DETAILED ACTION
Status of Claims
This Office action is responsive to communications filed on 2026-03-03. Claim(s) 3, 6, 15, 21, and 23 was/were cancelled. Claim(s) 1-2, 4-5, 7-14, 16-20, and 22 is/are pending and are examined herein.
Claim(s) 1-2, 4-5, 7-9, and 11-13 is/are objected to.
Claim(s) 10, 13, 16, and 22 is/are rejected under 35 USC 112(b).
Claim(s) 10 and 22 is/are rejected under 35 USC 103.
Notice of Pre-AIA or AIA Status
The present application, filed on or after 2013-03-16, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
Regarding 35 USC 112(b), the applicant asserts that they have “amended the claims to address the alleged issues” [remarks, page 9] but the examiner respectfully disagrees. While the claims resolve some of the issues of indefiniteness described in the previous Office action, they have not adequately addressed the substance of certain issues as noted below.
Regarding 35 USC 112(a), the rejections are rendered moot by the applicant’s cancellations.
Regarding 35 USC 101, the rejections are withdrawn upon further consideration of the amended claims viewed a whole.
Regarding 35 USC 103:
Regarding claims 1 and 14, the applicant argues that the prior art made of record does not disclose the specific configuration of normalizations that appear in the claims, namely, the first set of convolutional neural networks explicitly using a logarithmic normalization while the second set of convolutional neural networks explicitly does not. While van den Berg discloses logarithmic normalizations together with both its advantages and its disadvantages (cf. rejection of claim 7 in previous Office actions), the examiner agrees that the references do not disclose the specific configuration of elements that appear in the pending independent claims. The rejections are consequently withdrawn in view of the claims regarded as a whole.
Regarding claim 10, the applicant indicates merely that the claim “recites features that are similar… to the features recited in amended independent claim 1” and that “independent claim 10 is also patentable for at least the same reasons as those submitted for claim 1” [remarks, pages 21-22]. However, independent claim 10 does not include the relevant claim elements that appear in claim 1 and regarding which the applicant has submitted remarks. It does not recite two different sets of convolutional neural networks, leave alone two different types of normalization used for each set. The rejections are consequently maintained with only minor updates in view of the applicant’s amendments.
Claim Objections
Claim(s) 1-2, 4-5, 7-9, and 11-13 is/are objected to because of the following informalities:
Claim 1 step b) recites to obtain a transformed spectrum being a normalized histogram but this is ungrammatical. It should be “to obtain a transformed spectrum, the transformed spectrum being a normalized histogram” for grammaticality. Dependent claims 2, 4-5, 7-9, and 11-13 inherit the objection.
Claim 1 step e) recites to obtain a second transformed spectrum being a second normalized histogram but this is ungrammatical. It should be “to obtain a second transformed spectrum, the second transformed spectrum being a second normalized histogram” for grammaticality. Dependent claims 2, 4-5, 7-9, and 11-13 inherit the objection.
Claim 1 step g) recites to individually determine a signal proportion associated with said group of one or more emitting species [emphasis added] but the claim already recites “a signal proportion” and “said group of one or more emitting species” lacks antecedent basis. The examiner suggests “to individually determine the signal proportion of the associated group of one or more emitting species” for proper antecedent basis and consistent nomenclature. Dependent claims 2, 4-5, 7-9, and 11-13 inherit the objection.
Appropriate correction is required.
Claim Rejections - 35 USC 112(b)
The following is a quotation of 35 USC 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 USC 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(s) 10, 13, 16, and 22 is/are rejected under 35 USC 112(b) or 35 USC 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 applications subject to pre-AIA 35 USC 112, the applicant), regards as the invention.
Claim 13 is indefinite for at least the following reasons:
It recites the at least two groups of one or more emitting species emitting X- or gamma ray radiation but the intended antecedent of this phrase is not clear. The parent claim recites a group of emitting species associated to each convolutional neural network of the first set, as well as a group of emitting species associated to each convolutional neural network of the second set, and it is not clear whether “the at least two groups” of this dependent claim refers to the groups associated to the convolutional neural networks of the first set, or to the groups associated to the convolutional neural networks of the second set, or to all of them together.
Claim 10 is indefinite for at least the following reasons:
It recites a spectrum calculated as a function of group or groups of one or more emitting species determined as being present in the scene [emphasis added] but the underlined phrase is both ungrammatical (due to a lack of article before “group”) and has ambiguous antecedent basis. There is a plurality of groups of one or more emitting species (one associated to each of the at least two convolutional neural networks of the first set) and it is not clear whether this phrase refers to those associated groups of one or more emitting species (and if so, it is not clear which of those groups) or to some other group or groups. For the purpose of compact prosecution, the claim is interpreted broadly as encompassing any function of any emitting species.
Dependent claim 22 inherits the rejections.
Claim 16 is indefinite for at least the following reasons:
It recites a spectrum calculated as a function of a group or groups of one or more emitting species determined as being present in the scene [emphasis added] but the underlined phrase lacks antecedent basis. There is a plurality of groups of one or more emitting species (one associated to each of the at least two convolutional neural networks of the first set) and it is not clear whether this refers to one of those associated groups of one or more emitting species (and if so, it is not clear which one of those groups) or to some other group. For the purpose of compact prosecution, the claim is interpreted broadly as encompassing any function of any emitting species.
Claim Rejections - 35 USC 103
The following is a quotation of 35 USC 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) 10 and 22 is/are rejected under 35 USC 103 as being unpatentable over GONG Pin et al. (CN107229787A, published 2017-10-03; hereafter, “Gong”) in view of Vaishali TIDAKE et al. (Multi-label Classification: A Survey, published 2018; hereafter, “Tidake”), Gordon GILMORE (Practical Gamma-Ray Spectrometry, published 2008; hereafter, “Gilmore”), Daniel MAIER et al. (Energy calibration via correlation, published 2015-11-14; hereafter, “Maier”), and Adrian NUNN et al. (US20210012917A1, effectively filed 2018-03-28; hereafter, “Nunn”).
Claim 10
Gong discloses:
applying to the acquired energy spectrum a first data transformation operation including at least one normalization to obtain a transformed spectrum; ([Gong, 0042-0044]: Gong discloses performing a transformation [Gong, 0042-0044] which includes a “normaliz[ation]” [Gong, 0044] before the spectrum is input into a deep learning model.)
supplying the transformed spectrum as input of a first set comprising [at least two] convolutional neural networks, each convolutional neural network of said first set being associated with a respective and distinct group of one or more emitting species to be identified, ([Gong, 0046-0047]: Gong discloses using the normalized spectrum as input to a deep learning model “to predict the composition of nuclides” [Gong, 0046] and further discloses that the model may be a “convolutional neural network” [Gong, 0047]. In preparation for the combination to follow, the examiner notes that this convolutional neural network is performing a multi-label classification task, with one label for each emitting species which may be identified.)
each convolutional neural network of the first set comprising an output layer and a layer, said layer comprising a plurality of neurons, ([Gong, 0020, 0059]: This merely recites structure which is present in any neural network. Gong specifically discloses that the network may have “an input layer, a hidden layer, and an output layer and the number of the hidden layers is 1-50” [Gong, 0020] and further indicates “128 neurons in the input layer, 1024 neurons in the hidden layer, and 9 neurons in the output layer” [Gong, 0059]. The output layer of Gong maps to the “output layer” of the claim, and any of the layers indicated in Gong can map the “layer” of the claim.)
each convolution neural network of the first set trained to individually identify the associated group of one more emitting species, ([Gong, 0046-0047]: As noted above, Gong discloses using a convolutional neural network to predict the composition of nuclides.)
and each convolution neural network of the first set having at least one output; ([Gong, 0020, 0046-0047, 0059]: As noted above, the neural network of Gong predicts the composition of nuclides [Gong, 0046-0047] and has an “output layer” with “9 neurons in the output layer” [Gong, 0020, 0059]. Moreover, “the 9 output neurons respectively indicate the presence or absence of the 9 nuclides” [Gong, 0059]. In other words, the values at the output neurons map to the “at least one output” of the claim.)
and for each convolutional neural network of the first set, determining whether the associated group of one or more emitting species is present in the scene as a function of said at least one output; ([Gong, 0046-0047, 0059]: As noted above, Gong discloses using the normalized spectrum as input to neural network whose output is a predicted composition of nuclides [Gong, 0046].)
Gong might not distinctly disclose:
A method for calibrating a spectrometric detector, the method implemented by a signal processing circuit, the method comprising the following steps: acquiring a series of events, each event being associated with a physical quantity representative of an energy value of an X- or gamma photon detected by said spectrometric detector;
and converting said series of events into an energy spectrum of the X- or gamma radiation by application of a calibration function dependent on an initial set of calibration parameters of the spectrometric detector stored in a table;
[a first set comprising] at least two [convolutional neural networks, each convolutional neural network of said first set being associated with a respective and distinct group of one or more emitting species to be identified]
the method also comprising a step of determination of values of calibration parameters which maximize a correlation function between said energy spectrum and a spectrum calculated as a function of group or groups of one or more emitting species determined as being present in the scene and updating the table with said values of calibration parameters.
Tidake is also in the field machine learning. Moreover, Gong in view of Tidake discloses:
[a first set comprising] at least two [convolutional neural networks, each convolutional neural network of said first set being associated with a respective and distinct group of one or more emitting species to be identified] ([Tidake, section 3.1.1]: Tidake discloses the technique of binary relevance (BR) for addressing multi-label classification by training a plurality of separate binary classifiers, one for each label. In other words, the combination of Gong and Tidake replaces the single convolutional neural network performing multi-label classification as disclosed by Gong with at least two convolutional neural networks, each one performing the single binary classification task of identifying one emitting species.)
Before the effective filing date of the invention, it would have been obvious to a person of ordinary skill in the art to combine the spectrum analysis method using a convolutional neural network as disclosed by Gong with the binary relevance (BR) technique as disclosed by Tidake, because BR “has many good features also. As it treats each label independently, the classifier model can be easily updated dynamically if the label set is appended with a new label and scales linearly with the number labels. Also it is beneficial to handle active data. The classifier model can run in parallel multiple classifiers of different labels. Due to so many features and ease of design, BR is very popular and widely used” [Tidake, section 3.1.1]. Therefore, the combination would inherit all of these advantages and result in a more effective and efficient system overall.
Gong in view of Tidake might not distinctly disclose:
A method for calibrating a spectrometric detector, the method implemented by a signal processing circuit, the method comprising the following steps: acquiring a series of events, each event being associated with a physical quantity representative of an energy value of an X- or gamma photon detected by said spectrometric detector;
and converting said series of events into an energy spectrum of the X- or gamma radiation by application of a calibration function dependent on an initial set of calibration parameters of the spectrometric detector stored in a table;
the method also comprising a step of determination of values of calibration parameters which maximize a correlation function between said energy spectrum and a spectrum calculated as a function of group or groups of one or more emitting species determined as being present in the scene and updating the table with said values of calibration parameters.
Gilmore is also in the field of gamma-ray spectrometry. Moreover, Gong in view of Tidake and Gilmore discloses:
A method for calibrating a spectrometric detector, ([Gilmore, section 7.7]: Gilmore discloses performing efficiency calibration [Gilmore, section 7.7 first paragraph].) the method implemented by a signal processing circuit, ([Gilmore, section 9.1]: Gilmore discloses that “it is almost certain nowadays that a computer will be used to perform spectrum analysis” [Gilmore, section 9.1 first paragraph]. The computer maps to the “signal processing circuit” recited by the claim.)
the method comprising the following steps: acquiring a series of events, each event being associated with a physical quantity representative of an energy value of an X- or gamma photon detected by said spectrometric detector; ([Gilmore, section 2.1 paragraph beginning “The instrumental detection”]: Gilmore discloses that “[g]amma-ray detection depends upon… interactions [of gamma photons] which transfer the gamma-ray energy to electrons within the detector material”. These interactions of gamma photons map to the “series of events” recited by the claim, and the energy transferred by the interactions maps to the “energy value” recited by the claim.)
and converting said series of events into an energy spectrum of the X- or gamma radiation by application of a calibration function dependent on an initial set of calibration parameters of the spectrometric detector ([Gilmore, section 7.7]: Gilmore discloses performing efficiency calibration [Gilmore, section 7.7 first paragraph]. The method uses parameters such as “the geometrical arrangement of the sample, detector, and shielding” [Gilmore, section 7.7 paragraph beginning “Consider all we know”] in order to perform Monte Carlo simulations and “create a spectrum that will be comparable with an actual measured spectrum” [Gilmore, section 7.7 two paragraphs beginning “Consider all we know”].)
the method also comprising a step of determination of values of calibration parameters which [maximize a correlation function] between said energy spectrum and a spectrum calculated as a function of group or groups of one or more emitting species determined as being present in the scene and updating [the table] with said values of calibration parameters. ([Gilmore, section 7.7]: Gilmore moreover discloses “optimizing parameters… by comparing simulation and practice” [Gilmore, section 7.7 paragraph beginning “More fundamental”]. The actual measured spectrum of Gilmore the “spectrum” of the claim, and the spectrum created by simulation is the “spectrum calculated as a function of the group of one or more emitting species” of the claim as best understood by the examiner in view of the 112(b) rejections. The optimized parameters are the “values of calibration parameters” of the claim.)
Before the effective filing date of the invention, it would have been obvious to a person of ordinary skill in the art to combine the spectrum analysis method of Gong in view of Tidake with the use of computers as disclosed by Gilmore because using a computer would significantly speed up the spectrum analysis process, as well as with calibration as disclosed by Gilmore, because “calibration allows the gamma-ray spectrum to be interpreted in terms of energy rather than channel number or voltage, and amount of radionuclide, rather than the number of pulses” [Gilmore, chapter 7 first paragraph], thereby improving interpretability of the data that is fed into the neural networks and resulting in a more effective system overall.
Gong in view of Tidake and Gilmore might not distinctly disclose:
[calibration parameters of the spectrometric detector] stored in a table; … [updating] the table
[determination of values of calibration parameters] which maximize a correlation function [between said energy spectrum and a spectrum calculated as a function of group or groups of one or more emitting species determined as being present in the scene]
Maier is in the field of gamma ray spectrometry. Like Gilmore, it describes a method for “energy calibration” [Maier, abstract] involving a comparison between a “synthetic energy spectrum” and an “observed pulse-height spectrum” [Maier, abstract]. Moreover, Gong in view of Tidake, Gilmore, and Maier discloses:
[determination of values of calibration parameters] which maximize a correlation function [between said energy spectrum and a spectrum calculated as a function of group or groups of one or more emitting species determined as being present in the scene] ([Maier, section 2]: Maier discloses computing a “correlation factor C(P)” [Maier, section 2 and equation (2)]. It moreover discloses finding the parameters P^* which approach the maximum correlation C_{max}, taking these to be the “optimal parameter set” [Maier, section 2 and equation (3)]. In other words, the optimal parameters P^* are the “values of calibration parameters which maximize a correlation function” of the claim.)
Before the effective filing date of the invention, it would have been obvious to a person of ordinary skill in the art to combine the spectrum analysis method of Gong in view of Tidake and Gilmore with the calibration method of Maier because it “enables a fast and accurate calibration that can be used to monitor the spectroscopic properties of a detector system in near realtime” [Maier, abstract], thereby resulting in a more efficient and effective system overall.
Gong in view of Tidake, Gilmore, and Maier might not distinctly disclose:
[calibration parameters of the spectrometric detector] stored in a table; … [updating] the table
Nunn is in the field of gamma-ray spectrometry. Moreover, Gong in view of Tidake, Gilmore, Maier, and Nunn discloses:
[calibration parameters of the spectrometric detector] stored in a table; … [updating] the table ([Nunn, 0286]: Nunn discloses that “calibration parameter may be in the form of one or more values, and may be stored in an equation, table, or other data structure” [Nunn, 0286]. In the combination, the calibration parameters determined by the method disclosed by Gong in view of Tidake, Gilmore, and Maier as described above are stored in a table as described in Nunn. The applicant is invited to consult Atwell as cited in the conclusion of this Office action for an alternative reference.)
Before the effective filing date of the invention, it would have been obvious to a person of ordinary skill in the art to combine the spectrum analysis method of Gong in view of Tidake, Gilmore, and Maier with storing calibration parameters in a table as disclosed by Nunn because a table is a fundamental tool for storing and retrieving information efficiently.
Claim 22
Gong in view of Tidake, Gilmore, Maier, and Nunn discloses the elements of the parent claim(s). It also discloses:
[The method as claimed in claim 10, wherein] the spectrometric detector is a pixelated detector ([Maier, section 3]: Maier discloses using a “8 × 8 pixel CdTe detector” [Maier, section 3 first paragraph].) and the calibration is done pixel by pixel, with a different calibration table for each pixel. ([Maier, figures 2-3, section 3-4; Nunn, 0286]: Pixel by pixel calibration is a standard property of pixel detectors. For example, energy calibration via correlation (ECC) “for one pixel” is shown in [Maier, figures 2-3]. Maier further explains that “energy relation which is caused by the sensitivity of its front-end readout electronics to the detector dark current which deviates from pixel to pixel” [Maier, section 3.2 first paragraph] and discusses the “pixel specific calibration” [Maier, section 4.1 first paragraph; see also, section 5.3]. As explained above, in the combination, the calibration parameters as determined by Maier are stored in tables as disclosed in Nunn.)
The same motivation to combine applies.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Shishir AGRAWAL whose telephone number is +1 703-756-1183. The examiner can normally be reached Monday through Thursday, 08:30-14:30 Pacific Time.
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, Alexey SHMATOV can be reached on +1 571-270-3428. The fax phone number for the organization where this application or proceeding is assigned is +1 571-273-8300.
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 +1 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call +1 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/S.A./Examiner, Art Unit 2123
/ALEXEY SHMATOV/Supervisory Patent Examiner, Art Unit 2123
Prosecution Insights