CTNF 19/228,830 CTNF 86525 Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. 12-151 AIA 26-51 12-51 Status of Claims This action is in reply to the application filed on June 5, 2025. Claim(s) 1-20 are currently pending and have been examined. Claim Objections 07-29-01 AIA Claim s 18-19 are objected to because of the following informalities: Claims 18-19 recite, “The digital imaging and AI-based method of claim 33 further comprising…” The claims are dependent on a claim that does not exist. Examiner made claims dependent off of independent Claim 17 to continue with Office Action . Appropriate correction is required. Claim Rejections - 35 USC § 101 07-04-01 AIA 07-04 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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more. Based upon consideration of all of the relevant factors with respect to the claims as a whole, the claims are directed to non-statutory subject matter which do not include additional elements that are sufficient to amount to significantly more than the judicial exception because of the following analysis: Independent Claim(s) 1, 17 and 20 are directed to an abstract idea consisting of collecting product and image data, analyzing the data with an AI/ML dosing model to compare observed dosage to a target dosage, and providing feedback on product usage. Independent claim 1 recites, in substance: a digital imaging and AI based system comprising processors, an app, and a dosing learning model trained with dosage data and pixel data of product images and associated appliances/implements, where the app detects a product identifier, obtains images depicting product dosage and an appliance/implement, generates a dosage comparison between observed dosage and a target dosage at a time state using the model, and outputs a feedback indication based on the comparison. Independent claim 17 recites, in substance: a digital imaging and AI based method that detects a product identifier from product data, obtains images of a product depicting dosage and an appliance/implement, generates a dosage comparison between observed and target dosage at a time state using a dosing learning model trained with dosage and pixel data, and outputs a feedback indication based on features in the image. Independent claim 20 recites, in substance: a tangible, non-transitory computer readable medium storing instructions that, when executed, cause processors to detect a product identifier from product data, obtain images of a product depicting dosage and an appliance/implement, generate a dosage comparison between observed and target dosage at a time state using a dosing learning model trained with dosage and pixel data, and output a feedback indication based on features in the image. Under their broadest reasonable interpretation, the limitations of claims 1, 17, and 20 cover the performance of: • Certain methods of organizing human activity, including managing personal behavior and clinical/consumer workflows (e.g., guiding how a user applies a product over time, verifying that usage complies with a desired regimen, and adjusting behavior based on feedback about over or under dosing). • Mathematical concepts, including calculations, scoring, or model-based computations (e.g., applying an AI/ML “dosing learning model” trained on dosage and pixel data to compute a comparison between observed dosage and target dosage, analogous to the dose maps and comparisons to clinical goals used). But for the recitation of generic computer components, the claim steps are simply: collect product and image information, apply mathematical/AI analysis to compare observed dosage to a desired dosage, and present the result as feedback to influence product use behavior. The claims recite additional elements such as: • One or more machine learning or “dosing learning” models. • At least one processor. • Non transitory processor readable memory / computer readable medium. • Generic computing devices (servers, client devices, app portions). • Database or record storage for product data, dosage data, and training datasets. • User interfaces and displays that render comparisons and feedback indications (e.g., visual projections, recommendations). • Generic imaging devices that capture pixel data. These elements are recited at a high level of generality and merely use generic computer components to perform generic computer functions such as receiving data, storing data, running models, and displaying outputs. This judicial exception is not integrated into a practical application. In particular, the claims recite the additional elements to perform all of the “obtaining, transforming, parsing, determining, transforming, selecting and storing” steps. The additional elements are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function) of executing computer-executable instructions for implementing the specified logical function(s) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea. The use of a general-purpose computer, taken alone, does not impose any meaningful limitation on the computer implementation of the abstract idea, so it does not amount to significantly more than the abstract idea. Also, although the claims add “[storage]” steps, it is only considered as insignificant extrasolution activity. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements individually. The combination of elements does not indicate a significant improvement to the functioning of a computer or any other technology and their collective functions merely provide a conventional computer implementation of the abstract idea. Furthermore, the additional elements or combination of elements in the claims, other than the abstract idea per se, amount to no more than a recitation of generally linking the abstract idea to a particular technological environment or field of use, as the courts have found in Parker v. Flook. Therefore, there are no limitations in the claims that transform the judicial exception into a patent eligible application such that the claims amount to significantly more than the judicial exception. It is worth noting that the above analysis already encompasses each of the current dependent claims (i.e., claims 2-16 and 18-19). Particularly, each of the dependent claims also fails to amount to “significantly more’ than the abstract idea since each dependent claim is directed to a further abstract idea, and/or a further conventional computer element/function utilized to facilitate the abstract idea. Accordingly, none of the current claims implements an element—or a combination of elements—directed to an inventive concept (e.g., none of the current claims is reciting an element—or a combination of elements—that provides a technological improvement over the existing/conventional technology). These information characteristics do not change the fundamental analogy to the abstract idea grouping of “Certain Methods of Organizing Human Activity and Mathematical Concepts,” and, when viewed individually or as a whole, they do not add anything substantial beyond the abstract idea. Furthermore, the combination of elements does not indicate a significant improvement to the functioning of a computer or any other technology. Therefore, the claims when taken as a whole are ineligible for the same reasons as the independent claims. Claims 1-20 are therefore not drawn to eligible subject matter as they are directed to an abstract idea without significantly more. Claim Rejections - 35 USC § 103 07-20-aia AIA 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. 07-21-aia AIA Claim s 1–20 are rejected under 35 U.S.C. 103 as being unpatentable over Gao et al. (US 2024/0157172 A1) in view of Kondziolka et al. (US 2017/0216624 A1) . Claim 1: "A digital imaging and artificial intelligence (AI)-based system configured to analyze product dosing, the digital imaging and AI-based system comprising:-- one or more processors;-- a dosing application (app) comprising computing instructions configured to execute on the one or more processors; and-- a dosing learning model, accessible by the dosing app, and trained with dosage data of one or more products, pixel data of a plurality of training images depicting the one or more products, and one or more product appliances or product implements associated with the one or more products, the dosing learning model trained to output analysis of one or more dosages corresponding to the one or more products based on one or more corresponding target dosages applied at different times during a product application lifecycle,-- wherein the computing instructions of the dosing app when executed by the one or more processors, cause the one or more processors to:-- detect, based on product data, a product identifier of a product,-- obtain a set of one or more images of the product, the set of one or more images comprising pixel data as captured by an imaging device, and the pixel data depicting a dosage of the product and at least one of (a) a product appliance configured to apply the product and (b) a product implement configured to receive the product,-- generate, based on output of the dosing learning model, a first analysis comprising a dosage comparison comparing the dosage of the product as depicted in pixel data to a target dosage of the product at a first time state, the target dosage of the product defining an expected dosage of the product at the first time state, and-- output, based on the dosage comparison, a feedback indication designed to address at least one feature identifiable within the pixel data comprising the dosage of the product." Gao et al. teaches: "A digital imaging and artificial intelligence (AI)-based system configured to analyze product dosing" and "one or more processors; a dosing application (app) comprising computing instructions configured to execute on the one or more processors; and a dosing learning model" to the extent of an AI-based dose modeling system comprising an analytics server with a processor and non-transitory computer-readable medium containing instructions to generate a training dataset from medical images, structure masks, modality indicators, and beam geometry, to train an artificial intelligence model, to execute the artificial intelligence model for a new patient, and to output a predicted dose map indicating dosage received by one or more internal structures of the new patient, see paragraphs 0007–0015 and 0045–0050 of Gao et al. "A dosing learning model, accessible by the dosing app, and trained with dosage data of one or more products, pixel data of a plurality of training images depicting the one or more products" to the extent of an artificial intelligence model trained using medical images, structure masks for structures within the medical image such as planning target volumes and organs at risk, and reference dose maps that represent approved dose distributions for a set of patients, such that the artificial intelligence model is configured to receive data associated with a new patient and generate a predicted dose map indicating dosage received by one or more internal structures of the new patient, see paragraphs 0062–0067 and 0073–0077 of Gao et al. "The dosing learning model trained to output analysis of one or more dosages corresponding to the one or more products based on one or more corresponding target dosages applied at different times during a product application lifecycle" to the extent of training the artificial intelligence model using clinically approved dose plans and associated patient data so that the model predicts three-dimensional dose maps that are compared with clinical goals and used in an automatic radiotherapy treatment planning pipeline (knowledge-based planning) to support dose prediction and optimization across radiotherapy treatments, see paragraphs 0005–0007 and 0093–0101 of Gao et al. "Obtain a set of one or more images of the product, the set of one or more images comprising pixel data as captured by an imaging device" to the extent of obtaining medical images such as CT scans that depict internal structures and are used, along with structure masks and dose maps, as input channels to the artificial intelligence model, see paragraphs 0064–0067 and 0075–0079 of Gao et al. "Generate, based on output of the dosing learning model, a first analysis comprising a dosage comparison comparing the dosage of the product as depicted in pixel data to a target dosage of the product" to the extent of generating a predicted dose map and comparing the predicted dose map with at least one clinical goal, including generation of dose-volume histograms, and using the predicted dose map as input to a plan optimizer, which collectively constitutes a comparison between predicted dose and target dose distributions and outputs feedback in the form of dose maps, dose-volume histograms, and optimized plans, see paragraphs 0005–0007 and 0093–0101 of Gao et al. Gao et al. fails to explicitly teach: "Analyze product dosing" in the context of external products and "product application lifecycle" outside of radiotherapy contexts. "Detect, based on product data, a product identifier of a product" where the product is a non-medical product identified in product data independent of patient and treatment identifiers. "Obtain a set of one or more images of the product … depicting a dosage of the product and at least one of (a) a product appliance configured to apply the product and (b) a product implement configured to receive the product" where the subject of the image is an external product and appliance/implement rather than internal anatomical structures and radiotherapy equipment. "Output, based on the dosage comparison, a feedback indication designed to address at least one feature identifiable within the pixel data comprising the dosage of the product" in the sense of instructing or guiding a user regarding external product application patterns, placement, or quantities. Kondziolka et al. teaches: "The dosing learning model trained to output analysis of one or more dosages corresponding to the one or more products based on one or more corresponding target dosages applied at different times during a product application lifecycle" to the extent of a method for treating a target in a treatment subject via radiation that includes acquiring imaging information relating to the target based on imaging markers reflecting metabolic, physiological, or histological features, computing a radiation dose based at least on the imaging information, delivering the radiation dose, and tracking tumor responsiveness over time, including comparing personalized recommendations based on imaging to standard recommendations derived from clinical population data and adjusting doses when discrepancies occur, see paragraphs 0005–0007, 0023–0033, and 0035–0037 of Kondziolka et al. "Generate, based on output of the dosing learning model, a first analysis comprising a dosage comparison comparing the dosage of the product as depicted in pixel data to a target dosage" and "output, based on the dosage comparison, a feedback indication" to the extent of computing a radiation dose based on cellular imaging data (such as ADC maps), obtaining a standard dose recommendation from clinical population data, comparing the personalized imaging-based dose recommendation with the standard recommendation, and alerting the health-care professional with a sign or message when a significant discrepancy exists, thereby providing a feedback indication that a change in dose may be warranted, see paragraphs 0035–0037 of Kondziolka et al. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include the radiation-dose comparison and feedback features taught by Kondziolka et al. within the artificial intelligence-based dose modeling system taught by Gao et al., with the motivation of improving dose verification and treatment planning by combining predictive dose maps with imaging-based dose recommendations and alerts that highlight discrepancies between computed and target doses, as taught in paragraphs 0035–0037 of Kondziolka et al. and paragraphs 0005–0007. As per Claim 2, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 1, wherein the computing instructions of the dosing app when executed by the one or more processors, further cause the one or more processors to:-- obtain a second set of one or more images of the product, the second set of one or more images comprising second pixel data as captured by the imaging device, and the second pixel data depicting a second dosage of the product and the product appliance or the product implement,-- generate, based on output of the dosing learning model, a second analysis comprising a second dosage comparison of the second dosage of the product as depicted in second pixel data to a second target dosage of the product at a second time state, the second target dosage of the product defining a second expected dosage of the product at the second time state, and-- output, based on the second dosage comparison, a second feedback indication designed to address at least one feature identifiable within the second pixel data comprising the second dosage of the product." Gao et al. teaches: "Obtain a second set of one or more images of the product … second pixel data as captured by the imaging device" to the extent of using multiple medical images and dose maps across a set of patients and treatment conditions, and applying the artificial intelligence model to new patient data to generate multiple predicted dose maps, see paragraphs 0062–0067 and 0073–0077 of Gao et al. "Generate, based on output of the dosing learning model, a second analysis comprising a second dosage comparison" to the extent of repeatedly executing the artificial intelligence model for different patients and/or different treatment conditions, generating predicted dose maps that can be compared with clinical goals and previous dose maps, see paragraphs 0073–0077 and 0093–0101 of Gao et al. Gao et al. fails to explicitly teach: "Obtain a second set of one or more images of the product" in the specific context of external products and appliances. "Second target dosage of the product at a second time state" and "second feedback indication" explicitly directed to external product usage at different time states. Kondziolka et al. teaches: "Second target dosage of the product at a second time state" and "second feedback indication" to the extent of acquiring imaging information before and after stereotactic radiosurgery, computing radiation doses based on serial imaging (e.g., GRASP MRI), tracking tumor responsiveness, and altering dose recommendations based on changes in imaging parameters over time, see paragraphs 0038–0043 and 0045–0047 of Kondziolka et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 3, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 1, further comprising a product-based learning model, accessible by the dosing app, and trained with pixel data of a plurality of training images depicting one or more products, the product-based learning model trained to output product predictions of one or more product identifiers corresponding to the one or more products depicted within the pixel data of the plurality of training images, and wherein the computing instructions of the dosing app when executed by the one or more processors, further cause the one or more processors to: -- obtain a set of one or more images of the product, wherein the product data comprises the set of one or more images of the product, the set of one or more images of the product comprising pixel data of the product as captured by an imaging device, and the pixel data of the product depicting least a portion of the product, -- detect, based on output of the product-based learning model inputting the pixel data of the product, the product identifier of the product." Gao et al. teaches: "Further comprising a product-based learning model, accessible by the dosing app, and trained with pixel data of a plurality of training images depicting one or more products" to the extent of an artificial intelligence model (AI model 111) trained with medical images and structure masks depicting one or more internal structures (e.g., PTVs and OARs) and associated radiotherapy treatment attributes, where the model is accessible to the analytics server and related applications, see paragraphs 0045–0049, 0062–0067, and 0075–0079 of Gao et al. "The product-based learning model trained to output product predictions of one or more product identifiers corresponding to the one or more products depicted within the pixel data of the plurality of training images" to the extent that the AI model is trained to output predicted dose maps conditioned on modality and beam geometry for different patients and treatment configurations, effectively classifying and predicting dose distributions for different planning types and beam geometries based on image and mask pixel data, see paragraphs 0061–0067 and 0073–0077 of Gao et al. "Obtain a set of one or more images of the product … pixel data of the product as captured by an imaging device" to the extent of obtaining CT images of the patient’s internal structures that are used as inputs to the artificial intelligence model, see paragraphs 0064–0067 of Gao et al. Gao et al. fails to explicitly teach: "Product-based learning model" distinct from the dosing learning model, where the model’s explicit output is "product predictions of one or more product identifiers" for external products. "Detect, based on output of the product-based learning model … the product identifier of the product" in the sense of an external product identifier. Kondziolka et al. teaches: Use of imaging-based classification and parameter estimation to categorize tumors and treatment targets, including determination of tumor types, sizes, locations, and imaging-derived biomarkers such as ADC, which effectively identifies target categories based on imaging data, see paragraphs 0023–0033 and 0030–0031 of Kondziolka et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 4, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 4, wherein the one or more product identifiers are based on one or more features identifiable within the pixel data of the plurality of training images, the one or more features selected from a product category of the one or more products, a product brand of the one or more products, a product variant of the one or more products, a product form of the one or more products, a product packaging of the one or more products and combinations thereof." Gao et al. teaches: "One or more product identifiers … based on one or more features identifiable within the pixel data of the plurality of training images" to the extent of using structure masks and CT images to identify anatomical structures (planning target volumes and organs at risk) and beam geometries from pixel data, and conditioning the artificial intelligence model on modality and beam geometry indicators that are derived from dose maps and treatment plans, see paragraphs 0064–0067 and 0071–0075 of Gao et al. Gao et al. fails to explicitly teach: "Product category … product brand … product variant … product form … product packaging" as explicit feature types. Kondziolka et al. teaches: Classification of tumors and targets based on imaging-derived features such as size, shape, location, ADC, and perfusion parameters, which are identifiable within pixel data and used to categorize targets and adjust dose, see paragraphs 0019–0024, 0023–0033, and 0030–0034 of Kondziolka et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 5, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 4, wherein the output of the product-based learning model comprises a product prediction with a 90% or greater percentage accuracy that the product identifier correctly identifies the product." Gao et al. teaches: "Output of the product-based learning model comprises a product prediction" to the extent of the AI model generating predicted dose maps conditioned on modality and beam geometry, which embodies predictions about dose distributions, see paragraphs 0061–0067 and 0073–0077 of Gao et al. Gao et al. fails to explicitly teach: "90% or greater percentage accuracy that the product identifier correctly identifies the product" or explicit numerical accuracy thresholds for classification outputs. Kondziolka et al. teaches: Use of imaging-derived parameters and studies demonstrating significant correlation between imaging metrics and treatment outcomes, including quantitative assessments such as reductions in area under the curve and wash-in kinetics for permeability imaging, which indicate performance characteristics of the imaging-based methods, see paragraphs 0039–0042 of Kondziolka et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 6, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 1, wherein the dosage data of one or more products comprise at least one of: (a) an amount, size, or dimension of the product; (b) an amount, size, or dimension of the product relative to the product appliance and/or the product implement; and/or (c) a composition of the product." Gao et al. teaches: "Dosage data of one or more products comprise at least one of: (a) an amount, size, or dimension of the product" to the extent that dose maps represent spatial distributions and magnitudes of dose (amount and spatial extent), and that medical images and structure masks encode sizes and dimensions of target structures and organs at risk, see paragraphs 0064–0067 and 0065–0066 of Gao et al. Gao et al. fails to explicitly teach: "Amount, size, or dimension of the product relative to the product appliance and/or the product implement" and "composition of the product" as explicit data categories. Kondziolka et al. teaches: Use of imaging parameters and quantitative measures such as tumor volume, ADC, and perfusion metrics to determine dose, which correspond to amount and size of the target, and consideration of tumor characteristics (e.g., cell density, metabolic activity) that correspond to composition-like properties of the target, see paragraphs 0023–0031 and 0030–0034 of Kondziolka et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 7, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 1, wherein each image of the one or more of first plurality of training images or the first set of one or more images comprises at least one cropped image removing at least a portion of personally identifiable information (PII) of a user." Gao et al. teaches: Use of medical images (CT scans and other imaging modalities) that may be de-identified or anonymized in clinical datasets, although Gao et al. does not explicitly state "cropped image removing at least a portion of personally identifiable information (PII) of a user," see paragraphs 0062–0067 and 0064–0065 of Gao et al. Gao et al. fails to explicitly teach: "Each image … comprises at least one cropped image removing at least a portion of personally identifiable information (PII) of a user." Kondziolka et al. teaches: Use of patient imaging data in a manner consistent with clinical research and patient safety, including references to clinical data and imaging studies where de-identification and anonymization practices are standard, though not explicitly recited as cropping PII, see paragraphs 0019–0024 and 0039–0043 of Kondziolka et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 8, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 1, wherein the product identifier is submitted as an input to look up or link to additional data defining the product, the additional data being selected from formula specification of the product, a trait of the product, packaging data of the product, a clinical indication of the product and combinations thereof." Gao et al. teaches: Use of identifiers and data linking in radiotherapy systems where patient identifiers, treatment plans, and clinical goals are used to retrieve and link additional data such as dose constraints, structure definitions, and treatment modalities, see paragraphs 0051–0053 and 0093–0101 of Gao et al. Gao et al. fails to explicitly teach: "Product identifier" and "additional data defining the product" such as "formula specification of the product, a trait of the product, packaging data of the product, a clinical indication of the product" as explicit categories. Kondziolka et al. teaches: Use of clinical outcome data, tumor volume, safety data, and pathological information to determine doses, effectively using identifiers (e.g., tumor type and clinical category) to retrieve additional data such as outcome and safety guidelines, see paragraphs 0003–0005 and 0031–0033 of Kondziolka et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 9, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 1, wherein each image of the plurality of training images comprises multiple angles or perspectives depicting the one or more products, and wherein each image of the plurality of training images comprises multiple angles or perspectives depicting the one or more dosages." Gao et al. teaches: Use of three-dimensional medical images and structure masks that inherently provide multiple angles or perspectives of internal structures and dose distributions, and use of beam geometry angle plates and beam plates that encode angles and perspectives of beams relative to structures, see paragraphs 0064–0067, 0069–0071, and 0070–0071 of Gao et al. Gao et al. fails to explicitly teach: "Each image … comprises multiple angles or perspectives" expressed in terms of external products and dosages. Kondziolka et al. teaches: Use of multiple imaging contrasts and sequences (e.g., multiple MRI sequences, CT, PET) and GRASP MRI imaging at multiple times and potentially multiple orientations, which collectively provide multiple perspectives on the tumor and dose distribution, see paragraphs 0023–0031, 0038–0043, and 0039–0042 of Kondziolka et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 10, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 1, wherein the dosing learning model comprises a segmentation model trained to generate a segmentation mapping defining, in the pixel data, the dosages of the product and the product appliance or the product implement configured to apply the dosages." Gao et al. teaches: "Segmentation model trained to generate a segmentation mapping defining, in the pixel data, the dosages of the product and the product appliance or the product implement" to the extent that the artificial intelligence model uses structure masks (segmentations) for planning target volumes and organs at risk and uses angle plates and beam plates to encode beam geometry in pixel space, and that dose maps and masks encode the regions and magnitudes of dose in voxelized form, see paragraphs 0064–0067, 0069–0071, and 0075–0079 of Gao et al. Gao et al. fails to explicitly teach: Segmentation mapping that explicitly segments external "product" and "product appliance" or "product implement" in consumer-product contexts. Kondziolka et al. teaches: Use of imaging parameters and maps such as ADC maps and GRASP MRI permeability maps, which function as segmentation-like mappings that define regions with differing imaging characteristics and guide dose determination, see paragraphs 0023–0031 and 0038–0043 of Kondziolka et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 11, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 1, wherein the feedback indication is generated based on the dosing comparison and at least one of (a) a physical attribute of the product appliance or the product implement; (b) a pattern or arrangement of the product as positioned on or with respect to the product appliance or the product implement; and (c) a provision of the dosage of the product by a user when applying the product with the product appliance or the product implement." Gao et al. teaches: "Feedback indication … generated based on the dosing comparison" to the extent of outputting predicted dose maps and related visual and numerical outputs (dose-volume histograms and optimized plans) that reflect differences between predicted dose distributions and clinical goals, see paragraphs 0005–0007 and 0093–0101 of Gao et al. Gao et al. fails to explicitly teach: "Physical attribute of the product appliance or the product implement" and "pattern or arrangement of the product" as applied to external products and appliances. Kondziolka et al. teaches: Use of imaging-derived patterns such as permeability curves and ADC maps to infer treatment response and recurrence, including shifts in enhancement-time curves that indicate structural and vascular changes, see paragraphs 0039–0043 of Kondziolka et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 12, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 1, wherein the feedback indication comprises at least one of (a) a qualitative rating; (b) a numeric assessment; (c) a visual projection; (d) an augmented reality annotation; (e) and a categorical rating." Gao et al. teaches: "Feedback indication comprises at least one of (a) a qualitative rating; (b) a numeric assessment; (c) a visual projection" to the extent that the system outputs predicted dose maps (visual projections), dose-volume histograms (numeric assessments), and comparisons to clinical goals that can be interpreted qualitatively and categorically with respect to adequate or inadequate dose distributions, see paragraphs 0008–0012 and 0093–0101 of Gao et al. Gao et al. fails to explicitly teach: "Augmented reality annotation" and explicit labeling as "qualitative rating" or "categorical rating" in the context of external product applications. Kondziolka et al. teaches: Presentation of imaging results and experimental data (e.g., GRASP MRI images and enhancement-time graphs) that can be interpreted and annotated for clinical decision making, see paragraphs 0038–0043 of Kondziolka et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 13, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 1, wherein the target dosage comprises at least one of a visual appearance of the product, a color of the product, a volume of the product, an amount of the product, a dimension of the product, a pattern of the product, a shape of application of the product, a texture of the product, a density of the product, a relative ratio of the product, and/or a position of the product relative to the product appliance or the product implement." Gao et al. teaches: "Target dosage comprises … volume of the product, an amount of the product, a dimension of the product, a pattern of the product, a shape of application of the product, a density of the product, a relative ratio of the product, and/or a position of the product relative to the product appliance or the product implement" to the extent that dose maps represent volumetric dose distributions (volume, amount, dimensions, patterns, shapes) and dose-volume histograms represent relative ratios and distributions of dose within structures, see paragraphs 0064–0067 and 0093–0101 of Gao et al. Gao et al. fails to explicitly teach: "Visual appearance of the product, a color of the product, a texture of the product" and explicit reference to "position of the product relative to the product appliance or the product implement" in external product contexts. Kondziolka et al. teaches: Use of imaging parameters and maps that reflect tissue characteristics such as cellular density and perfusion (corresponding to density and texture-like features) and patterns of enhancement and permeability over time, see paragraphs 0023–0031 and 0038–0043 of Kondziolka et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 14, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 1, wherein the computing instructions of the dosing app when executed by the one or more processors, further cause the one or more processors to render, on a display screen of a computing device, the feedback indication to indicate a difference or similarity between the dosage of the product and the target dosage of the product." Gao et al. teaches: "Render, on a display screen of a computing device, the feedback indication to indicate a difference or similarity between the dosage of the product and the target dosage of the product" to the extent that the analytics server renders graphical user interfaces on end-user devices and medical device computers that display predicted dose maps and dose-volume histograms, and that these displays inherently indicate differences or similarities between predicted dose distributions and clinical goals, see paragraphs 0045–0049 and 0093–0101 of Gao et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 15, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 1, wherein the computing instructions of the dosing app when executed by the one or more processors, further cause the one or more processors to render, on a display screen of a computing device, at least one dosage recommendation based on the feedback indication." Gao et al. teaches: "Render … at least one dosage recommendation based on the feedback indication" to the extent that the system outputs predicted dose maps and dose-volume histograms that are used as inputs to a plan optimizer, which generates treatment plans that implicitly contain dosage recommendations, and that these results are displayed to medical professionals via the electronic platform, see paragraphs 0005–0007, 0093–0101, and 0103–0107 of Gao et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 16, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based system of claim 1, wherein the one or more processors comprises a server processor of a server, wherein the server is communicatively coupled to a computing device via a computer network, and where the dosing app comprises a server app portion configured to execute on the one or more processors of the server and a computing device app portion configured to execute on one or more processors of the computing device, the server app portion configured to communicate with the computing device app portion, wherein the server app portion is configured to implement one or more of: (1) detecting, based on the product data, the product identifier of the product; (2) obtaining the set of one or more images of the product; (3) generating, based on the output of the dosing learning model, the first analysis comprising a dosage comparison; and/or (4) outputting, based on the dosage comparison, the feedback indication." Gao et al. teaches: "One or more processors comprises a server processor of a server, wherein the server is communicatively coupled to a computing device via a computer network" and "server app portion … and computing device app portion" to the extent that Gao et al. discloses an analytics server (server 110a) connected via a network to end-user devices (clinic computer 140a, clinic server 140b, medical professional device 140c) and medical device computers (162), with the analytics server generating and hosting an electronic platform and graphical user interfaces that are displayed on end-user devices, see paragraphs 0045–0053 of Gao et al. "Server app portion … configured to implement one or more of: (1) detecting, based on the product data, the product identifier of the product; (2) obtaining the set of one or more images of the product; (3) generating, based on the output of the dosing learning model, the first analysis comprising a dosage comparison; and/or (4) outputting, based on the dosage comparison, the feedback indication" to the extent that the analytics server retrieves patient and treatment data from electronic data sources, retrieves medical images and dose maps, generates training datasets, trains and executes the AI model, generates predicted dose maps, compares predicted dose maps with clinical goals, and outputs results to client devices, see paragraphs 0051–0053, 0062–0067, 0073–0077, and 0093–0101 of Gao et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 1, and incorporated herein. As per Claim 17, Gao et al. and Kondziolka et al. teach: "A digital imaging and artificial intelligence (AI)-based method for analyzing product usage, the digital imaging and AI-based method comprising: -- detecting, by one or more processors based on product data, a product identifier of a product,-- obtaining, by a dosing application (app) executing on the one or more processors, a set of one or more images of the product, the set of one or more images comprising pixel data as captured by an imaging device, and the pixel data depicting a dosage of the product and at least one of: (a) a product appliance configured to apply the product, or (b) a product implement configured to receive the product,-- generating, based on output of a dosing learning model, a first analysis comprising a dosage comparison comparing the dosage of the product as depicted in pixel data to a target dosage of the product at a first time state, the target dosage of the product defining an expected dosage of the product at the first time state, wherein the dosing learning model executes on the one or more processors and is trained with dosage data of one or more products that includes the product, pixel data of a plurality of training images depicting the one or more products, and one or more product appliances or product implements associated with the one or more products, the dosing learning model trained to output analysis of one or more dosages corresponding to the one or more products based on one or more corresponding target dosages applied at different times during a product application lifecycle, and-- outputting, by the one or more processors based on the dosage comparison, a feedback indication designed to address at least one feature identifiable within the pixel data comprising the dosage of the product." Gao et al. teaches: "Digital imaging and artificial intelligence (AI)-based method" and "dosing learning model executes on the one or more processors" to the extent of a method executed by an analytics server that includes generating a training dataset from medical images, structure masks, modality indicators, and beam geometry, training an artificial intelligence model, executing the artificial intelligence model for new patients to generate predicted dose maps indicating dosage received by internal structures, and outputting predicted dose maps for use in treatment planning, see paragraphs 0007–0015, 0062–0067, and 0073–0077 of Gao et al. "Obtaining, by a dosing application (app) executing on the one or more processors, a set of one or more images … pixel data as captured by an imaging device" to the extent that the analytics server retrieves medical images (e.g., CT scans) and structure masks from electronic data sources, see paragraphs 0062–0067 and 0064–0065 of Gao et al. "Generating, based on output of a dosing learning model, a first analysis comprising a dosage comparison" and "outputting … a feedback indication" to the extent that the method includes generating predicted dose maps, comparing them to clinical goals, generating dose-volume histograms, and providing outputs to a plan optimizer and graphical user interfaces, see paragraphs 0005–0007 and 0093–0101 of Gao et al. Gao et al. fails to explicitly teach: "Detecting, by one or more processors based on product data, a product identifier of a product" and explicit reference to external products and appliances. Kondziolka et al. teaches: "Generating … a first analysis comprising a dosage comparison" and "outputting … a feedback indication" to the extent of computing a radiation dose based on imaging information, comparing the computed dose to a dose determined from clinical outcome data and other factors, and alerting the health-care professional when a discrepancy indicates that further evaluation is warranted, see Claim 1 and paragraphs 0035–0037 of Kondziolka et al. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include the dosage comparison and feedback method steps taught by Kondziolka et al. within the artificial intelligence-based method taught by Gao et al., with the motivation of enabling comparison of predicted or measured dosages to target dosages and providing feedback indications to guide dose adjustments, as taught in paragraphs 0035–0037 of Kondziolka et al. and paragraphs 0005–0007. As per Claim 18, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based method of claim 17 further comprising:-- obtaining a second set of one or more images of the product, the second set of one or more images comprising second pixel data as captured by the imaging device, and the second pixel data depicting a second dosage of the product and the product appliance or the product implement,-- generating, based on output of the dosing learning model, a second analysis comprising a second dosage comparison of the second dosage of the product as depicted in second pixel data to a second target dosage of the product at a second time state, the second target dosage of the product defining a second expected dosage of the product at the second time state, and-- outputting, based on the second dosage comparison, a second feedback indication designed to address at least one feature identifiable within the second pixel data comprising the second dosage of the product." Gao et al. teaches: "Obtaining a second set of one or more images" and "generating … a second analysis comprising a second dosage comparison" to the extent of executing the artificial intelligence model for multiple patients or multiple treatment conditions, generating multiple predicted dose maps, and comparing those maps with clinical goals, see paragraphs 0073–0077 and 0093–0101 of Gao et al. Gao et al. fails to explicitly teach: "Second target dosage of the product at a second time state" and "second feedback indication" directed to external product applications. Kondziolka et al. teaches: Serial imaging and dose adjustment based on changes observed at different times, including GRASP MRI imaging at multiple time points (e.g., 83 days, 169 days, 280 days after stereotactic radiosurgery) and interpreting changes in permeability curves to identify tumor recurrence, see paragraphs 0038–0043 of Kondziolka et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 17, and incorporated herein. As per Claim 19, Gao et al. and Kondziolka et al. teach: "The digital imaging and AI-based method of claim 17, further comprising a product-based learning model, accessible by the dosing app, and trained with pixel data of a plurality of training images depicting one or more products, the product-based learning model trained to output product predictions of one or more product identifiers corresponding to the one or more products depicted within the pixel data of the plurality of training images,-- and wherein the AI-based method further comprises:-- obtaining a set of one or more images of the product, wherein the product data comprises the set of one or more images of the product, the set of one or more images of the product comprising pixel data of the product as captured by an imaging device, and the pixel data of the product depicting least a portion of the product,-- detecting, based on output of the product-based learning model inputting the pixel data of the product, the product identifier of the product." Gao et al. teaches: "Product-based learning model, accessible by the dosing app, and trained with pixel data of a plurality of training images" to the extent of an artificial intelligence model trained using medical images and structure masks representing internal structures, where the model is stored in a system database and accessed by the analytics server and end-user devices, see paragraphs 0045–0049 and 0062–0067 of Gao et al. "Output product predictions of one or more product identifiers" to the extent that the artificial intelligence model outputs dose predictions conditioned on modality and beam geometry, effectively predicting dose distributions associated with specific modality and beam configurations, see paragraphs 0061–0067 and 0073–0077 of Gao et al. "Obtaining a set of one or more images of the product … pixel data of the product as captured by an imaging device" to the extent of obtaining CT images and structure masks as inputs to the artificial intelligence model, see paragraphs 0064–0067 of Gao et al. Gao et al. fails to explicitly teach: "Product-based learning model" distinct from the dosing learning model whose explicit output is a "product identifier of the product" in external product contexts. Kondziolka et al. teaches: Classification of tumor types and treatment targets based on imaging parameters and features, as described in the context of ADC maps and other imaging-derived parameters, see paragraphs 0023–0031 and 0030–0034 of Kondziolka et al. The obviousness of combining the teachings of Gao et al. and Kondziolka et al. are discussed in the rejection of claim 17, and incorporated herein. As per Claim 20, Gao et al. and Kondziolka et al. teach: "A tangible, non-transitory computer-readable medium storing instructions for analyzing product usage, that when executed by one or more processors cause the one or more processors to: -- detect, based on product data, a product identifier of a product,-- obtain, by a dosing application (app), a set of one or more images of the product, the set of one or more images comprising pixel data as captured by an imaging device, and the pixel data depicting a dosage of the product and at least one of: (a) a product appliance configured to apply the product, or (b) a product implement configured to receive the product,-- generate, based on output of a dosing learning model, a first analysis comprising a dosage comparison comparing the dosage of the product as depicted in pixel data to a target dosage of the product at a first time state, the target dosage of the product defining an expected dosage of the product at the first time state, wherein the dosing learning is trained with dosage data of one or more products that includes the product, pixel data of a plurality of training images depicting the one or more products, and one or more product appliances or product implements associated with the one or more products, the dosing learning model trained to output analysis of one or more dosages corresponding to the one or more products based on one or more corresponding target dosages applied at different times during a product application lifecycle, and-- output, based on the dosage comparison, a feedback indication designed to address at least one feature identifiable within the pixel data comprising the dosage of the product." Gao et al. teaches: "Tangible, non-transitory computer-readable medium storing instructions" to the extent that Gao et al. discloses a computer system comprising a server with a processor and a non-transitory computer-readable medium containing instructions that, when executed by the processor, generate a training dataset comprising medical images, structure masks, modality indicators, and beam geometry; train an artificial intelligence model using the training dataset; execute the artificial intelligence model for a new patient to receive a predicted dose map indicating dosage received by internal structures; and output the predicted dose map, see paragraphs 0014–0020 of Gao et al. "Obtain … a set of one or more images" and "generate … a first analysis comprising a dosage comparison" and "output … a feedback indication" to the extent of instructions configured to retrieve medical images, execute the artificial intelligence model to generate predicted dose maps, compare predicted dose maps with clinical goals, generate dose-volume histograms, and output results to graphical user interfaces and plan optimizers, see paragraphs 0007–0015, 0062–0067, 0073–0077, and 0093–0101 of Gao et al. Gao et al. fails to explicitly teach: "Detect, based on product data, a product identifier of a product" and "product appliances or product implements" in external product contexts. Kondziolka et al. teaches: Non-transitory computer-readable memory having instructions thereon for acquiring imaging information and computing a radiation dose based at least on the imaging information, as well as instructions for serially measuring cellular imaging responses and using them to study tumor response and evaluate treatment efficacy, see paragraphs 0007 and 0044–0047 of Kondziolka et al. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to include the imaging-based dose computation and serial response analysis instructions taught by Kondziolka et al. within the non-transitory computer-readable medium taught by Gao et al., with the motivation of providing a comprehensive software implementation that supports dose prediction, comparison, and response tracking on a single tangible medium, as taught in paragraphs 0007 and 0044–0047 of Kondziolka et al . Conclusion 07-96 AIA The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. US 20240075216 A1 : A dosage verification system for use prior to administering an injection of a medicinal fluid drawn into a medical syringe, the system comprising a medical syringe having a barrel with an outwardly facing, flat indicia display surface, plunger having a plunger seal disposed inside and slidably engaging an inwardly facing wall of the barrel and a plunger handle projecting rearwardly from the barrel, and a hypodermic needle projecting forwardly from the barrel, all in combination with an imaging device configured to view and selectively capture, store or transmit a digital image of the plunger position relative to the barrel when a dose of the medicinal fluid is drawn into the fluid chamber of the barrel prior to an injection to verify and provide a record of the dosage drawn, and to alert a user prior to injection when an incorrect dosage is drawn into the fluid chamber of the syringe. Any inquiry concerning this communication or earlier communications from the examiner should be directed to EDWARD B WINSTON III whose telephone number is (571)270-7780. The examiner can normally be reached M-F 1030 to 1830. 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, Robert Morgan can be reached at (571) 272-6773. 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. /E.B.W/Examiner, Art Unit 3683 /ROBERT W MORGAN/Supervisory Patent Examiner, Art Unit 3683 Application/Control Number: 19/228,830 Page 2 Art Unit: 3683 Application/Control Number: 19/228,830 Page 3 Art Unit: 3683
Prosecution Insights