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 at pages 8-9 of Remarks filed 16 September 2026 (hereinafter “Remarks”), with respect to the rejections of claims 3, 4 and 21 under 35 U.S.C. 112(b) have been fully considered and are persuasive. The rejections have been withdrawn.
Applicant’s arguments at pages 9-13 of Remarks with respect to the rejections under 35 U.S.C. 103 have been fully considered and are persuasive. The rejections have been withdrawn.
Kim describes generating a 2D tumor mask generated from concentric circles (e.g., see Kim, p2188). However, Applicant argues, “Kim does not describe a bounding box around the tumor mask. Moreover, Kim does not describe determination of effects extending outside the tumor mask.” Remarks at pg. 9. Examiner agrees.
Applicant argues, “Kim is also insufficient to describe using a second diffusion model machine-learned network, a second noise input to generate the medical image with the synthesized medical abnormality positioned in accord with the abnormality spatial mask, as recited by claim 1, as amended.” Remarks at pg. 10. Examiner agrees.
Kim discloses mask-conditioned synthesis of tumor images, where the mask is further broken down into different regions. As shown in Figure 2 of Kim, the three regions include two different tumor regions and one outer edema region of the tumor. The synthesized tumor is essentially pasted into the normal/healthy image leaving the pixels outside the synthesized area being unchanged. Kim’s synthesis method is GAN-based, not diffusion-based.
Machacek discloses a two-stage diffusion model in Figure 1. The first stage generates a synthetic mask. The second stage generates a synthetic image conditioned on the mask. It would be beneficial to use Kim’s structured tumor mask in place of Machecek’s mask by modifying the conditioning input to accept a multi-region mask. Doing so would inform the diffusion model not only where the lesion is, but also give it internal spatial structure, for example, c1 is a central region, c2 is an intermediate region, and c3 is an outer region. The model would have to be re-trained/fine-tuned for the model to learn the meaning of c1, c2 and c3.
Machacek does not disclose bounding-box conditioning. While masks and bounding boxes are similar in their application within diffusion models, a bounding box has lower annotation cost because it provides a localization, whereas masks are pixel-wise annotated which has a higher cost. Masks can be generated from bounding boxes.
Han is a GAN-based method like Kim. Specifically, Han discloses bounding box conditioned GAN synthesis. Han also refers to “bounding box masks” (pg. 2) and treats them in a similar manner to Kim by using the bounding box as a mask to delineate synthetic tumor image data from surrounding normal tissue.
Examiner agrees with Applicant’s characterization of Han as not describing “the original image as being a pre-abnormality image.” See Remarks at pg. 10. However, from the standpoint of prior art-based rejections, this in itself does not make Han unable to be combined with other prior art under 35 U.S.C. 103. Accordingly, while Han may be “unable to generate images of abnormalities from original images without such an abnormality” (See Remarks at pg. 10), as a standalone disclosure, it is reasonable to assume that the image processing operations of Han could be confined to a particular region within a larger image.
Applicant’s remaining arguments concerning rejections under 35 U.S.C. 103 are either predicated on the arguments addressed above or are essentially duplicative of the substantive issues raised above.
The previously-applied ground of rejection under 35 U.S.C. 103 is no longer tenable to reject the pending claims. Accordingly, the rejections under 35 U.S.C. 103 are withdrawn.
Drawings
The drawings are objected to because of a minor informality in Figure 2. Step 220 is
described with the text, “Denoise a first noise input to obtain an abnormality spatial mask.” Based on paragraph 31 of the specification, the term “first” in the text describing step 220 should be changed to “second”.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Objections
Claim 14 is objected to because of the following informalities: the second instance of “a defined multidimensional space” should be changed to “the defined multidimensional space” for clarity. Appropriate correction is required.
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 1-13 and 17-19 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 1 recites, “obtain a pre-abnormality image mapped into the defined multidimensional space” (emphasis added). The phrase “a defined multidimensional space” (emphasis added) appears later in the claim. It is unclear whether “a defined multidimensional space” is the antecedent basis of “the defined multidimensional space”, as they could be interpreted as referring to different spaces. For purposes of applying prior art, “the defined multidimensional space” is interpreted as “[[the]] a defined multidimensional space” and “a defined multidimensional space” is interpreted as “[[a]] the defined multidimensional space”. Dependent claims 2-13 are rejected for inheriting and not curing the deficiencies of claim 1.
Claim 17 recites, “the defined multidimensional space”, but there are two instances of “a defined multidimensional space” in claim 14, which confuses the antecedent basis. Dependent claims 18 and 19 are rejected for inheriting and not curing the deficiencies of claim 1.
Allowable Subject Matter
Claim 1 would be allowable if rewritten or amended to overcome the rejection under 35 U.S.C. 112(b) set forth in this Office action.
Claims 2-13 and 17-19 would be allowable if rewritten to overcome the rejection(s) under 35 U.S.C. 112(b) set forth in this Office action and to include all of the limitations of the base claim and any intervening claims.
Claim 14 is objected to for minor informalities and would be allowed if the objection was overcome.
Claims 15, 20 and 21 are allowed.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion to Xie et al. discloses image diffusion constrained by bounding boxes with spatial constraints of an inner box, an outer box, and corners, which is conceptually similar to the concentric circular tumor mask of Kim.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RYAN P POTTS whose telephone number is (571)272-6351. The examiner can normally be reached M-F, 9am-5pm 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, Sumati Lefkowitz can be reached at 571-272-3638. 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.
/RYAN P POTTS/Examiner, Art Unit 2672
Prosecution Insights