DETAILED ACTION
This office action is in response to the communication received on February 4, 2026 concerning application No. 18/665,857 filed on May 16, 2024.
Claims 1-11, 14-18, and 20 are currently pending.
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 .
Response to Arguments
Applicant's arguments filed 02/04/2026 regarding the claim objections have been fully considered. The amendments to the claims have been entered and overcome the claim objections of claims 2 and 6 previously set forth. The amendments have led to further claim objections.
Applicant's arguments filed 02/04/2026 regarding the 35 USC 112 rejection have been fully considered. The amendments to the claims have been entered and overcome the 35 USC 112b rejection of claim 11, previously set forth.
Applicant's arguments filed 02/04/2026 regarding the prior art rejection have been fully considered but they are not persuasive. In response to the applicant’s arguments that the prior art fails to teach “monitoring, during the executing, a confidence score generated by the at least a first one of the multiple analysis functions” and “pausing, in response to the confidence score being below a predetermined threshold, the executing and altering, by the LLM AI, the executable program based on a second user input received in response to the pausing”, examiner respectfully disagrees. Examiner notes that applicant's amendments necessitated the new ground(s) of rejection supplied by Sharma and discussed below. [0083] of Sharma discloses “an LLM or physics-based computer module can analyze the images for image quality (resolution, noise level, etc.). Such analysis can be performed while a patient is still undergoing an imaging exam”. Fig. 2 further discloses the image quality is an image quality score and therefore corresponds to a quantitative confidence score. Therefore, Sharma teaches “monitoring, during the executing, a confidence score generated by the at least a first one of the multiple analysis functions”. As set forth above, the monitoring is performed while the executable program is being executed to assess a granular, quantitative score (image quality score) and analyze the function.
[0083] of Sharma additionally discloses if the image quality is insufficient (below a predetermined threshold) the LLM generates an adjusted imaging protocol (alters the executable program) and performs the adjusted imaging protocol, thereby pausing the executing to generate and perform the adjusted protocol. [0083] further discloses the generating of the adjusted imaging protocol is in response to a user overriding the process and adjusting the protocol parameters. Therefore, Sharma teaches “pausing, in response to the confidence score being below a predetermined threshold, the executing and altering, by the LLM AI, the executable program based on a second user input received in response to the pausing”. As set forth above and in [0083] of Sharma, the current protocol being run is paused, adjusted and performed in its adjusted manner. Examiner notes that as the claims are currently written they do not require the program to be resumed after it has been altered.
In response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., “monitor a ‘confidence score’ from a single ‘analysis function’ for example, the specific confidence that a landmark was correctly identified by a single API call” and “the claims describe an entirely different structure: Run Program -> Pause Mid-Execution -> Alter Program -> Resume Program”) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
In response, to applicant’s arguments regarding claim 12-13 and 19. The claims have been canceled, therefore applicant’s arguments are considered moot. As discussed above, Sharma teaches the newly filed claim limitations included in the amended claims.
Claim Objections
Claims 2 and 6 objected to because of the following informalities:
Claim 2, lines 8, 9, and 15, “the sequence” should read “the sequence of calls”,
Claim 18, lines 1-2 and 2, “the sequence” should read “the sequence of calls”.
Appropriate correction is required.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-9, 11, 15-18, and 20 is/are rejected under 35 U.S.C. 102(a)(2) as being unpatentable by Sharma, Anuj et al. (US 20250271528, hereinafter Sharma).
Regarding claim 1, Sharma teaches a method for decision making in a medical imaging system ([0064] process 200 in fig. 2), the method comprising:
acquiring a first medical image of a patient ([0066] discloses in step 202 accessing patient data which includes acquired image data);
receiving, by a large language model artificial intelligence (LLM AI), user input identifying a goal with respect to the first medical image ([0066] discloses receiving a manually generated prompt by the clinician. [0072] discloses the LLM then receives the input data);
generating, by the LLM AI, an executable program calling multiple analysis functions of the medical imaging system to achieve the goal ([0072] discloses the LLM generates imaging pipeline data including an imaging protocol which is considered an executable program. [0074] discloses the imaging pipeline data includes image analysis);
executing, by an image processor of the medical imaging system, the executable program, at least a first one of the multiple analysis functions called by the executing of the executable program operating on the first medical image ([0073] discloses the imaging pipeline data is further output and performed by an MRI system);
monitoring, during the executing, a confidence score generated by the at least a first one of the multiple analysis functions ([0083] discloses “an LLM or physics-based computer module can analyze the images for image quality (resolution, noise level, etc.). such analysis can be performed while a patient is still undergoing an imaging exam”. Fig. 2 further discloses the image quality is an image quality score and therefore corresponds to a confidence score);
pausing, in response to the confidence score being below a predetermined threshold, the executing and altering, by the LLM AI, the executable program based on a second user input received in response to the pausing ([0083] discloses if the image quality is insufficient (below a predetermined threshold) the LLM generates a new imaging protocol (alters the executable program) and performs the new imaging protocol, thereby pausing the executing to perform the new protocol. [0083] further discloses the generating of the new imaging protocol is in response to a user overriding the process and adjusting the protocol parameters); and
displaying an estimate of the goal, the estimate being derived from results of the executing ([0025] discloses as part of the Magnetic Resonance Imaging, “the digital signals are processed using a computer program to reconstruct images that are post-processed and displayed to the operator”. The processed images are considered the estimate of the goal and the acquiring of the images is considered the results of the executing).
Regarding claim 2, Sharma teaches the method of claim 1, as set forth above. Sharma further teaches acquiring comprises acquiring the first medical image and a second medical image ([0064] discloses analyzing multiple images. [0095] discloses acquiring multiple medical images from different modalities), the first and second medical images being from different medical imaging modalities ([0095] discloses acquiring images from CT scans and MRIs), wherein at least a second one of the multiple analysis functions called by executing the operating on the second medical image ([0051] and [0064] disclose analyzing the images using the processor, therefore at least a second analysis function is executed on the second medical image).
Regarding claim 3, Sharma teaches the method of claim 1, as set forth above. Sharma further teaches receiving comprises receiving the user input as a selection from a user interface, text, or audio ([0065] discloses the user input is in the form of a language prompt or open clinical question which are considered text).
Regarding claim 4, Sharma teaches the method of claim 1, as set forth above. Sharma further teaches receiving comprises receiving a question in a sentence structure ([0065] discloses receiving an open clinical question as a language prompt).
Regarding claim 5, Sharma teaches the method of claim 1, as set forth above. Sharma further teaches generating the executable program comprises generating computer code ([0050] and [0061] disclose the pipeline data includes a series of computer program modules which represent computer code. [0041] further discloses the LLM is a programming assistant which writes sequences).
Regarding claim 6, Sharma teaches the method of claim 1, as set forth above. Sharma further teaches generating comprises generating the executable program calling the multiple analysis functions as application programming interfaces of the medical imaging system ([0050] and [0061] disclose the pipeline data includes a series of computer program modules).
Regarding claim 7, Sharma teaches the method of claim 6, as set forth above. Sharma further teaches the application programming interfaces comprise image processing for loading the first image, detection of a landmark, and measurement with respect to the landmark ([0062] discloses the analysis agent receives the images and further identifies lesion (landmark), provides volumetric analysis (measurement), identifies regions of interest (landmark) and provides image or lesion segmentation within the images).
Regarding claim 8, Sharma teaches the method of claim 1, as set forth above. Sharma further teaches generating the executable program comprises generating the executable program with a selection of the multiple analysis functions as a sub-set from a group of available analysis functions and an order of the multiple analysis functions based on input parameters of the multiple analysis functions ([0050] discloses generating the pipeline data includes selecting a series of computer program modules (sub-set of analysis functions from a group of available analysis functions) as the pipeline data. The series the modules are performed in is considered the order).
Regarding claim 9, Sharma teaches the method of claim 1, as set forth above. Sharma further teaches generating comprises generating by the LLM AI ([0072] discloses the LLM generates imaging pipeline data including an imaging protocol) where the LLM AI was prompt-engineered with a database of workflow examples of uses of the medical imaging system and available analysis functions of the medical imaging system ([0050] discloses the LLM generates the pipeline data based on the clinical question (prompt) in order to select a series of computer program modules (available analysis functions). [0057] further discloses the LLM is fine-tuned using the population data (database of workflow examples) that is received by the LLM).
Regarding claim 11, Sharma teaches the method of claim 1, as set forth above. Sharma further teaches generating comprises generating by the LLM AI ([0072] discloses the LLM generates imaging pipeline data including an imaging protocol) where the LLM AI was calibrated from (1) questions for workflow examples ([0082] discloses training the LLM using a large group of population data which includes particular clinical questions being posed) and (2) positive and/or negative feedback for executable programs generated by the LLM AI for the questions ([0083] discloses adjusting the LLM based on outputs (feedback) generated from the LLM. [0094] further discloses the LLM updates itself).
Regarding claim 15, Sharma teaches the method of claim 1, as set forth above. Sharma further teaches generating comprises generating the executable program as a program not pre-existing in the medical imaging system ([0072] discloses generating a new imaging protocol (program), since the protocol is new it is not pre-existing in the medical imaging system).
Regarding claim 16, Sharma teaches a medical system ([0033] systems 100 and 120 in figs. 1A-B) comprising:
a memory configured to store a large language model artificial intelligence (LLM AI) calibrated for medical imaging ([0033] discloses the system includes a memory for storing large language models. [0037]] discloses the LLM is trained for generating an MRI protocol and is therefore calibrated for medical imaging);
a user input configured to receive a sentence defining a user request with respect to a medical image of a patient ([0058] discloses receiving an input 124 from a user that includes a specific prompt defining a request with respect to a medical image of a patient. Also see [0065]);
a processor (the electronic circuitry of systems 100 and 120 in figs. 1A-B) configured to input the sentence to the LLM AI, to receive a sequence of calls for application programming interfaces from the LLM AI generated in response to the input ([0072] discloses the LLM generates imaging pipeline data in response to the input including an imaging protocol which is considered a sequence of calls), and to implement the sequence using the medical image ([0073] discloses the imaging pipeline data is further output and performed by an MRI system), wherein the processor is further configured to monitor, during the implementation of the sequence, a confidence score from at least one of the application programming interfaces ([0083] discloses “an LLM or physics-based computer module can analyze the images for image quality (resolution, noise level, etc.). such analysis can be performed while a patient is still undergoing an imaging exam”. Fig. 2 further discloses the image quality is an image quality score and therefore corresponds to a confidence score) and in response to the confidence score being below a predetermined threshold, pause the implementation, receive a second user request via the user input, and provide for the LLM AI to alter the sequence of calls based on the second user request ([0083] discloses if the image quality is insufficient (below a predetermined threshold) the LLM generates a new imaging protocol (alters the sequence) and performs the new imaging protocol, thereby pausing the executing to perform the new protocol. [0083] further discloses the generating of the new imaging protocol is in response to a user overriding the process and adjusting the protocol parameters); and
a display configured to display an answer to the user request derived from the implementation of the sequence ([0116] discloses display 404. [0025] discloses as part of the Magnetic Resonance Imaging, “the digital signals are processed using a computer program to reconstruct images that are post-processed and displayed to the operator”. The processed images are considered the answer of the request).
Regarding claim 17, Sharma teaches the method of claim 16, as set forth above. Sharma further teaches the medical image is part of a multi-modal image set ([0064] discloses analyzing multiple images. [0095] discloses acquiring multiple medical images from different modalities), and wherein the generated sequence of calls uses the medical image and another image of the multi-modal image set ([0051] and [0064] disclose analyzing the images using the processor, therefore all of the images obtained from all of the modalities are used in the sequence of calls).
Regarding claim 18, Sharma teaches the method of claim 16, as set forth above. Sharma further teaches the LLM AI generates the sequence where the memory is free of the sequence prior to the generation by the LLM AI ([0072] discloses generating a new imaging protocol (sequence), since the protocol is new it is not within the memory prior to its generation).
Regarding claim 20, Sharma teaches a method for decision making in a medical imaging system ([0064] process 200 in fig. 2), the method comprising:
programming the medical imaging system by a large language model to operate on medical images of different modalities using available functions of the medical imaging system to answer a user request ([0066] discloses receiving a manually generated prompt by the clinician. [0072] discloses the LLM then receives the input data. [0072] further discloses the LLM generates imaging pipeline data including an imaging protocol which is considered programming for the medical imaging system. [0064] discloses analyzing multiple images. [0095] discloses acquiring multiple medical images from different modalities), wherein the programming comprises:
generating and executing a sequence of the available functions ([0072] discloses the LLM generates imaging pipeline data including an imaging protocol which is considered a sequence. [0073] discloses the imaging pipeline data is further output and performed by an MRI system);
monitoring, during the executing of the sequence, a confidence score from at least one of the available functions ([0083] discloses “an LLM or physics-based computer module can analyze the images for image quality (resolution, noise level, etc.). such analysis can be performed while a patient is still undergoing an imaging exam”. Fig. 2 further discloses the image quality is an image quality score and therefore corresponds to a confidence score); and
in response to the confidence score being below a predetermined threshold, pausing the executing and altering the sequence based on a second user request received in response to the pausing ([0083] discloses if the image quality is insufficient (below a predetermined threshold) the LLM generates a new imaging protocol (alters the sequence) and performs the new imaging protocol, thereby pausing the executing to perform the new protocol. [0083] further discloses the generating of the new imaging protocol is in response to a user overriding the process and adjusting the protocol parameters); and
displaying an answer to the user request ([0025] discloses as part of the Magnetic Resonance Imaging, “the digital signals are processed using a computer program to reconstruct images that are post-processed and displayed to the operator”. The processed images are considered the answer).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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.
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sharma in view of Ghose et al. (US 20250095642, hereinafter Ghose).
Regarding claim 10, Sharma teaches the method of claim 9, as set forth above. Sharma further teaches generating comprises generating by the LLM AI ([0072] discloses the LLM generates imaging pipeline data including an imaging protocol) where the LLM AI is prompted engineered with a prompt describing the database, an instruction to generate the executable program, and a limitation ([0050] discloses the LLM generates the pipeline data based on the clinical question (prompt) in order to select a series of computer program modules (available analysis functions). [0041] and [0100] disclose the prompts describes the setting (database) for the prompt, provides an instruction to generate the executable program and provides a limitation).
Sharma does not specifically teach the LLM AI is prompted engineered with ground truth examples.
However,
Ghose in a similar field of endeavor teaches the LLM AI is prompted engineered with ground truth examples ([0036] “the LLM may be trained on data pairs including the realistic natural language prompts, where the associated responses are included as ground truth data).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the prompt disclosed by Sharma to have the LLM AI be prompted engineered with ground truth examples in order to improve the quality of the LLM, as recognized by Ghose ([0102]).
Claim(s) 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sharma in view of Wang et al. (US 20210251608, hereinafter Wang).
Regarding claim 14, Sharma teaches the method of claim 1, as set forth above. Sharma does not specifically teach determining a sensitivity of the estimate, wherein displaying comprises displaying the estimate and the sensitivity.
However,
Wang in a similar field of analyzing and displaying medical images teaches determining a sensitivity of the estimate, wherein displaying comprises displaying the estimate and the sensitivity (Abstract, discloses obtaining a tracking result (estimate) and determining a tracking quality (sensitivity) of the tracking result and display the tracking quality. [0073] and fig. 4 disclose displaying the tracking result and the tracking quality together).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method disclosed by Sharma to have determined a sensitivity of the estimate, wherein displaying comprises displaying the estimate and the sensitivity in order to indicate to a user a credibility of the estimate, as recognized by Wang (abstract).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANDREW BEGEMAN whose telephone number is (571)272-4744. The examiner can normally be reached Monday-Thursday 8:30-5:00.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Keith Raymond can be reached at 5712701790. 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.
/ANDREW W BEGEMAN/Examiner, Art Unit 3798
Prosecution Insights