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
Applicant's arguments filed July 08, 2026 have been fully considered but they are not persuasive.
Applicant argues that Ozcan and Takeshima do not teach or render obvious at least the features of "the adjacent pixels used in the regularization term include pixels adjacent in orthogonal directions and pixels adjacent in diagonal directions". The Office Action relies on the configuration disclosed in Fig. 35A, and Formulas (19) to (21) described in paragraphs 0199 to 0201 of Ozcan for a teaching of Applicant's claimed evaluation function including the error evaluation term and the regularization term. However, in the anisotropic total variation loss TV{G(x)} represented by Formula (21) in paragraph 0201 of Ozcan, only the pixels adjacent in orthogonal directions are used for obtaining the loss term. On the other hand, in the configuration of the present embodiment of the invention, as clearly described in above amended claim, the adjacent pixels used in the regularization term of the evaluation function include pixels adjacent in orthogonal directions, and in addition, include pixels adjacent in diagonal directions.
In response, the Examiner respectfully disagrees. Ozcan discloses in page 23, paragraph #0201 that “where i and j are the pixel indices in an MxN pixel image. …”. It is clear that the pixel indices i and j in an MxN pixel image of Ozcan include the pixels adjacent in orthogonal directions and pixels adjacent in diagonal directions. Thus, the proposed combination of references does disclose the newly added limitations.
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 are rejected under 35 U.S.C. 103 as being unpatentable over Ozcan et al. (US 2022/0114711 A1) in view of Takeshima Tomochika et al. (JP 2021071936 A).
In considering claim 1, Ozcan et al. discloses all the claimed subject matter, note 1) the claimed a processing unit configured to input an input image to a convolutional neural network, and output an output image from the convolutional neural network is met by x is the low-resolution input image 20 to the generator network 120, g(x) is the network output image and the loss is computed using g(x) (Fig. 35A, page 22, paragraph #0197 to page 23, paragraph #0200), 2) the claimed a training unit configured to use an evaluation function including an error evaluation term representing an evaluation value related to an error between the output image and the target image ( the L.sub.1 loss is the mean pixel difference between the generator's output 124 and the ground truth image) and a regularization term representing an evaluation value related to a difference of pixel values between adjacent pixels in the output image (the formula [0201] calculates the anisotropic total variation loss using differences between adjacent pixels), and train the convolutional neural network based on a value of the evaluation function is met by training the deep neural network 10 based on the overall loss function for the generator network (Fig. 35A, page 23, paragraph #0199 to paragraph #0203), and 3) the claimed the adjacent pixels used in the regularization term include pixels adjacent in orthogonal directions and pixels adjacent in diagonal directions is met by training the deep neural network 10 based on the overall loss function for the generator network (Fig. 35A, page 23, paragraph #0199 to paragraph #0203).
However, Ozcan et al. explicitly do not disclose the claimed wherein the output image after respective processes of the processing unit and the training unit are repeatedly performed a plurality of times is set as an image after the noise reduction processing.
Takeshima Tomochika et al. teach that the first processing unit 10 repeatedly learns a convolutional neural network (CNN) by using a random noise image Bn as an input image and the target image A as a teaching image for each of N pieces of random noise images B1-BN, and acquires an image output from the CNN after the repeated learning as an intermediate image Cn (Fig. 1, see the abstract).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the repeatedly performed training as taught by Takeshima Tomochika et al. into Ozcan et al.’s system in order to effectively reduce noise of the target image even when only one target image exists or even when an SN ratio of the target image is low.
In considering claim 2, the claimed wherein the target image is a tomographic image of a subject created based on coincidence information collected by using a radiation tomography apparatus is met by the tomographic image (page 1, lines 17-26 of Takeshima Tomochika et al.).
The motivation to combine the references has been discussed in claim 1 above.
In considering claim 3, the claimed wherein the processing unit is configured to input an image representing morphological information of the subject to the convolutional neural network as the input image is met by the TIRF-SIM images that undergo rapid morphological changes during development (Figs. 31A-31O, page 5, paragraph #0060 of Ozcan et al.).
The motivation to combine the references has been discussed in claim 1 above.
In considering claim 4, the claimed wherein the processing unit is configured to input an MRI image of the subject to the convolutional neural network as the input image is met by the MRI image (page 1, lines 17-26 of Takeshima Tomochika et al.).
The motivation to combine the references has been discussed in claim 1 above.
In considering claim 5, the claimed wherein the processing unit is configured to input a CT image of the subject to the convolutional neural network as the input image is met by the CT image (page 1, lines 17-26 of Takeshima Tomochika et al.).
The motivation to combine the references has been discussed in claim 1 above.
In considering claim 6, the claimed wherein the processing unit is configured to input a static PET image of the subject to the convolutional neural network as the input image is met by the PET image (page 1, lines 17-26 of Takeshima Tomochika et al.).
The motivation to combine the references has been discussed in claim 1 above.
In considering claim 7, the claimed wherein the processing unit is configured to input a random noise image to the convolutional neural network as the input image is met by the random noise image B (Fig. 1, page 2, lines 26-44 of Takeshima Tomochika et al.).
The motivation to combine the references has been discussed in claim 1 above.
Method claims 8-14 are rejected for the same reason as discussed in apparatus claims 1-7 above, respectively.
In considering claim 15, the claimed wherein the regularization term is a term for suppressing overtraining of the convolutional neural network by penalizing the difference of the pixel values between the adjacent pixels in the output image is met by training the deep neural network 10 based on the overall loss function for the generator network (Fig. 35A, page 23, paragraph #0199 to paragraph #0203 of Ozcan et al.).
The motivation to combine the references has been discussed in claim 1 above.
Claim 16 is rejected for the same reason as discussed in claim 15 above.
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 TRANG U TRAN whose telephone number is (571)272-7358. The examiner can normally be reached M-F 10:00AM- 6:00PM.
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, JOHN W. MILLER can be reached at 571-272-7353. 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.
September 22, 2026
/TRANG U TRAN/Primary Examiner, Art Unit 2422
Prosecution Insights