Prosecution Insights
Last updated: November 20, 2026
Application No. 18/180,939

MEDICAL IMAGE PROCESSING APPARATUS, METHOD OF MEDICAL IMAGE PROCESSING, AND NON-TRANSITORY COMPUTER READABLE MEDIUM

Final Rejection §103
Filed
Mar 09, 2023
Priority
Mar 09, 2022 — JP 2022-036241
Examiner
ZHANG, FAN
Art Unit
2682
Tech Center
2600 — Communications
Assignee
Canon Inc.
OA Round
4 (Final)
55%
Grant Probability
Moderate
5-6
OA Rounds
0m
Est. Remaining
72%
With Interview

Examiner Intelligence

Grants 55% of resolved cases
55%
Career Allowance Rate
340 granted / 614 resolved
-6.6% vs TC avg
Strong +17% interview lift
Without
With
+16.6%
Interview Lift
resolved cases with interview
Typical timeline
3y 3m
Avg Prosecution
31 currently pending
Career history
655
Total Applications
across all art units

Statute-Specific Performance

§101
7.8%
-32.2% vs TC avg
§103
70.7%
+30.7% vs TC avg
§102
11.6%
-28.4% vs TC avg
§112
2.4%
-37.6% vs TC avg
Black line = Tech Center average estimate • Based on career data from 614 resolved cases

Office Action

§103
DETAILED ACTION Notice of AIA Status 1. 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 2. Applicant’s remarks received on 08/19/2026 with respect to the amended independent claims have been acknowledged and are moot in view of a new ground of rejection necessitated by the corresponding amendment. Currently claims 1-25 are rejected. Response to Amendment Claim Rejections - 35 USC § 103 3. 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 of this title, 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. 4. Claims 1-20 and 22-25 are rejected under 35 U.S.C. 103 as being unpatentable over Zheng et al (Deep Pancreas Segmentation with Uncertain Regions of Shadowed Sets, May 2020) and in further view of Wang et al (Ensemble of Deep Learning Cascades for Segmentation of Blood Vessels in Confocal Microscopy Images, October 2021), Yuan et al (Automatic liver and tumor segmentation based on deep learning and globally optimized refinement, 2021), and Simon (US Pub: 2011/0317888). Regarding claim 1 (currently amended), Zheng et al teaches: An image processing apparatus comprising processing circuitry configured to acquire an input image obtained from a medical scan of a subject by a medical scanning apparatus, infer a first region image about a first region included in the input image, generate a corrected mask image in which the first portion is corrected using the acquired mask image by executing correction processing, and perform inference about a second region included in the input image based on the input image and the corrected image [page 46: 2, 2.1, 2.2, page 47: 2.3, fig. 1 (Probability map shows the first region image corrected through re-weighting for boundaries of pancreas. And the uncertain region is the second region estimated based on the first corrected region image.)]. Zheng et al does not takes the input image and the corrected mask as inputs to a learned model for a second portion. In the same field of endeavor, Wang et al teaches: acquire a mask image, which indicates a first portion in the input image, wherein the mask image is generated from a first inference using a medical imaging result of a subject [page 2: DBAC (P attention map/soft mask); page 3: p04 (feature map Q)], generate a corrected mask image, in which the first portion is corrected using the acquired mask image by executing correction processing [page 3: p03, p04], and perform a second inference to obtain a second portion in the input image by inputting the input image and the corrected acquired mask image to a learned model [page 4: p01 (Concatenated input comprises input image and corrected mask Q.); figs. 3 and 4]. Therefore, given Wang et al’s prescription, it would have been obvious for an ordinary skilled in the art before the effective filing date of the claimed invention to combine the teaching of the two to apply the corrected mask to further refine a region from an input image as suggested by Wang et al’s cascade approach to Zheng et al’s setting for precise segmentation. Zheng et al in view of Wang et al does not explicitly disclose reducing sharpness of a boundary of the first region. In the same field of endeavor, Yuan et al teaches: acquire a mask image, which indicates a first portion in the input image [page 306: p02]; generate a corrected mask image by applying correction processing to broaden or blur at least part of the first portion in the acquired mask image [page 311: 2.4 (get more smooth, precise and connective segmentation result…)]. Therefore, given Yuan et al’s prescription on two stage liver mask and tumor inference generation by applying correction processing to smooth boundary of masked liver image, it would have been obvious for an ordinary skilled in the art before the effective filing date of the claimed invention to combine the teaching of all to generate corrected mask image by reducing sharpness of boundary and use processed mask for tumor region of interest restriction with narrowed search range and improved accuracy. Zheng et al in view of Wang et al and Yuan et al does not blur or broaden a portion of the image. In the same field of endeavor, wherein the corrected mask image is generated by applying the correction processing to broaden or blur the at least part of the first portion in the acquired mask image, and the second portion is a region of medical interest in the subject [p0049]; and cause a display to display the second portion in the input image [00083]. Therefore, it would have been obvious for an ordinary skilled in the art before the effective filing date of the claimed invention to combine the teaching of all to implement Simon’s mask blurring technique with Gaussian filter to define a spatial region for smoother lesion boundaries near liver surface to reduce segmentation leakage. Regarding claim 2 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al and Wang et al further teaches: The image processing apparatus according to claim 1, wherein the processing circuitry is further configured to generate the corrected mask image with a shape or a distribution of the first portion corrected using the acquired mask image [Zheng: fig. 1 (Probability map shows a shape of the first region corrected.); Wang: page 2: B]. Regarding claim 3 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 1, wherein the correction processing executed by the processing circuitry is processing to mitigate an influence of an inference error of the mask image on the second inference about the second portion [page 47: 2.3 (weights for each pixel are corrected.)]. Regarding claim 4 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 1, wherein the correction processing executed by the processing circuitry is processing to increase an ambiguity of a shape of the first portion in the acquired mask image or an ambiguity of a distribution of the first portion in the acquired mask image [page 46: p3 (U-net involves a combination of down sampling to shrink an image to clarify a boundary and up sampling to re-enlarge the image, which leads to blurred boundaries.)]. Regarding claim 5 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 1, wherein the correction processing executed by the processing circuitry is processing to smooth the acquired mask image [page 49: p03 (Smoothing boundaries of pancreas)]. Regarding claim 6 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 1, wherein the processing circuitry is further configured to: acquire a correction parameter for use in the correction processing and generate the corrected image using the correction parameter [page 46: 2 (ground truth labeling)]. Regarding claim 7 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 1, wherein the processing circuitry is further configured to: determine a correction parameter for use in the correction processing and generate the corrected mask image using the correction parameter [page 47: 2.3, 2.4 (weights)]. Regarding claim 8 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 7, wherein the correction parameter is a value associated with the learned model for use in the second inference about the second portion [page 47: 2.3, 2.4]. Regarding claim 9 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 1, wherein the processing circuitry is further configured to perform learning to generate a first learned model for use in the first inference about the first portion [page 46: 2.1]. Regarding claim 10 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 7, wherein the processing circuitry is further configured to determine the correction parameter based on a number of pixels forming the first portion [page 46: p3, p7]. Regarding claim 11 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 7, wherein the processing circuitry is further configured to determine a respective plurality of the correction parameters in accordance with a plurality of partial portions forming the first portion [page 46: p3 (Confident and uncertain regions are forming the first region.)]. Regarding claim 12 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 11, wherein the processing circuitry is further configured to determine the respective plurality of correction parameters for the plurality of partial portions in accordance with a prior probability of accuracy of the second inference about the second portion [fig. 1: Weights are correction parameters.]. Regarding claim 13 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing device according to claim 1, wherein the correction processing executed by the processing circuitry is processing to expand the first portion in the acquired mask image [page 47: 2.3 (Defining uncertain boundary expands the first region.)]. Regarding claim 14 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 1, wherein the first portion is an organ and the second portion is a tumor or lesion [fig. 5]. Regarding claim 15 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 1, wherein the processing circuitry is further configured to infer a second portion image, which is an image of the second portion [page 47: 2.3, fig. 3 (The uncertain/second region is further inferred based on the probability maps of pancreas.)]. Regarding claim 16 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 1, wherein the processing circuitry is further configured to infer a presence or an absence of the second portion [page 47: 2.3 (Defining uncertain region’s presence or absence)]. Regarding claim 17 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 1, wherein the processing circuitry is configured to perform a first correction to clarify a boundary of the first portion and then performs second correction to blur the boundary of the first portion to generate the corrected image [page 46: p3 (U-net involves a combination of down sampling to shrink an image to clarify a boundary and up sampling to re-enlarge the image, which leads to blurred boundaries.)]. Claim 18 (currently amended) has been analyzed and rejected with regard to claim 1. Claim 19 (currently amended) has been analyzed and rejected with regard to claim 1 and in accordance with Zheng et al’s further teaching on: A non-transitory computer readable medium storing instructions that cause a computer to execute a procedure comprising [page 46: 2.1 (Neural network is stored and executed on a computer.)]. Regarding claim 20 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Wang et al further teaches: The image processing apparatus according to claim 1 wherein the acquired mask image is acquired based on the first inference about the first portion on the input image as the medical imaging result of a subject [page 2: DBAC (attention map), page 3: DDMAC (feature map), page 7: conclusion]. Regarding claim 22 (New), the rationale applied to the rejection of claim 1 has been incorporated herein. Yuan et al further teaches: The image processing apparatus according to claim 1, wherein the processing circuitry is further configured to generate the corrected mask by applying the correction processing to (a) increase an ambiguity of a shape of the first portion in the mask image, (b) increase an ambiguity of distribution of the first portion in the mask image, (c) smooth the mask image, or (d) blur the boundary of the first portion in the mask image [page 311: 2.4]. Regarding claim 23 (New), the rationale applied to the rejection of claim 1 has been incorporated herein. Simon further teaches: The image processing apparatus according to claim 1, wherein the correction processing executed by the processing circuitry is processing to apply a Gaussian filter to the mask image [p0049]. Regarding claim 24 (New), the rationale applied to the rejection of claim 1 has been incorporated herein. Simon further teaches: The image processing apparatus according to claim 1, wherein the correction processing executed by the processing circuitry is processing to complement lost parts of the first portion [p0056, p0057]. Regarding claim 25 (New), the rationale applied to the rejection of claim 1 has been incorporated herein. Zheng et al further teaches: The image processing apparatus according to claim 1, wherein the first portion is a region of pancreas, and wherein the second portion is a region of pancreatic cancer [abstract]. 5. Claim 21 is rejected under 35 U.S.C. 103 as being unpatentable over Zheng et al (Deep Pancreas Segmentation with Uncertain Regions of Shadowed Sets, May 2020), Wang et al (Ensemble of Deep Learning Cascades for Segmentation of Blood Vessels in Confocal Microscopy Images, October 2021), Yuan et al (Automatic liver and tumor segmentation based on deep learning and globally optimized refinement, 2021), and Simon (US Pub: 2011/0317888); and in further view of Han et al (Boundary Loss-Based 2.5D Fully Convolutional Neural Networks Approach for Segmentation: A Case Study of the Liver and Tumor on Computed Tomography, April, 2021). Regarding claim 21 (previously presented), the rationale applied to the rejection of claim 1 has been incorporated herein. Yuan et al further teaches smoothing mask image with first portion is liver and the second portion is tumor and smooth the first portion of mask image to narrow down search of tumor of [page 310: p01]. For a redundant teaching in the same field of endeavor, Han et al teaches: The image processing apparatus according to claim 1, wherein the correction processing executed by the processing circuitry is processing to (a) increase an ambiguity of a shape of the first portion in the mask image. (b) increase an ambiguity of distribution of the first portion in the mask image, or (c) smooth the mask image [page 10: p03], wherein the first portion is an organ of the subject and the second portion is a tumor or lesion [page 7: fig. 2], and wherein the corrected first portion in the corrected mask image is used as information to narrow down a search range of the second portion to be inferred [page 10: 3.4]. Therefore, it would have been obvious for an ordinary skilled in the art before the effective filing date of the claimed invention to combine the teaching of all to smooth a mask to obtain a ROI for more accurate and narrowing inference. Conclusion 6. There is a new ground of rejection necessitated by the corresponding amendment 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 extension fee 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. Contact 7. Any inquiry concerning this communication or earlier communications from the examiner should be directed to FAN ZHANG whose telephone number is (571)270-3751. The examiner can normally be reached on Mon-Fri 9:00-5:00. 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, Benny Tieu can be reached on 571-272-7490. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /Fan Zhang/ Patent Examiner, Art Unit 2682
Read full office action

Prosecution Timeline

Show 3 earlier events
Jan 12, 2026
Final Rejection mailed — §103
Apr 13, 2026
Request for Continued Examination
Apr 15, 2026
Response after Non-Final Action
Apr 22, 2026
Non-Final Rejection mailed — §103
Aug 17, 2026
Applicant Interview (Telephonic)
Aug 17, 2026
Examiner Interview Summary
Aug 21, 2026
Response Filed
Nov 04, 2026
Final Rejection mailed — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12804097
STORAGE MEDIUM STORING COMPUTER-READABLE INSTRUCTIONS CAUSING COMPUTER TO EXECUTE IMAGE PROCESS ON IMAGE DATA TO GENERATE OUTPUT DATA RELATED TO DEFECT IN APPEARANCE OF OBJECT
2y 6m to grant Granted Nov 17, 2026
Patent 12761003
SYSTEM AND METHOD FOR DETECTING A SCATTERED MINEFIELD
4y 6m to grant Granted Oct 13, 2026
Patent 12762889
FACE DETECTION METHOD USING VOICE
3y 6m to grant Granted Oct 13, 2026
Patent 12764242
CONTROL METHOD AND STORAGE MEDIUM
2y 0m to grant Granted Oct 13, 2026
Patent 12739333
IMAGE READING DEVICE WITH DOCUMENT LIFT MOVING UP AND DOWN
2y 4m to grant Granted Sep 15, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

5-6
Expected OA Rounds
55%
Grant Probability
72%
With Interview (+16.6%)
3y 3m (~0m remaining)
Median Time to Grant
High
PTA Risk
Based on 614 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month