12 and 22, the rationales provided for claims 1 and 11 are incorporated herein. In addition, the device of claim 1 corresponds to the method of claim 12; and the system of 11 corresponds to the method of claim 22; and performs the steps disclosed herein. Therefore, the claims are all rejected.
Claims 6 and 22 are rejected under 35 U.S.C. §103 as being unpatentable over Ikeda [as modified by Wang and Sun], in view of Brooks (Brooks et al (2018). Unprocessing Images for Learned Raw Denoising (1811.11127v1). arXiv.).
Regarding claim 6, Ikeda [as modified by Wang and Sun] teaches the radiographic image acquiring device according to claim 1, wherein the image processor is configured to
Ikeda [as modified by Wang and Sun], as set forth in the claim 1 mapping above, provides radiographic-image acquisition, addition-based readout, and trained-model noise removal. However, that combination does not expressly disclose the additional sequence where Brooks teaches:
derive an evaluation value obtained by evaluating spread of a noise value from the pixel value of each pixel of the radiographic image on the basis of relationship data indicating a relationship between the pixel value and the evaluation value and generate a noise map that is data in which the derived evaluation value is associated with each pixel of the radiographic image, and
( [§3.1, Eqs. (1)–(2), and §4.3, Fig. 6]: Brooks teaches a signal-dependent noise model in which noise variance is expressed as
σ
2
x
=
λ
r
e
a
d
+
λ
s
h
o
t
x
, where
x
denotes the true signal intensity and the parameters characterize read noise and shot noise. The continuation of §3.1 on page 4 explains that these parameters can be calculated for an exposure and stored with the image metadata. Section 4.3 teaches generating a per-pixel estimate of noise standard deviation based on the shot- and read-noise parameters, and Fig. 6 identifies the corresponding spatially organized noise-level-map input. The noise-model parameters, together with the disclosed relationship, provide the relationship data, while the pixel-associated estimates provide evaluations of noise spread. )
input the radiographic image and the noise map to the trained model and execute noise removal processing of removing noise from the radiographic image.
( [§4.3–§4.4, p. 6, Fig. 6]: Brooks teaches a denoising neural network receiving a noisy raw image together with a corresponding noise-level map, with the map concatenated to the image as additional input channels. The network predicts a residual that is added to the input image to produce a reduced-noise output image. Section 4.4 describes training the network using noisy and clean image pairs and optimizing its parameters before evaluation. )
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to further modify the image processor of Ikeda [as modified by Wang and Sun] to derive pixel-associated noise-spread evaluations using an intensity-dependent noise relationship, generate the corresponding noise map, and provide both the acquired radiographic image and that map to a trained denoising model, according to Brooks’s noise-conditioned denoising approach and the identified implementation. The reason for the modification would have been to provide the denoiser with explicit information concerning the expected noise magnitude at each image location, rather than require the model to determine the local noise level solely from image content. Brooks supplies this additional input [§4.3], and reports reduced denoising quality when the noise-level input is omitted [§5]. These teachings provide a reason to incorporate pixel-associated noise information into the existing trained-denoising stage.
Regarding claim 17, the rationale provided for claims 6 is incorporated herein. In addition, the device of claim 6 corresponds to the method of claim 17, and performs the steps disclosed herein. Therefore, the claims are all rejected.
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 KEN KUDO whose telephone number is (571)272-4498. The examiner can normally be reached M-F 8am - 5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Vincent Rudolph can be reached at 571-272-8243. 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.
KEN KUDO
Examiner
Art Unit 2671
/KEN KUDO/Examiner, Art Unit 2671
/VINCENT RUDOLPH/Supervisory Patent Examiner, Art Unit 2671
