DETAILED ACTION
Note: The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Applicant’s arguments filed in the reply on May 15, 2026 were received and fully considered. Claims 1-6, 8, 9, 13-15, and 28 were amended. Claims 16-27 were cancelled. Claims 29-36 are new. The current action is FINAL. Please see corresponding rejection headings and response to arguments section below for more detail.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-15 and 28-36 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) as a whole, considering all claim elements both individually and in combination, do not amount to significantly more than an abstract idea. A streamlined analysis of claim 1 follows.
Regarding claim 1, the claim recites a method for deriving a blood glucose level of a user. Thus, the claim is directed to a process, which is one of the statutory categories of invention.
The claim is then analyzed to determine whether it is directed to any judicial exception. The following limitations set forth a judicial exception:
“A method for deriving a blood glucose level of a user… cropping each of the one or more hyperspectral images to predefined sets of image excerpts that are spectrally aligned using crop coordinates for an identified region of the user, the crop coordinates being derived from image data corresponding to one or more of the plurality of electromagnetic spectrum band channels and applied across the plurality of layered data sets according to a plurality of predefined crop position variations corresponding to different spatial subsections of the user; feeding the predefined sets of image excerpts to a machine learning model trained on a plurality of correlated pairs of one or more training images associated with training blood glucose measurements; and generating, with the machine learning model, an estimated blood glucose level for the user corresponding to the one or more images thereof.”
These limitations describe a mathematical calculation. When given their broadest reasonable interpretation in light of the specification, the limitations identified above, including the highly generic machine learning model, correspond to mathematical relationships/calculations. Moreover, the plain meaning of “machine learning” is a series of mathematical calculations. See also 2024 AI SME Update, which held a similar claim construction was not patent eligible (see claim 2 of example 47, using a trained artificial neural network to analyze anomalies on input data was not patent eligible). The 2024 AI SME Update also sets forth that a trained machine learning model/engine amounts to a mental process (claim 2 of example 47) as nothing from the claims suggest that the limitations cannot be practically performed by a human, using simple pen/paper.
Next, the claim as a whole is analyzed to determine whether any element, or combination of elements, integrates the identified judicial exception into a practical application.
For this part of the 101 analysis, the following additional limitations are considered:
“…capturing one or more hyperspectral images of the user with a hyperspectral imaging sensor, the one or more hyperspectral images being defined by a plurality of layered data sets each corresponding to a respective electromagnetic spectrum band channel of a plurality of electromagnetic spectrum band channels…”
These additional limitations do not integrate the judicial exception into a practical application. Rather, the additional limitations are each recited at a high level of generality such that it amounts to insignificant pre-solution extra-solution activity, e.g., mere data gathering steps necessary to perform the identified judicial exception.
The additional limitations also do not add significantly more to the identified judicial exception because they relate to well-understood, routine, and conventional techniques for obtaining known types of data via generic hyperspectral imaging sensor. Examiner also cites references that hyperspectral imaging sensors are conventional1. Moreover, the machine learning module is also recited at a high level of generality such that it does not equate to significantly more.
Independent claims 28 is also not patent eligible for substantially similar reasons.
Dependent claims 2-15 and 29-36 also fail to add something more to the abstract independent claims as they merely further limit the abstract idea, recite limitations that do not integrate the claims into a practical application for substantially similar reasons as set forth above, and/or do not recite significantly more than the identified abstract idea for substantially similar reasons as set forth above.
Therefore, claims 1-15 and 28-36 are not patent eligible under 35 USC 101.
Claim Rejections - 35 USC § 103
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 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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-15 and 28-36 are rejected under 35 U.S.C. 103 as being unpatentable over Clemente (US PG Pub. No. 2024/0023838 A1), Uzair et al. (Hyperspectral Face Recognition with Spatiospectral Information Fusion and PLS Regression¸ IEEE Transactions on Image Processing, Vol. 24, No. 3, pgs. 1127-1137, March 2015) (hereinafter “Uzair”), and in view of Krause et al. (US PG Pub. No. 2021/0181093 A1) (hereinafter “Krause”).
Clemente and Krause were applied in the previous office action.
With respect to claims 1 and 28, Clemente teaches a method for deriving a blood glucose level of a user (see title “Non-invasive blood glucose monitoring system), comprising: capturing one or more images of the user with an imaging device (par.0059 “medical diagnostics, spectroscopy-based techniques… and/or image processing… to achieve accurate, non-invasive blood glucose estimation”), the images being defined by a plurality of layered data sets each corresponding to a respective electromagnetic spectrum band channel of a plurality of electromagnetic spectrum band channels (par.0107 “Image Measurement Datasets. Five datasets were created by extracting measurement data from the images. To create the dataset, each image in the dataset was split into four channels including red, green, blue, and grayscale (the image with color removed). Then, for each color channel, the channel's pixel center of mass, minimum, maximum, mean, median, standard deviation, and variance were calculated”); cropping each of the one or more images to predefined sets of image excerpts (par.0082 “Data captured using main bodies of the present disclosure must be prepared prior to processing via pre-processing…Data augmentation techniques including cropping, zooming, height and width shift, and horizontal flipping can be used, as well”); feeding the predefined sets of image excerpts to a machine learning model trained on a plurality of correlated pairs of one or more training images associated with training blood glucose measurements (par.0067 “machine learning models… to monitor blood glucose levels in real time. The machine learning model utilizes its learned knowledge to accurately estimate the glucose levels from spectroscopy images. The estimation is based on the correlation between the extracted image features and glucose concentrations”); and generating, with the machine learning model, an estimated blood glucose level for the user corresponding to the one or more images thereof by averaging predictions over the predefined sets of image excerpts (par.0067 “The machine learning model utilizes its learned knowledge to accurately estimate the glucose levels from spectroscopy images. The estimation is based on the correlation between the extracted image features and glucose concentrations. The device provides real-time glucose readings, displaying them on a user-friendly interface for easy interpretation”; par.0080 “the model takes the output value… averages those values, and outputs that average”; par.0112 “blood glucose values that a model predicts and the actual blood glucose value ties to an image… treated as an average”).
However, Clemente does not explicitly teach capturing hyperspectral images of the user with a hyperspectral imaging device… cropping each of the one or more hyperspectral images to predefined sets of image excerpts that are spectrally aligned using crop coordinates for an identified region of the user, the crop coordinates being derived from image data corresponding to one or more of the plurality of electromagnetic spectrum band channels and applied across the plurality of layered data sets according to a plurality of predefined crop position variations corresponding to different spatial subsections of the user.
Uzair teaches capturing hyperspectral images of the user with a hyperspectral imaging device… cropping each of the one or more hyperspectral images to predefined sets of image excerpts that are spectrally aligned using crop coordinates for an identified region of the user, the crop coordinates being derived from image data corresponding to one or more of the plurality of electromagnetic spectrum band channels and applied across the plurality of layered data sets according to a plurality of predefined crop position variations corresponding to different spatial subsections of the user (see title “Hyperspectral Face Recognition with spatiospectral information fusion and PLS regression”; pgs. 1131-1132 Hyperspectral Face Databases: “hyperspectral image cube contains 33 bands covering the spectral range… Faces are cropped using the eye coordinates and resized”).
Krause teaches capturing images of the user with a hyperspectral imaging device for the purposes of blood sugar analyses in the medical field (par.0032 “The method is hence suitable, in an altogether outstanding way, for analysing spectroscopic data. Comparable data sets can be produced for analysis with different measuring devices… it is suitable particularly well for analyses of reflectance and transmission, preferably in the ultraviolet, visual and/or infrared spectrum, with mobile spectrometers, for example so-called low-cost spectrometers, and in hyper-spectral imaging. Application areas, given by way of example, are food scanners in the foodstuffs sphere, ground analyses in the agricultural sector, sorting plants for bulk goods and blood sugar analyses in the medical field”).
Therefore, it would have been prima facie obvious to person having ordinary skill in the art (“PHOSITA”) when the invention was filed to incorporate Uzair’s hyperspectral imaging device in place of Clemente’s spectroscopy device as doing so would be a simple substitution in order to allow for face recognition via improved discrimination along the spectral dimension, as evidence by Uzair (see abstract on pg. 1127). Furthermore, PHOSITA would have had predictable success modifying Clemente to incorporate Uzair’s hyperspectral face recognition as hyperspectral imaging provides comparable data sets that is suitable particularly well for blood glucose analysis in the medical field, as suggested by Krause (par.0032).
With respect to claims 2 and 29, Clemente teaches the plurality of electromagnetic spectrum band channels includes visible spectrum primary color bands of red, blue, and green (par.0107).
With respect to claims 3 and 30, Uzair teaches wherein the electromagnetic spectrum band channel of a given one of the plurality layered data sets corresponds to a hyperspectral band channel between approximately 10 nanometers and approximately 0.1 millimeters with 1 nanometer channel steps (pg. 1131 “step size of 10 nm”). Therefore, it would have been prima facie obvious to PHOSITA when the invention was filed to incorporate Uzair’s hyperspectral imaging device in place of Clemente’s spectroscopy device as doing so would be a simple substitution in order to allow for face recognition via improved discrimination along the spectral dimension, as evidence by Uzair (see abstract on pg. 1127).
With respect to claims 4 and 31, Uziar teaches wherein the one or more hyperspectral images are of a specific body part of the user (title “Hyperspectral Face Recognition”; pg. 1132 “Faces are cropped using the eye coordinates”). Therefore, it would have been prima facie obvious to PHOSITA when the invention was filed to incorporate Uzair’s hyperspectral imaging device in place of Clemente’s spectroscopy device as doing so would be a simple substitution in order to allow for face recognition via improved discrimination along the spectral dimension, as evidence by Uzair (see abstract on pg. 1127).
With respect to claims 5 and 32, Uzair teaches wherein the specific body part of the user is selected from a group consisting of: a face, a wrist, and an arm (title “Hyperspectral Face Recognition”; pg. 1132 “Faces are cropped using the eye coordinates”). Therefore, it would have been prima facie obvious to PHOSITA when the invention was filed to incorporate Uzair’s hyperspectral imaging device in place of Clemente’s spectroscopy device as doing so would be a simple substitution in order to allow for face recognition via improved discrimination along the spectral dimension, as evidence by Uzair (see abstract on pg. 1127).
With respect to claims 6 and 33, Clemente teaches normalizing each of the plurality of layered data sets to a constrained minimum and maximum range according to the corresponding electromagnetic spectrum band channel (par.0069, 0085, 0107).
With respect to claims 7 and 34, Clemente teaches wherein a given one of the predefined sets of image excerpts is selected from a group consisting of: a central crop targeting main facial features, a top-left crop, a top-right crop, a bottom-left crop, a bottom-right crop, a mirrored central crop targeting main facial features, a mirrored top-left crop, a mirrored top-right crop, a mirrored bottom-left crop, and a mirrored bottom-right crop (par.0082, 0091, 0093).
With respect to claims 8 and 35, Clemente teaches capturing the one or more training images of a plurality of training users with the device, the training images being defined by a plurality of layered data sets each corresponding to an electromagnetic spectrum band channel; capturing the training blood glucose measurements of the training users concurrently with the capturing of the one or more training images; and feeding one or more correlated pair of the training blood glucose measurement and the one or more training images to the machine learning model (par.0066, 0068+). Uzair also teaches capturing hyperspectral images of the user with a hyperspectral imaging device (see title “Hyperspectral Face Recognition with spatiospectral information fusion and PLS regression”; pgs. 1131-1132 Hyperspectral Face Databases: “hyperspectral image cube contains 33 bands covering the spectral range… Faces are cropped using the eye coordinates and resized”). Therefore, it would have been prima facie obvious to PHOSITA when the invention was filed to incorporate Uzair’s hyperspectral imaging device in place of Clemente’s spectroscopy device as doing so would be a simple substitution in order to allow for face recognition via improved discrimination along the spectral dimension, as evidence by Uzair (see abstract on pg. 1127). Furthermore, PHOSITA would have had predictable success modifying Clemente to incorporate Uzair’s hyperspectral face recognition as hyperspectral imagine provides comparable data sets that is suitable particularly well for blood glucose analysis in the medical field, as suggested by Krause (par.0032).
With respect to claims 9 and 36, Clemente teaches training the machine learning model with the one or more correlated pairs of the training blood glucose measurements and the one or more training images (par.0067).
With respect to claim 10, Clemente teaches wherein the machine learning model implements a neural architecture (par.0013).
With respect to claim 11, Clemente teaches wherein the neural architecture is a convolutional neural network (par.0013).
With respect to claim 12, Clemente teaches wherein the neural architecture is a vision transformer (par.0068-71, 0102).
With respect to claim 13, Clemente teaches wherein the convolutional neural network applies a regression model, with the estimated blood glucose level being generated as a numeric score value (par.0072-81).
With respect to claim 14, Clemente teaches wherein the convolutional neural network applies a classification model, with the estimated blood glucose level being generated as a class defined by sequential ranges of blood glucose concentrations (par.0070-87).
With respect to claim 15, Clemente teaches wherein the convolutional neural network applies a multi-task model including the application of a combination of a regression model and a classification model (par.0070-87).
Response to Arguments
Applicant’s arguments filed with respect to the 35 USC 112F section and 35 USC 112B rejections raised in the previous office action were persuasive in view of amendment. Therefore, these issues are overcome.
Applicant’s arguments filed with respect to the 35 USC 101 rejections raised in the previous office action were fully considered, but they are not persuasive. Applicant appears to argue that the claims do not set forth an abstract idea. Examiner respectfully disagrees and maintains that the claims recite a judicial exception (mathematical calculation and/or mental process) that is not integrated into a practical application. While Examiner agrees that capturing one or more hyperspectral images of the user with a hyperspectral imaging sensor cannot be practically performed by a human, this is an additional (structural) limitation, i.e. not considered part of the identified abstract idea. Examiner argues that obtaining hyperspectral images of the user amounts to mere pre-solution activity as utilizing a hyperspectral imaging sensor is widely known2. AS such, these structural limitations do not integrate the claims into a practical application; and do not recite significantly more. Moreover, and upon further consideration, Examiner presents that the recited “cropping” limitation can be performed mentally as nothing suggests that the skilled artisan would not be able to practically perform this step, having first obtained hyperspectral images from a conventional hyperspectral imaging sensor. Examiner also argues that subsequently feeding and generating steps (with the machine learning model) corresponds to mathematical concepts3 and any purported improvement to the claimed invention appears to lie within the judicial exception itself4. For at least these reasons, the 35 USC 101 rejections are maintained. Please see corresponding rejection heading above for more detail.
Applicant’s arguments filed with respect to the prior art rejections raised in the previous office action have been considered, but are moot in view of the current combination of references that were necessitated by amendment. Please see prior art section above for more detail, updated citations (new secondary reference, Uzair), and updated obviousness rationale.
Prior Art of Record
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Example teachings demonstrating that hyperspectral imaging sensors are widely known (for matters pertaining to 35 USC 101, RE: Berkheimer):
2003/0123056: par.0010
2010/0288910: par.0001
Conclusion
No claim is allowed.
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 PUYA AGAHI whose telephone number is (571)270-1906. The examiner can normally be reached M-F 8 AM - 5 PM.
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, Alexander Valvis can be reached at 5712724233. 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.
/PUYA AGAHI/Primary Examiner, Art Unit 3791
1 See prior art applied in current and previous office actions. See also 2003/0123056: par.0010; and 2010/0288910: par.0001
2 See prior art applied in current and previous office actions. See also 2003/0123056: par.0010; and 2010/0288910: par.0001
3 See also 2024 AI SME Update, which held using machine learning to analyze anomalies in input data was not patent eligible (see claim 2 of example 47).
4 See MPEP 2106.05(a) “the judicial exception alone cannot provide the improvement.”
Prosecution Insights