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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 30 September 2025, 02 February 2026, and 27 April 2026 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the IDS’s are being considered by the Examiner in this Office Action.
Response to Amendment
Claims 1-31 were previously pending in this application. The amendment filed 02 February 2026 has been entered and the following has occurred: Claims 1 & 16 have been amended. No claims have been cancelled or added.
Claims 1, 3-16, & 18-31 remain pending in the application
Claim Analysis - 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.
The claims recite subject matter within a statutory category as a process (claims 1 & 3-15), machine (claims 16 & 18-30), and manufacture (claim 31) (Subject Matter Eligibility (SME) Test Step 1: Yes) which recite steps of:
receiving, at a processor, order data, the order data comprising clinical request data relating to a patient;
receiving, at the processor from a first imaging device, a current study corresponding to the order data for the patient, the current study comprising current study metadata and one or more current series, each of the one or more current series comprising current series metadata;
applying, at the processor, one or more relevancy matching rules associated with the plurality of clinical software applications to the current study, the one or more relevancy matching rules comprising an order data rule, wherein the order data rule is applied to the order data corresponding to the current study;
based on the applying the one or more relevancy matching rules associated with the plurality of clinical software applications:
determining, at the processor, that the current study is a matched current study by:
sending, from the processor to each of a plurality of enterprise image management devices, a query for one or more candidate prior studies based on the matched current study, the one or more candidate prior studies each comprising prior study metadata and one or more prior series, each of the one or more prior series comprising prior series metadata, wherein applying the related study order data rule comprises matching one or more portions of the order data corresponding to the current study with information with one or more portion of an order data corresponding to the one or more candidate prior studies;
receiving, at the processor from at least one enterprise image management device of the plurality of enterprise image management devices, candidate prior study data relating to the one or more candidate prior studies; and
determining, at the processor, that the one or more candidate prior studies are one or more matched prior studies by applying a related study order data rule of the one or more relevancy matching rules to the one or more candidate prior studies; and
identifying, at the processor, a matching clinical software application in the plurality of clinical software applications based on applying the order data rule,
generating, at the processor, an assembled matched study set comprising the matched current study and the one or more matched prior studies;
retrieving, at the processor, image data corresponding to the assembled matched study set; and
processing, at the processor the assembled matched study set and the image data corresponding to the assembled matched study set using the matching clinical software application to generate a processed study.
These steps of receiving order data, receiving a current study corresponding to the order data for the patient, applying one or more relevancy matching rules associated with the plurality of clinical software applications to the current study, and based on the applying the one or more relevancy matching rules associated with the plurality of clinical software applications: determining that the current study is a matched current study by sending a query for one or more candidate prior studies, receiving candidate prior study data relating to the one or more candidate prior studies, and determining that one or more candidate prior studies are one or more matched prior studies by applying an order data rule; identifying a matching clinical software application in the plurality of clinical software applications based on applying the order data rule, generating an assembled matched study set comprising the matched current study, retrieving image data corresponding to the assembled matched study set; and processing the assembled matched study set and the image data corresponding to the assembled matched study set using the matching clinical software application to generate a processed study, as drafted, under the broadest reasonable interpretation, includes performance of the limitation in the mind but for recitation of generic computer components. That is, other than reciting steps as performed by the generic computer components, nothing in the claim element precludes the step from practically being performed in the mind. For example, but for the receiving order data and a current study (the current study comprising metadata and one or more image series) language, receiving said information in the context of this claim encompasses a mental process of the user physically receiving said information such as a physical case, imaging file, or image itself that is/are associated with a particular imaging series, session, and/or patient. Similarly, the limitation of applying one or more relevancy rules, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, such as the user mentally applying categorical/relevancy rules to determine similar/relevant medical imaging studies previously performed for a particular series, patient, session, etc. but for the recitation of generic computer components. For example, but for the determining that the current study is a matched current study language, determining that the current study is matching in the context of this claim encompasses a mental process of the user determining if a case is relevant based on applying said categorical/relevancy rules to determine similar/relevant medical imaging studies previously performed for a particular series, patient, or session and determining metadata is the same between said prior studies and/or current studies either based on generic computer operation or human identification. For example, but for specifying the manner of applying the relevancy rules, such as by identifying a matching clinical software application, generating an assembled study set that includes the current study, retrieving image data corresponding to the study set and processing the study set and image data in the context of this claim encompasses a mental process of the user determining an appropriate clinical software to use based on previous cases of similar natures/characteristics, adding the current study to a study file or multiple files that are relevant to the current study, retrieving relevant data, findings, conclusions, modalities, etc. for the multiple relevant files and comparing them to the current study, and processing or analyzing said current study based on the same or similar processing/analyses performed in the relevant files, respectively. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea (SME Test Step 2A, Prong 1: Yes).
Dependent claims recite additional subject matter which further narrows or defines the abstract idea embodied in the claims (such as claims 3-15 & 18-31, reciting particular aspects of how determining the status of an imaging study, processing or reviewing an image study, retrieving a plurality of imaging studies or matching imaging studies, and/or formatting an imaging study/imaging study metadata/results from an imaging study, may be performed in the mind but for recitation of generic computer components).
This judicial exception is not integrated into a practical application. In particular, the additional elements do not integrate the abstract idea into a practical application, other than the abstract idea per se, because the additional elements amount to no more than limitations which:
amount to mere instructions to apply an exception (such as recitation of clinical software applications, a processor/processing unit, an imaging device, a memory, a network device, a non-transitory computer readable medium, an enterprise image management device, amounts to invoking computers as a tool to perform the abstract idea, see Applicant’s Specification [0187]-[0188] for software applications, [0154]-[0155] for processor/processing unit, [0076] & [0148] for imaging devices, [0156] for memory, [0144] for network/network device, [0070] for non-transitory computer readable medium, [0076] & [0148] for imaging/enterprise image management devices, see MPEP 2106.05(f));
add insignificant extra-solution activity to the abstract idea (such as recitation of receiving order data, receiving a current study, retrieving image data corresponding to the assembled matched study set, receiving one or more relevancy matching rules, sending a query for one or more candidate prior studies based on the matched current study, receiving candidate prior study data relating to one or more candidate prior studies, amounts to mere data gathering, recitation of applying one or more relevancy matching rules, determining that the current study is a matched current study, identifying a matching clinical software application based on the order data rule, generating an assembled matched study set, processing the assembled matched study set and the image data using the matching clinical software application, determining that the one or more candidate prior studies are one or more matched prior studies by applying a related study order data rule of the one or more relevancy matching rules to the one or more candidate prior studies, matching one or more portions of the order data corresponding to the current study with information with one or more portion of an order data corresponding to the one or more candidate prior studies amounts to selecting a particular data source or type of data to be manipulated, recitation of using a matching clinical software application to generate a processed study amounts to insignificant application, see MPEP 2106.05(g));
generally link the abstract idea to a particular technological environment or field of use (such as generally linking the abstract idea to the technological environment of an imaging software application/imaging enterprise device and/or associated clinical settings where imaging is used, see MPEP 2106.05(h)).
Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims (such as claims 4-5, 7-8, 13, 16 & 18-31, which recite limitations relating to a processor, an EMR system, an RIS system, a parser engine, a network device, a matched clinical application, additional limitations which amount to invoking computers as a tool to perform the abstract idea, see Applicant’s Specification [0154]-[0155] for processor/processing unit, [0076] & [0148] for imaging/enterprise image management devices, [0077] for EMR system, [0077] for RIS system, [0126] for parser engine, [0144] for network/network device, [0187]-[0188] for software/matched clinical applications, see MPEP 2106.05(f); claims 3-8, 10-11, 14-15, 18-23, 25-26, & 29-31, which recite limitations relating to receiving studies, receiving queries, receiving relevancy matching rules, receiving order data rule, specifying where the data is received from, specifying the type of data being received, and/or the formatting of the data, additional limitations which add insignificant extra-solution activity to the abstract idea which amounts to mere data gathering; claims 3, 6-7, 9-10, 12-13, 16, 21-22, 24-25, 27-28, & 31, which recite limitations relating to determining that one or more candidate prior study are one or more matched prior studies by applying a related study order data rule, identifying a particular related study order rule and applying said rule, defining an order data rule such as a data matching pattern, using a parser engine, i.e. parsing the order/clinical request data, processing the study by processing patient metadata/imaging data/order data, automatically processing the matched study set, additional limitations which add insignificant extra-solution activity to the abstract idea by selecting a particular data source or type of data to be manipulated, claims 3-15 & 18-31, which generally recite limitations relating to medical imaging systems, medical imaging processing systems, and clinical communication networks additional limitations which generally link the abstract idea to a particular technological environment or field of use). Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation and do not impose a meaningful limit to integrate the abstract idea into a practical application (SME Test Step 2A, Prong 2: No).
The claims do include additional elements that are sufficient to amount to significantly more than the judicial exception. The additional elements found in the independent claims regarding the training and subsequent modification of the machine learning parameters for said machine learning image routing model fall outside the realm of being reasonably performed/amounting to significantly more than processes performed in the human mind. Additionally, said aspects of the applied machine learning model and subsequent improvements to medical image study routing/software compatibility seem to result in significantly more, at least by subsequent adjustment of said machine learning model parameters in view of the USPTO’s 2025 Subject Matter Eligibility Updates, which expresses the view that subsequent model parameterization and/or optimization of said parameters, especially parameters specific to the machine learning model (in the case of the instant application, these parameters stem from more than just generically received data, but rather are claimed as training datasets comprising “medical study data for a plurality of training studies and labels identifying one or more matched clinical software applications for respective ones of the plurality of training studies, wherein training the machine learning routing model comprises adjusting model parameters based on the labels”) amounts to a particular machine or particularly-curated model. Therefore, these aspects amount to a particular machine and/or models that go beyond generic, off-the-shelf machine learning models that are typically found in the prior art and merely being applied to the characterized abstract idea. Rather, the aspects read as specifically-built/tailored models for appropriately routing and matching clinical software for clinical images and studies associated therewith, thereby representing patent-eligible subject matter. Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims and further limit said independent claims, and therefore by virtue of dependency, the dependent claims also represent patent-eligible subject matter (SME Test Step 2B: Yes).
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 inventions 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, 3-16, & 18-31 are rejected under 35 U.S.C. 103 as being unpatentable over Baker et al. (U.S. Patent Publication No. 2021/0398650), hereinafter “Baker”, in view of Sorenson et al. (U.S. Patent Publication No. 2021/0098113), hereinafter “Sorenson”.
Claim 1 –
Regarding Claim 1, Baker discloses a method for processing a plurality of medical images using a plurality of clinical software applications, the method comprising:
receiving, at a processor, order data, the order data comprising clinical request data relating to a patient (See Baker Par [0038] & [0044] for order data corresponding to a particular order with a particular set of study images; See Baker Par [0030]-[0031] which discloses the medical imaging system configuration including an imaging system such as an imaging device with an associated processor as described in Baker Par [0033]);
receiving, at the processor from a first imaging device, a current study corresponding to the order data for the patient, the current study comprising current study metadata and one or more current series, each of the one or more current series comprising current series metadata (See Baker Par [0038] & [0044] for order data corresponding to a particular order with a particular set of study images; See Baker Par [0038] & [0045] which discloses extracting metadata from each image file in a series of images, metadata that may include a type of imaging modality/technique used to obtain the images and identification information such as a patient or study identifier; See Baker Par [0030]-[0031] which discloses the medical imaging system configuration including an imaging system such as an imaging device);
training a machine learning routing model using a training dataset (See Baker Par [0197]-[0198] which discloses the use of AI model training functions that may be used to implement training of an AI model, such that the AI model verification functions may be used to modify machine learning model parameters based on verification of outcomes),
the training dataset comprising:
medical study data for a plurality of training studies (See Baker Par [0194] which discloses a machine learning model and associated database providing a location for storage of deep learning models, inputs, and relevant parameters for operation of the machine learning algorithms; See Baker Par [0197]-[0198] which discloses the use of AI model training functions that may be used to implement training of an AI model, such that the AI model verification functions may be used to modify machine learning model parameters based on verification of outcomes, albeit not based on labels identifying one or more matched clinical software applications for respective ones of the plurality of training studies) and wherein
training the machine learning routing model comprises adjusting model parameters based on the labels (See Baker Par [0197]-[0198] which discloses the use of AI model training functions that may be used to implement training of an AI model, such that the AI model verification functions may be used to modify machine learning model parameters based on verification of outcomes, albeit not based on labels identifying one or more matched clinical software applications for respective ones of the plurality of training studies);
applying, at the processor, one or more relevancy matching rules associated with the plurality of clinical software applications to the current study, the one or more relevancy matching rules comprising an order data rule, wherein the order data rule is applied to the order data corresponding to the current study (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules” such that certain processing algorithms and/or image recognition models may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata);
based on the applying the one or more relevancy matching rules associated with the plurality of clinical software applications:
determining, at the processor, that the current study is a matched current study (See Baker Par [0038] which discloses correlating a particular order (and order data) with a particular set of study images (and image data) such that lateral and horizontal movement of studied can be orchestrated; See Baker Par [0049] which discloses the use of previous historical studies and expert results including the same format and content as the medical imaging study to be evaluated; See Baker Par [0124]-[0125] which discloses AI model ensuring that the anatomy, view type, study type, and other information matches what the tech is ordering, i.e. that the current study is a matching criteria to the order);
sending, from the processor to each of a plurality of enterprise image management devices, a query for one or more candidate prior studies based on the matched current study (See Baker Par [0047], [0062], & [0165] which discloses information such as previous imaging evaluations (such as prior images in medical image data and reports in patient data) being evaluated and a data cohort, such as of previous studies including study metadata such as described in Baker Par [0046] & [0190] which states that AI detection logic can be trained on prior image metadata; See Baker Par [0068] which discloses a user operating such as in an RIS/PACS instance on a medical imaging data processing platform, i.e. “enterprise image management device” without further specifying what delineates said enterprise image management device from simple RIS/PACS devices, and being able to order or request analysis for one or more studies),
the one or more candidate prior studies each comprising prior study metadata and one or more prior series, each of the one or more prior series comprising prior series metadata (See Baker Par [0047], [0062], & [0165] which discloses information such as previous imaging evaluations (such as prior images in medical image data and reports in patient data) being evaluated and a data cohort, such as of previous studies including study metadata such as described in Baker Par [0046] & [0190] which states that AI detection logic can be trained on prior image metadata);
receiving, at the processor from at least one enterprise image management device of the plurality of enterprise image management devices, candidate prior study data relating to the one or more candidate prior studies (See Baker Par [0047], [0062], & [0165] which discloses information such as previous imaging evaluations (such as prior images in medical image data and reports in patient data) being evaluated and a data cohort, such as of previous studies including study metadata such as described in Baker Par [0046] & [0190] which states that AI detection logic can be trained on prior image metadata; See Baker Par [0068] which discloses a user operating such as in an RIS/PACS instance on a medical imaging data processing platform, i.e. “enterprise image management device” without further specifying what delineates said enterprise image management device from simple RIS/PACS devices, and being able to order or request analysis for one or more studies);
determining, at the processor, that the one or more candidate prior studies are one or more matched prior studies by:
applying a related study order data rule of the one or more relevancy matching rules to the one or more candidate prior studies (See Baker Par [0038] which discloses the image server storing all or part of the extracted information in a study record that may be correlated with appropriate orders and studies and further processing orders or correlating a particular order, i.e. matched current study, with a particular set of study images, i.e. assembled matched study set; See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order), wherein
applying the related study order data rule comprises matching one or more portions of the order data corresponding to the current study with information with one or more portion of an order data corresponding to the one or more candidate prior studies (See Baker Par [0095]-[0096] which discloses validating varying data entry includes ensuring that the images sent match the exam being ordered, such that discrepancies between imaging and order data (or other medical metadata) may be identified; See Baker Par [0124]-[0125] which discloses the result of the image AI model classification is passed to RIS, and the RIS then uses the information to ensure that the anatomy, view type, study type, and other information from the image AI model matches what the tech is ordering, i.e. a study order data rule is applied by matching order data with the one or more portion of an order data of the prior studies, and if the match is not correct, the technician is informed and/or blocked from validating the study details);
identifying, at the processor, a matching clinical software application in the plurality of clinical software applications based on the matched application output, and applying the order data rule (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order),
generating, at the processor, an assembled matched study set comprising the matched current study and the one or more matched prior studies (See Baker Par [0038] which discloses processing orders or correlating a particular order, i.e. matched current study, with a particular set of study images, i.e. assembled matched study set; See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order; See Baker Par [0038] which discloses the image server storing all or part of the extracted information in a study record that may be correlated with appropriate orders and studies and further processing orders or correlating a particular order, i.e. matched current study, with a particular set of study images, i.e. assembled matched study set);
retrieving, at the processor, image data corresponding to the assembled matched study set (See Baker Par [0038] which discloses the image server storing all or part of the extracted information in a study record that may be correlated with appropriate orders and studies and further processing orders or correlating a particular order, i.e. matched current study, with a particular set of study images, i.e. assembled matched study set); and
processing, at the processor the assembled matched study set and the image data corresponding to the assembled matched study set using the matching clinical software application to generate a processed study (See Baker Par [0038] which discloses the image server storing all or part of the extracted information in a study record that may be correlated with appropriate orders and studies and further processing orders or correlating a particular order, i.e. matched current study, with a particular set of study images, i.e. assembled matched study set; See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order).
While Baker generally discloses the use of one or more clinical software applications and metadata/labels identifying one or more techniques used to obtain the images, Baker does not explicitly disclose that the identified “techniques” are the “clinical software applications” used to obtain the images, as given by the limitations below:
the training dataset comprising:
labels identifying one or more matched clinical software applications for respective ones of the plurality of training studies,
applying, at the processor, the trained machine learning routing model to at least a portion of the order data, at least a portion of the current study metadata and the current series metadata to generate a matched application output that identifies one or more clinical software applications, of the plurality of clinical software applications, that are matched to the current study.
Therefore, Sorenson discloses the training dataset comprising labels identifying one or more matched software applications for respective ones of the plurality of training studies (See Sorenson Par [0187]-[0189] which discloses that the medical data provided by data sources and processed by machine learning model may include medical image data specifying certain formats and/or software being used for said medical image data, possibly in one or more formats identifying said formats, i.e. labels) and applying, at the processor, the trained machine learning routing model to at least a portion of the order data, at least a portion of the current study metadata and the current series metadata to generate a matched application output that identifies one or more software applications, of the plurality of software applications, that are matched to the current study (See Sorenson Par [0187]-[0189] which discloses that the medical data provided by data sources and processed by machine learning model may include medical image data specifying certain formats and/or software being used for said medical image data, possibly in one or more formats identifying said formats, i.e. labels; See Sorenson Par [0190] which discloses that because various data sources and programs may use different communication standards, formats, or protocols, a machine learning module and other elements can use specific connectors or data source interfaces, i.e. applications, that can route data from the data source to the image processing server based on the received image data). The disclosure of Sorenson is directly applicable to the disclosure of Baker because both disclosures share limitations and capabilities, such as being directed towards the automated processing and management of medical images.
It would have been obvious to one of ordinary skill in the effective filing date of the claimed invention to modify the disclosure of Baker, which already discloses the use of one or more clinical software applications and metadata/labels identifying one or more techniques used to obtain the images, to further specifically include the identified “techniques” are the “clinical software applications” used to obtain the images, as disclosed by Sorenson, because this allows for automatic identification and compatible integration with data source interfaces to access the data using specific connectors or application communication software (See Sorenson Par [0190]).
Claim 3 –
Regarding Claim 3, Baker and Sorenson disclose the method of Claim 1 in its entirety. Baker further discloses a method, wherein:
the current study is determined to be the matched current study based on applying one or more particular matching rules of the one or more relevancy matching rules (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order), and applying the related study order data rule comprises:
identifying a particular related study order data rule associated with the one or more particular matching rules (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order); and
applying the related study order data rule by applying the particular related study order data rule (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules” being applied) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order).
Claim 4 –
Regarding Claim 4, Baker and Sorenson disclose the method of Claim 1 in its entirety. Baker further discloses a method, wherein:
the order is received from an EMR system (See Baker Par [0030]-[0032] & [0044] which discloses accessing an EMR or HIS for obtaining information relating to previous studies, evaluations, reports, etc., and/or being updated for the current imaging procedure).
Claim 5 –
Regarding Claim 5, Baker and Sorenson disclose the method of Claim 1 in its entirety. Baker further discloses a method, wherein:
the order data is received from an RIS system (See Baker Par [0068], [0193], & [0195] which discloses providing RIS functionality for managing the radiology workflows, order creation (understood to include order data), worklist applications for the operations center and radiologists, and case pages for the radiologist).
Claim 6 –
Regarding Claim 6, Baker and Sorenson disclose the method of Claim 1 in its entirety. Baker further discloses a method, wherein:
the order data rule defines a data matching pattern that specifies a set of relevant data from one or more data fields that must be matched in order to satisfy the order data rule (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order).
Claim 7 –
Regarding Claim 7, Baker and Sorenson disclose the method of Claim 1 in its entirety. Baker further discloses a method, wherein:
receiving at least one order message at a parser engine (See Baker Par [0045] which discloses an HL7 order message (ORM) being sent when a healthcare provider requests a service, procedure, or treatment for a patient; While not “parser engine” per se, Baker Par [0046] and Fig. 2 which disclose AI-coordinated model processing of image data and order data, which as disclosed in Baker Par [0045] can include an ORM, by the use of a processing algorithm and other condition detection logic; See Baker Par [0036] & [0062] which discloses the AI model including artificial neural network, convolutional neural network, recurrent neural network, reinforcement learning model, natural language processing model, machine learning algorithm, decision tree, support vector machine, genetic algorithm, etc., which is understood to include parsing embodiments based on the recitation of natural language processing);
parsing, using the parser engine at the processor, the at least one order message to identify the order data comprising the clinical request data based on at least one clinical request parsing rule (See Baker Par [0045] which discloses an HL7 order message (ORM) being sent when a healthcare provider requests a service, procedure, or treatment for a patient; While not “parser engine” per se, Baker Par [0046] and Fig. 2 which disclose AI-coordinated processing of image data and order data, which as disclosed in Baker Par [0045] can include an ORM, by the use of a processing algorithm and other condition detection logic, and the condition detection logic may select processing algorithms or image recognition models based on the characteristics of the medical imaging procedure indicated by order data or image metadata, which is understood to read on a clinical request parsing rule; See Baker Par [0036] & [0062] which discloses the AI model including artificial neural network, convolutional neural network, recurrent neural network, reinforcement learning model, natural language processing model, machine learning algorithm, decision tree, support vector machine, genetic algorithm, etc., which is understood to include parsing embodiments based on the recitation of natural language processing).
Claim 8 –
Regarding Claim 8, Baker and Sorenson disclose the method of Claim 1 in its entirety. Baker further discloses a method, wherein:
the current study is received at the processor directly from an image acquisition device (See Baker Par [0032] which discloses the series of images produced by the image data source being obtained directly by the imaging device).
Claim 9 –
Regarding Claim 9, Baker and Sorenson disclose the method of Claim 1 in its entirety. Baker further discloses a method, wherein:
each relevancy matching rule specifies one or more corresponding patient model fields (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute patient model and associated model fields) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order), and applying each relevancy matching rule comprises:
determining the presence or absence of relevant data within the one or more corresponding patient model fields of the patient model associated with the current study (See Baker Par [0037] & [0048] which discloses the system indicating the presence or particular identified conditions and the absence of certain identified conditions, e.g. descriptors, markings, annotations, or additional metadata for images of the medical imaging procedure data); and
determining that the current study is matched according to that relevancy matching rule in response to determining the presence of the relevant data within the one or more corresponding patient model fields (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order; See Baker Par [0037] & [0048] which discloses the system indicating the presence or particular identified conditions and the absence of certain identified conditions, e.g. descriptors, markings, annotations, or additional metadata for images of the medical imaging procedure data).
Claim 10 –
Regarding Claim 10, Baker and Sorenson disclose the method of Claim 9 in its entirety. Baker further discloses a method, wherein:
for at least one of the relevancy matching rules the at least one patient model field to be evaluated is selected from the group of:
an order notes field, a diagnosis description field, a diagnosis code field, a procedure code field, and a study indication field (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, i.e. procedure codes, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order; See Baker Par [0037] & [0048] which discloses the system indicating the presence or particular identified conditions and the absence of certain identified conditions, e.g. descriptors, markings, annotations, i.e. order notes, or additional metadata for images of the medical imaging procedure data, and further describes at Baker Par [0018] that the AI models may be trained to classify certain medical conditions, i.e. diagnosis code/description, and/or imaging modality, i.e. study indication; Baker Par [0032] further discloses that for images formatting according to the DICOM standard, data fields such as unique image identifier, unique study identifier, i.e. procedure code, patient’s name, and facility from which the image originates may be included).
Claim 11 –
Regarding Claim 11, Baker and Sorenson disclose the method of Claim 1 in its entirety. Baker further discloses a method, wherein:
the processed study is provided in a DICOM format (See Baker Par [0032], [0073], [0128], & [0177] which discloses reporting for a processed study being provided in DICOM structured reports).
Claim 12 –
Regarding Claim 12, Baker and Sorenson disclose the method of Claim 11 in its entirety. Baker further discloses a method, wherein:
the processed study comprises at least one of processed patient metadata, processed imaging data and processed order data (See Baker Par [0032] which discloses reporting for a processed study being provided such that images formatted according to DICOM standard include unique image identifiers, unique study identifiers, patient’s name (i.e. patient metadata), and the facility from which the image originates and Baker Par [0177] further discloses that reporting results/data can include the image data (i.e. DICOM image data), and non-image data (radiology order data) from a radiological imaging procedure).
Claim 13 –
Regarding Claim 13, Baker and Sorenson disclose the method of Claim 1 in its entirety. Baker further discloses a method, wherein:
the matched clinical application automatically processes the assembled matched study set (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, i.e. procedure codes, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order; See Baker Par [0037] & [0048] which discloses the system indicating the presence or particular identified conditions and the absence of certain identified conditions, e.g. descriptors, markings, annotations, i.e. order notes, or additional metadata for images of the medical imaging procedure data, and further describes at Baker Par [0018] that the AI models may be trained to classify certain medical conditions, i.e. diagnosis code/description, imaging modality, i.e. study indication).
Claim 14 –
Regarding Claim 14, Baker and Sorenson disclose the method of Claim 1 in its entirety. Baker further discloses a method, wherein:
the patient data is defined using a DICOM data format (See Baker Par [0032] which discloses reporting for a processed study being provided such that images formatted according to DICOM standard include unique image identifiers, unique study identifiers, patient’s name (i.e. patient metadata)).
Claim 15 –
Regarding Claim 15, Baker and Sorenson disclose the method of Claim 1 in its entirety. Baker further discloses a method, wherein:
the order data is defined using an HL7 format or a FHIR format (See Baker Par [0045] which discloses an HL7 order message (ORM) being sent when a healthcare provider requests a service, procedure, or treatment for a patient).
Claim 16 –
Regarding Claim 16, Baker discloses a system for processing a plurality of medical images using a plurality of clinical software applications (See Baker Par [0207] which discloses the use of one or more modules or software applications), the system comprising:
a memory (See Baker Par [0033], [0035], & [0201] which discloses the use of one or more memories), wherein
one or more relevancy matching rules are stored in the memory, the one or more relevancy matching rules associated with the plurality of clinical software applications, the one or more relevancy matching rules comprising an order data rule (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata);
a network device (See Baker Par [0025], [0201] & [0204] which discloses use of a network/communication interface device);
a processor in communication with the memory and the network device (See Baker Par [0033], [0035], & [0201] which discloses the use of one or more memories, processors, and/or computers with said components), the processor configured to:
receive, using the network device, order data, the order data comprising clinical request data relating to a patient (See Baker Par [0038] & [0044] for order data corresponding to a particular order with a particular set of study images; See Baker Par [0030]-[0031] which discloses the medical imaging system configuration including an imaging system such as an imaging device; See Baker Par [0025], [0201] & [0204] which discloses use of a network/communication interface device);
receive, using the network device from a first imaging device, a current study corresponding to the order data and the captured image for the patient, the current study comprising current study metadata and one or more current series, each of the one or more current series comprising current series metadata (See Baker Par [0038] & [0044] for order data corresponding to a particular order with a particular set of study images; See Baker Par [0038] & [0045] which discloses extracting metadata from each image file in a series of images, metadata that may include a type of imaging modality/technique used to obtain the images and identification information such as a patient or study identifier; See Baker Par [0030]-[0031] which discloses the medical imaging system configuration including an imaging system such as an imaging device);
train a machine learning routing model using a training dataset (See Baker Par [0197]-[0198] which discloses the use of AI model training functions that may be used to implement training of an AI model, such that the AI model verification functions may be used to modify machine learning model parameters based on verification of outcomes),
the training dataset comprising:
medical study data for a plurality of training studies (See Baker Par [0194] which discloses a machine learning model and associated database providing a location for storage of deep learning models, inputs, and relevant parameters for operation of the machine learning algorithms; See Baker Par [0197]-[0198] which discloses the use of AI model training functions that may be used to implement training of an AI model, such that the AI model verification functions may be used to modify machine learning model parameters based on verification of outcomes, albeit not based on labels identifying one or more matched clinical software applications for respective ones of the plurality of training studies )
training the machine learning routing model comprises adjusting model parameters based on the labels (See Baker Par [0197]-[0198] which discloses the use of AI model training functions that may be used to implement training of an AI model, such that the AI model verification functions may be used to modify machine learning model parameters based on verification of outcomes, albeit not based on labels identifying one or more matched clinical software applications for respective ones of the plurality of training studies);
apply the one or more relevancy matching rules to the current study (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata), wherein
the order data rule is applied to the order data corresponding to the current study (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata);
based on the applying the one or more relevancy matching rules:
determine that the current study is a matched current study (See Baker Par [0038] which discloses correlating a particular order (and order data) with a particular set of study images (and image data) such that lateral and horizontal movement of studied can be orchestrated; See Baker Par [0049] which discloses the use of previous historical studies and expert results including the same format and content as the medical imaging study to be evaluated; See Baker Par [0124]-[0125] which discloses AI model ensuring that the anatomy, view type, study type, and other information matches what the tech is ordering, i.e. that the current study is a matching criteria to the order) by:
sending, using the network device to each of a plurality of enterprise image management devices, a query for one or more candidate prior studies based on the matched current study (See Baker Par [0047], [0062], & [0165] which discloses information such as previous imaging evaluations (such as prior images in medical image data and reports in patient data) being evaluated and a data cohort, such as of previous studies including study metadata such as described in Baker Par [0046] & [0190] which states that AI detection logic can be trained on prior image metadata; See Baker Par [0068] which discloses a user operating such as in an RIS/PACS instance on a medical imaging data processing platform, i.e. “enterprise image management device” without further specifying what delineates said enterprise image management device from simple RIS/PACS devices, and being able to order or request analysis for one or more studies),
the one or more candidate prior studies each comprising prior study metadata and one or more prior series, each of the one or more prior series comprising prior series metadata (See Baker Par [0047], [0062], & [0165] which discloses information such as previous imaging evaluations (such as prior images in medical image data and reports in patient data) being evaluated and a data cohort, such as of previous studies including study metadata such as described in Baker Par [0046] & [0190] which states that AI detection logic can be trained on prior image metadata);
receiving, using the network device from at least one enterprise image management device of the plurality of enterprise image management devices, candidate prior study data relating to the one or more candidate prior studies (See Baker Par [0047], [0062], & [0165] which discloses information such as previous imaging evaluations (such as prior images in medical image data and reports in patient data) being evaluated and a data cohort, such as of previous studies including study metadata such as described in Baker Par [0046] & [0190] which states that AI detection logic can be trained on prior image metadata; See Baker Par [0068] which discloses a user operating such as in an RIS/PACS instance on a medical imaging data processing platform, i.e. “enterprise image management device” without further specifying what delineates said enterprise image management device from simple RIS/PACS devices, and being able to order or request analysis for one or more studies);
determining that the one or more candidate prior studies are one or more matched prior studies by:
applying a related study order data rule of the one or more relevancy matching rules to the one or more candidate prior studies (See Baker Par [0038] which discloses the image server storing all or part of the extracted information in a study record that may be correlated with appropriate orders and studies and further processing orders or correlating a particular order, i.e. matched current study, with a particular set of study images, i.e. assembled matched study set; See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order), wherein
applying the related study order data rule comprises matching one or more portions of the order data corresponding to the current study with information with one or more portion of an order data corresponding to the one or more candidate prior studies (See Baker Par [0095]-[0096] which discloses validating data entry includes ensuring that the images sent match the exam being ordered, such that discrepancies between imaging and order data (or other medical metadata) may be identified; See Baker Par [0124]-[0125] which discloses the result of the image AI model classification is passed to RIS, and the RIS then uses the information to ensure that the anatomy, view type, study type, and other information from the image AI model matches what the tech is ordering, i.e. a study order data rule is applied by matching order data with the one or more portion of an order data of the prior studies, and if the match is not correct, the technician is informed and/or blocked from validating the study details);
identify a matching clinical software application in the plurality of clinical software applications based on applying the order data rule (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order);
generate an assembled matched study set comprising the matched current study and the one or more matched prior studies (See Baker Par [0038] which discloses processing orders or correlating a particular order, i.e. matched current study, with a particular set of study images, i.e. assembled matched study set; See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order);
retrieve, using the network device, image data corresponding to the assembled matched study set (See Baker Par [0038] which discloses the image server storing all or part of the extracted information in a study record that may be correlated with appropriate orders and studies and further processing orders or correlating a particular order, i.e. matched current study, with a particular set of study images, i.e. assembled matched study set); and
process the assembled matched study set and the image data corresponding to the assembled matched study set using the matching clinical software application to generate a processed study (See Baker Par [0038] which discloses the image server storing all or part of the extracted information in a study record that may be correlated with appropriate orders and studies and further processing orders or correlating a particular order, i.e. matched current study, with a particular set of study images, i.e. assembled matched study set; See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order).
While Baker generally discloses the use of one or more clinical software applications and metadata/labels identifying one or more techniques used to obtain the images, Baker does not explicitly disclose that the identified “techniques” are the “clinical software applications” used to obtain the images, as given by the limitations below:
the training dataset comprising:
labels identifying one or more matched clinical software applications for respective ones of the plurality of training studies,
applying, at the processor, the trained machine learning routing model to at least a portion of the order data, at least a portion of the current study metadata and the current series metadata to generate a matched application output that identifies one or more clinical software applications, of the plurality of clinical software applications, that are matched to the current study.
Therefore, Sorenson discloses the training dataset comprising labels identifying one or more matched software applications for respective ones of the plurality of training studies (See Sorenson Par [0187]-[0189] which discloses that the medical data provided by data sources and processed by machine learning model may include medical image data specifying certain formats and/or software being used for said medical image data, possibly in one or more formats identifying said formats, i.e. labels) and applying, at the processor, the trained machine learning routing model to at least a portion of the order data, at least a portion of the current study metadata and the current series metadata to generate a matched application output that identifies one or more software applications, of the plurality of software applications, that are matched to the current study (See Sorenson Par [0187]-[0189] which discloses that the medical data provided by data sources and processed by machine learning model may include medical image data specifying certain formats and/or software being used for said medical image data, possibly in one or more formats identifying said formats, i.e. labels; See Sorenson Par [0190] which discloses that because various data sources and programs may use different communication standards, formats, or protocols, a machine learning module and other elements can use specific connectors or data source interfaces, i.e. applications, that can route data from the data source to the image processing server based on the received image data).
It would have been obvious to one of ordinary skill in the effective filing date of the claimed invention to modify the disclosure of Baker, which already discloses the use of one or more clinical software applications and metadata/labels identifying one or more techniques used to obtain the images, to further specifically include the identified “techniques” are the “clinical software applications” used to obtain the images, as disclosed by Sorenson, because this allows for automatic identification and compatible integration with data source interfaces to access the data using specific connectors or application communication software (See Sorenson Par [0190]).
Claim 18 –
Regarding Claim 18, Baker and Sorenson disclose the system of Claim 16 in its entirety. Baker further discloses a method, wherein:
the processor is configured to:
determine that the current study is the matched current study based on applying one or more particular matching rules of the one or more relevancy matching rules (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order); and
apply the related study order data rule by:
identifying a particular related study order data rule associated with the one or more particular matching rules (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order); and
applying the related study order data rule by applying the particular related study order data rule (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules” being applied) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order).
Claim 19 –
Regarding Claim 19, Baker and Sorenson disclose the system of Claim 16 in its entirety. Baker further discloses a method, wherein:
the order data is received from an EMR system (See Baker Par [0030]-[0032] & [0044] which discloses accessing an EMR or HIS for obtaining information relating to previous studies, evaluations, reports, etc., and/or being updated for the current imaging procedure).
Claim 20 –
Regarding Claim 20, Baker and Sorenson disclose the system of Claim 16 in its entirety. Baker further discloses a method, wherein:
the order data is received from an RIS system (See Baker Par [0068], [0193], & [0195] which discloses providing RIS functionality for managing the radiology workflows, order creation (understood to include order data), worklist applications for the operations center and radiologists, and case pages for the radiologist).
Claim 21 –
Regarding Claim 21, Baker and Sorenson disclose the system of Claim 16 in its entirety. Baker further discloses a method, wherein:
the order data rule defines a data matching pattern that specifies a set of relevant data from one or more data fields that must be matched in order to satisfy the order data rule (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order).
Claim 22 –
Regarding Claim 22, Baker and Sorenson disclose the system of Claim 16 in its entirety. Baker further discloses a method, wherein:
the processor is further configured to:
receive at least one order message at a parser engine (See Baker Par [0045] which discloses an HL7 order message (ORM) being sent when a healthcare provider requests a service, procedure, or treatment for a patient; While not “parser engine” per se, Baker Par [0046] and Fig. 2 which disclose AI-coordinated model processing of image data and order data, which as disclosed in Baker Par [0045] can include an ORM, by the use of a processing algorithm and other condition detection logic; See Baker Par [0036] & [0062] which discloses the AI model including artificial neural network, convolutional neural network, recurrent neural network, reinforcement learning model, natural language processing model, machine learning algorithm, decision tree, support vector machine, genetic algorithm, etc., which is understood to include parsing embodiments based on the recitation of natural language processing);
parse, using the parser engine, the at least one order message to identify the order data comprising the clinical request data based on at least one clinical request parsing rule (See Baker Par [0045] which discloses an HL7 order message (ORM) being sent when a healthcare provider requests a service, procedure, or treatment for a patient; While not “parser engine” per se, Baker Par [0046] and Fig. 2 which disclose AI-coordinated processing of image data and order data, which as disclosed in Baker Par [0045] can include an ORM, by the use of a processing algorithm and other condition detection logic, and the condition detection logic may select processing algorithms or image recognition models based on the characteristics of the medical imaging procedure indicated by order data or image metadata, which is understood to read on a clinical request parsing rule; See Baker Par [0036] & [0062] which discloses the AI model including artificial neural network, convolutional neural network, recurrent neural network, reinforcement learning model, natural language processing model, machine learning algorithm, decision tree, support vector machine, genetic algorithm, etc., which is understood to include parsing embodiments based on the recitation of natural language processing).
Claim 23 –
Regarding Claim 23, Baker and Sorenson disclose the system of Claim 16 in its entirety. Baker further discloses a method, wherein:
the current study is received using the network device directly from an image acquisition device (See Baker Par [0032] which discloses the series of images produced by the image data source being obtained directly by the imaging device).
Claim 24 –
Regarding Claim 24, Baker and Sorenson disclose the system of Claim 16 in its entirety. Baker further discloses a method, wherein:
each relevancy matching rule specifies one or more corresponding patient model fields (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute patient model and associated model fields) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order) and the processor is further configured to apply each relevancy matching rules by:
determining the presence or absence of relevant data within the one or more corresponding patient model fields of the patient model associated with the current study (See Baker Par [0037] & [0048] which discloses the system indicating the presence or particular identified conditions and the absence of certain identified conditions, e.g. descriptors, markings, annotations, or additional metadata for images of the medical imaging procedure data); and
determining that the current study is matched according to that relevancy matching rule in response to determining the presence of the relevant data within the one or more corresponding patient model fields (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order; See Baker Par [0037] & [0048] which discloses the system indicating the presence or particular identified conditions and the absence of certain identified conditions, e.g. descriptors, markings, annotations, or additional metadata for images of the medical imaging procedure data).
Claim 25 –
Regarding Claim 25, Baker and Sorenson disclose the system of Claim 24 in its entirety. Baker further discloses a method, wherein:
for at least one of the relevancy matching rules the at least one patient model field to be evaluated is selected from the group of:
an order notes field, a diagnosis description field, a diagnosis code field, a procedure code field, and a study indication field (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, i.e. procedure codes, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order; See Baker Par [0037] & [0048] which discloses the system indicating the presence or particular identified conditions and the absence of certain identified conditions, e.g. descriptors, markings, annotations, i.e. order notes, or additional metadata for images of the medical imaging procedure data, and further describes at Baker Par [0018] that the AI models may be trained to classify certain medical conditions, i.e. diagnosis code/description, and/or imaging modality, i.e. study indication; Baker Par [0032] further discloses that for images formatting according to the DICOM standard, data fields such as unique image identifier, unique study identifier, i.e. procedure code, patient’s name, and facility from which the image originates may be included).
Claim 26 –
Regarding Claim 26, Baker and Sorenson disclose the system of Claim 16 in its entirety. Baker further discloses a method, wherein:
the processed study is provided in a DICOM format (See Baker Par [0032], [0073], [0128], & [0177] which discloses reporting for a processed study being provided in DICOM structured reports).
Claim 27 –
Regarding Claim 27, Baker and Sorenson disclose the system of Claim 16 in its entirety. Baker further discloses a method, wherein:
the processed study comprises at least one of processed patient metadata, processed imaging data and processed order data (See Baker Par [0032] which discloses reporting for a processed study being provided such that images formatted according to DICOM standard include unique image identifiers, unique study identifiers, patient’s name (i.e. patient metadata), and the facility from which the image originates and Baker Par [0177] further discloses that reporting results/data can include the image data (i.e. DICOM image data), and non-image data (radiology order data) from a radiological imaging procedure).
Claim 28 –
Regarding Claim 28, Baker and Sorenson disclose the system of Claim 16 in its entirety. Baker further discloses a method, wherein:
the matched clinical application is configured to automatically process the assembled matched study set (See Baker Par [0046], [0060], & [0088] which discloses an a trained image recognition model (e.g., provided by one or more AI models) with use of a processing algorithm and other condition detection logic (understood to constitute “relevancy matching rules”) such that certain processing algorithms and/or image recognition models (understood to constitute “software application”) may be selected, i.e. matched, based on the characteristics of the medical image procedure indicated by the order data or image metadata; See Baker Par [0095]-[0096] & [0124]-[0125] which discloses an AI model ensuring that the anatomy, view type, study type, i.e. procedure codes, and other information (order data rule) for a current order/procedure matches what the tech is ordering, i.e. that the current study is a matching criteria to the order; See Baker Par [0037] & [0048] which discloses the system indicating the presence or particular identified conditions and the absence of certain identified conditions, e.g. descriptors, markings, annotations, i.e. order notes, or additional metadata for images of the medical imaging procedure data, and further describes at Baker Par [0018] that the AI models may be trained to classify certain medical conditions, i.e. diagnosis code/description, imaging modality, i.e. study indication).
Claim 29 –
Regarding Claim 29, Baker and Sorenson disclose the system of Claim 16 in its entirety. Baker further discloses a method, wherein:
the current study data is defined using a DICOM data format (See Baker Par [0032] which discloses reporting for a processed study being provided such that images formatted according to DICOM standard include unique image identifiers, unique study identifiers, patient’s name (i.e. patient metadata)).
Claim 30 –
Regarding Claim 30, Baker and Sorenson disclose the system of Claim 16 in its entirety. Baker further discloses a method, wherein:
the order data is defined using an HL7 format or a FHIR format (See Baker Par [0045] which discloses an HL7 order message (ORM) being sent when a healthcare provider requests a service, procedure, or treatment for a patient).
Claim 31 –
Regarding Claim 31, Baker and Sorenson disclose a non-transitory computer readable medium with instructions stored thereon (See Baker Par [0203]) for processing a plurality of medical images using a clinical software application (See Baker Par [0207] which discloses the use of one or more modules or software applications), that when executed by a processor (See Baker Par [0033], [0035], & [0201] which discloses the use of one or more memories, processors, and/or computers with said components), performs the method of Claim 1 (See analysis of Claim 1 which is met in its entirety by Baker and Sorenson).
Response to Arguments
Applicant's arguments filed 02 February 2026 have been fully considered but they are not persuasive:
Regarding 35 U.S.C. 101 rejections of claims 1-31, Applicant argues on p. 11-23 of Arguments/Remarks that claims 1, 3-16, & 18-31 do not recite an abstract idea because the claimed invention is an improvement in the technological field and an improvement in the functioning of a computer and is not simply an automation that substitutes computer execution for human performance. More specifically, Applicant argues that the claimed invention is not merely the automation of steps that results in reduced time wasted and/or possibility of human error, but rather that it is the combination of the unique recited processing steps that results in the improvement, such as specifically implementing machine learning algorithms and adjusting said machine learning model’s parameters based on varying received training data labels, resulting in a practical application in the form of a technological improvement and/or significantly more, and falling outside the realm of reasonably being performed in the human mind. Examine agrees with Applicant’s arguments. More specifically, Examiner finds Applicant’s arguments regarding the training and subsequent modification of the machine learning parameters for said machine learning image routing model fall outside the realm of being reasonably performed in the human mind persuasive. Additionally, said aspects of the applied machine learning model and subsequent improvements to medical image study routing/software compatibility seem to result in significantly more, at least by subsequent adjustment of said machine learning model parameters in view of the USPTO’s 2025 Subject Matter Eligibility Updates, which expresses the view that subsequent model parameterization and/or optimization of said parameters, especially parameters specific to the machine learning model (in the case of the instant application, these parameters stem from more than just generically received data, but rather are claimed as training datasets comprising “medical study data for a plurality of training studies and labels identifying one or more matched clinical software applications for respective ones of the plurality of training studies, wherein training the machine learning routing model comprises adjusting model parameters based on the labels”) amounts to a particular machine or particularly-curated model. Therefore, these aspects amount to a particular machine and/or model that goes beyond generic, off-the-shelf machine learning models that are typically found in the prior art and merely being applied to the characterized abstract idea. Rather, the aspects read as a specifically built/tailored model for appropriately routing and matching clinical software for clinical images and studies associated therewith. As such, the 35 U.S.C. 101 rejections for claims 1, 3-16, & 18-31 have been withdrawn.
Regarding 35 U.S.C. 102 rejections of claims 1-31, Applicant generally argues on p. 24-27 of Arguments/Remarks that previous rejections for the independent claims in view of Baker do not read on the newly amended portions of independent claims 1, 16, & 31, and therefore previous 35 U.S.C. 102 rejections for claims 1, 16, & 31 should be withdrawn. More specifically applicant argues that Baker’s AI models alone do not include labeled image data identifying matched clinical software applications as required by amended claims 1 & 16. Examiner agrees with Applicant arguments. Therefore, the rejection has been withdrawn. However, upon further consideration, a new grounds of rejection is made in view of newly reasoned portions of Baker and newly cited Sorenson to fully read on the newly amended portions of the independent claims 1, 16, & 31. That is, Baker Par [0194]-[0198] generally discloses the use of machine learning models and applying one or more matching rules based on various medical study data and/or study metadata. Additionally, newly applied Sorenson Par [0187]-[0190] discloses utilizing machine learning to identify matching clinical software applications that were used or are compatible for varying matching medical image studies. Therefore, Baker and Sorenson effectively read on a machine learning model including labeled image data identifying matched clinical software applications as required by amended claims 1 & 16. While Applicant generally argues against Baker “training a routing model with labels identifying matched clinical software applications” at p. 28 of Arguments/Remarks, this is now effectively met by the entire combination of Baker and Sorenson. As such, independent claims 1, 16, & 31 and claims dependent therefrom remain rejected under 35 U.S.C. 103 over Baker in view of Sorenson.
Regarding 35 U.S.C. 102 rejections of claims 1-31, Applicant argues on p. 28-30 of Arguments/Remarks that the previous Office Action’s characterization does not accurately represent Baker’s disclosure, because Baker’s cited paragraphs do not mention “determining at the processor, that the one or more candidate prior studies are one or more matched prior studies by applying a related study order data rule to the one or more candidate prior studies” as found in independent claims 1, 16, & 31, because Baker does not disclose the use of relevancy matching rules or order metadata (see p. 29 of Arguments/Remarks). Examiner respectfully disagrees with Applicant’s arguments. As shown above, Baker Par [0194]-[0198] generally discloses the use of machine learning models and applying one or more matching rules based on various medical study data and/or study metadata. Furthermore, Examiner contends that e Baker Par [0124]-[0125] discloses the RIS using an AI model classification information/result to ensure that the anatomy, view type, study type, and other information from the image AI model matches what the tech is ordering, i.e. Baker effectively discloses a “study order data rule” being applied by matching order data with the one or more portions of an order data of the prior studies, as required by the limitations argued by Applicant. Without further specifying what portions of the current and/or prior studies are matched, or to what extent said portions are matched based on the training datasets produced for the machine learning models, Baker effectively reads on applying a machine learning model to identify matching studies based on metadata associated with those studies. While the claim was further specified to include metadata that went beyond Baker’s identification of certain metadata, i.e. the clinical software application that matches the clinical software label in the order studies, Sorenson is relied upon for specifically utilizing machine learning to identify matching clinical software applications that were used or are compatible for varying matching medical image studies, and thereby resolves this deficiency of Baker. As such, independent claims 1, 16, & 31 and claims dependent therefrom remain rejected under 35 U.S.C. 103 over Baker in view of Sorenson.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Shin et al. (U.S. Patent No. 12,125,277) discloses the use of machine learning models for determining whether an application or container developed is compliant with or compatible with a system, such as for receiving one or more data via said application/containers;
Bai et al. (U.S. Patent Publication No. 2020/0153699) discloses a system for identifying metadata associated with implementing a cloud-native application, such that a manifest may include metadata associated with security and dependencies of an application and/or may include supplemental instructions for deploying or otherwise implementing the application under various operating conditions;
Reicher et al. (U.S. Patent Publication No. 2016/0364857) discloses a system for automatically determining image characteristics as a basis for diagnosis associated with an image study type, such that the server may include a processor configured to receive an image study from the at least one data source over the interface and determine image characteristics for each of a plurality of images in the image study to determine whether each of the plurality of images was used to establish a diagnosis and providing indicators of whether the images were used in said diagnosis.
Applicant's amendment necessitated the new ground 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 HUNTER J RASNIC whose telephone number is (571)270-5801. The examiner can normally be reached M-F 8am-5:30pm.
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, Shahid Merchant can be reached on (571) 270-1360. 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.
/H.R./Examiner, Art Unit 3626
/Shahid Merchant/Supervisory Patent Examiner, Art Unit 3684
Prosecution Insights