DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application is being examined under the pre-AIA first to invent provisions.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on December 3, 2025, has been entered.
Response to Amendment
Claims 1, 7, 12, 14, 18, and 20 have been amended. Claims 1-20 are pending and are provided to be examined upon their merits.
Response to Arguments
Applicant’s arguments with respect to claims 1-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. A response is provided below in bold where appropriate.
Applicant argues 35 USC §101 Rejection, starting pg. 8 of Remarks:
Response to Comments in Advisory Action with Respect to Claim Rejection under 35 U.S.C. § 101
With respect to the arguments presented in the Amendment of November 5, 2025, the Advisory Action first alleges that "the claimed step of a warning signal does not even require a computer to perform the step." The Advisory Action further alleges that "a person with pen can line through or mark with an "X" a diagnostic report to prevent anyone completing or signing the report." Applicants respectfully disagree.
Claim 1 is directed to a computer-implemented method. Thus, the method steps are computer implemented and require a computer to perform the steps. Further, marking through or adding an "X" to a report is not a warning signal that is output by a computer-implemented method. Additionally, a manual process of marking through or adding an "X" to a report does not block completion or signing of a report. In contrast, marking through or adding an "X" to a report is a manual process that may add a marking to a report. A report may still be signed if a mark or "X" has been added to a report. As recited in claim 1, the warning signal blocks completion or signing of a report which is not a mental process.
With all due respect, a computer implemented method in the preamble is not the same as a computer performing a step.
Even if it’s not an “X” a person can with pen can mark out a space for a signature so there appears to be no place to sign. Even if the step included a computer, automating an abstract manual process using a computer is not enough to make abstract claims statutory.
From MPEP 2106.05(a) I…
“Examples that the courts have indicated may not be sufficient to show an improvement in computer-functionality:…
… iii. Mere automation of manual processes, such as using a generic computer to process an application for financing a purchase, Credit Acceptance Corp. v. Westlake Services, 859 F.3d 1044, 1055, 123 USPQ2d 1100, 1108-09 (Fed. Cir.2017) or speeding up a loan-application process by enabling borrowers to avoid physically going to or calling each lender and filling out a loan application, LendingTree, LLC v. Zillow, Inc., 656 Fed. App'x 991, 996-97 (Fed. Cir. 2016) (non-precedential);
iv. Recording,
A person can look at an image and compare that image to an image in a medical report and with pen block by out completion or signature areas.
With respect to the arguments presented in the Amendment of November 5, 2025, related to the allegation that the claims recite certain methods of organizing human activity, the Advisory Action states that "the claims recite not to complete or sign the diagnostic report, which is teaching." The Advisory Action then alleges that "[t]his is managing personal behavior."
Teaching is not an activity that falls within the enumerated sub-groupings of fundamental economic principles or practices, commercial or legal interactions, and managing personal behavior and relationships or interactions between people. The MPEP notes that the abstract idea subgrouping of certain methods of organizing human activity "is not to be expanded beyond these enumerated sub-groupings except in rare circumstances." MPEP 2106.04(a)(2)(II). Further, even if "teaching" were considered to fall within one of the enumerated subgroupings, outputting a warning signal as recited in amended claim 1 is not "teaching." In contrast, this is an action performed by a computer in response to determining that the first position does not match the at least one second position. Accordingly, claim 1 is not directed to a method of organizing human activity.
Teaching is managing personal behavior and interactions between people.
From MPEP 2106.04(a)…
2) Certain methods of organizing human activity – fundamental economic principles or practices (including hedging, insurance, mitigating risk); commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations); managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions) (see
MPEP §2106.04(a)(2) (s2106.html#ch2100_d29a1b_13ae3_321)
, subsection II);
For at least the reasons above, as well as those set forth in Applicants' prior response, claim 1 is patent eligible. Claims 12 and 20 are amended similarly to claim 1. For at least the reasons above with respect to claim 1, claims 12 and 20 are patent eligible. Claims 2-11 and 13-19 are patent eligible at least by virtue of their dependencies.
Accordingly, Applicants request the Examiner to reconsider and withdraw this rejection.
The rejection is respectfully maintained but modified for the claim amendments based on the above response.
Applicant argues 35 USC §112(b) Rejection, pg. 9 of Remarks:
Claim Rejection under 35 U.S.C. § 112(b) and 35 U.S.C. § 103
Applicants thank the Examiner for acknowledging that the claim amendments presented in the Amendment of November 5, 2025 overcome the rejections under 35 U.S.C. @ 112(b). Applicants further acknowledge the
The 35 USC 112(b) rejections are withdrawn based on the claim amendments.
Applicant argues 35 USC §103 Rejection, starting pg. 10 of Remarks (filed 11/05/2025 in After Final):
Examiner's comment that the amended claims would require further search and consideration with respect to the rejection under 35 U.S.C. @ 103.
Claim Rejection under 35 U.S.C. 9 103
Claims 1-9, 12-17, and 20 stand rejected under 35 U.S.C. § 103 as allegedly being unpatentable over U.S. 2016/0162745 ("Cohen-Solal"), in view of U.S. 2020/0176112 ("Sati") and U.S. 2021/0313051 ("Asselmann"). Claims 10 and 11 stand rejected under 35 U.S.C. § 103 as allegedly being unpatentable over Cohen-Solal, Sati, and Asselmann, further in view of U.S. 2018/0101645 ("Sorenson") and U.S. Atty. Dkt. No. 32860HC-003862-US U.S. Application No. 18/466,356 2022/0084645 ("Ginsburg"). Claim 18 stands rejected under 35 U.S.C. @ 103 as allegedly being unpatentable over Cohen-Solal, Sati, and Asselmann, further in view of U.S. 2024/0177836 ("Paik"). Claim 19 stands rejected under 35 U.S.C. @ 103 as allegedly being unpatentable over Cohen-Solal, Sati, and Asselmann, further in view of U.S. 2021/0313045 ("Wu"). Applicants traverse these rejections for at least the reasons below.
Claim 1 is amended to recite, in part, "the warning signal including blocking at least one of completing or signing the medical diagnostic report." The Office Action notes on page 18 that no patentable weight is given to the alternative claim language where only one is selected. The Office Action then cites to Asselmann to describe a text output. Office Action, pages 19-20. The Office Action thus does not provide a citation to the warning signal including "blocking at least one of completing or signing the medical diagnostic report," as recited in amended claim 1. Further, none of Cohen-Solal, Salti, or Asselman describes the warning signal including "blocking at least one of completing or signing the medical diagnostic report," as recited in amended claim 1.
Claim 1 has been amended requiring new prior art.
For at least the reasons above, a prima facie case of obviousness cannot be established with regard to claim 1. Consequently, a prima facie case of obviousness cannot be established with regard to claims 2-11, 14, and 16-19, at least by virtue of their dependency from claim 1. Claims 12 and 20 are amended similarly to claim 1. For at least the reasons above with respect to claim 1, a prima facie case of obviousness cannot be established with regard to claim 12 or claim 20. Consequently, a prima facie case of obviousness cannot be established with regard to claims 13 and 15, at least by virtue of their dependency from claim 12.
Accordingly, Applicants request the Examiner to reconsider and withdraw the above rejection.
Based on the claim amendments, new prior art is cited.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1-20 are directed to a method, system or product, which are statutory categories of invention. (Step 1: YES).
The Examiner has identified method Claim 1 as the claim that represents the claimed invention for analysis and is similar to system claims 12 and 20 and product claims 16 and 17.
Claim 1 recites the limitations of:
A computer-implemented method for safety checking a medical diagnostic report for a patient based on an image file acquired using a medical imaging device, the computer- implemented method comprising:
reading in sensor data relating to the image file;
assigning the sensor data to a first position of an anatomical structure of the patient;
extracting at least one second position of the anatomical structure from the medical diagnostic report;
comparing the first position and the at least one second position; and
outputting a warning signal in response to determining that the first position does not match the at least one second position, the warning signal including blocking at least one of completing or signing the medical diagnostic report.
These above limitations, under their broadest reasonable interpretation, cover performance of the limitation as mental processes. The claim recites elements, in non-bold above, which covers performance of the limitation that can be concepts performed in the mind of a person or with pen and paper. A person can read in their mind sensor data related to an image file, assign with pen sensor data to a first position of an anatomical structure of a patient, extract by reading in their mind second position data from a medical diagnostic report, compare (analyze in their mind) the first and second positions, and output a warning with pen and paper if the positions do not match. A person can prevent by covering over with pen signature places to prevent completing or signing. Further using generic computers to perform a judicial exception has been shown to be abstract (see MPEP 2106.04(a)(2) III C). If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation as a mental process, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. Claims 12, 16, 17, and 20 are also abstract for similar reasons. (Step 2A-Prong 1: YES. The claims are abstract)
In as much as the claims are reading sensor data for a patient’s image file, assigning sensor data to a first position of an anatomical structure of the patient, extracting second position from a medical diagnostic report, comparing the first and second positions, and outputting a warning signal, giving the claims their broadest reasonable interpretation, the claims are managing personal behavior by teaching (warning signal) medical professionals when positions from their reading sensor data of first position (patient images) does not match second position medical diagnostic report (patient’s records). Warning someone of a problem by blocking completing or signing off on a report (blocking signing) is teaching, therefore managing personal behavior. Managing personal behavior falls under the abstract concept of certain methods of organizing human activity.
This judicial exception is not integrated into a practical application. In particular, the claims only recite: medical imaging device (Claim 1); medical imaging device (Claim 12); computer (Claim 16); computer (Claim 17); medical imaging device, memory, processor (Claim 20). The computer hardware is recited at a high-level of generality (i.e., as a generic processor performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer component. See Applicant’s specification para. [00184] about implantation using general purpose computing devices and MPEP 2106.05(f) where applying a computer as a tool is not indicative of significantly more. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Therefore claims 1, 12, 16, 17, and 20 are directed to an abstract idea without a practical application. (Step 2A-Prong 2: NO. The additional claimed elements are not integrated into a practical application)
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because, when considered separately and as an ordered combination, they do not add significantly more (also known as an “inventive concept”) to the exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a computer hardware amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Steps such as reading (receiving) and outputting (transmitting) are steps that are considered insignificant extra solution activity and mere instructions to apply the exception using general computer components (see MPEP 2106.05(d), II). Thus claims 1, 12, 16, 17, and 20 are not patent eligible. (Step 2B: NO. The claims do not provide significantly more)
Dependent claims 2-11, 13-15, 18, and 19 further define the abstract idea that is present in their respective independent claims 1, 12, 16, 17, and 20 and thus correspond to Mental Processes and hence are abstract for the reasons presented above. The dependent claims do not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception when considered both individually and as an ordered combination. Claim 2 recites an input device on a display, claim 8 recites medical imaging device and X-ray machine, magnetic resonance tomograph, positron emission tomograph, angiography system, and ultrasound scanner, claim 14 recites a medical imaging device, and claim 15 recites a signal output device. These devices are generic devices being applied at a high level of generality. Therefore, the claims 2-11, 13-15, 18, and 19 are directed to an abstract idea. Thus, the claims 1-20 are not patent-eligible.
Examiner Request
The Applicant is requested to indicate where in the specification there is support for amendments to claims should Applicant amend. The purpose of this is to reduce potential 35 U.S.C. §112(a) or §112 1st paragraph issues that can arise when claims are amended without support in the specification. The Examiner thanks the Applicant in advance.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-9, 12-17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Pub. No. US 2016/0162745 to Cohen-Solal et al. in view of Pub. No. US 2020/0176112 to Sati et al. and in view of Pub. No. US 2014/0358585 to Reiner teaches:
Regarding claims 1, 16, and 17
(claim 1) A computer-implemented method for safety checking a medical diagnostic report for a patient based on an image file acquired using a medical imaging device, the computer- implemented method comprising:
reading in sensor data relating to the image file;
Cohen-Solal et al. teaches:
Sensor senses (reading) focus of attention (sensor data) to image…
“In another aspect, a system includes a sensor that senses a focus of attention of an observer of an anatomical image, of a set of images, displayed on a monitor, a mapper that maps the focus of attention to the image based on a display geometry of the monitor, a metric determiner that determine a metric based on the map, logic that compares the metric with a predetermined metric and determines a location of the anatomical image includes tissue with a finding of interest in response to the metric satisfying the predetermined metric, an image selector that identifies an anatomical image, from an earlier acquired imaging data set, with a same tissue as the displayed image, and a display monitor that displays graphical indicia that identifies the earlier acquired image.” [0008]
Another example of scanned (read) anatomy (image)…
“Where the signal identifies a follow-up imaging data set, a previous data identifier 114 is used to identify a previously generated and stored imaging data set corresponding to the follow-up imaging data set. The previously generated and stored imaging data set is identified as related to a follow-up imaging data set for example based on imaging protocol, scanned anatomy of interest, imaging modality, and/or other data, and/or by the most recent (chronologically) scan of the patient.” [0022]
Fig. 1, ref. 124 and 126 where 128 reads in sensor data relating to output devices…
PNG
media_image1.png
220
476
media_image1.png
Greyscale
assigning the sensor data to a first position of an anatomical structure of the patient;
Mapper that maps (assigning) focus of attention (sensor data) to display geometry (first position)…
“In another aspect, a system includes a sensor that senses a focus of attention of an observer of an anatomical image, of a set of images, displayed on a monitor, a mapper that maps the focus of attention to the image based on a display geometry of the monitor, a metric determiner that determine a metric based on the map, logic that compares the metric with a predetermined metric and determines a location of the anatomical image includes tissue with a finding of interest in response to the metric satisfying the predetermined metric, an image selector that identifies an anatomical image, from an earlier acquired imaging data set, with a same tissue as the displayed image, and a display monitor that displays graphical indicia that identifies the earlier acquired image.” [0008]
Where scanning is for a patient…
“Patient follow-up may include consecutive studies performed with the same imaging protocols (i.e. same modality, same scanned body part and scanner parameters). These studies can contain hundreds of slices to be looked at. The original study will often contain key images that have been marked as the radiologist reviews the case. In a follow-up study, the radiologist will report on the previously marked findings (annotated within key images).” [0003]
“The eye tracker 124 further includes a mapper 128 that processes the signal from the sensor 126 and maps the gaze and/or motion of the eye(s) to a coordinate system (the x,y coordinates) of the monitor of the output device(s) 110. The mapper 128 generates a signal indicative of the mapping. The mapping, in one instance, provides a time based mapping of the line of sight with respect to the plane of the monitor for each observed image.” [0032]
Another example of metric that indicates (assigns) each location (first position) within each image based on output of mapper…
“A metric determiner 130 receives the output of the mapper 128 and/or the output of the image selector 118 and generates one or more metrics based thereon. For example, in one instance, the metric determiner 130 processes the output of the mapper 128 and generates a metric that indicates a total amount of time the observer spent observing each location within each image for each observed image. In another instance, the metric determiner 130 processes the output of the image selector 118 and generates a metric that indicates a sequential order in which the images are observed.” [0033]
extracting at least one second position of the anatomical structure from the medical diagnostic report;
Previously stored imaging data (medical diagnostic report)…
“Where the signal identifies a follow-up imaging data set, a previous data identifier 114 is used to identify a previously generated and stored imaging data set corresponding to the follow-up imaging data set. The previously generated and stored imaging data set is identified as related to a follow-up imaging data set for example based on imaging protocol, scanned anatomy of interest, imaging modality, and/or other data, and/or by the most recent (chronologically) scan of the patient.” [0022]
Employ segmentation (extracting) object based on location (second position) of prior findings on the object (image)…
“In another variation, the logic 132 may employ segmentation using the eye tracking location as a seed to initiate the segmentation of a finding (e.g., mass, tumor, cyst, etc.). This may provide a more accurate location of a prior finding for matching, not based on the annotation provided by the user but based on the object itself. In addition, this provides an ability to compute a shape, a margin and/or any other feature(s) to further compute the matching score and avoid mismatch (i.e. appearance-based matching).” [0038]
See Extracting below.
comparing the first position and the at least one second position; and
“An eye tracker 124 detects or tracks a focus of attention of an observer of an anatomical image of a set of images. Generally, the eye tracker 124 can employ any approach that can identify focus-of-attention regions. Examples of suitable approaches are discussed in “Eye Tracking: A comprehensive guide to methods and measures,” by Kenneth Holmqvist, Marcus Nyström, Richard Andersson, Richard Dewhurst, Halszka Jarodzka, Joost van de Weijer, Oxford University Press, 2011. These approaches include line of sight, eye movement, pattern of eye movement, dwelling, etc. Other approaches are also contemplated herein.” [0029]
Same anatomical regions (first and second positions)….
“In a variation, the logic 132 may register (e.g., model-based or segmentation-based) images in order to have the same anatomical regions geometrically corresponding between them (e.g., organ level, slice number, location within a slice). This may improve the precision of the matching. Rigid and/or elastic registration algorithms can be used. Where the imaging data sets correspond to different modalities (e.g., CT and MR), a registration or fusion of the two types of images can be performed.” [0037]
Confirms (comparing) a correct match…
“In the case where the observer confirms a correct match, the observer can seamlessly edit the image annotation and associated text description starting with the prior finding description. The text from the prior study can be propagated and displayed in a small window on the side of the current finding. When done and submitted, finding details will be added to the final report. Image annotation from the prior finding can also be positioned at the gaze location in the current image for final edition.” [0043]
“Optionally, the system 100 can be used to identify overlooked findings in a prior study: For example, if the observer visually detects a new finding in the current study which was not seen and reported before (no suggested match by the invention), the logic 132 invokes the image selector 118 to display the corresponding region from the most recent prior study (slice number and series) where the overlooked finding might be located.” [0048]
outputting a warning signal in response to determining that the first position does not match the at least one second position, the warning signal including blocking at least one of completing or signing the medical diagnostic report.
[No Patentable Weight is given to alternative claim language where only one selection is required.]
When no match, invokes image selector (output a warning) to display region that was overlooked…
“Optionally, the system 100 can be used to identify overlooked findings in a prior study: For example, if the observer visually detects a new finding in the current study which was not seen and reported before (no suggested match by the invention), the logic 132 invokes the image selector 118 to display the corresponding region from the most recent prior study (slice number and series) where the overlooked finding might be located.” [0048]
Notify (output warning signal) of overlooked areas (does not match) that correspond to findings in prior study…
“For ignored findings in the current study. If the radiologist visually fails to examine areas in the current study that correspond to findings in prior study, the system can notify and visualize those ignored prior findings in their corresponding areas of the current study. This can be done dynamically as the radiologist already past the findings scrolling down the stack of images or later when the reading phase is completed to notify the radiologist of one or more overlooked regions.” [0050]
Restrict (blocking) acquisition (completing) of imaging extent…
“The foregoing may also be used to restrict acquisition of a subsequent scan, which may reduce the x-ray dose the patient receives, relative to not restricting the subsequent scan. For this, the logic 132 determines the corresponding regions between the prior findings location, associated organs and sub-regions and suggests an imaging extent to restrict the acquisition to only the regions useful for comparison.” [0051]
See Signature below.
Extracting
Cohen-Solal et al. teaches matching anatomical location. They also teach segmentation. They do not literally use the term extracting.
Sati et al. also in the business of matching anatomical locations teaches:
Automatically associate medical report findings with medical image based on location…
“According to at least one embodiment, a cognitive imaging program may implement natural language processing (NLP) to read a medical report and automatically detect findings (e.g., lesions, tumors, diseases) and the anatomical location of the findings reported by a doctor. The cognitive imaging program may also implement an image detection component (e.g., image detection algorithm) to automatically detect potential findings within the medical image and to automatically detect the anatomy within the medical image. Then, the cognitive imaging program may implement an algorithm which may automatically associate the findings from the medical report with the potential findings from the medical image based on a description of the location of the finding in the report and the anatomical location of the potential finding in the medical image. Thereafter, the cognitive imaging program may record the association of the findings from the medical report and the potential findings from the medical image as strongly labeled information. The cognitive imaging program may then feed the strongly labeled information into a machine learning algorithm to help train the machine learning algorithm to automatically detect the target structure.” [0026]
Example of extraction using existing NLP methods with geometric description of anatomical location…
“In response to receiving the medical report from the unlabeled dataset, the cognitive imaging program 110a, 110b may implement a natural language processing (NLP) component or algorithm to determine one or more report data. Specifically, the NLP algorithm may breakdown and analyze the text of the medical report using existing NLP methods (e.g., sentence segmentation, tokenization, parts-of-speech tagging, parsing, fact extraction). Then, the NLP algorithm may process the textual data in the medical report and may automatically detect the findings (e.g., lesions, nodules, diseases, tumors, fractures) and the geometric description of the anatomical location (e.g., left lung, superior lobe) of the findings observed by the doctor. The report data may include the findings and the anatomical location of the findings detected using the NLP algorithm of the cognitive imaging program 110a, 110b.” [0036]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of Cohen-Solal et al. the ability to do extract location data from a medical diagnostic report as taught by Sati et al. since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Sati et al. who teaches using natural language processing for breaking down and analyzing text is using existing NLP methods and Cohen-Solal et al. benefits by the advantage of using existing NLP techniques for further analyzing the text of their records.
Signature
The combined references teach medical report. They also teach no matching with warning. They do not teach signature.
Reiner also in the business of medical reports teaches:
Before allowed to sign off (therefore block) on report, cross reference (matching) of imaging and clinical data where report is analyzed and flagged for findings…
“16. Once the report has been constructed and reviewed by the radiologist, it is ready to be signed and distributed to the referring clinician. 17. Before the radiologist is allowed to "sign off" on the report, computer analysis is performed by the program 110 on the report content, along with cross-reference of the pre-report supporting historical imaging and clinical data of the patient. 18. In the process of performing this computer-based analysis, findings deemed to be of high clinical significance and constituting "critical results" (based upon predefined criteria) are flagged by the program 110 and presented to the radiologist for formal review prior to be allowing to `sign off" on the report.” [0301] – [0303]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to block signatures as taught by Reiner since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Reiner who teaches the advantages of reviewing reports prior to signature. The combined references benefit as they also are concerned about accurate reports.
Regarding claim 2
The method as claimed in claim 1, wherein the sensor data includes at least one of:
a duration of display, on a screen, of an image slice within an image stack of medical images of the image file;
Cohen-Solal et al. teaches:
Amount of time (duration) observing at a location…
“At 208, for each location of each image, the amount of time spent observing each location is compared against a predetermined threshold time interval.” [0058]
Image slices…
“The following describes an approach to match findings between a current image data set and a prior study and, optionally, provide a notification when a match is found. The user can then decide to follow-up on the suggestion and display the matching image slice and location of the relevant finding in the prior study. In one instance, this avoids having to have the clinician go through all the prior image slices for a given series in search of a corresponding finding, resulting in a much quicker visual comparison, faster finding annotation and report editing. This approach can also identify when a new finding in a current image data set has not been annotated in the previous image data set, when a finding in the previous image data set may have been missed in the current image data set, and/or reduce the scan extent (and hence dose) in a follow-up imaging procedure.” [0006]
movement data from an input device on a display of an image or image slice of the image file;
A mouse to hover over an icon…
“By way of non-limiting example, the logic 132 can display an icon at the level of the observer's gaze and at the side of the screen to visually notify the observer. Alternatively, an arrow can appear on the image at the level of the match and gaze location along with an audio signal. If the observer decides to consider the match, the observer can hover a mouse over and/or click on the icon and the corresponding finding in a prior study appears on the other monitor to evaluate and confirm the match.” [0042] Inherent with mouse is the ability to move.
movement data from gaze detection on the display of the image or the image slice of the image file;
Cohen-Solal et al. teaches:
Eye tracker and gaze of point and/or motion…
“By way of non-limiting example, in one non-limiting approach, the eye tracker 124 measures a point of gaze and/or motion of an eye(s) of an observer observing a follow up image displayed via the output device(s) 110 relative a geometry of a display area of the output device(s) 110 and generates a signal indicative thereof. The illustrated eye tracker 124 includes a sensor 126 such as a video camera or the like. Other sensors are also contemplated herein. The sensor 126 is for example mounted on a device such as a table, a stand, the computing system 100, etc., a head set worn by the observer, and/or otherwise.” [0030]
mark-ups of a region of interest on the display of the image or the image slice of the image file;
Marked images…
“Patient follow-up may include consecutive studies performed with the same imaging protocols (i.e. same modality, same scanned body part and scanner parameters). These studies can contain hundreds of slices to be looked at. The original study will often contain key images that have been marked as the radiologist reviews the case. In a follow-up study, the radiologist will report on the previously marked findings (annotated within key images).” [0003]
measurements of at least one of a distance, a diameter or a density on the display of the image or the image slice of the image file;
Distance…
“In response to a metric satisfying a threshold in connection with observing an image of a follow-up imaging data set, the logic 132 invokes the image selector 118 to concurrently display the corresponding image from the previously generated and stored imaging data set. In one instance, the particular image can be identified by computing a distance to a prior finding localized by an annotation, where a shortest distance below a given threshold is identified as the corresponding image.” [0036]
annotations about the display of the image or image slice of the image file; or
Annotations…
“An annotator 120, receives as an input, via the input device(s) 108, a signal identifying an annotation to superimpose or overlay over a displayed image. The annotation is conveyed to the rendering engine 116 to visually present via the monitor of the output device(s) 110. The annotator 120 also allows for propagating an annotation of one image to another image.” [0027]
operating data with regard to display of at least one image of the image file.
Regarding claim 3
The method as claimed in claim 1, wherein the assigning the sensor data to the first position of the anatomical structure comprises:
identifying anatomical landmarks or segmenting at least one organ of the patient.
Cohen-Solal et al. teaches:
Example of determining (identifying) tissue (anatomical landmark)…
“In one aspect, a method includes detecting a focus of attention of an observer of an anatomical image of a set of images, determining a location of the anatomical image includes tissue with a finding of interest based on the detected focus of attention, identifying an anatomical image, from an earlier acquired imaging data set, with a same portion of tissue as the displayed image, visually displaying graphical indicia, concurrently with the displayed image, that identifies the earlier acquired image.” [0007]
“In a variation, the logic 132 may register (e.g., model-based or segmentation-based) images in order to have the same anatomical regions geometrically corresponding between them (e.g., organ level, slice number, location within a slice). This may improve the precision of the matching. Rigid and/or elastic registration algorithms can be used. Where the imaging data sets correspond to different modalities (e.g., CT and MR), a registration or fusion of the two types of images can be performed.” [0037]
Regarding claim 4
The method as claimed in claim 1, wherein the assigning the sensor data to the first position of the anatomical structure comprises:
outputting a result of the assigning in a first coding scheme.
Cohen-Solal et al. teaches:
Example of displaying (outputting) graphical indicia (coding scheme)…
“In one aspect, a method includes detecting a focus of attention of an observer of an anatomical image of a set of images, determining a location of the anatomical image includes tissue with a finding of interest based on the detected focus of attention, identifying an anatomical image, from an earlier acquired imaging data set, with a same portion of tissue as the displayed image, visually displaying graphical indicia, concurrently with the displayed image, that identifies the earlier acquired image.” [0007]
Regarding claim 5
The method as claimed in claim 4, wherein the extracting the at least one second position of the anatomical structure from the medical diagnostic report comprises: outputting the at least one second position in a second coding scheme.
Cohen-Solal et al. teaches:
Previous data identifier with anatomy of interest (therefore, second position coding scheme)…
“Where the signal identifies a follow-up imaging data set, a previous data identifier 114 is used to identify a previously generated and stored imaging data set corresponding to the follow-up imaging data set. The previously generated and stored imaging data set is identified as related to a follow-up imaging data set for example based on imaging protocol, scanned anatomy of interest, imaging modality, and/or other data, and/or by the most recent (chronologically) scan of the patient.” [0022]
Regarding claim 6
The method as claimed in claim 5, wherein the comparing the first position and the at least one second position comprises:
comparing the first coding scheme and the second coding scheme.
Cohen-Solal et al. teaches:
Previous data identifier with anatomy of interest (therefore, second position coding scheme)…
“Where the signal identifies a follow-up imaging data set, a previous data identifier 114 is used to identify a previously generated and stored imaging data set corresponding to the follow-up imaging data set. The previously generated and stored imaging data set is identified as related to a follow-up imaging data set for example based on imaging protocol, scanned anatomy of interest, imaging modality, and/or other data, and/or by the most recent (chronologically) scan of the patient.” [0022]
Example of employing the previous data identifier and follow up imaging data set (therefore, using the identifier for imaging)…
“The previous data identifier 114 can instead be employed during observation of images of the follow up imaging data set. In this instance, a previously generated image from a previously generated image data set is identified by computing a normalized weighted score between the currently observed image and images of the data sets. For example, if an image is generated with data from a same modality, a binary count of 1 is added to the score. The same counting is done for anatomy, series, image slice number, etc.” [0023]
The combined references teach previous data identifier with imaging. They do not explicitly teach first and second coding scheme. However one of ordinary skill in the art would recognize that using the identifier used for previous data and [current] image data to identify imaging data, is using the identifier as a first and second coding scheme.
It would have been obvious to one of ordinary skill in the art before the effective filing date of Applicant’s filing to modify the combined references with the knowledge available to such an artisan that coding scheme of some type is required to match image data with data in a medical record. This would have been known work in the field of endeavor prompting variations of it in the same field based on use of matching location data and would provide predictable results.
Regarding claim 7
The method as claimed in claim 1, wherein the outputting of the warning signal further includes at least one of outputting, on a display of an image or a slice of a 3D image file, the first position assigned to the sensor data for which the comparing did not identify a corresponding second position extracted from the medical diagnostic report, or text outputting a missing match with regard to the first position assigned to the sensor data.
[No Patentable Weight is given to non-functional descriptive claim language of “display of an image or a slice of a 3D image file, the first position assigned to the sensor data for which the comparing did not identify a corresponding second position extracted from the medical diagnostic report, or text outputting a missing match with regard to the first position assigned to the sensor” as there is no functional interaction with the display. Also, No Patentable Weight is given to alternative claim language of “…or text outputting a missing match…”]
Cohen-Solal et al. teaches:
Display (outputting) using current study region (fist position) corresponding region where overlooked finding might be located…
“Optionally, the system 100 can be used to identify overlooked findings in a prior study: For example, if the observer visually detects a new finding in the current study which was not seen and reported before (no suggested match by the invention), the logic 132 invokes the image selector 118 to display the corresponding region from the most recent prior study (slice number and series) where the overlooked finding might be located.” [0048]
Regarding claim 8
The method as claimed in claim 1, wherein the medical imaging device is one of:
an X-ray machine,
Cohen-Solal et al. teaches:
“The imaging system(s) 102 includes for example one or more of a computed tomography (CT), a magnetic resonance imaging (MM), a positron emission tomography (PET), single photon emission computed tomography (SPECT), X-ray, and/or other imaging system. The data repository 104 includes for example one or more of a picture archiving and communication system (PACS), a radiology information system (RIS), a hospital information system (HIS), and/or other data repository.” [0017]
a magnetic resonance tomograph,
“The imaging system(s) 102 includes for example one or more of a computed tomography (CT), a magnetic resonance imaging (MM), a positron emission tomography (PET), single photon emission computed tomography (SPECT), X-ray, and/or other imaging system. The data repository 104 includes for example one or more of a picture archiving and communication system (PACS), a radiology information system (RIS), a hospital information system (HIS), and/or other data repository.” [0017]
a positron emission tomograph,
“The imaging system(s) 102 includes for example one or more of a computed tomography (CT), a magnetic resonance imaging (MM), a positron emission tomography (PET), single photon emission computed tomography (SPECT), X-ray, and/or other imaging system. The data repository 104 includes for example one or more of a picture archiving and communication system (PACS), a radiology information system (RIS), a hospital information system (HIS), and/or other data repository.” [0017]
an angiography system,
a computed tomograph, or
“The imaging system(s) 102 includes for example one or more of a computed tomography (CT), a magnetic resonance imaging (MM), a positron emission tomography (PET), single photon emission computed tomography (SPECT), X-ray, and/or other imaging system. The data repository 104 includes for example one or more of a picture archiving and communication system (PACS), a radiology information system (RIS), a hospital information system (HIS), and/or other data repository.” [0017]
an ultrasound scanner.
Regarding claim 9
The method as claimed in claim 1, further comprising:
reading in further patient data, wherein the further patient data has been collected independently of the image file;
Cohen-Solal et al. teaches:
Example of imaging data set with other data…
“Where the signal identifies a follow-up imaging data set, a previous data identifier 114 is used to identify a previously generated and stored imaging data set corresponding to the follow-up imaging data set. The previously generated and stored imaging data set is identified as related to a follow-up imaging data set for example based on imaging protocol, scanned anatomy of interest, imaging modality, and/or other data, and/or by the most recent (chronologically) scan of the patient.” [0022]
extracting at least one third position of the anatomical structure from the further patient data;
Location with a finding of interest (third position)…
“In one instance, satisfying the threshold indicates that the location of the displayed image being observed includes a feature of interest to the observer. That is, if the observer spends at least the threshold amount of time observing a particular location in an image and/or scrolls back and forth several times through a sub-set of images, the logic 132 determines that the location in the image or a 3D location in the series of images includes a finding of interest to the observer.” [0035]
comparing the at least one third position extracted from the further patient data with at least one of the first position or the at least one second position; and
Threshold (comparing) location of displayed image (first position) with feature of interest (third position)…
“In one instance, satisfying the threshold indicates that the location of the displayed image being observed includes a feature of interest to the observer. That is, if the observer spends at least the threshold amount of time observing a particular location in an image and/or scrolls back and forth several times through a sub-set of images, the logic 132 determines that the location in the image or a 3D location in the series of images includes a finding of interest to the observer.” [0035]
outputting an indication whether the comparing yields a match between the at least one third position and the at least one of the first position and the at least one second position, wherein the indication is directed toward reviewing a consistency of the medical diagnostic report with the further patient data.
Display (outputting) corresponding image satisfying a threshold, and corresponding previous image (medical diagnostic report) where distance of prior finding localized by an annotation is computed (reviewing consistency)…
“In response to a metric satisfying a threshold in connection with observing an image of a follow-up imaging data set, the logic 132 invokes the image selector 118 to concurrently display the corresponding image from the previously generated and stored imaging data set. In one instance, the particular image can be identified by computing a distance to a prior finding localized by an annotation, where a shortest distance below a given threshold is identified as the corresponding image.” [0036]
Regarding claim 12
A device for safety checking a medical diagnostic report for a patient based on an image file acquired using a medical imaging device, the device comprising:
a sensor interface configured to receive, from at least one sensor, sensor data relating to the image file;
Cohen-Solal et al. teaches:
Sensor senses (reading) focus of attention (sensor data) to image…
“In another aspect, a system includes a sensor that senses a focus of attention of an observer of an anatomical image, of a set of images, displayed on a monitor, a mapper that maps the focus of attention to the image based on a display geometry of the monitor, a metric determiner that determine a metric based on the map, logic that compares the metric with a predetermined metric and determines a location of the anatomical image includes tissue with a finding of interest in response to the metric satisfying the predetermined metric, an image selector that identifies an anatomical image, from an earlier acquired imaging data set, with a same tissue as the displayed image, and a display monitor that displays graphical indicia that identifies the earlier acquired image.” [0008]
Example of image selector as sensor interface to receive an image file…
“An image selector 118 allows an operator, via the input device(s) 108, to scroll, jump, and/or otherwise navigate through and select an image (slice) for the rendering engine 116 to visually present via the monitor of the output device(s) 110. The image selector 118 maintains, in real-time, the displayed image slice number, the series in an imaging examination data, etc.” [0026]
Example of annotator as a sensor interface…
“An annotator 120, receives as an input, via the input device(s) 108, a signal identifying an annotation to superimpose or overlay over a displayed image. The annotation is conveyed to the rendering engine 116 to visually present via the monitor of the output device(s) 110. The annotator 120 also allows for propagating an annotation of one image to another image.” [0027]
an assignment unit configured to assign the sensor data to a first position of an anatomical structure of the patient;
Mapper (assignment unit) the maps (assigning) focus of attention (sensor data) to display geometry (first position)…
“In another aspect, a system includes a sensor that senses a focus of attention of an observer of an anatomical image, of a set of images, displayed on a monitor, a mapper that maps the focus of attention to the image based on a display geometry of the monitor, a metric determiner that determine a metric based on the map, logic that compares the metric with a predetermined metric and determines a location of the anatomical image includes tissue with a finding of interest in response to the metric satisfying the predetermined metric, an image selector that identifies an anatomical image, from an earlier acquired imaging data set, with a same tissue as the displayed image, and a display monitor that displays graphical indicia that identifies the earlier acquired image.” [0008]
Where scanning is for a patient…
“Patient follow-up may include consecutive studies performed with the same imaging protocols (i.e. same modality, same scanned body part and scanner parameters). These studies can contain hundreds of slices to be looked at. The original study will often contain key images that have been marked as the radiologist reviews the case. In a follow-up study, the radiologist will report on the previously marked findings (annotated within key images).” [0003]
an extraction unit configured to extract at least one second position of the anatomical structure of the patient from the medical diagnostic report;
“Where the signal identifies a follow-up imaging data set, a previous data identifier 114 is used to identify a previously generated and stored imaging data set corresponding to the follow-up imaging data set. The previously generated and stored imaging data set is identified as related to a follow-up imaging data set for example based on imaging protocol, scanned anatomy of interest, imaging modality, and/or other data, and/or by the most recent (chronologically) scan of the patient.” [0022]
Logic as an extraction unit…
“Logic 132 evaluates the metrics. In one instance, this includes comparing the metrics against predetermined threshold and/or a pattern of observation. For example, the metric indicating a total amount of time the observer spent observing each location within the image can be compared with the time threshold, and the metric indicating the sequential order in which the images are observed can be compared with the pattern of observation.” [0034]
Where logic employs segmentation…
“In another variation, the logic 132 may employ segmentation using the eye tracking location as a seed to initiate the segmentation of a finding (e.g., mass, tumor, cyst, etc.). This may provide a more accurate location of a prior finding for matching, not based on the annotation provided by the user but based on the object itself. In addition, this provides an ability to compute a shape, a margin and/or any other feature(s) to further compute the matching score and avoid mismatch (i.e. appearance-based matching).” [0038]
See Extracting below.
a comparison unit configured to compare the first position and the at least one second position; and
“An eye tracker 124 detects or tracks a focus of attention of an observer of an anatomical image of a set of images. Generally, the eye tracker 124 can employ any approach that can identify focus-of-attention regions. Examples of suitable approaches are discussed in “Eye Tracking: A comprehensive guide to methods and measures,” by Kenneth Holmqvist, Marcus Nyström, Richard Andersson, Richard Dewhurst, Halszka Jarodzka, Joost van de Weijer, Oxford University Press, 2011. These approaches include line of sight, eye movement, pattern of eye movement, dwelling, etc. Other approaches are also contemplated herein.” [0029]
Same anatomical regions (first and second positions)….
“In a variation, the logic 132 may register (e.g., model-based or segmentation-based) images in order to have the same anatomical regions geometrically corresponding between them (e.g., organ level, slice number, location within a slice). This may improve the precision of the matching. Rigid and/or elastic registration algorithms can be used. Where the imaging data sets correspond to different modalities (e.g., CT and MR), a registration or fusion of the two types of images can be performed.” [0037]
Confirms (comparing) a correct match…
“In the case where the observer confirms a correct match, the observer can seamlessly edit the image annotation and associated text description starting with the prior finding description. The text from the prior study can be propagated and displayed in a small window on the side of the current finding. When done and submitted, finding details will be added to the final report. Image annotation from the prior finding can also be positioned at the gaze location in the current image for final edition.” [0043]
“Optionally, the system 100 can be used to identify overlooked findings in a prior study: For example, if the observer visually detects a new finding in the current study which was not seen and reported before (no suggested match by the invention), the logic 132 invokes the image selector 118 to display the corresponding region from the most recent prior study (slice number and series) where the overlooked finding might be located.” [0048]
Example of logic as comparison unit…
“By automatically displaying the corresponding image, the observer need not have to scroll through the previously generated imaging data set to find this image, saving time. The logic 132 can display visual feedback or indicia such as an icon, text, a graphic, etc. over the display of the follow-up image, apprising the observer that a match was found and is displayed on the other monitor. The observer, via the input device(s) 108 and the annotator 120, can annotate the follow up image and/or the previously generated image.” [0040]
an output interface configured to output a warning signal in response to determining that the first position does not match the at least one second position, the warning signal including blocking at least one of completing or signing the medical diagnostic report.
[No Patentable Weight is given to alternative claim language where only one selection is required.]
When no match, invokes image selector (output a warning) to display region that was overlooked…
“Optionally, the system 100 can be used to identify overlooked findings in a prior study: For example, if the observer visually detects a new finding in the current study which was not seen and reported before (no suggested match by the invention), the logic 132 invokes the image selector 118 to display the corresponding region from the most recent prior study (slice number and series) where the overlooked finding might be located.” [0048]
Notify (output warning signal) of overlooked areas (does not match) that correspond to findings in prior study…
“For ignored findings in the current study. If the radiologist visually fails to examine areas in the current study that correspond to findings in prior study, the system can notify and visualize those ignored prior findings in their corresponding areas of the current study. This can be done dynamically as the radiologist already past the findings scrolling down the stack of images or later when the reading phase is completed to notify the radiologist of one or more overlooked regions.” [0050]
Restrict (blocking) acquisition (completing) of imaging extent…
“The foregoing may also be used to restrict acquisition of a subsequent scan, which may reduce the x-ray dose the patient receives, relative to not restricting the subsequent scan. For this, the logic 132 determines the corresponding regions between the prior findings location, associated organs and sub-regions and suggests an imaging extent to restrict the acquisition to only the regions useful for comparison.” [0051]
See Signature below.
Extracting
Cohen-Solal et al. teaches matching anatomical location. They also teach segmentation. They do not literally use the term extracting.
Sati et al. also in the business of matching anatomical locations teaches:
Automatically associate medical report findings with medical image based on location…
“According to at least one embodiment, a cognitive imaging program may implement natural language processing (NLP) to read a medical report and automatically detect findings (e.g., lesions, tumors, diseases) and the anatomical location of the findings reported by a doctor. The cognitive imaging program may also implement an image detection component (e.g., image detection algorithm) to automatically detect potential findings within the medical image and to automatically detect the anatomy within the medical image. Then, the cognitive imaging program may implement an algorithm which may automatically associate the findings from the medical report with the potential findings from the medical image based on a description of the location of the finding in the report and the anatomical location of the potential finding in the medical image. Thereafter, the cognitive imaging program may record the association of the findings from the medical report and the potential findings from the medical image as strongly labeled information. The cognitive imaging program may then feed the strongly labeled information into a machine learning algorithm to help train the machine learning algorithm to automatically detect the target structure.” [0026]
Example of extraction using existing NLP methods with geometric description of anatomical location…
“In response to receiving the medical report from the unlabeled dataset, the cognitive imaging program 110a, 110b may implement a natural language processing (NLP) component or algorithm to determine one or more report data. Specifically, the NLP algorithm may breakdown and analyze the text of the medical report using existing NLP methods (e.g., sentence segmentation, tokenization, parts-of-speech tagging, parsing, fact extraction). Then, the NLP algorithm may process the textual data in the medical report and may automatically detect the findings (e.g., lesions, nodules, diseases, tumors, fractures) and the geometric description of the anatomical location (e.g., left lung, superior lobe) of the findings observed by the doctor. The report data may include the findings and the anatomical location of the findings detected using the NLP algorithm of the cognitive imaging program 110a, 110b.” [0036]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of Cohen-Solal et al. the ability to do extract location data from a medical diagnostic report as taught by Sati et al. since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Sati et al. who teaches using natural language processing for breaking down and analyzing text is using existing NLP methods and Cohen-Solal et al. benefits by the advantage of using existing NLP techniques for further analyzing the text of their records.
Signature
The combined references teach medical report. They also teach no matching with warning. They do not teach signature.
Reiner also in the business of medical reports teaches:
Before allowed to sign off (therefore block) on report, cross reference (matching) of imaging and clinical data where report is analyzed and flagged for findings…
“16. Once the report has been constructed and reviewed by the radiologist, it is ready to be signed and distributed to the referring clinician. 17. Before the radiologist is allowed to "sign off" on the report, computer analysis is performed by the program 110 on the report content, along with cross-reference of the pre-report supporting historical imaging and clinical data of the patient. 18. In the process of performing this computer-based analysis, findings deemed to be of high clinical significance and constituting "critical results" (based upon predefined criteria) are flagged by the program 110 and presented to the radiologist for formal review prior to be allowing to `sign off" on the report.” [0301] – [0303]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to block signatures as taught by Reiner since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Reiner who teaches the advantages of reviewing reports prior to signature. The combined references benefit as they also are concerned about accurate reports.
Regarding claim 13
The device as claimed in claim 12, wherein the at least one sensor includes at least one of:
at least one of a motion sensor or an input sensor of an input interface, wherein the input interface includes at least one of a computer mouse, a trackpad, a trackball, a joystick, a keyboard, or a touch-sensitive screen;
Cohen-Solal et al. teaches:
“The computer system 100 includes one or more microprocessors and computer readable storage medium (memory) 106 (i.e., physical memory and other non-transitory storage medium). The computer system 100 further includes an input device(s) 108 such as a keyboard, a mouse, a microphone, a touchscreen, etc.) and an output device(s) 110 such as a monitor, a filmer, a printer, etc.” [0018]
an eye tracking sensor; or
“An eye tracker 124 detects or tracks a focus of attention of an observer of an anatomical image of a set of images. Generally, the eye tracker 124 can employ any approach that can identify focus-of-attention regions. Examples of suitable approaches are discussed in “Eye Tracking: A comprehensive guide to methods and measures,” by Kenneth Holmqvist, Marcus Nyström, Richard Andersson, Richard Dewhurst, Halszka Jarodzka, Joost van de Weijer, Oxford University Press, 2011. These approaches include line of sight, eye movement, pattern of eye movement, dwelling, etc. Other approaches are also contemplated herein.” [0029]
a timer configured to measure a duration of viewing of a slice from an image stack.
“Logic 132 evaluates the metrics. In one instance, this includes comparing the metrics against predetermined threshold and/or a pattern of observation. For example, the metric indicating a total amount of time the observer spent observing each location within the image can be compared with the time threshold, and the metric indicating the sequential order in which the images are observed can be compared with the pattern of observation.” [0034]
Regarding claim 14
A system for safety checking the medical diagnostic report for the patient based on the image file acquired using the medical imaging device, the system including a computer processing device configured to carry out the computer-implemented method as claimed in claim 2.
Cohen-Solal et al. teaches:
Computer system…
“FIG. 1 schematically illustrates a computer system 100 in connection with an imaging system(s) 102 and/or a data repository 104. Imaging data may be stored by and/or transferred between the computer system 100, the imaging system(s) 102, and/or the data repository 104 in standard formats such as Digital Imaging and Communications in Medicine (DICOM), Health Level 7 (HL7), and/or other standard formats, and/or non-standard, proprietary, and/or other format.” [0015] – [0016]
“The imaging system(s) 102 includes for example one or more of a computed tomography (CT), a magnetic resonance imaging (MM), a positron emission tomography (PET), single photon emission computed tomography (SPECT), X-ray, and/or other imaging system. The data repository 104 includes for example one or more of a picture archiving and communication system (PACS), a radiology information system (RIS), a hospital information system (HIS), and/or other data repository.” [0017]
Regarding claim 15
A system for safety checking the medical diagnostic report, the system comprising:
at least one sensor configured to acquire the sensor data relating to an image file;
Cohen-Solal et al. teaches:
“An eye tracker 124 detects or tracks a focus of attention of an observer of an anatomical image of a set of images. Generally, the eye tracker 124 can employ any approach that can identify focus-of-attention regions. Examples of suitable approaches are discussed in “Eye Tracking: A comprehensive guide to methods and measures,” by Kenneth Holmqvist, Marcus Nyström, Richard Andersson, Richard Dewhurst, Halszka Jarodzka, Joost van de Weijer, Oxford University Press, 2011. These approaches include line of sight, eye movement, pattern of eye movement, dwelling, etc. Other approaches are also contemplated herein.” [0029]
the device as claimed in claim 12, the sensor interface configured to read in the sensor data from the at least one sensor; and
Mapper the maps (assigning) focus of attention (read in sensor data) to display geometry (first position)…
“In another aspect, a system includes a sensor that senses a focus of attention of an observer of an anatomical image, of a set of images, displayed on a monitor, a mapper that maps the focus of attention to the image based on a display geometry of the monitor, a metric determiner that determine a metric based on the map, logic that compares the metric with a predetermined metric and determines a location of the anatomical image includes tissue with a finding of interest in response to the metric satisfying the predetermined metric, an image selector that identifies an anatomical image, from an earlier acquired imaging data set, with a same tissue as the displayed image, and a display monitor that displays graphical indicia that identifies the earlier acquired image.” [0008]
a warning signal output device configured to output the warning signal based on the warning signal provided at the output interface of the device.
When no match, invokes image selector (output a warning) to display region (output device) that was overlooked…
“Optionally, the system 100 can be used to identify overlooked findings in a prior study: For example, if the observer visually detects a new finding in the current study which was not seen and reported before (no suggested match by the invention), the logic 132 invokes the image selector 118 to display the corresponding region from the most recent prior study (slice number and series) where the overlooked finding might be located.” [0048]
Regarding claim 20
A device for safety checking a medical diagnostic report for a patient based on an image file acquired using a medical imaging device, the device comprising:
a memory storing computer-executable instructions; and
Cohen-Solal et al. teaches:
Memory…
“The computer system 100 includes one or more microprocessors and computer readable storage medium (memory) 106 (i.e., physical memory and other non-transitory storage medium). The computer system 100 further includes an input device(s) 108 such as a keyboard, a mouse, a microphone, a touchscreen, etc.) and an output device(s) 110 such as a monitor, a filmer, a printer, etc.” [0018]
at least one processor configured to execute the computer- executable instructions to cause the device to
Microprocessors…
“The computer system 100 includes one or more microprocessors and computer readable storage medium (memory) 106 (i.e., physical memory and other non-transitory storage medium). The computer system 100 further includes an input device(s) 108 such as a keyboard, a mouse, a microphone, a touchscreen, etc.) and an output device(s) 110 such as a monitor, a filmer, a printer, etc.” [0018]
receive, from at least one sensor, sensor data relating to the image file,
Sensor senses (receive) focus of attention (sensor data) to image…
“In another aspect, a system includes a sensor that senses a focus of attention of an observer of an anatomical image, of a set of images, displayed on a monitor, a mapper that maps the focus of attention to the image based on a display geometry of the monitor, a metric determiner that determine a metric based on the map, logic that compares the metric with a predetermined metric and determines a location of the anatomical image includes tissue with a finding of interest in response to the metric satisfying the predetermined metric, an image selector that identifies an anatomical image, from an earlier acquired imaging data set, with a same tissue as the displayed image, and a display monitor that displays graphical indicia that identifies the earlier acquired image.” [0008]
assign the sensor data to a first position of an anatomical structure of the patient,
Mapper the maps (assigning) focus of attention (sensor data) to display geometry (first position)…
“In another aspect, a system includes a sensor that senses a focus of attention of an observer of an anatomical image, of a set of images, displayed on a monitor, a mapper that maps the focus of attention to the image based on a display geometry of the monitor, a metric determiner that determine a metric based on the map, logic that compares the metric with a predetermined metric and determines a location of the anatomical image includes tissue with a finding of interest in response to the metric satisfying the predetermined metric, an image selector that identifies an anatomical image, from an earlier acquired imaging data set, with a same tissue as the displayed image, and a display monitor that displays graphical indicia that identifies the earlier acquired image.” [0008]
Where scanning is for a patient…
“Patient follow-up may include consecutive studies performed with the same imaging protocols (i.e. same modality, same scanned body part and scanner parameters). These studies can contain hundreds of slices to be looked at. The original study will often contain key images that have been marked as the radiologist reviews the case. In a follow-up study, the radiologist will report on the previously marked findings (annotated within key images).” [0003]
extract at least one second position of the anatomical structure of the patient from the medical diagnostic report,
“Where the signal identifies a follow-up imaging data set, a previous data identifier 114 is used to identify a previously generated and stored imaging data set corresponding to the follow-up imaging data set. The previously generated and stored imaging data set is identified as related to a follow-up imaging data set for example based on imaging protocol, scanned anatomy of interest, imaging modality, and/or other data, and/or by the most recent (chronologically) scan of the patient.” [0022]
See Extracting below.
compare the first position and the at least one second position, and
“An eye tracker 124 detects or tracks a focus of attention of an observer of an anatomical image of a set of images. Generally, the eye tracker 124 can employ any approach that can identify focus-of-attention regions. Examples of suitable approaches are discussed in “Eye Tracking: A comprehensive guide to methods and measures,” by Kenneth Holmqvist, Marcus Nyström, Richard Andersson, Richard Dewhurst, Halszka Jarodzka, Joost van de Weijer, Oxford University Press, 2011. These approaches include line of sight, eye movement, pattern of eye movement, dwelling, etc. Other approaches are also contemplated herein.” [0029]
Same anatomical regions (first and second positions)….
“In a variation, the logic 132 may register (e.g., model-based or segmentation-based) images in order to have the same anatomical regions geometrically corresponding between them (e.g., organ level, slice number, location within a slice). This may improve the precision of the matching. Rigid and/or elastic registration algorithms can be used. Where the imaging data sets correspond to different modalities (e.g., CT and MR), a registration or fusion of the two types of images can be performed.” [0037]
Confirms (comparing) a correct match…
“In the case where the observer confirms a correct match, the observer can seamlessly edit the image annotation and associated text description starting with the prior finding description. The text from the prior study can be propagated and displayed in a small window on the side of the current finding. When done and submitted, finding details will be added to the final report. Image annotation from the prior finding can also be positioned at the gaze location in the current image for final edition.” [0043]
“Optionally, the system 100 can be used to identify overlooked findings in a prior study: For example, if the observer visually detects a new finding in the current study which was not seen and reported before (no suggested match by the invention), the logic 132 invokes the image selector 118 to display the corresponding region from the most recent prior study (slice number and series) where the overlooked finding might be located.” [0048]
output a warning signal in response to determining that the first position does not match the at least one second position, the warning signal including blocking at least one of completing or signing the medical diagnostic report.
No Patentable Weight is given to alternative claim language where only one selection is required.]
When no match, invokes image selector (output a warning) to display region that was overlooked…
“Optionally, the system 100 can be used to identify overlooked findings in a prior study: For example, if the observer visually detects a new finding in the current study which was not seen and reported before (no suggested match by the invention), the logic 132 invokes the image selector 118 to display the corresponding region from the most recent prior study (slice number and series) where the overlooked finding might be located.” [0048]
Notify (output warning signal) of overlooked areas (does not match) that correspond to findings in prior study…
“For ignored findings in the current study. If the radiologist visually fails to examine areas in the current study that correspond to findings in prior study, the system can notify and visualize those ignored prior findings in their corresponding areas of the current study. This can be done dynamically as the radiologist already past the findings scrolling down the stack of images or later when the reading phase is completed to notify the radiologist of one or more overlooked regions.” [0050]
Restrict (blocking) acquisition (completing) of imaging extent…
“The foregoing may also be used to restrict acquisition of a subsequent scan, which may reduce the x-ray dose the patient receives, relative to not restricting the subsequent scan. For this, the logic 132 determines the corresponding regions between the prior findings location, associated organs and sub-regions and suggests an imaging extent to restrict the acquisition to only the regions useful for comparison.” [0051]
See Signature below.
Extracting
Cohen-Solal et al. teaches matching anatomical location. They also teach segmentation. They do not literally use the term extracting.
Sati et al. also in the business of matching anatomical locations teaches:
Automatically associate medical report findings with medical image based on location…
“According to at least one embodiment, a cognitive imaging program may implement natural language processing (NLP) to read a medical report and automatically detect findings (e.g., lesions, tumors, diseases) and the anatomical location of the findings reported by a doctor. The cognitive imaging program may also implement an image detection component (e.g., image detection algorithm) to automatically detect potential findings within the medical image and to automatically detect the anatomy within the medical image. Then, the cognitive imaging program may implement an algorithm which may automatically associate the findings from the medical report with the potential findings from the medical image based on a description of the location of the finding in the report and the anatomical location of the potential finding in the medical image. Thereafter, the cognitive imaging program may record the association of the findings from the medical report and the potential findings from the medical image as strongly labeled information. The cognitive imaging program may then feed the strongly labeled information into a machine learning algorithm to help train the machine learning algorithm to automatically detect the target structure.” [0026]
Example of extraction using existing NLP methods with geometric description of anatomical location…
“In response to receiving the medical report from the unlabeled dataset, the cognitive imaging program 110a, 110b may implement a natural language processing (NLP) component or algorithm to determine one or more report data. Specifically, the NLP algorithm may breakdown and analyze the text of the medical report using existing NLP methods (e.g., sentence segmentation, tokenization, parts-of-speech tagging, parsing, fact extraction). Then, the NLP algorithm may process the textual data in the medical report and may automatically detect the findings (e.g., lesions, nodules, diseases, tumors, fractures) and the geometric description of the anatomical location (e.g., left lung, superior lobe) of the findings observed by the doctor. The report data may include the findings and the anatomical location of the findings detected using the NLP algorithm of the cognitive imaging program 110a, 110b.” [0036]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of Cohen-Solal et al. the ability to do extract location data from a medical diagnostic report as taught by Sati et al. since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Sati et al. who teaches using natural language processing for breaking down and analyzing text is using existing NLP methods and Cohen-Solal et al. benefits by the advantage of using existing NLP techniques for further analyzing the text of their records.
Signature
The combined references teach medical report. They also teach no matching with warning. They do not teach signature.
Reiner also in the business of medical reports teaches:
Before allowed to sign off (therefore block) on report, cross reference (matching) of imaging and clinical data where report is analyzed and flagged for findings…
“16. Once the report has been constructed and reviewed by the radiologist, it is ready to be signed and distributed to the referring clinician. 17. Before the radiologist is allowed to "sign off" on the report, computer analysis is performed by the program 110 on the report content, along with cross-reference of the pre-report supporting historical imaging and clinical data of the patient. 18. In the process of performing this computer-based analysis, findings deemed to be of high clinical significance and constituting "critical results" (based upon predefined criteria) are flagged by the program 110 and presented to the radiologist for formal review prior to be allowing to `sign off" on the report.” [0301] – [0303]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to block signatures as taught by Reiner since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Reiner who teaches the advantages of reviewing reports prior to signature. The combined references benefit as they also are concerned about accurate reports.
Claims 10 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over the combined references in section (6) above in further view of Pub. No. US 2018/0101645 to Sorenson et al. and in further view of Pub. No. US 2022/0084645 to Ginsburg et al.
Regarding claim 10
The method as claimed in claim 1, further comprising:
reading in a medical guideline, which is classed as potentially relevant at least to at least one of the image file, the sensor data or the first position of the anatomical structure;
See Guideline below.
reviewing the medical diagnostic report with regard to compliance with the medical guideline; and
See Guideline below.
outputting the warning signal in response to determining that the medical diagnostic report is not compliant with the medical guideline.
See Warning below.
Guideline
The combined references teach image file. They do not teach medical guideline.
Sorenson et al. also in the business of image file teaches:
Suggest (reading in) best practice or clinically accepted practice guidelines (medical guideline, and allows user to modify findings (reviewing in report (medical diagnostic report)…
“For example, the processing engines working in combination with tracking module 78 can essentially “learn” the display preferences and adapt them to user preferences or belief system. For example, there is sometimes a 40% or greater inter-physician variance in the areas or volumes they measure, when all other variables are constant. In such case, a processing engine can learn a “group think” ground truth normal result based on collective use. Then, it can consider information from tracking module 78, to adapt which findings are important to user 81 and to adjust these initial findings in accordance with the measured variance between her beliefs and adjustment actions and such ground truth group think norm result. This can be applied not only to findings, but to the layout of images, and which tools are evoked or available during interpretation. This will increase the physician adoption of this automation by increasing the likelihood that the computer-generated result will be accepted with little or no adjustment, or that physician productivity and usability of the interpretation system is enhanced over time with increased use and learning. Further, future interpretation systems using this approach will require significantly reduced system pre-configuration. For example, the processing engine can also suggest that certain tools or image views be used, based on a comparison of the current user or users practices as compared to best practice user groups, or compared to clinically accepted practice guidelines. For example, a diagnostic review system such as within workstation 73 uses a viewer to display images incorporated into a physician interpretation workflow. The user uses the diagnostic review system to view and confirm findings. For example, the tracking module 78 or the diagnostic review system tracks whether the findings are unviewed, viewed, unconfirmed or confirmed, adjusted, unadjusted, deleted, added, reported or unreported. For example, the diagnostic review system allows the user to modify findings 77 in report 75 and these changes are reflected when the user (e.g., a physician) views images and findings using workstation 73. In both report 75 and workstation 73, the status of findings can be synchronized. For example, image processor 76 relies on some combination of the findings engine 77, tracking module 78 and adjustment engine 79 to produce derived images with or without the findings, overlays, contours, measurements or other indications included.” [0152]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use medical guidelines as taught by Sorenson et al. since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Sorenson et al. who teaches the advantages of using medical guidelines for imaging data.
Warning
The combined references teach warning. They also teach image ana. They do not teach warning for not compliant guidelines.
Alerts generate when non-compliant with guidance (guidelines)…
“In exemplary embodiments, many third party supporting services 5002 are integrated to provide feedback and advice. Examples of these services include ePrescribing 5027, Insurance verification including referrals and pre-authorizations 5028, clinical pricing and location services 5029 used to find the best value on purchasing medications, procedures and imaging services, medical necessity checking 5030 to verify a procedure or medication is associated with a correct ICD10 code supporting its use, claim status checking 5031, services in support of the National Correct Coding Initiative 5032, Medically Unlikely Edits 5033 provided by Center of Medicare and Medicaid Services (CMS) to proactively ensure claims are coded correctly to prevent issues in billing, and claims compliance services 5034 which evaluate claims against CMS National Coverage Determination (NCD) and Local Coverage Determination (LCD) guidelines as well as local insurance regulations all in an effort to establish and document medical necessity and to document same in support of streamlined billing. Natural language processing program 5045 and artificial intelligence/cognitive systems 5046 may also be provided to, for example, provide clinical decision support features. In exemplary embodiments, the NCD and LCD guidance is programmed into the Command Center 5000 so that alerts may be generated when a physician attempts to follow a treatment protocol that is non-compliant with the NCD and LCD guidance.” [0493]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use warnings for non-compliant models (guidelines) as taught by Ginsburg et al. since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Ginsburg et al. who teaches the advantages of providing alerts for non-compliance.
Regarding claim 11
The method as claimed in claim 10, wherein the reviewing the medical diagnostic report with regard to compliance with the medical guideline utilizes an algorithm trained by at least one of machine learning or artificial intelligence.
The combined references teach report. They do not teach machine learning.
Sorenson et al. also in the business of medical report teaches:
Machine learning and group practices (medical guideline)…
“In one embodiment, automated contours can generate measurements. When a measurement does not match what user 81 measured or they adjust it, it can be flagged as not matching. The artificial intelligence engine can learn (deep learn, machine learn, log or any combination thereof) the difference and begin to notice trends in the feedback in order to suggest improved findings to the user, or to suggest changes in system settings, or even to suggest changes in clinical workflow that better match best practices, group practices, or the practices of certain colleagues, which are individually tailored based on the current user preferences and detected practice differences. In addition, some differences can be accommodated, such as the case where one physician contours anatomy consistently larger or more generously than others do. Rather than changing the practice of the physician or considering that the best practice variance is a problem, the system can accept that the physician has this preference and try to use its bi-directional learning capabilities to instead present the physician with findings adjusted in a way that they will accept them more often without adjustment. This can be done with user to user adaptation so that someone who contours lesions large and someone who contours lesions small can have individualized suggestions.” [0515]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use medical guidelines with machine learning as taught by Sorenson et al. since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Sorenson et al. who teaches the advantages of using medical guidelines with machine learning.
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over the combined references in section (6) above in further view of Pub. No. US 2024/0177836 to Paik et al.
Regarding claim 18
The method as claimed in claim 4, wherein the first coding scheme includes a common coding scheme format.
The combined references teach coding scheme. They do not teach SNOMED or Radlex (common coding scheme format).
Paik et al. also in the business of coding teaches:
Available resources such as RadLex…
“The Information Model can define what types of structured elements will be extracted from free-text. In some cases, the model is based on relevant classes described in published models, including observations (e.g., herniation, edema), anatomy and location (e.g., C2-C3 vertebral disc), certainty (e.g., likely, negated), temporality (e.g., present or past finding), and modifiers such as severity or laterality. The Ontology can represent concepts, their synonyms, their relations (hierarchical or otherwise) and mappings to external databases. It can include dictionaries listing valid examples of Information Model classes such as, for example, all valid observations and their severities. This Ontology can be based on various publicly available resources such as the RadLex radiology ontology and/or the UMLS and its associated Metamap.” [0262]
Example of RadLex and SNOMED…
“The systems and methods described herein may include one or more controlled terminologies or lexicons to describe biomedical concepts. One skilled in the arts will recognize that numerous formats may be suitable including web ontology language (OWL) or Resource Description Framework (RDF) and that queries may be made using a query language such as SPARQL. Relevant ontologies and related resources include non-limiting examples such as RadLex, the Foundational Model of Anatomy (FMA), SNOMED Clinical Terms, or the UMLS Metathesaurus.” [0313]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use coding scheme as taught by Paik et al. since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Paik et al. who teaches the existence of available codes. The combined references benefit by using existing codes for identifying images.
Claims 19 is rejected under 35 U.S.C. 103 as being unpatentable over the combined references in section (6) above in further view of Pub. No. US 2021/0313045 to Wu et al.
Regarding claim 19
The method as claimed in claim 1, wherein the extracting the at least one second position of the anatomical structure from the medical diagnostic report comprises:
linguistic data processing of text of the medical diagnostic report to extract the at least one second position; and
Cohen-Solal et al. teaches:
Text…
“In the case where the observer confirms a correct match, the observer can seamlessly edit the image annotation and associated text description starting with the prior finding description. The text from the prior study can be propagated and displayed in a small window on the side of the current finding. When done and submitted, finding details will be added to the final report. Image annotation from the prior finding can also be positioned at the gaze location in the current image for final edition.” [0043]
See Linguistic below.
encoding the at least one second position extracted from the linguistically data-processed text.
See Linguistic below.
Linguistic
The combined references teach medical report and second position. They also teach text. They do not septically teach linguistic data processing.
Wu et al. also in the business of report and second position teaches;
Natural language processing (linguistic processing) learns standard anatomical zones for medical imaging reports…
“In some illustrative embodiments, the mechanisms of the illustrative embodiments, through a natural language processing and machine learning approach, learn the standard anatomical zones utilized by authors of medical imaging reports to specify the locations of anomalies (findings). In some illustrative embodiments, such standard anatomical zones may be provided as part of a knowledge database that maps anomalies to standard anatomical zones which may be constructed by subject matter experts (SMEs) or the like. The standard anatomical zones may be subsections or sub-regions of anatomical structures and may have various levels of specificity. For example, an anatomical structure that may be found through medical image segmentation is a right and/or left lung, which itself may be considered a standard anatomical zone. Moreover, the standard anatomical zones may further include specific regions within the lungs, e.g., upper, middle, and lower lung zones, if authors of medical imaging reports utilize such zone designations to identify locations of anomalies, or if such zones are generally known to be the locations of particular types of anomalies even if the zones are not specifically identified in the medical reports themselves, e.g., a pulmonary edema involves all zones of the lungs and thus, if a medical report indicates pulmonary edema, all zones of the lungs should be considered as regions of interest.” [0023]
Identify instances (extract) from medical imaging report standardized anatomical zones (encoding second position)…
“Having identified the bounding regions of the standardized anatomical zones of the masked anatomical structures, the medical imaging report analysis mechanisms identify instances of references to anomalies in the text of the medical imaging report and identify the standardized anatomical zones corresponding to these identified instances of anomalies. The identified standardized anatomical zones are then labeled with corresponding labels as to the particular anomalies, if any, in the zones, or if the zone is does not include any anomalies labeling the zones as normal or non-anomalous, or not labeling those zones that do not include anomalies.” [0036]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use linguistic processing as taught by Wu et al. since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Wu et al. who teaches the advantages of using natural language processing for interpreting image zones and the combined references benefit as they have text with image location information.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KENNETH BARTLEY whose telephone number is (571)272-5230. The examiner can normally be reached Mon-Fri: 7:30 - 4:00 EST.
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 at (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.
/KENNETH BARTLEY/Primary Examiner, Art Unit 3684