DETAILED ACTION
This action is made in response to the request for continued examination filed on January 23, 2026. This action is made non-final.
Claims 1, 2, 5-10, 12, 13, 15-23 are pending. Claims 3 and 14 were previously cancelled. Claims 4 and 11 are presently cancelled. Claims 21-23 are newly added. Claims 1, 8, 12, and 20 are presently amended. Claims 1, 11, and 20 are independent claims.
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 January 23, 2026 has been entered.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1, 2, 5-10, 12, 13, 15-19, and 21-23 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
As to independent claims 1 and 12, the claims recite, among other things, “wherein the continuous score of interest is a probability that each pixel includes a morphology of interest”. However, a review of the specification fails to describe the continuous score of interest as a probability that each pixel includes a morphology of interest. Rather, the originally filed specification describes the “continuous score of interest may be a score assigned to one or more pixels to determine whether the one or more pixels should be considered within or part of a salient group”. Accordingly, appropriate correction is required.
Claims 2, 5-10, 13, 15-19, and 21-23 fail to resolve the 112 deficiency of the parent claims and are similarly rejected.
Response to Arguments
Applicant's arguments with respect to the 101 rejection has been fully considered but they are not persuasive.
Applicant argues the claimed invention is not directed towards an abstract idea of organizing human activity. However, the examiner, respectfully disagrees.
MPEP 2106. 04(a)(2)(II) states that a claimed invention is directed to certain methods of organizing human activity if the identified claim elements contain limitations that encompass fundamental economic principles or practices, commercial or legal interactions, or managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions). The Examiner submits that the identified claim elements represent a series of rules or instructions that a person or persons, with or without the aid of a computer, would follow to determine a contributing cause of death, particularly through analyzing images. The Examiner notes that Applicant’s Background describes identifying cause of death as a human task performed by an expert (see [0002], [0032]). Furthermore, the Examiner submits that healthcare itself is inherently represents the organization of human activity. Applicant has not pointed to anything in the claims that fall outside of this characterization. Because the claim elements fall under a series of rules or instructions that a person or persons would follow to determine a cause of death, the claimed invention is directed to an abstract idea.
Furthermore, insomuch as Applicant argues the use of pixels is not directed towards an abstract idea; the additional element of using pixels has been determined to generally link the use of the abstract idea to a particular technological environment or field of use and does not integrate the abstract idea into a practical application nor amount to significantly more.
Accordingly, for at least the above stated reasons, the previous 101 rejection is maintained.
As to the previous 103 rejection, Applicant argues the previous cited references fail to “the continuous score of interest is a probability that each pixel includes a morphology of interest”. However, the examiner respectfully disagrees.
As a first matter, it is noted that the claim limitation is not supported by the originally filed specification. Rather, the originally filed specification describes the “continuous score of interest may be a score assigned to one or more pixels to determine whether the one or more pixels should be considered within or part of a salient group” as per [0059]. The specification goes on to state that a higher score may indicate that a region (e.g., set of pixels) is more likely to be a salient region and a low score indicates a region is not salient. Accordingly, where the prior art teaches assigning a value to one or more pixels, wherein the value is indicative the pixel is a salient region or region of interest, then it meets the claimed limitation. Sjöstran is directed to the automated analysis of images for hot spots (i.e., regions of interest) wherein a plurality of pixels are assigned a corresponding value such that those pixels that exceed a likelihood threshold value are determined to be a hotspot or region of interest (e.g., see [0020], [0036], [0051]). Accordingly, Sjöstran teaches the claimed limitation.
Accordingly, for at least the above reasons, and those below, the claims are rejected.
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, 2, 5-10, 12, 13, and 15-23 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Claims 1-2, 5-10, and 21-23 recite a method of determining a contributing cause of death, which is within the statutory category of a process. Claims 12-13 and 15-19 recite a system for determining a contributing cause of death, which is within the statutory class of a machine. Claim 20 recites a non-transitory computer readable memory performing instructions for of determining a contributing cause of death, which is within the statutory class of a manufacture.
Claims are eligible for patent protection under § 101 if they are in one of the four statutory categories and not directed to a judicial exception to patentability. Alice Corp. v. CLS Bank Int'l, 573 U.S. ___ (2014). Claims 1, 2, 5-10, 12, 13, and 15-23, each considered as a whole and as an ordered combination, are directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
MPEP 2106 Step 2A – Prong 1:
The bolded limitations of:
Claims 1, 12, and 20 (claim 1 being representative)
receiving, by a salient region detection machine learning model, a plurality of electronic medical images of at least one slide having at least one pathology specimen, wherein the at least one pathology specimen is associated with a deceased patient; detecting, by the salient region detection machine learning model, one or more salient regions of each of the plurality of electronic medical images by: assigning, by the salient region detection machine learning model, a continuous score of interest to each regions of the plurality of electronic medical images, wherein the continuous score of interest is a probability that each pixel includes a morphology of interest, determining, by the salient region detection machine learning model, whether the continuous score of interest for each regions of the plurality of electronic medical images is greater than a threshold continuous score of interest value; and identifying, by the salient region detection machine learning model, a first plurality of continuous regions, each region of the first plurality of continuous regions with a continuous score of interest greater than the threshold continuous score of interest value as the one or more salient regions and a second plurality of continuous region, each region of the second plurality of continuous regions with a continuous score of interest equal to or less than the threshold continuous score of interest value as non-salient regions; extracting, by the salient region detection machine learning model, one or more pathology features of the at least one pathology specimen from the plurality of electronic medical images based on the one or more salient regions; providing, by the salient region detection machine learning model, the one or more pathology features to a cause of death detection machine learning model, wherein the model has been trained using one or more prior deceased subjects and/or synthetically generated sets of pathology features, to identify associations between the one or more pathology features and one or more potential contributing causes of death and output a highest prediction score; determining, by the cause of death detection machine learning model, that the highest prediction score exceeds a threshold value for at least one contributing cause of death, of the potential contributing causes of death, indicating which contributing cause of death is most likely; determining, by the cause of death detection machine learning model, a vector including probabilities of each contributing cause of death; and outputting the vector in a viewing platform.
as presently drafted, under the broadest reasonable interpretation, covers a method of organizing human activity (i.e., managing personal behavior including following rules or instructions) but for the recitation of generic computer components. For example, but for the noted computer elements, the claim encompasses a person following rules or instructions to analyze and process data in the manner described in the abstract idea to analyze images to predict a cause of death. The examiner further notes that “methods of organizing human activity” includes a person’s interaction with a computer (see October 2019 Update: Subject Matter Eligibility at Pg. 5). If the claim limitation, under its broadest reasonable interpretation, covers managing persona behavior or interactions between people but for the recitation of generic computer components, then it falls within the “method of organizing human activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
MPEP 2106 Step 2A – Prong 2:
This judicial exception is not integrated into a practical application because there are no meaningful limitations that transform the exception into a patent eligible application. The additional elements merely amount to instructions to apply the exception using generic computer components (“processor”, "a non-transitory computer readable medium”, “memory”, and “electronic” image—all recited at a high level of generality). Although they have and execute instructions to perform the abstract idea itself, this also does not serve to integrate the abstract idea into a practical application as it merely amounts to instructions to "apply it." (See MPEP 2106.04(d)(2) indicating mere instructions to apply an abstract idea does not amount to integrating the abstract idea into a practical application). Accordingly, the additional elements do not integrate the abstract idea into a practical application because they do not impose meaningful limits on practicing the abstract idea. Therefore, the claims are directed to an abstract idea.
The use of “pixels” is not integrated into a practical application as it generally links the abstract idea into a particular technological environment or field of use. (See MPEP 2106.04(d)(I) indicating generally linking an abstract idea to a particular technological environment or field of use cannot provide a practical application).
The claim further recites the additional elements of a salient region detection machine learning model and a cause of death detection machine learning model that has been trained. When given the broadest reasonable interpretation in light of the nonexistent description of machine learning training in the disclosure, training of a machine learning model with the noted data amounts to a mathematical concept that creates data associations. As such, this training of the machine learning model is interpreted to be subsumed within the identified abstract idea and the use of the trained model provides nothing more than mere instructions to implement the abstract idea, supra. July 2024 Subject Matter Eligibility Examples, Example 47, Claim 2, discussion of item (c) at Pgs. 7-9. Furthermore, the use of the trained machine learning model provides nothing more than mere instructions to implement an abstract idea on a generic computer (“apply it”). See MPEP 2106.05(f). MPEP 2106.05(f); July 2024 Subject Matter Eligibility Examples, Example 47, Claim 2, discussion of items (d) and (e) at Pgs. 8-9.
The claims only manipulate abstract data elements as part of performing the abstract idea. They do not set forth improvements to another technological field or the functioning of the computer itself and instead use computer elements as tools in a conventional way to improve the functioning of the abstract idea identified above. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation. None of the additional elements recited "offers a meaningful limitation beyond generally linking 'the use of the [method] to a particular technological environment,' that is, implementation via computers." Alice Corp., slip op. at 16 (citing Bilski v. Kappos, 561 U.S. 610, 611 (U.S. 2010)).
At the levels of abstraction described above, the claims do not readily lend themselves to a finding that they are directed to a nonabstract idea. Therefore, the analysis proceeds to step 2B. See BASCOM Global Internet v. AT&T Mobility LLC, 827 F.3d 1341, 1349 (Fed. Cir. 2016) ("The Enfish claims, understood in light of their specific limitations, were unambiguously directed to an improvement in computer capabilities. Here, in contrast, the claims and their specific limitations do not readily lend themselves to a step-one finding that they are directed to a nonabstract idea. We therefore defer our consideration of the specific claim limitations’ narrowing effect for step two.") (citations omitted).
MPEP 2106 Step 2B:
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception for the same reasons as presented in Step 2A Prong 2. Moreover, the additional elements recited are known and conventional generic computing elements (“processor”, "a non-transitory computer readable medium”, “memory”, and “electronic” image—see Specification Fig. 11, [0054], [0163], [0164] describing the various components as general purpose, common, standard, known to one of ordinary skill, and at a high level of generality, and in a manner that indicates that the additional elements are sufficiently well-known that the specification does not need to describe the particulars of such additional elements to satisfy the statutory disclosure requirements). Therefore, these additional elements amount 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 that amounts to significantly more. See MPEP 2106.05(f).
The Federal Circuit has recognized that "an invocation of already-available computers that are not themselves plausibly asserted to be an advance, for use in carrying out improved mathematical calculations, amounts to a recitation of what is 'well-understood, routine, [and] conventional.'" SAP Am., Inc. v. InvestPic, LLC, 890 F.3d 1016, 1023 (Fed. Cir. 2018) (alteration in original) (citing Mayo v. Prometheus, 566 U.S. 66, 73 (2012)). Apart from the instructions to implement the abstract idea, they only serve to perform well-understood functions (e.g., receiving, translating, and displaying data—see Specification above as well as Alice Corp.; Intellectual Ventures I LLC v. Symantec Corp., 838 F.3d 1307 (Fed. Cir. 2016); and Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334 (Fed. Cir. 2015) covering the well-known nature of these computer functions).
Furthermore, as discussed above, the additional element of using pixels, was determined to generally link the abstract idea to a particular technological environment or field of use. This has been re-evaluated under the “significantly more” analysis and has also been found insufficient to provide significantly more. (See MPEP 2106.05(A) indicating that generally linking an abstract idea to a particular technological environment or field of use cannot provide significantly more).
Also, as discussed above with respect to integration of the abstract idea into a practical application, the additional elements of the cause of death machine learning model that has been trained and the use of the salient region detection machine learning model and the cause of death detection machine learning model were considered to be part of the abstract idea and “apply it,” respectively. This has been re-evaluated under the “significantly more” analysis and has also been found insufficient to provide significantly more. The training of the machine learning model is considered part of the abstract idea and thus cannot provide a practical application. Furthermore, the use of the trained models represented saying “apply it.” The use of the trained models (e.g., salient region detection and cause of death) has been revaluated under the “significantly more” analysis and does not provide “significantly more” to the abstract idea. MPEP 2106.05(A) indicates also indicates that merely adding the words “apply it” or equivalent use cannot provide significantly more. Accordingly, even in combination, this additional element does not provide significantly more. As such the claim is not patent eligible.
Dependent Claims
The limitations of dependent but for those addressed below merely set forth further refinements of the abstract idea without changing the analysis already presented. Claims 2, 10 (13) merely recites additional data received for making a determination, claims 4-9, 11 (15-19) and 22 merely recite identifying specific regions to make the determination and the ranking of possible causes of death, claim 23 merely recites a type of contributing cause of death, which covers a method of organizing human activity (i.e., managing personal behavior including following rules or instructions).
Claim 21 merely recites receiving input from a plurality of modalities. Insomuch as the modalities are to be interpreted as machines or devices, the additional element is considered to “generally link” the abstract idea to a particular technology and does not provide a practical application or amount to significantly more for the same reasons detailed above.
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.
Claim(s) 1, 2, 5-7, 10, 12, 13, 15-18, and 20-23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Shibata et al. (USPPN: 2014/0337057; hereinafter Shibata) in further view of Sjöstrand et al. (USPPN: 2020/0337658; hereinafter Sjöstran) and Sethi et al. (USPPN: 2018/0232883; hereinafter Sethi).
As to claim 1, Shibata teaches A computer-implemented method for processing electronic medical images (e.g., see Abstract), the method comprising:
receiving a plurality of electronic medical images of at least one pathology specimen, wherein the at least one pathology specimen is associated with a deceased patient (e.g., see Figs. 3, 6, [0029], [0036], [0053], [0083] wherein the system receives one or more images of a patient after their death);
providing the one or more pathology features to a cause of death model, to identify associations between the one or more pathology features and one or more potential contributing causes of death and output a highest prediction score (e.g., see [0054], [0058], [0069], [0108]-[0110] wherein, based on the medical images, the system determines diagnostic information related to the cause of death and can further identify which diseases and/or wounds are related to the cause of death and ranks them according to their severity (i.e., prediction score));
determining that the highest prediction score exceeds a threshold value for at least one contributing cause of death, of the potential contributing causes of death, indicating which contributing cause of death is most likely (e.g., see [0112], [0133], [0137] wherein the disease with a high significance that occurs most frequently (i.e., threshold value) can be inferred as a cause of death candidate, out of plurality of cause-of-death candidates);
determining, by the cause of death detection machine learning model, a vector including probabilities of each contributing cause of death (e.g., see [0058], [0108], [0133], [0137], [0141] wherein various diseases/wounds are estimated and ranked (i.e., probabilities) to be the direct cause of death to the patient, wherein the diseases/wounds are consistent with the claimed “vector” as described in at least [0083], [0091], [0119] describing the data within a vector to be a specific cause of death); and
outputting the vector in a viewing platform (e.g., see [0123], [0133] wherein the estimated and ranked diseases/wounds are displayed).
While Shibata teaches identifying abnormal regions in the image (i.e., salient region), Shibata fails to teach detecting, by the salient region detection machine learning model, one or more salient regions of each of the plurality of electronic medical images by: assigning, by the salient region detection machine learning model, a continuous score of interest to each pixel of the plurality of electronic medical images, wherein the continuous score of interest is a probability that each pixel includes a morphology of interest, determining, by the salient region detection machine learning model, whether the continuous score of interest for each pixel of the plurality of electronic medical images is greater than a threshold continuous score of interest value; and identifying, by the salient region detection machine learning model, a first plurality of continuous pixels, each pixel of the first plurality of continuous pixels with a continuous score of interest greater than the threshold continuous score of interest value as the one or more salient regions and a second plurality of continuous pixels, each pixel of the second plurality of continuous pixels with a continuous score of interest equal to or less than the threshold continuous score of interest score value as non-salient regions.
However, in the same field of endeavor of medical image diagnostics, Sjöstran teaches detecting, by the salient region detection model, one or more salient regions of each of the plurality of electronic medical images by: assigning, by the salient region detection model, a continuous score of interest to each pixel of the plurality of electronic medical images, wherein the continuous score of interest is a probability that each pixel includes a morphology of interest, determining, by the salient region detection model, whether the continuous score of interest for each pixel of the plurality of electronic medical images is greater than a threshold continuous score of interest value; and identifying, by the salient region detection model, a first plurality of continuous pixels, each pixel of the first plurality of continuous pixels with a continuous score of interest greater than the threshold continuous score of interest value as the one or more salient regions and a second plurality of continuous pixels, each pixel of the second plurality of continuous pixels with a continuous score of interest equal to or less than the threshold continuous score of interest score value as non-salient regions (See 112 rejection above. e.g., see [0020], [0036], [0051] wherein each image comprises as plurality of pixels, each pixel having a corresponding intensity and identifying a hotspot (i.e., salient region) by comparing the pixel intensities to one or more threshold values, wherein each pixel has an intensity value for segmenting the images into regions of interest based on the intensities of the pixels in the region being greater than a threshold. Accordingly, the regions of interest being made up of a plurality of pixels, each having a value above a threshold, reads upon the claimed “continuous score of interest” which is consistent with Applicant’s originally filed specification [0059] of a score assigned to one or more pixels to determine whether the one or more pixels should be considered within the salient region).
Accordingly, it would have been obvious to modify Shibata in view of Sjöstran with a reasonable expectation of success. One would have been motivated to make the modification in order to easily identify regions of interest in medical imaging for various diseases (e.g., see [0003]-[0007] of Sjöstran).
While Shibata teaches the system makes an interpretation of the cause-of-death from the images and features extracted from patient data and Sjöstran teaches using machine learning models trained from identified regions of interest/hot spots, Shibata- Sjöstran fail to teach the medical images being at least one slide having at least one pathology specimen; extracting, by the salient region detection machine learning model, one or more pathology features of the at least one pathology specimen from the plurality of electronic medical images based on the one or more salient regions; a cause of death machine learning model, wherein the cause of death machine learning model has been trained using one or more prior deceased subjects and/or synthetically generated sets of pathology features.
However, in the same field of endeavor of medical image diagnostics, Sethi teaches the medical images being at least one slide having at least one pathology specimen (e.g., see Abstract, [0029], [0030] wherein patient tissue samples on examination slides and/or the images thereof are used to diagnose diseases) ; extracting, by the salient region detection machine learning model, one or more pathology features of the at least one pathology specimen from the plurality of electronic medical images based on the one or more salient regions (e.g., see [0041], [0051], [0057], [0059], [0071], [0072] wherein one or more point of interest are identified in the tissue image using a point of interest classifier or machine learning system); a cause of death machine learning model, wherein the cause of death machine learning model has been trained using one or more prior deceased subjects and/or synthetically generated sets of pathology features, to identify associations between one or more pathology features and one or more contributing causes of death and output a highest prediction score (e.g., see [0052], [0060], [0069], [0078]-[0080], [0082] teaching a machine learning model trained using training images including those from previous patients to identify one or more diseases and output the highest predicted disease (i.e., one or more potential contributing causes of death). Notably, Shibata teaches associations between diseases and causes of death)
Accordingly, it would have been obvious to modify Shibata in view of Sethi with a reasonable expectation of success. One would have been motivated to make the modification in order to improve accuracy in disease classification (e.g., see [0028] of Sethi).
As to claim 2, the rejection of claim 1 is incorporated. Shibata further teaches receiving, by the cause of death detection machine learning model, an autopsy report and information relating to an age, ethnicity, and ancillary test results associated with the deceased subject (e.g., see [0028], [0044], [0093] teaching receiving information including autopsy information, past test results, and patient health history. Shibata-Sethi fail to explicitly teach age and ethnicity; however, these differences are only found in the non-functional data selected for patient information. Thus, this description material will not distinguish the claimed invention from the prior art in terms of patentability, see Cf. In re Gulack, 703 F.2d 1381, 1385, 217 USPQ 401, 404 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994)).
As to claim 5, the rejection of claim 1 is incorporated. Shibata further teach determining, by the case of death detection machine learning model, a prediction score for reach of the one or more potential contributing cause of death (e.g., see [0060]-[0063] of Shibata teaching ranking each contributing cause of death based on their severity, wherein the substitution of score for severity rank is obvious (see MPEP 2144.05). See rejection above citing Sethi for explicitly teaching multiple machine learning models).
As to claim 6, the rejection of claim 1 is incorporated. While Shibata teaches including diagnostic information for the cause of death, Shibata fails to explicitly teach marking, by the cause of death detection machine learning model, the plurality of electronic medical images to depict one or more salient regions associated with evidence for the contributing cause.
However, in the same field of endeavor of medical image diagnostics, Sethi teaches marking, by the cause of death detection machine learning model, the plurality of electronic medical images to depict one or more salient regions associated with evidence for the contributing cause (e.g., see [0067]-[0068] wherein points of interest are identified on the image for diagnosing diseases. Notably, Shibata teaches associations between diseases and causes of death). Accordingly, it would have been obvious to modify Shibata in view of Sethi with a reasonable expectation of success. One would have been motivated to make the modification in order to improve accuracy in disease classification (e.g., see [0028] of Sethi).
As to claim 7, the rejection of claim 1 is incorporated. Shibata-Sethi further teach ranking, by the cause of death detection machine learning model, one or more prediction scores for each of the one or more potential contributing causes of death (e.g., see [0060]-[0063] of Shibata teaching ranking each contributing cause of death based on their severity. See rejection above citing Sethi for explicitly teaching multiple machine learning models).
As to claim 10, the rejection of claim 1 is incorporated. Shibata-Sethi further teaches further comprising: receiving, by the salient region detection machine learning model, a gross description, the gross description comprising data associated with the deceased subject; extracting, by the one or more processors, report metadata from the gross description; and providing, by the salient region detection machine learning model, the report metadata to the cause of death detection machine learning model (e.g., see [0044], [0055]-[0057] wherein historical patient information is received based on patient ID and using word extraction and analysis on the received data for determining cause-of-death. See also rejection above citing Sethi for teaching a machine learning system. Insomuch as the claims recite “gross description”, the limitation is interpreted as intended use. Applicant is reminded that no patentable distinction is made by an intended use unless some structural difference is imposed by the use or result on the structure or material recited in the claim, or some manipulative difference is imposed by the use or result on the action recited in the claim. An intended use generally does not impart a patentable distinction if it merely states an intention or is a description of how the claimed apparatus is to be used. claims (See MPEP 2111.05)).
As to claims 12-13 and 15-18, the claims are directed to the system implementing the method of claims 1-2 and 4-7 and are similarly rejected.
As to claim 20, the claim is directed to the non-transitory computer readable medium implementing the method of claim 1 and is similarly rejected.
As to claim 21, the rejection of claim 1 is incorporated. Shibata further teaches receiving, by the salient region detection machine learning model, input from a plurality of modalities (e.g., see Fig. 1, [0029] wherein the system receives input from a plurality of modalities).
As to claim 22, the rejection of claim 1 is incorporated. Sethi further teaches wherein providing, by the salient region detection machine learning model, the one or more pathology features to a cause of death detection machine learning model includes excluding one or more non-salient regions of each of the plurality of electronic medical images (e.g., see Fig. 8, [0028], [0057] teaching the removal of uninformative points of interest from the image to prevent them from being further examined).
Accordingly, it would have been obvious to modify Shibata in view of Sethi with a reasonable expectation of success. One would have been motivated to make the modification in order to improve accuracy in disease classification (e.g., see [0028] of Sethi).
As to claim 23, the rejection of claim 1 is incorporated. Shibata further teaches wherein the vector includes a probability corresponding to a contributing cause of death associated with cardiac arrhythemogenic genes (It is noted that the claim language of the particular type of contributing cause of death (e.g., cardiac arrhythemeogenic genes) is interpreted as nonfunctional descriptive information as they are not functionally required in the claimed method. See MPEP 2111.05. The function described in the claimed method would be performed the same regardless of whether the claimed contributing cause of death existed. Therefore, Shibata teaching a plurality of different contributing causes of death, including cardiac failure (e.g., see Fig. 4), it would have been obvious to substitute any type of contributing cause of death as a simple substitution. As such, it would have been obvious before the time of filing to substitute the contributing cause of death of the prior art with any specific contributing cause of death because the results would have been predictable for identifying desired causes of death). See KSR Int’l v. Teleflex Inc., 127 S. Ct. 1727, 1740-41, 82 USPQ2d 1385, 1396 (2007); and MPEP 2143.
Claim(s) 8, 11, and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Shibata, Sjöstran, and Sethi, in further view of Ahn et al. (USPPN: 2023/0030313; hereinafter Ahn).
As to claim 8, the rejection of claim 1 is incorporated. While Shibata teaches ranking the contributing cause of death and Sethi teaches a plurality of machine learning models, Shibata-Sjöstran-Sethi fail to teach determining and ranking each electronic medical image of the plurality of medical images based on the one or more prediction scores.
However, in the same field of endeavor of medical image diagnosis, Ahn teaches determining and ranking each electronic medical image of the plurality of medical images based on the one or more prediction scores (e.g., see [0079] wherein the one or more image features may be sorted by importance ranking. See rejection above wherein Shibata teaches determining and ranking of each of the one or more potential contributing causes of death).
Accordingly, it would have been obvious to modify Shibata-Sjöstran-Sethi in view of Ahn with a reasonable expectation of success. One would have been motivated to make the modification in order to generated interpretable prediction results for a patient thus aiding medical staff to make a clinical determination (e.g., see [0002]-[0004] of Ahn).
As to claim 11, the rejection of claim 1 is incorporated. While Shibata teaches determining potential cause of death (e.g., see Abstract) and Sethi teaches a plurality of machine learning models, Shibata-Sjöstran-Sethi fail to teach wherein the machine learning model outputs a vector associated with the one or more prediction scores.
However, in the same field of endeavor of medical image diagnosis, Ahn teaches wherein the machine learning model outputs a vector associated with the one or more prediction scores (e.g., see [0107] teaching the machine learning model outputting a vector indicating reliability and/or accuracy about a prediction result for the patient. See rejection above of Shibata teaching determining a cause of death s).
Accordingly, it would have been obvious to modify Shibata-Sjöstran-Sethi in view of Ahn with a reasonable expectation of success. One would have been motivated to make the modification in order to generated interpretable prediction results for a patient thus aiding medical staff to make a clinical determination (e.g., see [0002]-[0004] of Ahn).
As to claim 19, the claim is directed to the system implementing the method of claim 8 and is similarly rejected.
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Shibata, Sjöstran, and Sethi, in further view of McKinley et al. (USPPN: 2016/0078187; hereinafter McKinley).
As to claim 9, the rejection of claim 1 is incorporated. While Shibata teaches identifying contributing causes of death, including possible organ failure and Sethi teaches a plurality of machine learning models, Shibata-Sjöstran-Sethi fail to explicitly teach doing so based on the plurality of electronic medical images.
However, in the same field of endeavor of medical image diagnostics, McKinley teaches associating an organ with the contributing cause of death based on the plurality of electronic medical images (e.g., see Abstract teaching analysis of tissue sample images to determine potential organ failure).
Accordingly, it would have been obvious to modify Shibata-Sjöstran-Sethi in view of McKinley with a reasonable expectation of success. One would have been motivated to make the modification as a simple substitution of one type of disease (e.g., cancer, infectious diseases as taught in Sethi) with another (e.g., organ failure as taught in McKinley) to yield the predictable results of identifying multiple different types diseases See KSR Int’l v. Teleflex Inc., 127 S. Ct. 1727, 1740-41, 82 USPQ2d 1385, 1396 (2007); and MPEP 2143)
Relevant Art not Cited
As a courtesy, the following references have been found during the course of examination and deemed relevant to applicant’s disclosure. Applicant is encouraged to review the following references prior to any amendments/remarks:
Papier et al. (USPPN: 2002/0021828): System and method to aid diagnosis using cross-referenced knowledge and image databases
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to STELLA HIGGS whose telephone number is (571)270-5891. The examiner can normally be reached Monday-Friday: 9-5PM.
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, Peter Choi can be reached on (469) 295-9171. 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.
/STELLA HIGGS/Primary Examiner, Art Unit 3681