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 .
The following is a final office action in response to communications received March 16, 2026. Claims 15-18 have been added. Therefore, claims 1-18 are pending and addressed below.
Response to Arguments
Applicant's arguments filed March 16, 2026 have been fully considered but they are not persuasive.
As per the prior art rejection of claim 1 and 8 in page 1, applicant argue the cited art fails to teach or suggest “generating a de-identified image including a plurality of pattern areas with a predetermined size for the de-identification area," as recited in original claim 1 and similarly recited in original claim 8.
The examiner respectfully disagrees.
First, Schmidtlein teaches generating the de-identified image including a plurality of pattern areas in paragraph [0074]: “Responsive to applying a filter (and/or other modification techniques, such as image distortion), the computing system may blur, obfuscate, and/or obscure the image segment (pattern areas), thereby rendering the subject indistinguishable based on the medical image (generating the de-identified image).”. The “pattern areas” is a broad limitation. Using a pattern, such as a black box, blur, pixelation, or a patterned mask, over a segment of an image actively obfuscates that area to hide sensitive details, which fulfills the broader goal of de-identifying the data. The broadest reasonable interpretation (BRI) requires to be consistent with the specification. In the specification paragraph [0058]: “generating a de-identified image including a plurality of pattern areas with a predetermined size by applying a mosaic technique to the de-identification area”. One of ordinary skill in the art would know that the “mosaic technique” is one of the obscure/obfuscate method which is used to hide, mask or degrade details of the image. Therefore, “obfuscate, and/or obscure the image segment, thereby rendering the subject indistinguishable based on the medical image” as recited by Schmidtlein does teach “generate a plurality of pattern areas forming a de-identified image” as cited in the claim 1 and 8;
Second, Schmidtlein teaches pattern areas with a predetermined size in Paragraph [0075]: “One or more modification techniques may be selected based on various factors, such as the quality, size, type, or purpose of an image, or certain features of the image or portions thereof, such as the type of distinguishing feature, the ratio of the size of the portion of the image that includes distinguishing features relative to the size of the overall image and/or relative to the size of the ROI (predetermined size can be determined by the modification techniques for the de-identification area).”). As Schmidtlein teaches obfuscate, and/or obscure the image segment to generate a plurality of pattern areas for forming a de-identified image, as outlined above, one of ordinary skill in the art would know that obscuring or obfuscating an image segment involves generating a pattern of a predetermined size over the target area. One of the obfuscate/obscure techniques - pixelation (mosaicking) overlay a grid of squares (pixel boxes) of a fixed size which utilize predetermined size zones or patterns to alter the original visual data.
Therefore, the 35 U.S.C 102(a)(1) rejection to claim 1 and claim 8 are maintained. As claims 2-7 are dependent directly on claim 1, claims 9-14 are dependent directly on claim 8, the rejections of claims 2-7 and 9-14 are maintained.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-14 are rejected under 35 U.S.C. 102 (a)(1) as being anticipated by Schmidtlein et al (US PG-PUB No. 20240394408 A1).
Regarding claim 1 and claim 8, Schmidtlein teaches a method and apparatus for anonymizing medical images, the method comprising:
acquiring or receiving a first medical image (Paragraph [0066]: “In brief overview, process 350 can include obtaining a medical image associated with metadata (352) (receiving a first medical image).”);
separating an identification area containing anatomical structure information and a de-identification area containing a skin area in the first medical image (Paragraph [0066]: “The process 350 may include identifying one or more ROIs based on metadata (354) (separating an identification area and a de-identification area in the first medical image).”; Schmidtlein further teaches the identification area in paragraph [0069]: “Referring now to operation (354), and in some embodiments, the computing system may identify and/or determine one or more ROIs of the subject in the medical image(s). As such, and based on the metadata, the computing system can determine that the ROI(s) include or correspond to one or more regions of the medical image that include the particular anatomical feature of the subject (e.g., associated with the medical condition) (the identification area containing anatomical structure information in the first medical image).”; Schmidtlein further teaches de-identification area in paragraph [0072]: “As such, according to the set of metadata for example, the computing system can determine that the image segment includes or corresponds to an area or region of the medical image that excludes the particular anatomical feature of the subject (de-identification area). In certain embodiments, the image segment may include one or more distinguishing features of the subject (e.g., anatomical and/or physiological features that allow identification of the subject). In one example, the image segment may include at least one of: one or both eyes of the subject, a plurality of teeth of the subject, a face of the subject, a head of the subject, and/or other features of the subject (the de-identification area containing a skin area in the first medical image).”);
generating a de-identified image including a plurality of pattern areas with a predetermined size for the de-identification area (Paragraph [0066]: “The process 350 may include selecting a modification technique based on ROIs (356). The process 350 may include generating a modified image by applying the modification technique (358) (generating a de-identified image).”; Schmidtlein further teaches generating the de-identified image including a plurality of pattern areas in paragraph [0074]: “Responsive to applying a filter (and/or other modification techniques, such as image distortion), the computing system may blur, obfuscate, and/or obscure the image segment (pattern areas), thereby rendering the subject indistinguishable based on the medical image (generating the de-identified image).”; Paragraph [0075]: “One or more modification techniques may be selected based on various factors, such as the quality, size, type, or purpose of an image, or certain features of the image or portions thereof, such as the type of distinguishing feature, the ratio of the size of the portion of the image that includes distinguishing features relative to the size of the overall image and/or relative to the size of the ROI (predetermined size can be determined by the modification techniques for the de-identification area).”); and
generating a second medical image by replacing the de-identification area with the de-identified image (Paragraph [0066]: “The process 350 may include performing an operation using the modified image (364) (generating a second medical image).”; Schmidtlein further teaches generating a second medical image in paragraph [0081]: “By changing/adjusting the intensities of the pixels to said minimum intensity, the distinguishing feature(s) of the subject (e.g., the teeth and/or the eye(s)) can be removed and/or extracted from the medical image (replacing the de-identification area). As such, a volume rendering of the modified set of slices of the medical image (e.g., the slices modified by changing the intensities of the pixels to a minimum intensity) can render the subject indistinguishable/unidentifiable (e.g., the medical image is anonymized) (generating a second medical image by replacing the de-identification area with the de-identified image), as seen in FIG. 9.”).
Regarding claim 2 and claim 9, Schmidtlein teaches all of the features with respect to claim 1 and claim 8, as outlined above.
Schmidtlein further teaches wherein the plurality of pattern areas comprise first pattern areas having a first signal intensity value and second pattern areas having a second signal intensity value (Paragraph [0070]: “Referring now to operation (356), and in some embodiments, the computing system may select and/or identify a modification technique to apply to the medical image(s) (to generate a plurality of pattern areas). In one example, the computing system may select one or more modification techniques to apply to the medical image(s) (e.g., for anonymizing the medical image(s)). In certain embodiments, a selected modification technique may include or correspond to adjusting, modifying, and/or altering one or more intensities of pixels in an image segment (signal intensity value). For example, the image segment may include a set of pixels (e.g., pixels in an image segment) (plurality of pattern areas), the set of pixels comprising one or more intensities (the plurality of pattern areas comprise first pattern areas having a first signal intensity value and second pattern areas having a second signal intensity value). A selected modification technique can include adjusting, by the computing system, the intensity of each pixel within the set of pixels to another pixel intensity.”).
Regarding claim 3 and claim 10, Schmidtlein teaches all of the features with respect to claim 1 and claim 8, as outlined above.
Schmidtlein further teaches wherein each of the plurality of pattern areas is generated to have a randomized signal intensity value (Paragraph [0070]: “For instance, the computing system may adjust the intensity of each pixel within the minimum percentage of pixels to a random intensity value, such that a randomization operation (e.g., a randomization of the pixel intensity values) is performed across said pixels.”).
Regarding claim 4 and claim 11, Schmidtlein teaches all of the features with respect to claim 1 and claim 8, as outlined above.
Schmidtlein further teaches wherein each of the plurality of pattern areas has a signal intensity value generated based on a representative value of signal intensity values of a de-identification area in each of the plurality of pattern areas (Paragraph [0070]: “In certain embodiments, a selected modification technique may include or correspond to adjusting, modifying, and/or altering one or more intensities of pixels in an image segment (pattern areas has a signal intensity value) (e.g., image segment outside of the identified ROIs (de-identification area))”).
Regarding claim 5 and claim 12, Schmidtlein teaches all of the features with respect to claim 1 and claim 8, as outlined above.
Schmidtlein further teaches wherein the generating the de-identified image comprises: determining a second de-identification area including at least a portion of the de-identification area and having a thickness based on a user input; and generating the plurality of pattern areas having a predetermined size by using a representative value of signal intensity values in the second de-identification area (Paragraph [0066]: “The process 350 may include applying a second modification technique (366).”; Paragraph [0076]: “If the anonymization metric is below the threshold (e.g., the subject remains identifiable in the modified image), the computing system may further apply a second modification technique to the medical image (e.g., to further anonymize/de-identify the subject in the modified image) (366) (determining a second de-identification area including at least a portion of the de-identification area).”; Paragraph [0074]: “In certain embodiments, the computing system may determine the image segment based on a received user input. For instance, the computing system can receive, via user input, a selection of a boundary, contour, and/or outline of the distinguishing feature (e.g., a boundary encapsulating the distinguishing feature) (having a thickness based on a user input). Based on the received selection of the boundary, the computing system may determine the image segment (e.g., the image segment corresponds to the selected boundary). Responsive to identifying the image segment, the computing system can select and/or apply a modification technique (e.g., a filtering operation and/or other image modification techniques) to the image segment (or to the contour of the image segment) (generating the plurality of pattern areas having a predetermined size).”; Paragraph [0070]: “In certain embodiments, a selected modification technique may include or correspond to adjusting, modifying, and/or altering one or more intensities of pixels in an image segment (using a representative value of signal intensity values) (e.g., image segment outside of the identified ROIs (in the second de-identification area)).”).
Regarding claim 6 and claim 13, Schmidtlein teaches all of the features with respect to claim 1 and claim 8, as outlined above.
Schmidtlein further teaches wherein the first medical image is a magnetic resonance (MR) image set or a computed tomography (CT) image set including a plurality of slices, and wherein the separating, the generating the de-identified image, and the generating the second medical image are performed for each of the plurality of slices in the CT image set or the MR image set (Paragraph [0007]: “In one aspect, the present disclosure is directed to a method for anonymizing image data (e.g., medical images, such as a computed tomography (CT) image and/or a magnetic resonance imaging (MRI) image (the first medical image is a magnetic resonance (MR) image set or a computed tomography (CT) image set including a plurality of slices)) by modifying the image to render a distinguishing feature indistinguishable/unidentifiable. A computing system may obtain a medical image of a subject. The medical image may comprise a set of slices and be associated with a set of metadata regarding the medical image and the subject. In certain embodiments, each slice of the set of slices can be a medical image (separating, the generating the de-identified image, and the generating the second medical image are performed for each of the plurality of slices in the CT image set or the MR image set), wherein the set of slices may be combined to generate a second medical image.”).
Regarding claim 7 and claim 14, Schmidtlein teaches all of the features with respect to claim 1 and claim 8, as outlined above.
Schmidtlein further teaches wherein the identification area comprises information that can restore a three-dimensional (3D) anatomical structure based on the anatomical structure information in the first medical image (Paragraph [0067]: “In some embodiments, one or more volume rendering techniques, such as LIDAR, backscatter X-ray systems (e.g., low-energy backscatter X-ray scanner), and/or other techniques for generating 3D images, can generate or otherwise provide an image (e.g., a 3D image) that is suitable for anonymization, according to the systems and methods discussed herein. As such, any image that is suitable for 3D rendering (e.g., 3D renders of circuits, 3D renders of geographic features, and/or other types of 3D renders) can be anonymized based on the systems and methods described herein.”).
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 15 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Schmidtlein et al (US PG-PUB No. 20240394408 A1) in view of Watazawa (US PG-PUB No. 20210112198 A1).
Regarding claim 15 and 17, Schmidtlein teaches all of the features with respect to claim 1 and claim 8, as outlined above.
Schmidtlein is not relying on teaching, but Watazawa teaches wherein the plurality of pattern areas are generated to have the predetermined size and a predetermined shape (Paragraph [0071]: “the subject region specification unit 404 makes the determination in the present step based on whether the percentage of a low-contrast region within the target image falls below a threshold and the size of a detected face region falls within a predetermined area range (not too small and not too large) (the pattern area are generated to have a predetermined size).”; Paragraph [0075]: “a region in which a subject exists may be configured as a region having a predetermined shape (the pattern area are generated to have a predetermined shape) that has been designated based on, for example, the position of an image of a detected face or organ that composes a face.).
Schmidtlein and Watazawa are both considered to be analogous to the claimed invention because they both teach image processing. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the pattern areas disclosed by Schmidtlein with adding predetermined size and shape, as disclosed by Watazawa.
One of the ordinary skills in the art would have been motivated to make this modification in order to increase the accuracy of measurement of detection of images (patterns), as suggested by Watazawa in paragraph [0070].
Claims 16 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Schmidtlein et al (US PG-PUB No. 20240394408 A1) in view of KWON (US PG-PUB No. 20230343455 A1).
Regarding claim 16 and 18, Schmidtlein teaches all of the features with respect to claim 1 and claim 8, as outlined above.
Schmidtlein is not relying on teaching, but KWON teaches wherein, from among the plurality of pattern areas, a first pattern area has a first signal intensity value generated based on a first representative value of signal intensity values of a first de-identification sub-area in the first pattern area, and wherein, from among the plurality of pattern areas, a second pattern area has a second signal intensity value, different from the first signal intensity value, generated based on a second representative value of signal intensity values of a second de-identification sub-area in the second pattern area (Paragraph [0023]: “The first interval distribution quantification information (the first representative value) may comprise at least one of a percentile, maximum value, minimum value, mean value, mode value, and median value of pixels/voxels of signal intensity values (first signal intensity value) within the target region corresponding to the first interval (first de-identification sub-area in the first pattern area).”; Paragraph [0024]: “The second interval distribution quantification information (the second representative value) may comprise at least one of a percentile, maximum value, minimum value, mean value, mode value, and median value of pixels/voxels of signal intensity values (second signal intensity value) within the target region corresponding to the second interval (second de-identification sub-area in the second pattern area).”.).
Schmidtlein and KWON are both considered to be analogous to the claimed invention because they both teach image processing. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the pattern areas disclosed by Schmidtlein with adding signal intensity value, as disclosed by KWON.
One of the ordinary skills in the art would have been motivated to make this modification in order to help medical professional to verify the results of detection, as suggested by KWON in paragraph [0012].
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Kim (US 11164046 B1) discloses Method For Producing Labeled Image From Original Image While Preventing Private Information Leakage Of Original Image And Server Using The Same
Chen (US20190378607 A1) discloses System and method for patient privacy protection in medical images
Gogin (US10971263 B2) discloses Methods and apparatus for recording anonymized volumetric data from medical image visualization software
Schmidt (US20050283381 A1) discloses System and method to manipulate identification data of medical images and data sets for quality assurance
Poblenz (US-20200160963-A1) discloses Medical scan de-identification system
Pinel (US 11468617 B2) Selective Redaction Of Images
Igarashi et al (US 20190298304 A1) discloses MEDICAL DIAGNOSIS APPARATUS, MEDICAL IMAGE PROCESSING APPARATUS, AND IMAGE PROCESSING METHOD
Esashi et al (US 20170295300 A1) discloses IMAGE PROCESSING APPARATUS
Abe (US 20130129226 A1) discloses IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING PROGRAM
Jeong et al (US 11308359 B1) discloses Methods For Training Universal Discriminator Capable Of Determining Degrees Of De-identification For Images And Obfuscation Network Capable Of Obfuscating Images And Training Devices Using The Same
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 JASMINE DAY whose telephone number is (571)272-0204. The examiner can normally be reached Monday - Friday 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, Philip Chea can be reached at 571-272-3951. 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.
/J.M.D./Examiner, Art Unit 2499 /PHILIP J CHEA/Supervisory Patent Examiner, Art Unit 2499
Prosecution Insights