DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Remark(s)
Applicant's amendment filed May 07th, 2026 have been fully entered and considered. Applicant’s amendment to the claims have overcome each and every claim objection, 112f interpretation, 112a and 112b rejections previously set forth in the Non-Final Office Action mailed on February 11th, 2026. Regarding the arguments to the previous 101 and prior art rejections, the examiner respectfully finds the arguments to be non-persuasive. Accordingly, this action is made final.
Status of Claims
Claims 1, 5-6 and 10 are pending, claims 1, 5-6 and 10 have has been amended, claims 2-4 and 7-9 have been canceled. Claims 1, 5-6 and 10 remains rejected.
Response to Argument(s)
101 rejection:
In pages 8-11 of the Applicants’ remarks, the Applicants argue that the amended claims, particularly the independent claim 1 carry features that cannot practically be performed in the human mind, and not performed under mathematical concept. Moreover, the features of the claim such as “preprocessing the measured spectrum image, wherein the preprocessing includes filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image” which the human mind cannot perform the filing or inverting of pixel regions of a two-dimensional image and input of the resulting image into a convolution neural network for training, which is a specific recited combination of convolutional layer and fully connected layer in claims 5 and 10.
Furthermore, the Applicants argue that the claims integrate into a practical application, under Step 2A, Prong 2, by identifying a specific technical problem, of conventional methods in the field of electrochemical spectrum analysis would discard the two-dimensional morphological information contained in the spectrum curve, reducing prediction accuracy, while the instant invention help preprocess the image by filling or inverting a partial area and inputting the preprocessed image into a convolutional neural network that learns the full two-dimensional morphology of the spectrum, which produce a measurable improvement in prediction accuracy. See the instant specification’s Pars. [0029-0032]. Moreover, the Applicants believe the claim uses a particular machine of an apparatus comprising a memory, an image processor, and a processor, the processor being configured to input the preprocessed measured spectrum image as image data into a convolutional neural network which is a specific machine-learning architecture. The Applicants further state that the claim has a particular transformation of data which involves transforming the spectrum-image pixel data, such as shown in FIGS. 7c-7f.
In addition, the Applicants further state that the claims recite significantly more, including additional elements that are not well-understood, routine, or conventional. With the specific combination of filling or inverting a partial area of a space divided by a spectrum line to transform the measured spectrum image, etc., as recited in claim 1. As set forth to be not taught by none of the proposed prior arts as the Applicants believe. Therefore, the claims recited non-conventional method.
Examiner’s reply:
The examiner respectfully disagrees with the Applicants’ arguments and find them to be incommensurate with the scope of the claims. The Applicants are respectfully reminded that the claims are construed based on BRI (broadest reasonable interpretation) scope of the claims. Therefore, the Applicants’ arguments on that the preprocessing is to filling or inverting pixel regions of a 2D image is not reflected in the claims, nowhere in the claims have recited such as pixels, two-dimension features, nevertheless to perform filling or inverting on them. Moreover, based on BRI, the claim only has one instant scope between the options of “filling” or “inverting”, for instance that the claim performs only filling, it would just be understood as filling in an area of an image divided by a line, which by observation and evaluation the human mind can observe an image and its information such as a spectrum line dividing an image (which is a given observable information already present in the image, the human mind simply perform observing and evaluation) and fill in the area by performing high-level of generality of “filling” such as, mentally filling in missing information that can be evaluated by the human mind. Furthermore, for Step 2A, Prong 2 and Step 2B, the Applicants brought in support from the instant specification, which, under BRI, cannot be imported to be the instant scope of the claims, the claims have to be construed based on its own language. Nowhere in the claims, perform analyzing of morphological information, indication of measurable improvement that can avoid reduction in prediction accuracy. The convolutional network is recited at high level of generality to include well-known components such as convolutional layer, fully connected layers without further limiting how the convolutional layers functions to process the features of the image to output a specific result used for a practical outcome/solution. Therefore, there is no specific machine, but generic, well-known routine, generic neural network with generic components. The steps of predicting a feature of test sample of the analyte is a mental process that the human mind can perform by observing the spectrum image and predict a feature of test sample, which is totally doable by a human mind, therefore, by implementing this abstract idea using a generic neural network, is just a mere attempt to monopolize the use of abstract ideas using generic neural network, without meaningful limits to the claimed invention. Furthermore, the Applicants state that, under Step 2B, the claims perform specific transformation of data, this is incommensurate with the scope of the claims, nowhere in the claims recite a transformation step or specific steps that one person or ordinary skill in the art would understand a specific more than conventional method of transformation data. The Applicants pointed out the transformation being the spectrum-image pixel data undergo a linear graph containing a large empty background region being transformed into a structurally different image in which the region delineated by the spectrum line is filled or inverted, altering the pixel composition and spatial structure of the image, however, none of these features are explicitly reflected and recited in the claims.
The Applicants further state that, under Step 2B, the claims recited significantly more, however, the examiner finds the prior arts to still teach the claimed limitations, see the Response below, according to the premise of the Applicants’ argument that since the prior arts alone or in combination does not teach the limitations then the claims recite more than conventional. However, the Applicants are reminded that the ground for 101 rejection is separate from the prior art rejections, 101 rejection requires utility and practicability and patent eligibly and worthiness of the claimed invention, and that the requirements of the claims reciting significantly, need to indicate additional elements that, otherwise, to show that these additional elements give the claim and its abstract ideas considered significantly more as the requirements of step 2B.
102 rejection:
In pages 12-14 of the remarks, the Applicants argue that the proposed Perkins does teach or suggest the limitations of the claims:
“measured spectrum image,” “analysis model,” and related limitations of claims 1 and 6.
In support of the above argument, the Applicants assert that Perkins fails to disclose inputting the preprocessed measured spectrum image as image data into a convolutional neural network, of the limitation of “inputting the preprocessed measured spectrum image as image data into a convolutional neural network and learning the preprocessed measured spectrum image with the convolutional neural network.” Since Perkins acquires a set of discrete scalar optical-response values and input those values into a MLP. The set of discrete scalar numerical values is categorically different from a two-dimensional “measured spectrum image” processed as image data. Furthermore, Perkins’ MLP is lack of convolutional layers and does not operate on two-dimensional pixel data.
Furthermore, the Applicants asserts that Perkins fails to disclose the claimed filling or inverting preprocessing, as of the limitation “preprocessing the measured spectrum image, wherein the preprocessing includes filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image”. Since Perkins’ “preprocessing step” concerns about a quantitative calibration model of the neural network, that is a statistical calibration of the neural network’s numerical parameters using known-sample data, does not describe or suggest any image-domain transformation such as filling or inverting a partial area of a space as claimed.
Therefore, the Applicants believe that anticipation is not established.
Examiner’s reply:
The examiner respectfully disagrees with the Applicants’ arguments and find them to be incommensurate with the scope of the claims. The Applicants are respectfully reminded that the claims are construed based on BRI (broadest reasonable interpretation) in light of the specification. Therefore, the examiner finds the Applicants’ arguments to not be commensurate with the BRI scope of the claims, such as nowhere in the claim recite that the claimed “measured spectrum image” processing such as its feature of filling or inverting a partial area include processing of 2D pixel information, nevertheless the claim recites “filling or inverting” therefore, only one of these option is the instant scope of the claim since “or” indicates a selection, in the instance of “filling” is selected, then the claim can be read as involve a filling in a space in an image, which has been brought upon in a 103 rejections, wherein Boardman teaches such preprocessing limitation, see Response below. Moreover, nowhere in the claims recite a transformation process, transformation of data is a specific concept in the field of image processing that can further fall within specific transformation categories, the claims do not reflect this idea, filling of data is merely a data compensation process not necessarily or merely an indication of a specific transformation technique, this technique is therefore not included in the claims.
Furthermore, Perkins teaches a trained neural network, in Perkins’ Col. 9, lines 48-67, of “using the trained neural network by testing three unknown samples…the optical or spectral responses of the ten ICE components…may then be inputted into or otherwise applied to the classification model or trained neural network…FIG. 7 illustrates the fluid type index outputs for each of the three unknown fluid samples as corresponding to its respective optical response”, furthermore, the optical response can be shown as graphical illustrations 300 of FIG. 3, which is an image. therefore, what is FIG. 3 but an optical/spectral response image? that covers the scope of the claimed “measured spectrum image,” and what is a trained neural network being input the optical responses but measured spectrum image information/data? The term “optical” also indicates visual, optical or image features/data. Furthermore, the feature of the claim wherein the trained neural network being a convolutional area is mapped to a 103 rejection as taught by the proposed Kura, see Response below.
Even though, Perkins’ preprocessing is further modified to teach the claimed preprocessing as taught by Boardman.
103 rejection:
In pages 14-18 of the remarks, the Applicants argue that the proposed Perkins, Boardman and Kura, alone or in combination, does not teach or suggest the features of the claims such as for the independent claims 1 and 6:
“filling or inverting a partial area of the space divided by a spectrum line in the spectrum image;
Inputting the preprocessed measured spectrum image as image data into a convolutional neural network”
In support of the above argument, the Applicants assert that Boardman discloses analyzing hyperspectral imaging-spectrometer data using a N-dimensional geometry approach and a Mixture-Tuned Matched Filtering algorithm. Therefore, Boardman does not employ any artificial intelligence model, neural network, or machine-learning classifier. The preprocessing operation of Boardman is a statistical normalization of spectral-band numerical values, determination of a shift difference based on row and column shift differences, which is different to the claimed “filling or inverting preprocessing of the spectrum image”. With the combination of Perkins with Boardman, the resulting numerical spectral vectors through the MLP of Perkins and/or the MTMF filter of Boardman would not input a preprocessed spectrum image as image data into a convolutional neural network.
Moreover, Boardman’s noise-variance normalization is not the same as the claimed “filling-or-inverting” preprocessing. Boardman’s normalization does not modify the two-dimensional spatial pixel composition of any image which is what done by the claimed “filling-or-inverting” involving spatial image-domain transformation that substantively alters the pixel structure of a two-dimensional graph, as illustrated in the instant specification’s FIGS. 7c-7f.
Furthermore, there is no motivation to combine Perkins and Boardman. Since Perkin is directed to fluid-type classification of hydrocarbons in oil-and-gas downhole measurements using ICE-based optical computing devices and an MLP neural network, when Boardman is directed to remote-sensing analysis of hyperspectral imaging-spectrometer data using a statistical filtering algorithm, which are two different problems being addressed. A person of ordinary skill in the art would have had no apparent reason to consult Boardman while working with Perkins system, therefore, is lack of motivation to combine them.
Thus, the proposed combination rests on impermissible hindsight, that the combination of Perkins with Boardman to reach the claimed filling-or-inverting operation appears to rely on the present application itself as a roadmap.
In regards, to claims 5 and 10, the Applicants argue that the proposed Perkins and Kura, alone or in combination, does not teach or suggest the features of the claims:
“inputting the preprocessed measured spectrum image as image data into a convolutional neural network;
filling-or-inverting preprocessing of the spectrum image”
In support of the above argument, the Applicants state that Kura discloses convolutional layer and fully-connected layer architecture, however, cannot reasonable be cited for disclosing the claimed “obtaining and inputting a measured electrochemical-spectrum image as image data into a convolutional neural network in connection with analyte analysis” as recited in claims 1 and 6, or the claimed “filling-or-inverting preprocessing operation.”
Examiner’s reply:
The examiner respectfully disagrees with the Applicants’ arguments and find them to be incommensurate with the scope of the claims, the Applicants are respectfully remined that the claims are construed based on BRI in light of the specification. Therefore, the examiner finds the proposed Perkins, Boardman and Kura, in combination to teach the BRI scope of the claims.
Regarding the limitations of “filling or inverting a partial area of the space divided by a spectrum line in the spectrum image”, which was previously mapped in the previously presented claims 4 of the analogous limitation which is now amended into the independent claims 1 and 6; wherein Boardman was brought in to teach “wherein the step of preprocessing of the spectrum image includes filling or inverting a partial area of the space divided by a spectrum line in the spectrum image” wherein Boardman discloses, in section III.A, 1st par. of “preprocessing are noise whitening and data decorrelation…accomplished by estimating and applying an affine transform to the original data…for quantitative estimation of detection probability and spectral contrast measures” indicating a preprocessing step on spectral measures which are analogous to the optical/spectral measures of Perkins’s preprocessing, wherein Boardman’s section III.A, 3rd par. discloses “the shift difference uses the mean of a row shift difference and a column shift difference to estimate the noise in the data…allowing for the extra column and row associated with the shifting. Each band of N is the average of the row shift difference and the column shift difference of the same band of D” which indicates the process of the preprocessing of noise whitening in section III.A, 1st par.; moreover, the examiner finds Boardman’s shift difference to be analogous to the recited “a partial area of the space” wherein the shift difference here is determined according to an average of the row shift difference and the column shift difference of the same band which uses the mean of a row shift difference and a column shift difference, and the band here is analogous to the recited “spectrum line” which is a data of the spectrum image, therefore, analogous to the recited “spectrum line of the measured spectrum image” (which is the spectral measures as already explained the mapping to Perkins not to support that Boardman’s spectral measure would also fall under the scope of spectrum image), such as shown in equation 3:
PNG
media_image1.png
134
608
media_image1.png
Greyscale
Boardman’s equation 3 showing noise estimation.
Wherein the noise estimation is obtained by a division of information/data of the band, therefore, what else equation 3 represents but a noise obtained (the shift difference or the partial area of the space, as discussed previously) by a division equation pertaining to the mean value of a band (in other words, a division by a band) of divided by a spectrum line as claimed. Moreover, the mean value of the band, mean value of the shift differences is also a middle value or the dividing value between all the shift differences, therefore, the mean value of a band is analogous to the recited “divided by a spectrum line” as claimed, based on BRI. Moreover, the noise estimation is obtained so that it can be corrected, through a process such as disclosed in Boardman’s section III.A, 6th-7th pars., of “the next step in data preprocessing is the calculation of the…estimated noise covariance matrix….finally, each resulting band is divided by the square root of the associated noise eigenvalue, normalizing the noise variance to unity in each band. These processes produce zero-mean noise-whitened data, as shown in the following equation 4” indicating a zero-mean noise whitening which is compensating the shift difference calculated which is analogous to the recited “filling the partial area” as claimed, based on BRI.
Therefore, it would have been obvious for one person of ordinary skill in the art at the time the instant invention was filed to have an optical/spectral measure (including image data/information) to perform a preprocessing on the spectral image as taught in Perkins, moreover, Perkins’ preprocessing of spectral measures can be modified to include preprocessing to correct noise of the spectral measure data including calculating shift differences of a band according to a division calculation to determine the noise estimated, so that can be normalized and corrected to normalize the noise variance to unity in each band and produce zero-mean noise-whitened data. Thus, in order to decorrelate the data and provide accurate final output of spectral measure data through a preprocessing step so that the data can be used efficiently in subsequent processing (Boardman’s section III.A, 8th-9th paragraphs). Wherein Perkins and Boardman both share the same field of endeavor of preprocessing spectral measure data.
Therefore, the examiner finds Boardman to teach the BRI of the claimed limitation as discussed, moreover, the examiner finds the Applicants’ argument, regarding the discussed limitation, to be incommensurate with the claimed invention, since there is nowhere in the claims concerning about a 2D pixel data and a transformation technique of these data, the teachings of the instant specification cannot be imported to be the instant scope of the claims, claims are construed based on BRI of its own language.
Moreover, regarding Kura, Kura was brought in by the examiner to teach the limitation of “feature-mapping the inputted spectrum image to a convolutional neural network (CNN); and connecting the mapped data to a fully connected layer” which was previously presented claim 5, now have been amended into the independent claims 1 and 6 as “inputting the preprocessed measured spectrum image as image data into a convolutional neural network” which has changed the scope of the claim and narrow down the scope, however, the examiner still finds the proposed Kura to teach this amended features. Such as in Kura’s section 4.5.2, of page 46, which discloses “input consists of images…CNN…a fully connected layer of neurons in CNN”, moreover, section 4.6.1, of page 49, discloses, “a CNN model was computed for the same spectral data” indicating that the input to the CNN model include spectral images (analogous to Perkins’ spectral measure and Boardman’s spectral measure, and the claimed measured spectrum image); moreover, the spectral image correspond to spectral measures according to Kura’s page 18, 1st Par., and the input is into a neural network model of a CNN including fully connected layer, which falls with the scope of the claimed limitation.
Therefore, it would have been obvious for one person of ordinary skill in the art at the time the invention was made to have a neural network that can take input of spectral measure, moreover, the data input can be first preprocessed as taught in Perkins, moreover, Perkin’s preprocessing can be modified to include filling-or-inverting process such as discussed above, and Perkin’s neural network can include a convolutional neural network with fully connected layer that takes input of spectral measures as spectral images. Thus, in order to perform data processing using convolutional neural network to perform iterative training that can minimize output error and perform classification tasks on spectral images more accurately (Kura’s section 4.5.2, of page 47).
In response to applicant’s argument that there is no teaching, suggestion, or motivation to combine the references, the examiner recognizes that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR International Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007). In this case, as discussed above.
Therefore, the prior arts rejection remain.
Claim Objections
Claim 1 objected to because of the following informalities:
“comprising the steps of:” in lines 1-2, should be read as “comprising of:” since there is no antecedent basis for “the steps of”. Appropriate correction is required to avoid indefiniteness 112b issue.
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 limitation(s) 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 use the word “means” or “step” but are nonetheless not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph because the claim limitation(s) recite(s) sufficient structure, materials, or acts to entirely perform the recited function.
Claim 6, recite(s) limitation(s) that use words like “means” (or “step”) or similar terms with functional language and do invoke 35 U.S.C. 112(f):
Claim 6; recites the limitation, “an image processor configured to” [Line 5].
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.
After a careful analysis, as disclosed above, and a careful review of the specification the following limitation in claim 6;
(i) “an image processor” the specification does not disclose sufficient support for structure, material or act for the recited feature to perform the recited function, thus have no sufficient structure, material and/or act for the recited image processor to perform its corresponding recited function.
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 § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 6 along with its dependent claims are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
Claim 6’s limitations “an image processor configured to…“ in line 5:
Claim 6 respectively invokes 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. However, the written description fails to disclose the corresponding structure, material, or acts for performing the entire claimed function and to clearly link the structure, material, or acts to the function. The specification is devoid of adequate structure to perform the claimed functions. The specification does not provide sufficient details such that one of the ordinary skill in the art would understand which structure performed(s) the claimed function.
Therefore, the claim is indefinite and is rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph.
Applicant may:
(a) Amend the claim so that the claim limitation will no longer be interpreted as a limitation under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph;
(b) Amend the written description of the specification such that it expressly recites what structure, material, or acts perform the entire claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(c) Amend the written description of the specification such that it clearly links the structure, material, or acts disclosed therein to the function recited in the claim, without introducing any new matter (35 U.S.C. 132(a)).
If applicant is of the opinion that the written description of the specification already implicitly or inherently discloses the corresponding structure, material, or acts and clearly links them to the function so that one of ordinary skill in the art would recognize what structure, material, or acts perform the claimed function, applicant should clarify the record by either:
(a) Amending the written description of the specification such that it expressly recites the corresponding structure, material, or acts for performing the claimed function and clearly links or associates the structure, material, or acts to the claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(b) Stating on the record what the corresponding structure, material, or acts, which are implicitly or inherently set forth in the written description of the specification, perform the claimed function. For more information, see 37 CFR 1.75(d) and MPEP §§ 608.01(o) and 2181.
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.
Claim 6 along with its dependent claim 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 pre-AIA the inventor(s), at the time the application was filed, had possession of the claimed invention. As described above, the disclosure does not provide adequate structure to perform the claimed function in the recited limitation.
Claim 6; recites the limitation, “an image processor configured to,” [Line 5].
The specification does not demonstrate that applicant has made an invention that achieves the claimed function because the invention is not described with sufficient detail such that one of ordinary skill in the art can reasonably conclude that the inventor had possession of the claimed invention.
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 and 6 are rejected under 35 U.S.C. 101
Regarding Independent Claim 1:
Step 1 Analysis: Claim 1 is directed to a process/method, which falls within one of the four statutory categories.
Step 2A Prong 1 Analysis: Claim 1 recites, in part:
“…filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image;
creating an analysis model…; and
predicting a feature of a test sample of the analyte….”
The limitations as drafted, are processes that, under broadest reasonable interpretation, covers the performance of the limitation in the mind which falls within the “Mental Processes/Mathematical Concept” grouping of abstract ideas. The limitations of:
“filling or inverting a partial area of a space….in the measured spectrum image” which recites “or” therefore, only one of the option is the instant scope of the claim, “filling” is selected to be the instant scope of the claim, therefore, a human mind can observe and evaluate an image and its data to perform fill in an area mentally;
“creating an analysis model” is, under BRI, understood to be any analysis performance, including a mental analysis of a target through observation and evaluation.
“predicting…analyte” is a mental process that a human mind can observe some observable data/information and make a prediction through evaluation.
Notes: under MPEP 2106.04(a)(2)(III), mental process (thinking) “can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011): "methods which can be performed mentally, or which are the equivalent of human mental work, are unpatentable abstract ideas the ‘basic tools of scientific and technological work’ that are open to all." (citing Gottschalk v. Benson, 409 U.S. 63, 175 USPQ 673 [1972]). See also Mayo Collaborative Servs. v. Prometheus Labs. Inc., 566 U.S. 66, 71, 101 USPQ2d 1961, 1965 ("mental processes and abstract intellectual concepts are not patentable, as they are the basic tools of scientific and technological work’" (quoting Benson, 409 U.S. at 67, 175 USPQ at 675).
The courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that require a human to use a physical aid (e.g., pen and paper or a slide rule) to perform the claim limitation. See, e.g., Benson, 409 U.S. at 67, 65, 175 USPQ at 674-75, 674; Synopsys, Inc. v. Mentor Graphics Corp., 839 F.3d 1138, 1139, 120 USPQ2d 1473, 1474 (Fed. Cir. 2016).
Nor do the courts distinguish between claims that recite mental processes performed by humans and claims that recite mental processes performed on a computer, generic circuit or device, or the likes. See " Versata Dev. Group v. SAP Am., Inc., 793 F.3d 1306, 1335, 115 USPQ2d 1681, 1702 (Fed. Cir. 2015). See also Intellectual Ventures I LLC v. Symantec Corp., 838 F.3d 1307, 1318, 120 USPQ2d 1353, 1360 (Fed. Cir. 2016) (‘with the exception of generic computer-implemented steps, there is nothing in the claims themselves that foreclose them from being performed by a human, mentally or with pen and paper.’’).
Because both product/device and process claims may recite a "mental process", the phrase "mental processes" should be understood as referring to the type of abstract idea, and not to the statutory category of the claim. The courts have identified numerous product claims as reciting mental process-type abstract ideas, for instance the product claims to computer systems and computer-readable media in Versata Dev. Group. v. SAP Am., Inc., 793 F.3d 1306, 115 USPQ2d 1681 (Fed. Cir. 2015).
Accordingly, the claim recites an abstract idea.
Step 2A Prong 2 Analysis: This judicial exception is not integrated into a practical application. particular, the claim recites the following additional element(s) –
“obtaining a measured spectrum image of an analyte;
preprocessing the measured spectrum image…;
…by inputting the preprocessed measured spectrum image as image data into a convolutional neural network and learning the preprocessed measured spectrum image with the convolutional neural network;
by inputting a measured spectrum image of the test sample to the analysis model”
The additional elements of “obtaining a measured spectrum image of an analyte,” “by inputting the preprocessed measured spectrum image as image data into a convolutional neural network” and “by inputting a measured spectrum image of the test sample to the analysis model” include steps of insignificant extra-solution/post-solution activities of data gathering, data transmitting, etc. [acquiring data/information, transmitting data/info., outputting data/information, displaying data/info., converting data/info., generating data/info., etc.]. moreover, the recited analysis model here is not recited as a neural network, therefore, it can be understood to be any analysis performance as discussed above in Step 2A Prong 1. The additional elements of “preprocessing the measured spectrum image…” is a pre-solution activity being insignificant, preprocessing of data recited at no more than mere preprocessing on data to obtain some preprocessed data, “learning the preprocessed measured spectrum image with the convolutional neural network” is also an insignificant pre-solution activity of learning a model with input image, which is well-known in the field of machine learning, this is a step of learning recited at high level of generality, well-known conventional routine in the art.
The additional element of “a convolutional neural network” includes generic neural network/machine learning model(s)/classifier recited at high level of generality without limiting further, in details, on how the neural network/machine learning model(s) function to arrive at such output, these additional elements are recited as a mere attempt to implement the abstract ideas/judicial exceptions using generic neural network/machine learning models.
Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim as a whole is directed to an abstract idea.. Please see MPEP §2106.04.(d).III.C.
Step 2B Analysis: there are no additional elements, such as for these additional elements as indicated above, that amount to significantly more than the judicial exception. Please see MPEP §2106.05. The claim is directed to an abstract idea.
For all of the foregoing reasons, claim 1 does not comply with the requirements of 35 USC 101.
Regarding independent claim 6:
Regarding the independent claim 6, the claim recites analogous to the independent claim 1 hence, analyzed under the same approach to be 101 ineligible. Claim 6 further recites additional elements of “an apparatus,” “a memory,” and “store a measured spectrum image of an analyte”, “an image processor configured to preprocess the measured spectrum image” and “a processor configured to” which includes generic well-known computer and computer elements recited at high level of generality, and the additional element of “storing a measure spectrum image” is an insignificant extra-solution activity of data gathering, storing data/information.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 5-6 and 10 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by David L. Perkins et. al. (“US 10,684,388 B2” hereinafter as “Perkins”) in view of Joseph W. Boardman et. al. (“An Analysis of Imaging Spectrometer Data Using N-Dimensional Geometry and a Mixture-Tuned Matches Filtering Approach, Nov. 2011, IEEE Transactions on Geoscience and Remote Sensing, Vol. 49, No. 11” hereinafter as ” Boardman”) and Vinusha Reddy Kura (“Development and Analysis of Plasmonic Nanomaterials for Biosensors, 2018, University of California, Irvine, Master of Science in Engineering” hereinafter as “Kura”).
Regarding claim 1, Perkins explicitly teaches a method of analyzing a measured spectrum image comprising the steps of (title and abstract): obtaining a measured spectrum image (Col. 6, lines 64-67, discloses obtaining an optical response input of the spectrum response [spectrum image] such as shown in FIG. 2 2, moreover Col. 8, lines 5-24, further discloses the input into the neural network includes optical response input such as 300 of FIG. 3, hence, indicates an obtaining of a measured spectrum image such as 300 of FIG. 3) of an analyte (Col. 6, lines 15-17, discloses “related to characteristic or analyte of interest”); preprocessing the measured spectrum image (Col. 13, lines 55-67, discloses “after applying the API gravity quantitative calibration model of the neural network” is analogous to a preprocessing step); creating an analysis model by inputting the preprocessed measured spectrum image as image data into a machine learning model (Col. 11, lines 1-10, discloses “the neural network structure may also use a plurality of ICE components and their respective optical response as inputs” indicating taking input of the measured spectrum image into a machine learning model including optical data [spectrum image]; moreover, Col. 11, lines 11-19, discloses “the neural network may be configured to quantify a sample substance in terms of fluid concentration” indicating an analysis model) and learning the preprocessed measured spectrum image with the machine learning model (Col. 9, lines 48-67, discloses training different neural networks [analysis model as claimed] to predict different unknown substances based on the input of the optical response by learning the optical response input of the different substances); and predicting a feature of a test sample of the analyte by inputting the measured spectrum image of the test sample to the analysis model (Col. 9, lines 48-67, further discloses the neural network model).
However, Perkins does not explicitly disclose wherein the preprocessing includes filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image; the machine learning model being a convolutional neural network.
In the same field of spectrum image processing (title and abstract, Boardman) Boardman discloses wherein the preprocessing includes filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image (section III.A, 1st par., discloses preprocessing on the spectrum image, and section III.A, 3rd par., discloses by determining a shift difference based on the row shift difference and the column shift difference of the same band of D [a spectrum line as claimed] to correct the difference by normalizing the noise variance to unity in each band according to equation 4 as disclosed in 6th par., which is analogous to filing a partial area of the space divided by the spectrum line since the shift difference in the band D has a partial area to be even out by normalizing to correct the shift; Therefore, it would have been obvious for one person of ordinary skill in the art at the time the instant invention was filed to have an optical/spectral measure [including image data/information] to perform a preprocessing on the spectral image as taught in Perkins, moreover, Perkins’ preprocessing of spectral measures can be modified to include preprocessing to correct noise of the spectral measure data including calculating shift differences of a band according to a division calculation to determine the noise estimated, so that can be normalized and corrected to normalize the noise variance to unity in each band and produce zero-mean noise-whitened data. Thus in order to decorrelate the data and provide accurate final output of spectral measure data through a preprocessing step so that the data can be used efficiently in subsequent processing [Boardman’s section III.A, 8th-9th paragraphs]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Perkins of a method of analyzing a measured spectrum image comprising the steps of obtaining a measured spectrum image of an analyte; preprocessing the measured spectrum image. Moreover, Perkins’ preprocessing can be modified to include filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image as taught in Boardman.
Such a modification is the result of combing prior art elements. Perkins and Boardman share the same field of endeavor of preprocessing of spectral measure data. The motivation for the proposed modification would have been to have a method of analyzing a measured spectrum image comprising the steps of obtaining a measured spectrum image of an analyte; preprocessing the measured spectrum image, wherein the preprocessing include filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image. Thus, in order to decorrelate the data and provide accurate final output of spectral measure data through a preprocessing step so that the data can be used efficiently in subsequent processing (Boardman’s section III.A, 8th-9th paragraphs).
However, Perkins in view of Boardman, in combination, does not explicitly teach the machine learning model being a convolutional neural network.
In the same field of spectrum image processing (abstract, Kura) Kura explicitly teaches the machine learning model being a convolutional neural network (section 4.5.2, of page 46, discloses the convolution layer for the analysis model includes ReLU layer to perform feature mapping of a convolutional neural network to process the spectrum image for feature mapping; section 4.5.2, of page 46, discloses the full connection for fully connected layer of neurons in the CNN to connect the mapped data of the ReLU Layer; Therefore, it would have been obvious for one person of ordinary skill in the art at the time the invention was made to have a neural network that can take input of spectral measure, moreover, the data input can be first preprocessed as taught in Perkins, moreover, Perkin’s preprocessing can be modified to include filling-or-inverting process such as discussed above, and Perkin’s neural network can include a convolutional neural network with fully connected layer that takes input of spectral measures as spectral images. Thus, in order to perform data processing using convolutional neural network to perform iterative training that can minimize output error and perform classification tasks on spectral images more accurately [Kura’s section 4.5.2, of page 47]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Perkins in view of Boardman of a method of analyzing a measured spectrum image comprising the steps of obtaining a measured spectrum image of an analyte; preprocessing the measured spectrum image; creating an analysis model by inputting the preprocessed measured spectrum image as image data into a machine learning model and learning the preprocessed measured spectrum image with the machine learning model as taught in Perkins, and the preprocessing can be modified to include filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image as taught in Boardman. Moreover, Perkins’ machine learning can be modified to be a convolutional neural network as taught in Kura.
Such a modification is the result of combing prior art elements. Perkins and Boardman and Kura share the same field of endeavor of preprocessing of spectral measure data. The motivation for the proposed modification would have been to have a method of analyzing a measured spectrum image comprising the steps of obtaining a measured spectrum image of an analyte; preprocessing the measured spectrum image, wherein the preprocessing include filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image, creating an analysis model by inputting the preprocessed measured spectrum image as image data into a convolutional neural network and learning the preprocessed measured spectrum image with the convolutional neural network. Thus in order to perform data processing using convolutional neural network to perform iterative training that can minimize output error and perform classification tasks on spectral images more accurately (Kura’s section 4.5.2, of page 47).
Regarding claim 5, Perkins in view of Boardman and Kura explicitly teaches the method of claim 1, wherein the step of creating the analysis model.
However, Perkins in view of Boardmen does not explicitly disclose includes feature-mapping the preprocessed spectrum image through a convolutional layer of the a convolutional neural network and connecting data feature by the convolutional layer to a fully connected layer of the convolutional neural network.
In the same field of spectrum image processing (abstract, Kura) Kura discloses includes feature-mapping the preprocessed spectrum image through a convolutional layer of the a convolutional neural network (section 4.5.2, of page 46, discloses the convolution layer for the analysis model includes ReLU layer to perform feature mapping of a convolutional neural network to process the spectrum image for feature mapping); and connecting data feature by the convolutional layer to a fully connected layer of the convolutional neural network (section 4.5.2, of page 46, discloses the full connection for fully connected layer of neurons in the CNN to connect the mapped data of the ReLU Layer Therefore, it would have been obvious for one person of ordinary skill in the art at the time the invention was made to have a neural network that can take input of spectral measure, moreover, the data input can be first preprocessed as taught in Perkins, moreover, Perkin’s preprocessing can be modified to include filling-or-inverting process such as discussed above, and Perkin’s neural network can include a convolutional neural network with fully connected layer that takes input of spectral measures as spectral images. Thus in order to perform data processing using convolutional neural network to perform iterative training that can minimize output error and perform classification tasks on spectral images more accurately [Kura’s section 4.5.2, of page 47]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Perkins in view of Boardman of a method of analyzing a measured spectrum image comprising the steps of obtaining a measured spectrum image of an analyte; preprocessing the measured spectrum image; creating an analysis model by inputting the preprocessed measured spectrum image as image data into a machine learning model and learning the preprocessed measured spectrum image with the machine learning model as taught in Perkins, and the preprocessing can be modified to include filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image as taught in Boardman. Moreover, Perkins’ machine learning can be modified to be a convolutional neural network includes feature-mapping the preprocessed spectrum image through a convolutional layer of the a convolutional neural network; and connecting data feature by the convolutional layer to a fully connected layer of the convolutional neural network as taught in Kura.
Such a modification is the result of combing prior art elements. Perkins and Boardman and Kura share the same field of endeavor of preprocessing of spectral measure data. The motivation for the proposed modification would have been to have a method of analyzing a measured spectrum image comprising the steps of obtaining a measured spectrum image of an analyte; preprocessing the measured spectrum image, wherein the preprocessing include filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image, creating an analysis model by inputting the preprocessed measured spectrum image as image data into a convolutional neural network and learning the preprocessed measured spectrum image with the convolutional neural network includes feature-mapping the preprocessed spectrum image through a convolutional layer of the a convolutional neural network; and connecting data feature by the convolutional layer to a fully connected layer of the convolutional neural network. Thus in order to perform data processing using convolutional neural network to perform iterative training that can minimize output error and perform classification tasks on spectral images more accurately (Kura’s section 4.5.2, of page 47).
(best understood based on the 112f interpretation above) Regarding claim 6, Perkins explicitly teaches an apparatus for analyzing a measured spectrum image, the apparatus comprising: (title and abstract): a memory configured to store a measured spectrum image (Col. 6, lines 64-67, discloses obtaining an optical response input of the spectrum response [spectrum image] such as shown in FIG. 2 2, moreover Col. 8, lines 5-24, further discloses the input into the neural network includes optical response input such as 300 of FIG. 3, hence, indicates an obtaining of a measured spectrum image such as 300 of FIG. 3) of an analyte (Col. 6, lines 15-17, discloses “related to characteristic or analyte of interest”); an image processor configured to preprocess the measured spectrum image (Col. 13, lines 55-67, discloses “after applying the API gravity quantitative calibration model of the neural network” is analogous to a preprocessing step), a processor configured to (Col. 15, lines 7-29, discloses “algorithms described herein can include a processor configured to execute one or more sequences of instructions, programming instances, or code stored on a non-transitory, computer-readable medium”): create an analysis model by inputting the preprocessed measured spectrum image as image data into a machine learning model (Col. 11, lines 1-10, discloses “the neural network structure may also use a plurality of ICE components and their respective optical response as inputs” indicating taking input of the measured spectrum image into a machine learning model including optical data [spectrum image]; moreover, Col. 11, lines 11-19, discloses “the neural network may be configured to quantify a sample substance in terms of fluid concentration” indicating an analysis model) and learning the preprocessed measured spectrum image with the machine learning model (Col. 9, lines 48-67, discloses training different neural networks [analysis model as claimed] to predict different unknown substances based on the input of the optical response by learning the optical response input of the different substances); predict a feature of a test sample of the analyte by inputting the measured spectrum image of the test sample to the analysis model (Col. 9, lines 48-67, further discloses the neural network model).
However, Perkins does not explicitly disclose wherein the preprocessing includes filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image; the machine learning model being a convolutional neural network.
In the same field of spectrum image processing (title and abstract, Boardman) Boardman discloses wherein the preprocessing includes filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image (section III.A, 1st par., discloses preprocessing on the spectrum image, and section III.A, 3rd par., discloses by determining a shift difference based on the row shift difference and the column shift difference of the same band of D [a spectrum line as claimed] to correct the difference by normalizing the noise variance to unity in each band according to equation 4 as disclosed in 6th par., which is analogous to filing a partial area of the space divided by the spectrum line since the shift difference in the band D has a partial area to be even out by normalizing to correct the shift; Therefore, it would have been obvious for one person of ordinary skill in the art at the time the instant invention was filed to have an optical/spectral measure [including image data/information] to perform a preprocessing on the spectral image as taught in Perkins, moreover, Perkins’ preprocessing of spectral measures can be modified to include preprocessing to correct noise of the spectral measure data including calculating shift differences of a band according to a division calculation to determine the noise estimated, so that can be normalized and corrected to normalize the noise variance to unity in each band and produce zero-mean noise-whitened data. Thus in order to decorrelate the data and provide accurate final output of spectral measure data through a preprocessing step so that the data can be used efficiently in subsequent processing [Boardman’s section III.A, 8th-9th paragraphs]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Perkins of a method of analyzing a measured spectrum image comprising the steps of obtaining a measured spectrum image of an analyte; preprocessing the measured spectrum image. Moreover, Perkins’ preprocessing can be modified to include filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image as taught in Boardman.
Such a modification is the result of combing prior art elements. Perkins and Boardman share the same field of endeavor of preprocessing of spectral measure data. The motivation for the proposed modification would have been to have a method of analyzing a measured spectrum image comprising the steps of obtaining a measured spectrum image of an analyte; preprocessing the measured spectrum image, wherein the preprocessing include filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image. Thus in order to decorrelate the data and provide accurate final output of spectral measure data through a preprocessing step so that the data can be used efficiently in subsequent processing (Boardman’s section III.A, 8th-9th paragraphs).
However, Perkins in view of Boardman, in combination, does not explicitly teach the machine learning model being a convolutional neural network.
In the same field of spectrum image processing (abstract, Kura) Kura explicitly teaches the machine learning model being a convolutional neural network (section 4.5.2, of page 46, discloses the convolution layer for the analysis model includes ReLU layer to perform feature mapping of a convolutional neural network to process the spectrum image for feature mapping; section 4.5.2, of page 46, discloses the full connection for fully connected layer of neurons in the CNN to connect the mapped data of the ReLU Layer; Therefore, it would have been obvious for one person of ordinary skill in the art at the time the invention was made to have a neural network that can take input of spectral measure, moreover, the data input can be first preprocessed as taught in Perkins, moreover, Perkin’s preprocessing can be modified to include filling-or-inverting process such as discussed above, and Perkin’s neural network can include a convolutional neural network with fully connected layer that takes input of spectral measures as spectral images. Thus, in order to perform data processing using convolutional neural network to perform iterative training that can minimize output error and perform classification tasks on spectral images more accurately [Kura’s section 4.5.2, of page 47]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Perkins in view of Boardman of a method of analyzing a measured spectrum image comprising the steps of obtaining a measured spectrum image of an analyte; preprocessing the measured spectrum image; creating an analysis model by inputting the preprocessed measured spectrum image as image data into a machine learning model and learning the preprocessed measured spectrum image with the machine learning model as taught in Perkins, and the preprocessing can be modified to include filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image as taught in Boardman. Moreover, Perkins’ machine learning can be modified to be a convolutional neural network as taught in Kura.
Such a modification is the result of combing prior art elements. Perkins and Boardman and Kura share the same field of endeavor of preprocessing of spectral measure data. The motivation for the proposed modification would have been to have a method of analyzing a measured spectrum image comprising the steps of obtaining a measured spectrum image of an analyte; preprocessing the measured spectrum image, wherein the preprocessing include filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image, creating an analysis model by inputting the preprocessed measured spectrum image as image data into a convolutional neural network and learning the preprocessed measured spectrum image with the convolutional neural network. Thus in order to perform data processing using convolutional neural network to perform iterative training that can minimize output error and perform classification tasks on spectral images more accurately (Kura’s section 4.5.2, of page 47).
Regarding claim 10, Perkins in view of Boardman and Kura explicitly teaches the apparatus of claim 6, wherein the step of creating the analysis model.
However, Perkins in view of Boardman does not explicitly teach includes feature-mapping the preprocessed spectrum image through a convolutional layer of the a convolutional neural network and connecting data feature by the convolutional layer to a fully connected layer of the convolutional neural network.
In the same field of spectrum image processing (abstract, Kura) Kura discloses includes feature-mapping the preprocessed spectrum image through a convolutional layer of the a convolutional neural network (section 4.5.2, of page 46, discloses the convolution layer for the analysis model includes ReLU layer to perform feature mapping of a convolutional neural network to process the spectrum image for feature mapping); and connecting data feature by the convolutional layer to a fully connected layer of the convolutional neural network (section 4.5.2, of page 46, discloses the full connection for fully connected layer of neurons in the CNN to connect the mapped data of the ReLU Layer Therefore, it would have been obvious for one person of ordinary skill in the art at the time the invention was made to have a neural network that can take input of spectral measure, moreover, the data input can be first preprocessed as taught in Perkins, moreover, Perkin’s preprocessing can be modified to include filling-or-inverting process such as discussed above, and Perkin’s neural network can include a convolutional neural network with fully connected layer that takes input of spectral measures as spectral images. Thus in order to perform data processing using convolutional neural network to perform iterative training that can minimize output error and perform classification tasks on spectral images more accurately [Kura’s section 4.5.2, of page 47]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing data of the claimed invention was made to combine the teachings of Perkins in view of Boardman of a method of analyzing a measured spectrum image comprising the steps of obtaining a measured spectrum image of an analyte; preprocessing the measured spectrum image; creating an analysis model by inputting the preprocessed measured spectrum image as image data into a machine learning model and learning the preprocessed measured spectrum image with the machine learning model as taught in Perkins, and the preprocessing can be modified to include filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image as taught in Boardman. Moreover, Perkins’ machine learning can be modified to be a convolutional neural network includes feature-mapping the preprocessed spectrum image through a convolutional layer of the a convolutional neural network; and connecting data feature by the convolutional layer to a fully connected layer of the convolutional neural network as taught in Kura.
Such a modification is the result of combing prior art elements. Perkins and Boardman and Kura share the same field of endeavor of preprocessing of spectral measure data. The motivation for the proposed modification would have been to have a method of analyzing a measured spectrum image comprising the steps of obtaining a measured spectrum image of an analyte; preprocessing the measured spectrum image, wherein the preprocessing include filling or inverting a partial area of a space divided by a spectrum line in the measured spectrum image, creating an analysis model by inputting the preprocessed measured spectrum image as image data into a convolutional neural network and learning the preprocessed measured spectrum image with the convolutional neural network includes feature-mapping the preprocessed spectrum image through a convolutional layer of the a convolutional neural network; and connecting data feature by the convolutional layer to a fully connected layer of the convolutional neural network. Thus in order to perform data processing using convolutional neural network to perform iterative training that can minimize output error and perform classification tasks on spectral images more accurately (Kura’s section 4.5.2, of page 47).
Pertinent Prior Art(s)
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
DIEM; Max et. al., “US 20180180537 A1”, discloses spectral imaging to provide a medical diagnosis includes obtaining spectral and visual images of biological specimens and registering the images to detect cell abnormalities, pre-cancerous cells, and cancerous cells. This method eliminates the bias and unreliability of diagnoses that is inherent in standard histopathological and other spectral methods. In addition, a method for correcting confounding spectral contributions that are frequently observed in microscopically acquired infrared spectra of cells and tissue includes performing a phase correction on the spectral data. This phase correction method may be used to correct various types of absorption spectra that are contaminated by reflective components. Wherein Par. [0067] discloses “an infrared spectral image created from artificial neural network analysis of an infrared dataset collected prior to staining the tissue”.
Griffin; Christopher E. et. al., “US 7136518 B2”, discloses displaying diagnostic results obtained from a tissue sample. In general, the invention assigns tissue-class probability values to discrete regions of a patient sample, and creates an overlay for displaying the results. The overlay facilitates display of the tissue class probabilities in a way that reflects the diagnostic relevance of the data. For example, methods of the invention comprise applying filtering and color-blending techniques in order to facilitate display of diagnostic results.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PHUONG HAU CAI whose telephone number is (571)272-9424. The examiner can normally be reached M-F 8:30 am - 5:00pm.
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, Chineyere Wills-Burns can be reached at (571) 272-9752. 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.
/PHUONG HAU CAI/Examiner, Art Unit 2673
/CHINEYERE WILLS-BURNS/Supervisory Patent Examiner, Art Unit 2673
Prosecution Insights