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 .
Notice to Applicants
This action is in response to the Request for Continued Examination filed on 07/21/2026.
Claims 18-20 are pending.
Corrective Actions by Applicant
Claims 18-20 have been amended.
Information Disclosure Statement
The Information Disclosure Statement (IDS) filed on 08/05/2026 has been fully considered by the examiner.
Request for Continued Examination
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 07/21/2026 has been entered.
Response to Arguments
The examiner has fully considered Applicant’s presented arguments.
On pages 8-9 of the remarks, Applicant argues that Amir fails to teach “comparing the plurality of images to a plurality of images captured during a different time period to determine a change in the severity of the at least one dermatological condition” of amended claim 18. The examiner respectfully disagrees.
The argument is that Amir is merely silent as to comparing images from different time periods, let alone the specific claim language. Although Amir doesn’t explicitly state that images of different time periods are compared, it is clear that doing so is implicitly required for Amir to determine changes in the skin conditions using their disclosed image analysis embodiments.
In Amir, figure 1, step 102, and paras. 0086-0087 show that multiple images can be captured at each iteration of the method. Figure 1, step 104, figure 3, and paras. 0090-0092, 0098-0100, 0110-0114 show that these images can be analyzed to determine the current skin status.
Finally, paras. 0089, 0092, 0098, 0114, 0158 specify that the current skin status can be further determined by comparing to past skin statuses from previous iterations of the method. In the case that images are used at both of the compared times, this would require some comparison of the images, whether that be direct image comparison or comparison of the image analysis results, both of which read on the broad image comparison as claimed.
On page 9 of the remarks, Applicant argues that Dehghan fails to teach this limitation and also teaches away from it. The examiner agrees that Dehghan fails to teach this limitation, but also notes that this aspect of the argument is rendered moot by the above argument response where Amir teaches this limitation instead.
As to Dehghan teaching away from comparing images of different time periods, the examiner respectfully disagrees. The examiner does agree that it would not be compatible to use images of different time periods for the initial image inputs to Dehghan’s model (see figure 1B, medical images 142 of different viewpoints and para. 0045), as using different viewpoint images from different times would not necessarily reflect the actual condition of the anatomy at the present time, for example if the A2C view were a present image, but the A4C view were a past image.
However, nothing in Dehghan precludes any further comparison in the temporal domain, whether that be a separate comparison of the past/present individual viewpoint images, or comparison of the past/present image features output by the convolutional network.
Furthermore, the claim does not require that these image comparisons be performed by the neural network with the separate backbone structures; thus, this comparison can take place within or subsequent to the network and still read on the claim.
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 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Amir et al. (U.S. Publ. US-2018/0014777-A1) in view of Dehghan et al. (U.S. Publ. US-2019/0183366-A1).
Regarding claim 18, Amir discloses a computer-implemented method (see figures 1-2) comprising:
receiving, by an image sensor of a computing device, a plurality of images of a subject (see figure 1, step 102, figure 2, and paras. 0086-0087, where images of a patient's face can be acquired by an image sensor 214 of a computing device, such as a skin treatment applicator 202);
determining, by the computing device, a region of interest for each image in the plurality of images (see paras. 0086-0087, where for image analysis of the facial images, the identified region of the image depicting the face reads on a region of interest; see paras. 0093-0094, where a further subset of the image depicting a specific facial skin segment of interest is further identified);
receiving, by the computing device, at least one current dermatological treatment plan used by the subject during a current time period (see figure 1, steps 102, 112 and paras. 0089 and 0155, where the previous treatment plan is obtained or already present from the previous iteration of step 112 of figure 1);
generating, by a neural network disposed within the computing device, a dermatological condition metric related to a severity of at least one dermatological condition exhibited by the subject in the plurality of images (see figure 1, step 104, figure 3, and paras. 0090-0092, 0098-0100, 0110-0114, where the facial images can be analyzed to determine values of variable skin characteristics and/or worsening of said characteristics relative to earlier skin states);
comparing the plurality of images to a plurality of images captured during a different time period to determine a change in the severity of the at least one dermatological condition (paras. 0089, 0092, 0098, 0114, 0158 specify that the current skin status can be further determined by comparing to past skin statuses from previous iterations of the method; in the case that images are used at both of the compared times, this would require some comparison of the images, whether that be direct image comparison or comparison of the image analysis results, both of which read on the broad image comparison as claimed);
providing, to a trained machine learning (ML) model, the at least one current dermatological treatment plan and the dermatological condition metric, wherein the trained ML model is trained to receive current dermatological treatment plans and dermatological condition metrics for subjects and predict dermatological treatment plans for the subjects during future time periods (see figure 1, step 106 and paras. 0125, 0133-0139, where the current facial skin profile and current or past treatment plans are input to a machine learning classifier that predicts new treatment plans);
obtaining, from the trained ML model, a dermatological treatment plan for the subject during a future time period; and providing the dermatological treatment plan (see figure 1, steps 108-110, figure 2, and paras. 0140, 0142, 0151, 0154, where instructions for how to operate a skin treatment applicator 202 are obtained from the model and presented to the user, such as through a GUI 236).
Amir fails to disclose the limitations indicated via strikethrough above. More specifically, paras. 0043, 0133 do specify that machine learning methods can train a classifier, such as an artificial neural network, to perform the skin analysis and treatment plan predictions, but not with a neural network of the specific claimed architecture.
Pertaining to the same field of endeavor, Dehghan discloses wherein the neural network comprises a convolutional neural network (see figure 1B, CNN 160 and para. 0045) with separate backbone structures (see figure 1B, convolutional modules 161-163 and para. 0046),
wherein each separate backbone structure comprises multi-layer inter-connected sub-blocks (para. 0046 specifies that each convolutional module contains multiple sets of convolutional layers with activation, batch normalization, and dropout layers),
and wherein generating the dermatological condition metric comprises: (i) applying, for the region of interest for each image in the plurality of images (see figure 1B, medical images 142 and para. 0045, which specifies that the input images can depict the same subject from different viewpoints), one of the separate backbone structures (see figure 1B and para. 0046, where each of the convolutional modules are applied to one of the input images to extract features);
and (ii) combining outputs from the separate backbone structures into a single output (see figure 1B, convolutional modules 164 and paras. 0046-0047, where the outputs from each of the three modules 161-163 are concatenated by the fourth module 164 for further processing).
Amir and Dehghan are considered analogous art, as they are both directed to neural networks for medical image recognition. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Dehghan into Amir by using Dehghan's neural network structure for Amir's multiple-image skin analysis because combining the recognition of different viewpoint images of the same anatomy improves system performance and mitigates individual image quality issues (see Dehghan paras. 0058-0060).
Regarding claim 19, Amir in view of Dehghan discloses receiving, by the computing device, patient information related to the subject (see Amir figure 1, step 102 and paras. 0086, 0088, 0109, where additional patient data can be input, such as age, gender, location, demographics, and historical or scheduling records),
and providing, to the trained ML model, the patient information (see Amir para. 0125, where the additional patient data can also be input with the facial data and treatment plans),
wherein the trained ML model is trained to receive current dermatological treatment plans, dermatological condition metrics, and patient information for subjects and predict dermatological treatment plans for the subjects during future time periods (see Amir figure 1, step 106 and paras. 0125, 0133-0139, where the current facial skin profile, current or past treatment plans, and additional patient data are input to a machine learning classifier that predicts new treatment plans).
Regarding claim 20, Amir in view of Dehghan discloses receiving, by the computing device, at least one previous dermatological treatment plan used by the subject during a previous time period (see Amir figure 1, steps 102, 112 and paras. 0089, 0092, 0155, where the previous treatment plan is obtained or already present from the previous iteration of step 112 of figure 1),
and providing, to the trained ML model, the at least one previous dermatological treatment plan (see Amir para. 0136, where the current or previous treatment plans can also be input to the model),
wherein the trained ML model is trained to receive current dermatological treatment plans, dermatological condition metrics, and previous dermatological treatment plans for subjects and predict dermatological treatment plans for the subjects during future time periods (see Amir figure 1, step 106 and paras. 0125, 0133-0139, where the current facial skin profile and current or past treatment plans are input to a machine learning classifier that predicts new treatment plans).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NICHOLAS JOHN HELCO whose telephone number is (703)756-5539. The examiner can normally be reached on Monday-Friday from 9:00 AM to 5:00 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Matthew Bella, can be reached at telephone number 571-272-7778. 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 Patent Center. Status information for published applications may be obtained from Patent Center. Status information for unpublished applications is available through Patent Center for authorized users only. Should you have questions about access to Patent Center, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/NICHOLAS JOHN HELCO/Examiner, Art Unit 2667 /MATTHEW C BELLA/Supervisory Patent Examiner, Art Unit 2667
