Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Election/Restrictions
Applicant's election with traverse of claims 1-14 and 16-18 in the reply filed on 06/23/2026 is acknowledged. The traversal is on the ground(s) that 1) the claim 15 depends on claim 1 and restricting a dependent claim from its independent parent is contrary to established Office practice under MPEP 806.05(c) and 2) the inventions in Groups I and II are not independent or distinct. They are not found persuasive for the following reasons.
With respect to 1), MPEP does not prohibit restricting a dependent claim from its parent. A proper restriction inquires, not whether one of the claims one group depends on a claim of another group, but all the inventions listed in the to be independent or distinct and there would be a serious search and/or examination burden if restriction were not required (see MPEP 803(I)). As such, the argument 1) is not substantiated and hence is a mere attorney argument. Moreover, MPEP 806.05(c), which the applicant cited, is a section about “Criteria of Distinctness Between Combination and Subcombination” and does not appear to discuss any policy of USPTO, let alone an established policy that is contrary to restricting a dependent from its parent.
With respect to 2), unlike the argument, Group I, which includes Claims 1-14 and 16-18 and drawn to a technique for generating an enhanced radiological image using a trained machine-learning model, and Group II, which includes Claims 15 and 19-20 and drawn to a contrast agent for a radiological examination, are distinct because they do not overlap in scope and are not obvious variants, and at least one subcombination is separately usable. As discussed in the restriction dated 04/23/2026, subcombination/Group I has separate utility such as enhancing various types of images of radiological examinations and is not limited to enhancing images induced using the contrast agent in subcombination Group II. Indeed, Subcombination I does not require particulars of subcombination II, the contrast agent, for patentability (see MPEP § 806.05(d)). Also, there would be a serious search and/or examination burden if restriction were not required here because the groups have separate classification, and they have a different field of search, requiring searching difference classes/subclasses and employing different search queries.
For the aforementioned reasons, the requirement is still deemed proper and is therefore made FINAL.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 09/23/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Drawings
Figs. 7-10 are objected to as depicting a block diagram without “readily identifiable” descriptors of each block, as required by 37 CFR 1.84(n). Rule 84(n) requires “labeled representations” of graphical symbols, such as blocks; and any that are “not universally recognized may be used, subject to approval by the Office, if they are not likely to be confused with existing conventional symbols, and if they are readily identifiable.” In the case of Figs. 7-10, the blocks are not readily identifiable per se and therefore require the insertion of text that identifies the function of that block. That is, each vacant block should be provided with a corresponding label identifying its function or purpose.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Objections
Claim 13 is objected to because of the following informalities:
Claim 13 recites “The method according to any of claim 1” in line 1. The examiner suggests deleting “any of” so that line 1 recites “The method according to claim 1”. Appropriate correction is required.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are:
Receiving unit in claim 16;
Control and calculation unit in claim 16; and
Output unit in claim 16.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
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.
Claim 17 is rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter because it may be interpreted under broadest reasonable interpretation as covering non-statutory embodiments, such as a computer program per se and signals perse. The claimed computer program product includes data carrier that may encompass non-statutory forms of signal transmission without any structural recitations. The examiner suggests amending the claim to be directed to a computer program product stored on a non-transitory computer readable medium.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 4-7, 10, 12, 13, and 16-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wo patent application publication no. 2022/184298 to Lenga et al. (hereinafter Lenga) in view of us patent application publication no. 2023/0385986 to Park et al. (hereinafter Park).
The examiner notes that Lenga’s paragraph number resets after paragraph 114. For the paragraphs that come before the reset, the examiner has placed ‘*’ after the paragraph number.
For claims 1 and 18, Lenga as applied teaches a computer-implemented method comprising:
providing a trained machine-learning model (MT) (see, e.g., pars. 94*, 18-23 and 39-41 and FIGS. 3, 4 and 5B, which teach providing a trained machine learning model);
wherein the trained machine-learning model (MT) has been trained on the basis of training data (TD) (see, e.g., pars. 10, 18-20 and 22-23 and FIG. 4),
wherein the training data (TD) for each reference object of a plurality of reference objects comprise as target data:
(i) a first reference representation (RR1) of a reference region of the reference object and a second reference representation (RR2) of the reference region of the reference object as input data (see, e.g., pars. 10, 12 and 35-37 and FIGS. 4 and 5A which teach that the training data set includes the first and second reference representations of an examination region of an examination object) and
(ii) a third reference representation (RR3) of the reference region of the reference object (see, e.g., pars. 10, 12 and 35-37 and FIG. 4, which teach that the training data set includes the third reference representation of the examination region of the examination object),
wherein the first reference representation (RR1) represents the reference region without contrast agent or after administration of a first amount of a contrast agent (see, e.g., pars. 12 and 35-37 and FIG. 5A, which teach that the first reference representation includes the examination region without or with a first amount of a contrast agent and that first amount is smaller than the second amount, and the second dose is smaller than the third amount),
wherein the second reference representation (RR2) represents the reference region after administration of a second amount of the contrast agent, the second amount being larger than the first amount (see, e.g., pars. 12 and 35-37 and FIG. 5A, which teach that the second reference representation includes the examination region with a second amount of the contrast agent and that first amount is smaller than the second amount, and the second dose is smaller than the third amount),
wherein the third reference representation (RR3) represents the reference region after administration of a third amount of the contrast agent, the third amount being different from the second amount (see, e.g., pars. 12 and 35-37 and FIG. 5A, which teach that the third reference representation includes the examination region with a third amount of the contrast agent and that first amount is smaller than the second amount, and the second dose is smaller than the third amount),
providing a first representation (R1) (see, e.g., pars. 95*, 42-43, and FIGS. 3 and 5C, which teach providing the first representation of an examination region of an examination object), wherein the first representation (R1) represents an examination region of an examination object without contrast agent or after administration of a first amount of a contrast agent (see, e.g., pars. 95* and 42-43 and FIGS. 3 and 5C, which teach providing the first representation without or with a first amount of contrast agent);
providing a second representation (R2) (see, e.g., pars. 100* and 42-43, and FIGS. 3 and 5C, which teach providing a second representation of the examination region of the examination object), wherein the second representation (R2) represents the examination region of the examination object after administration of a second amount of the contrast agent, the second amount being larger than the first amount (see, e.g., pars. 100* and 42-43 and FIGS. 3 and 5C, which teach providing the second representation with a second amount of the contrast agent, the second amount being greater than the first amount);
feeding the first representation (R1) and the second representation (R2) to the trained machine-learning model (MT) (see, e.g., pars. 105* and 43 and FIGS. 3 and 5C, which teach providing the first and second representations to the trained machine learning model);
receiving from the trained machine-learning model (MT) a synthetic third representation (R3*) of the examination region of the examination object (see, e.g., pars. 105-106*, 3 and 43-44 and FIGS. 3 and 5C, which teach receiving from the trained machine learning model the third representation of the examination region with a third amount of the contrast agent), wherein the synthetic third representation (R3*) represents the reference region after administration of a third amount of the contrast agent, the third amount being different from the second amount (see, e.g., pars. 105-106* and 3 and 43-44 and FIGS. 3 and 5C, which teach that the third representation represents the examination region after administration of the third amount of the contrast agent, the third amount being greater than the second amount); and
outputting and storing the synthetic third representation (R3*) and transmitting the synthetic third representation (R3*) to a separate computer system (see, e.g., pars. 6 and 44 and FIGS. 3 and 5C, which teach outputting and storing the output and transmitting the output to a user device/medical imaging system).
While Lenga as applied teaches generating, based on the first and the second reference representations and the model parameters, the prediction of the representation (see, e.g., pars. 39-41 and FIGS. 4 and 5B), it does not explicitly teach that wherein the trained machine-learning model (MT) comprises two submodels:
a first submodel (SM1T) and a second submodel (SM2), that the first submodel (SM1T) is configured and has been trained to determine, based on the first reference representation (RR1) and second reference representation (RR2) of an examination region of a reference object, at least one model parameter for the second submodel (SM2) and
wherein the second submodel (SM2) is configured to generate, based on at least one of the first reference representation (RR1) and second reference representation (RR2) and on the at least one model parameter (MP) determined by the first submodel (SM1T), a synthetic third representation (RR3*).
Park in the analogous art teaches that the trained machine-learning model (MT) comprises two submodels (see, e.g., FIG. 2 of Park, which shows the first and second neural networks):
a first submodel (SM1T) and a second submodel (SM2) (see, e.g., FIG. 2 of Park, which shows the first and second neural networks (NNs)),
wherein the first submodel (SM1T) is configured and has been trained to determine, based on the first reference representation (RR1) and second reference representation (RR2) of an examination region of a reference object, at least one model parameter for the second submodel (SM2) (see, e.g., pars. 47-49, 86-90 and 128-130 and FIGS. 2-4 and 14 of Park, which teach that the second NN determines, based on the same input image fed to the first NN, the correction parameter that is inputted to the first NN), and
wherein the second submodel (SM2) is configured to generate, based on at least one of the first reference representation (RR1) and second reference representation (RR2) and on the at least one model parameter (MP) determined by the first submodel (SM1T), a synthetic third representation (RR3*) (see, e.g., pars. 43-47, 73-76 and 125-127 and FIGS. 1-3 and 13 of Park, which teach that the first NN generates, based on the input image and the correction parameter determined by the second NN, an inference image with the enhanced contrast).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Lenga to utilize one model that generate a model parameter to be used by another model as taught by Park because Lenga suggest implementing the trained machine learning model as multiple, distributed systems or devices (see, e.g., pars. 84*, 94*, 9, 34, and 45 of Lenga) and doing so would provide a model parameter that would correct the input image to have optimal image characteristics that are generally preferred (see pars. 81-85 of Park).
For claim 16, Lenga as applied teaches a computer system (see, e.g., FIGS. 1-2), comprising:
a receiving unit (see, e.g., pars. 84-93* and FIG. 2);
a control and calculation unit (see, e.g., pars. 84-93* and FIG. 2); and
an output unit (see, e.g., pars. 84-93* and FIG. 2);
wherein the control and calculation unit is configured to:
generate a first representation (R1) or cause the receiving unit to receive a first representation (R1) (see, e.g., pars. 95* and 42-43, and FIGS. 3 and 5C, which teach providing the first representation of an examination region of an examination object), wherein the first representation (R1) represents an examination region of an examination object without contrast agent or after administration of a first amount of a contrast agent (see, e.g., pars. 95* and 42-43 and FIGS. 3 and 5C, which teach providing the first representation without or with a first amount of contrast agent);
generate a second representation (R2) or to cause the receiving unit to receive a second representation (R2) (see, e.g., pars. 100* and 42-43, and FIGS. 3 and 5C, which teach providing a second representation of the examination region of the examination object), wherein the second representation (R2) represents the examination region of the examination object after administration of a second amount of the contrast agent, the second amount being larger than the first amount (see, e.g., pars. 100* and 42-43 and FIGS. 3 and 5C, which teach providing the second representation with a second amount of the contrast agent, the second amount being greater than the first amount);
feed the first representation (R1) and the second representation (R2) to a trained machine-learning model (MT) (see, e.g., pars. 105* and 43 and FIGS. 3 and 5C, which teach providing the first and second representations to the trained machine learning model);
wherein the trained machine-learning model (MT) has been trained on the basis of training data (TD) (see, e.g., pars. 10, 18-20 and 22-23 and FIG. 4),
wherein the training data (TD) for each reference object of a plurality of reference objects comprise as target data:
(i) a first reference representation (RR1) of a reference region of the reference object and a second reference representation (RR2) of the reference region of the reference object as input data (see, e.g., pars. 10, 12 and 35-37 and FIGS. 4 and 5A which teach that the training data set includes the first and second reference representations of an examination region of an examination object) and
(ii) a third reference representation (RR3) of the reference region of the reference object (see, e.g., pars. 10, 12 and 35-37 and FIG. 4, which teach that the training data set includes the third reference representation of the examination region of the examination object),
wherein the first reference representation (RR1) represents the reference region without contrast agent or after administration of a first amount of a contrast agent (see, e.g., pars. 12 and 35-37 and 5A, which teach that the first reference representation includes the examination region without or with a first amount of a contrast agent and that first amount is smaller than the second amount, and the second dose is smaller than the third amount),
wherein the second reference representation (RR2) represents the reference region after administration of a second amount of the contrast agent, the second amount being larger than the first amount (see, e.g., pars. 12 and 35-37 and FIG. 5A, which teach that the second reference representation includes the examination region with a second amount of the contrast agent and that first amount is smaller than the second amount, and the second dose is smaller than the third amount),
wherein the third reference representation (RR3) represents the reference region after administration of a third amount of the contrast agent, the third amount being different from the second amount (see, e.g., pars. 12 and 35-37 and FIG. 5A, which teach that the third reference representation includes the examination region with a third amount of the contrast agent and that first amount is smaller than the second amount, and the second dose is smaller than the third amount),
receive from the trained machine-learning model (MT) a synthetic third representation (R3*) of the examination region of the examination object (see, e.g., pars. 105-106*, 3 and 43-44 and FIGS. 3 and 5C, which teach receiving from the trained machine learning model the third representation of the examination region with a third amount of the contrast agent), wherein the synthetic third representation (R3*) represents the reference region after administration of a third amount of the contrast agent, the third amount being different from the second amount (see, e.g., pars. 105-106* and 3 and 43-44 and FIGS. 3 and 5C, which teach that the third representation represents the examination region after administration of the third amount of the contrast agent, the third amount being greater than the second amount); and
cause the output unit to output the synthetic third representation (R3*) and to store it in a data storage medium and to transmit it to a separate computer system (see, e.g., pars. 6 and 44 and FIGS. 3 and 5C, which teach outputting and storing the output and transmitting the output to a user device/medical imaging system).
While Lenga as applied teaches generating, based on the first and the second reference representations and the model parameters, the prediction of the representation (see, e.g., pars. 39-41 and FIGS. 4 and 5B), it does not explicitly teach that wherein the trained machine-learning model (MT) comprises two submodels:
a first submodel (SM1T) and a second submodel (SM2), that the first submodel (SM1T) is configured and has been trained to determine, based on the first reference representation (RR1) and second reference representation (RR2) of an examination region of a reference object, at least one model parameter for the second submodel (SM2) and
wherein the second submodel (SM2) is configured to generate, based on at least one of the first reference representation (RR1) and second reference representation (RR2) and on the at least one model parameter (MP) determined by the first submodel (SM1T), a synthetic third representation (RR3*).
Park in the analogous art teaches that the trained machine-learning model (MT) comprises two submodels (see, e.g., FIG. 2 of Park, which shows the first and second neural networks):
a first submodel (SM1T) and a second submodel (SM2) (see, e.g., FIG. 2 of Park, which shows the first and second neural networks (NNs)),
wherein the first submodel (SM1T) is configured and has been trained to determine, based on the first reference representation (RR1) and second reference representation (RR2) of an examination region of a reference object, at least one model parameter for the second submodel (SM2) (see, e.g., pars. 47-49, 86-90 and 128-130 and FIGS. 2-4 and 14 of Park, which teach that the second NN determines, based on the same input image fed to the first NN, the correction parameter that is inputted to the first NN), and
wherein the second submodel (SM2) is configured to generate, based on at least one of the first reference representation (RR1) and second reference representation (RR2) and on the at least one model parameter (MP) determined by the first submodel (SM1T), a synthetic third representation (RR3*) (see, e.g., pars. 43-47, 73-76 and 125-127 and FIGS. 1-3 and 13 of Park, which teach that the first NN generates, based on the input image and the correction parameter determined by the second NN, an inference image with the enhanced contrast).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Lenga to utilize one model that generate a model parameter to be used by another model as taught by Park because Lenga suggest implementing the trained machine learning model as multiple, distributed systems or devices (see, e.g., pars. 84*, 94*, 9, 34, and 45 of Lenga) and doing so would provide a model parameter that would correct the input image to have optimal image characteristics that are generally preferred (see pars. 81-85 of Park).
For claim 17, Lenga as applied teaches a computer program product comprising a data carrier on which there is stored a computer program that can be loaded into a working memory of a computer system (see, e.g., pars. 79-84* and FIG. 1), wherein the computer program causes the computer system to:
provide a trained machine-learning model (MT) (see, e.g., pars. 94*, 18-23 and 39-41 and FIGS. 3, 4 and 5B, which teach providing a trained machine learning model);
wherein the trained machine-learning model (MT) has been trained on the basis of training data (TD) see, e.g., pars. 10, 18-20 and 22-23 and FIG. 4),
wherein the training data (TD) for each reference object of a plurality of reference objects comprise as target data:
(i) a first reference representation (RR1) of a reference region of the reference object and a second reference representation (RR2) of the reference region of the reference object as input data (see, e.g., pars. 10, 12 and 35-37 and FIGS. 4 and 5A which teach that the training data set includes the first and second reference representations of an examination region of an examination object) and
(ii) a third reference representation (RR3) of the reference region of the reference object (see, e.g., pars. 10, 12 and 35-37 and FIG. 4, which teach that the training data set includes the third reference representation of the examination region of the examination object),
wherein the first reference representation (RR1) represents the reference region without contrast agent or after administration of a first amount of a contrast agent (see, e.g., pars. 12 and 35-37 and 5A, which teaches that the first reference representation includes the examination region without or with a first amount of a contrast agent and that first amount is smaller than the second amount, and the second dose is smaller than the third amount),
wherein the second reference representation (RR2) represents the reference region after administration of a second amount of the contrast agent, the second amount being larger than the first amount (see, e.g., pars. 12 and 35-37 and FIG. 5A, which teaches that the second reference representation includes the examination region with a second amount of the contrast agent and that first amount is smaller than the second amount, and the second dose is smaller than the third amount),
wherein the third reference representation (RR3) represents the reference region after administration of a third amount of the contrast agent, the third amount being different from the second amount (see, e.g., pars. 12 and 35-37 and FIG. 5A, which teaches that the third reference representation includes the examination region with a third amount of the contrast agent and that first amount is smaller than the second amount, and the second dose is smaller than the third amount),
provide a first representation (R1) (see, e.g., pars. 95* and 42-43, and FIGS. 3 and 5C, which teach providing the first representation of an examination region of an examination object), wherein the first representation (R1) represents an examination region of an examination object without contrast agent or after administration of a first amount of a contrast agent (see, e.g., pars. 95* and 42-43 and FIGS. 3 and 5C, which teach providing the first representation without or with a first amount of contrast agent);
provide a second representation (R2) (see, e.g., pars. 100*, 42-43, and FIGS. 3 and 5C, which teach providing a second representation of the examination region of the examination object), wherein the second representation (R2) represents the examination region of the examination object after administration of a second amount of the contrast agent, the second amount being larger than the first amount (see, e.g., pars. 100* and 42-43 and FIGS. 3 and 5C, which teach providing the second representation with a second amount of the contrast agent, the second amount being greater than the first amount);
feed the first representation (R1) and the second representation (R2) to the trained machine-learning model (MT) (see, e.g., pars. 105* and 43 and FIGS. 3 and 5C, which teach providing the first and second representations to the trained machine learning model);
receive from the trained machine-learning model (MT) a synthetic third representation (R3*) of the examination region of the examination object (see, e.g., pars. 105-106*, 3 and 43-44 and FIGS. 3 and 5C, which teach receiving from the trained machine learning model the third representation of the examination region with a third amount of the contrast agent), wherein the synthetic third representation (R3*) represents the reference region after administration of a third amount of the contrast agent, the third amount being different from the second amount (see, e.g., pars. 105-106* and 3 and 43-44 and FIGS. 3 and 5C, which teach that the third representation represents the examination region after administration of the third amount of the contrast agent, the third amount being greater than the second amount); and
output and store the synthetic third representation (R3*) and transmit the synthetic third representation (R3*) to a separate computer system (see, e.g., pars. 6 and 44 and FIGS. 3 and 5C, which teach outputting and storing the output and transmitting the output to a user device/medical imaging system).
While Lenga as applied teaches generating, based on the first and the second reference representations and the model parameters, the prediction of the representation (see, e.g., pars. 39-41 and FIGS. 4 and 5B), it does not explicitly teach that wherein the trained machine-learning model (MT) comprises two submodels:
a first submodel (SM1T) and a second submodel (SM2), that the first submodel (SM1T) is configured and has been trained to determine, based on the first reference representation (RR1) and second reference representation (RR2) of an examination region of a reference object, at least one model parameter for the second submodel (SM2) and
wherein the second submodel (SM2) is configured to generate, based on at least one of the first reference representation (RR1) and second reference representation (RR2) and on the at least one model parameter (MP) determined by the first submodel (SM1T), a synthetic third representation (RR3*).
Park in the analogous art teaches that the trained machine-learning model (MT) comprises two submodels (see, e.g., FIG. 2 of Park, which shows the first and second neural networks):
a first submodel (SM1T) and a second submodel (SM2) (see, e.g., FIG. 2 of Park, which shows the first and second neural networks (NNs)),
wherein the first submodel (SM1T) is configured and has been trained to determine, based on the first reference representation (RR1) and second reference representation (RR2) of an examination region of a reference object, at least one model parameter for the second submodel (SM2) (see, e.g., pars. 47-49, 86-90 and 128-130 and FIGS. 2-4 and 14 of Park, which teach that the second NN determines, based on the same input image fed to the first NN, the correction parameter that is inputted to the first NN), and
wherein the second submodel (SM2) is configured to generate, based on at least one of the first reference representation (RR1) and second reference representation (RR2) and on the at least one model parameter (MP) determined by the first submodel (SM1T), a synthetic third representation (RR3*) (see, e.g., pars. 43-47, 73-76 and 125-127 and FIGS. 1-3 and 13 of Park, which teach that the first NN generates, based on the input image and the correction parameter determined by the second NN, an inference image with the enhanced contrast).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Lenga to utilize one model that generate a model parameter to be used by another model as taught by Park because Lenga suggest implementing the trained machine learning model as multiple, distributed systems or devices (see, e.g., pars. 84*, 94*, 9, 34, and 45 of Lenga) and doing so would provide a model parameter that would correct the input image to have optimal image characteristics that are generally preferred (see pars. 81-85 of Park).
For claim 4, while Lenga as applied does not explicitly teach, Park in the analogous art teaches that the first submodel (SM1T) is an artificial neural network or includes such a network (see, e.g., FIG. 2, which shows the first and second neural networks (NNs)),
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Lenga to utilize a neural network model that generate a model parameter as taught by Park because Lenga suggest implementing the trained machine learning model as multiple, distributed systems or devices (see, e.g., pars. 84*, 94*, 9, 34, and 45 of Lenga) and doing so would provide a model parameter that is corrected without user intervention (see pars. 82-83 of Park).
For claim 5, while Lenga as applied does not explicitly teach, Park in the analogous art teaches that the second submodel (SM2) is a mechanistic model (see, e.g., pars. 84-85 and 138-140 of Park, which teach that the first NN is trained on a relationship that its output, e.g., an inference image, changes correspondingly to its input, e.g., correction parameters; the examiner finds such a relationship to indicate that the first NN is a deterministic model).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Lenga to utilize a mechanistic/deterministic model as taught by Park because Lenga suggest implementing the trained machine learning model as multiple, distributed systems or devices (see, e.g., pars. 84*, 94*, 9, 34, and 45 of Lenga) and doing so would yield predictable results of making it more predictable to adjust the correction parameter for desired output (see MPEP 2143(I)(D)).
For claim 6, Lenga in view of Park teaches that model parameters of the second submodel (SM2) are not trainable parameters (see, e.g., par. 86 of Park, which teach that the parameters in the first NN may be fixed).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Lenga to utilize a fixed model as taught by Park because Lenga suggest implementing the trained machine learning model as multiple, distributed systems or devices (see, e.g., pars. 84*, 94*, 9, 34, and 45 of Lenga) and doing so would yield predictable results of being able to train each NN separately (see par. 86 of Park and MPEP 2143(I)(D)).
For claim 7, Lenga in view of Park teaches that the machine-learning model (MT) is differentiable (see, e.g., par. 86 of Park, which teach that the NNs are differentiable) and the training takes place in an end-to-end manner (see, e.g., par. 86-90 and FIG. 4 of Park, which teach that the NNs may be trained in end to end manner).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Lenga to utilize a fixed model as taught by Park because Lenga suggest implementing the trained machine learning model as multiple, distributed systems or devices (see, e.g., pars. 84*, 94*, 9, 34, and 45 of Lenga) and doing so would yield predictable results of being able to train each NN separately (see par. 86 of Park and MPEP 2143(I)(D)).
For claim 10, Lenga as applied teaches that the trained machine-learning model (MT) has been trained (see, e.g., pars. 94*, 18-23, and 39-41 and FIGS. 3, 4, 5B, which teach providing a trained machine learning model) and wherein the training of the trained machine-learning model (MT) comprises:
providing the training data (TD) (see, e.g., pars. 10, 18-20, 22-23, and 35-40 and FIGS. 4 and 5A);
providing a machine-learning model (M) (see, e.g., pars. 10, 18-20, 22-23, and 35-40 and FIGS. 4 and 5B, which teach providing a predictive machine learning model to be trained);
training the machine-learning model (M) (see, e.g., FIGS. 4 and 5B), wherein the training comprises:
feeding a first reference representation (RR1) and a second reference representation (RR2) of a reference region of a reference object to the first submodel (SM1) (see, e.g., pars. 39-41 and FIG. 5B, which teach inputting the first and second representations of an examination region of an examination object to the trained machine learning model),
feeding the at least one model parameter (MP) that has been determined and the first reference representation (RR1) and the second reference representation (RR2) to the second submodel (SM2) (see, e.g., pars. 39-41 and FIGS. 4 and 5B, which teach inputting the first and the second reference representations and the model parameters to the machine learning model),
wherein the second submodel (SM2) is configured to generate, based on at least one of the first reference representation (RR1) and the second reference representation (RR2) and on the model parameter (MP) determined by the first submodel (SM1), a synthetic third reference representation (RR3*) (see, e.g., pars. 39-41 and FIGS. 4 and 5B, which teach generating, based on the first and the second reference representations and the model parameters, the third reference representation);
receiving of the synthetic third reference representation (RR3*) generated by the second submodel (SM2) (see, e.g., pars. 18-20 and 39-41 and FIGS. 4 and 5B, which teach receiving the prediction of the representation of the examination region with a third amount of the contrast agent);
quantifying the differences between the synthetic third reference representation (RR3*) and the third reference representation (RR3) of the training data (see, e.g., pars. 39-41 and FIGS. 4 and 5B, which teach determining a deviation between the prediction of the representation and the third representation);
reducing the differences by modifying model parameters of the first submodel (SM1) (see, e.g., pars. 39-41 and FIGS. 4 and 5B, which teach reducing the deviation to a defined minimum); and
storing the trained machine-learning model (MT) and using the trained machine-learning model (MT) to generate a synthetic representation (R3*) of an examination region of an examination object (see, e.g., pars. 42-44 and FIGS. 3 and 5C, which teaches providing the trained machine learning model for predictive purposes).
Lenga as applied does not explicitly teach that the first submodel (SM1) is configured to determine, based on the first reference representation (RR1), on the second reference representation (RR2) and on model parameters, at least one model parameter for the second submodel (SM2) and receiving and feeding the at least one model parameter determined by the first submodel to the second submodel.
Park in the analogous art teaches that that the first submodel (SM1T) is configured to determine, based on the first reference representation (RR1), on the second reference representation (RR2) and on model parameters, at least one model parameter for the second submodel (SM2) (see, e.g., pars. 47-49, 86-90 and 128-130 and FIGS. 2-4 and 14 of Park, which teach that the second NN determines, based on the same input image fed to the first NN, the correction parameter that is inputted to the first NN) and receiving and feeding the at least one model parameter determined by the first submodel to the second submodel (see, e.g., pars. 43-47, 73-76 and 125-127 and FIGS. 1-3 and 13 of Park, which teach that the first NN generates, based on the input image and the correction parameter determined by the second NN, an inference image with the enhanced contrast).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Lenga to utilize one model that generate a model parameter to be used by another model as taught by Park because Lenga suggest implementing the trained machine learning model as multiple, distributed systems or devices (see, e.g., pars. 84*, 94*, 9, 34, and 45 of Lenga) and doing so would provide a model parameter that would correct the input image to have optimal image characteristics that are generally preferred (see pars. 81-85 of Park).
For claim 12, Lenga in view of Park teaches that the examination object is a human and the examination region is a part of the human, wherein each reference object is a human and the reference region of each such reference object is a part of the reference object and wherein the reference region of each such reference object and the examination region are the same part of the human (see, e.g., par. 95-96*, 100-101*, 27, and 35 of Lenga, which teach that the examination object is a human being, the examination region is of the examination object).
For claim 13, Lenga in view of Park teaches that the first representation (R1) and the second representation (R2) and also each reference representation (RR1, RR2, RR3) of one such reference object is a result of a radiological examination, wherein the radiological examination is an MRI examination or a CT examination and the contrast agent is an MRI contrast agent or a CT contrast agent (see, e.g., pars. 3-6*, 81*, 96*, 97*, and 101* of Lenga, which teach that all of the representations are results of the radiological examination, such as MRI and CT and the contrast agent is an agent for the radiological examination ).
Claim(s) 8 and 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lenga in view of Park and further in view of us patent application publication no. 2025/0191139 to Tamir et al. (hereinafter Tamir).
For claim 8, while Lenga in view of Park does not explicitly teach, Tamir in the analogous art teaches the machine-learning model (MT) includes a third submodel (SM3T), wherein the third submodel (SM3T) is configured and has been trained to generate, based on the synthetic third representation (R3*) generated by the second submodel (SM2), a corrected third representation (R3*C) (see, e.g., pars. 81-87 and FIG. 12 of Tamir, which teach using an additional model that has been trained to generate a corrected, e.g., denoised, image based on the contrast enhanced image generated by another model) ,
wherein the step of receiving from the trained machine-learning model (M) a synthetic third representation (R3*) of the examination region of the examination object comprises:
receiving from the trained machine-learning model (MT) the corrected third representation (R3*C) of the examination region of the examination object (see, e.g., pars. 81-87 and FIG. 12 of Tamir, which teach receiving the contrast enhanced image generated from the trained contrast boost model),
wherein the corrected third representation (R3*C) represents the reference region after administration of the third amount of the contrast agent (see, e.g., pars. 81-87 and FIG. 12 of Tamir, which teach that the contrast enhanced image mimics an image acquired with increased dose of contrast agent compared to the full-dose level) and
wherein the step of outputting and storing the synthetic third representation (R3*) and transmitting the synthetic third representation (R3*) to a separate computer system comprises:
outputting and storing the corrected third representation (R3*C) and transmitting the corrected third representation (R3*C) to a separate computer system (see, e.g., pars. 81-87 and FIG. 12 of Tamir, which teaches outputting the denoised image as the final output image).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Lenga in view of Park to utilize an additional denoise model to correct the third representation as taught by Tamir because Lenga suggest implementing the trained machine learning model as multiple, distributed systems or devices (see, e.g., pars. 84*, 94*, 9, 34, and 45 of Lenga) and doing so would yield predictable results of improving the quality of the final output, e.g., greater SNR, higher resolution, or less aliasing (see par. 82 of Tamir and MPEP 2143(I)(D)).
For claim 9, while Lenga in view of Park does not explicitly teach, Tamir in the analogous art teaches that the third submodel (SM3T) is a trained machine-learning model and wherein the third submodel (SM3T) is an artificial neural network or includes such a network (see, e.g., pars. 64 and 82-84 of Tamir, which teach that the denoise model may be a trained deep learning model, such as a neural network).
Claim(s) 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lenga in view of Park and further in view of Us patent application publication no. 2025/0049405 to Bone et al. (hereinafter Bone).
For claim 14, Lenga in view of Park teaches that the first amount is equal to zero (see, e.g., pars. 13 and 36 of Lenga), the second amount is smaller than a standard amount of the contrast agent or equal to the standard amount of the contrast agent (see, e.g., pars. 12-13 of Lenga, which teach that the second amount is smaller than the third amount, which may be a standard amount). Lenga in view of Park does not explicitly teach that the third amount is larger than the standard amount of the contrast agent.
In the analogous art, Bone teaches generating a synthetic contrast image which is representation of a body part after an injection of a super dose, a dose higher than the standard dose (see, e.g., pars. 68-76 of Bone).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Lenga in view of Park to synthesize a representation with a dosage higher than the standard amount as taught by Bone because doing so would provide allow obtaining a high quality/dose image without having to administer a high dose that could be dangerous to a patient (see par. 69 of Bone).
Allowable Subject Matter
Claims 2, 3 and 11 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
In regard to claim 2, when considered as a whole, prior art of record fails to disclose or render obvious, alone or in combination:
“wherein the second submodel (SM2) comprises:
subtracting the first representation (R1) of the examination region of the examination object from the second representation (R2) of the examination region of the examination object, wherein a difference (R2−R1) is formed;
multiplying the difference (R2−R1) by a gain factor (α), wherein the gain factor (α) is a positive or negative real number and wherein the at least one model parameter (MP) determined by the first submodel (SM1T) includes the gain factor (α); and
adding the difference (R2−R1) multiplied by the gain factor (α) to the first representation (R1) or the second representation (R2).”
In regard to claim 3, when considered as a whole, prior art of record fails to disclose or render obvious, alone or in combination:
“wherein the first representation (R1) and the second representation (R2) are representations (R1F, R2F) of the examination region of the examination object in frequency space, wherein the second submodel (SM2) comprises:
subtracting the first representation (R1F) of the examination region of the examination object from the second representation (R2F) of the examination region of the examination object, wherein a difference (R2F−R1F) is formed;
multiplying the difference (R2F−R1F) by a frequency-dependent weight function (WF), wherein a weighted difference (R2F− R1F)W is formed, wherein the at least one model parameter (MP) determined by the first submodel (SM1T) includes one or more parameters of the frequency-dependent weight function (WF);
multiplying the weighted difference (R2F−R1F)W by a gain factor (α), wherein the gain factor (α) is a positive or negative real number and wherein the at least one model parameter (MP) determined by the first submodel (SM1T) includes the gain factor (α); and
adding the weighted difference (R2F−R1F)W multiplied by the gain factor (α) to the first representation (R1F) or the second representation (R2F).”
In regard to claim 11, it depends on objected claim 3. Therefore, by virtue of its dependency, claim 11 is also indicated as objected subject matter.
Additional Citations
The following table lists several references that are relevant to the subject matter claimed and disclosed in this Application. The references are not relied on by the Examiner, but are provided to assist the Applicant in responding to this Office action.
Citation
Relevance
Muhamedrahimov et al. (us pat. pub. 2022/0318567)
Describes a method, comprising: accessing medical images of subjects, depicting contrast phases of contrast administered to the respective subject, accessing for a first subset of the medical images, metadata indicating a respective contrast phase, wherein a second subset of the medical images are unassociated with metadata, mapping each respective contrast phase of the contrast phases to a respective time interval indicating estimated amount of time from a start of contrast administration to time of capture of the respective medical image, creating a training dataset, by labelling images of the first subset with a label indicating the respective time interval, and including the second subset as non-labelled images, and training the ML model using the training dataset for generating an outcome of a target time interval indicating estimated amount of time from the start of contrast administration, in response to an input of a target medical image.
Zarachuk et al. (us pat. pub. 2021/0241458)
Describes techniques to enhance image quality of diagnostic imaging modalities using a lower dose of contrast than is currently possible. This enables new opportunities for improving the value of medical imaging. In addition to MRI, the techniques are generally applicable to a variety of diagnostic imaging techniques including angiography, fluoroscopy, computed tomography (CT), and ultrasound.
Lee et al. (us pat. pub. 2023/0386193)
Describes a method of processing an image by using a neural network model. In one embodiment, the method includes obtaining an image captured via an image sensor, identifying a shooting context of the image, selecting a neural network model included in at least one of an image reconstruction module or an image correction module according to the shooting context, and processing the image by using the selected neural network model.
Table 1
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See table 1 and form 892.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WOO RHIM whose telephone number is (571)272-6560. The examiner can normally be reached Mon - Fri 9:30 am - 6:00 pm et.
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, Henok Shiferaw can be reached at 571-272-4637. 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.
/WOO C RHIM/Examiner, Art Unit 2676
Prosecution Insights