DETAILED ACTION
This Office Action is sent in response to Applicant’s Communication received 2/3/2023 for application number 18/164,145.
Claims 1-24 are pending.
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 .
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-5, 10-12, 15-19, and 24 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Sarzi Amade et al., (US 2022/0129750 A1).
In reference to claim 1, Sarzi Amade discloses a method (para. 0002), comprising: providing input data to an input layer of an artificial neural network (ANN), the input data comprising features corresponding to respective channels of a spectrum associated with a subject (spectroscopic image with number of channels is input, para. 0052, 0039-41); configuring the ANN to produce prediction data for respective labels in response to the input data, each label configured to represent a respective one of a plurality of radioisotopes (neural network identifies isotopes in spectrum, para. 0045-51, 0107-09); and determining an amount of each radioisotope of the plurality of radioisotopes within the subject based, at least in part, on the prediction data determined for the respective labels by the ANN (see fig. 5 and para. 0045-69: isotopes are quantified based on predictive data sent through the neural network).
In reference to claim 2, Sarzi Amade discloses the method of claim 1, wherein each label corresponds to a characteristic energy of the radioisotope represented by the label, the method further comprising: configuring the ANN to determine an activity quantity for each label, the activity quantity determined for each label configured to quantify emission of radiation at the characteristic energy corresponding to the label within the spectrum (output class correspond to detected energy of isotope and quantification of isotope, para. 0045-69).
In reference to claim 3, Sarzi Amade discloses the method of claim 2, wherein the ANN is configured to predict a plurality of labels, each label configured to represent a respective radioisotope of the plurality of radioisotopes, the method further comprising: determining the amount of each radioisotope within the subject based, at least in part, on activity quantities determined for each label of the plurality of labels (NN can detect a plurality of isotopes and quantifications of each, para. 0045-69, also see tables 3 and 4, para. 0088).
In reference to claim 4, Sarzi Amade discloses the method of claim 1, wherein the ANN is configured to determine prediction data for respective labels of a plurality of labels, the plurality of labels comprising: a first label configured to represent a first emission range of a first radioisotope of the plurality of radioisotopes; and a second label configured to represent a second emission range of the first radioisotope, the second emission range different from the first emission range (two labels are determined for each isotope, the weight and probability of the isotope being present, para. 0049; these labels are then combined to determine both the presence and quantity of the isotope, para. 0045-69).
In reference to claim 5, Sarzi Amade discloses the method of claim 4, further comprising, determining an amount of the first radioisotope within the subject based, at least in part, on first prediction data determined for the first label and second prediction data determined for the second label (weight and probability of the isotope being present, para. 0049, are both used to determine quantity of the isotope, para. 0045-69).
In reference to claim 10, Sarzi Amade discloses the method of claim 1, further comprising determining a confidence metric for the prediction data, comprising: configuring the ANN to include a dropout layer; producing a plurality of prediction datasets, each prediction dataset comprising prediction data determined by the ANN including the dropout layer; and determining quantiles of the prediction datasets (dropout layer may be used, para. 0059, cost function, which is a confidence metric the NN is fully trained, on training mini-batches is determined, para. 0083-84).
In reference to claim 11, Sarzi Amade discloses an apparatus, comprising: a processor; and a machine-learned (ML) module configured for operation on the processor (ANN would be executed on a processor, para. 0009-11), the ML module comprising an artificial neural network (ANN) comprising an input layer, a first hidden layer, and an output layer (see fig. 5); wherein the ANN is trained to produce prediction data for respective labels in response to radiation spectra, the labels configured to represent respective radioisotopes of a plurality of radioisotopes (neural network identifies isotopes in spectrum, para. 0045-51, 0107-09), and wherein the prediction data produced by the ANN in response to a spectrum of a subject is configured to predict an amount of each radioisotope of the plurality of radioisotopes within the subject (see fig. 5 and para. 0045-69: isotopes are quantified based on predictive data sent through the neural network).
In reference to claim 12, Sarzi Amade discloses the apparatus of claim 11, wherein the first hidden layer of the ANN comprises a larger number of nodes than the input layer of the ANN (see para. 0051-69 and fig. 5: the hidden layers would have more nodes than the input layer).
In reference to claim 15, this claim is directed to a non-transitory computer-readable medium associated with the method claimed in claim 1 and is therefore rejected under a similar rationale.
In reference to claim 16, this claim is directed to a non-transitory computer-readable medium associated with the method claimed in claim 2 and is therefore rejected under a similar rationale.
In reference to claim 17, this claim is directed to a non-transitory computer-readable medium associated with the method claimed in claim 3 and is therefore rejected under a similar rationale.
In reference to claim 18, this claim is directed to a non-transitory computer-readable medium associated with the method claimed in claim 4 and is therefore rejected under a similar rationale.
In reference to claim 19, this claim is directed to a non-transitory computer-readable medium associated with the method claimed in claim 5 and is therefore rejected under a similar rationale.
In reference to claim 24, this claim is directed to a non-transitory computer-readable medium associated with the method claimed in claim 10 and is therefore rejected under a similar rationale.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim(s) 6-9, 14, and 20-23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sarzi Amade et al., (US 2022/0129750 A1) in view of Cui et al., Class-Balanced Loss Based on Effective Number of Samples (see attached NPL).
In reference to claim 6, Sarzi Amade does not explicitly teach the method of claim 1, configuring nodes of the ANN to incorporate bias weights, the bias weights based on a determined training bias of the ANN.
Cui teaches the method of claim 1, configuring nodes of the ANN to incorporate bias weights, the bias weights based on a determined training bias of the ANN (class-balanced loss term is a weighting factor based on the number of samples of a class relative to other classes, page 9271).
It would have been obvious to one of ordinary skill in art, having the teachings of Sarzi Amade and Rezaei-Dastjerdehei before the earliest effective filing date, to modify the neural network as disclosed by Sarzi Amade to include the bias weights as taught by Cui.
One of ordinary skill in the art would have been motivated to modify the neural network of Sarzi Amade to include the bias weights of Cui because it can help more accurately classify data in long-tailed datasets (Cui, Introduction, pages 9268-69).
In reference to claim 7, Sarzi Amade teaches the method of claim 6, wherein the ANN is trained to predict a plurality of labels, each label configured to represent a different radioisotope of the plurality of radioisotopes (NN can detect a plurality of isotopes and quantifications of each, para. 0045-69, also see tables 3 and 4, para. 0088).
However, Sarzi Amade does not explicitly teach the method further comprising: determining a mean number of occurrences within a training dataset of each label of the plurality of labels; and calculating bias weights for respective labels of the plurality of labels, wherein the bias weight of a particular label is based, at least in part, on a mean number of occurrences of the particular label within the training dataset and a mean number of occurrences of other labels of the plurality of labels within the training dataset.
Cui teaches the method further comprising: determining a mean number of occurrences within a training dataset of each label of the plurality of labels; and calculating bias weights for respective labels of the plurality of labels, wherein the bias weight of a particular label is based, at least in part, on a mean number of occurrences of the particular label within the training dataset and a mean number of occurrences of other labels of the plurality of labels within the training dataset (class-balanced loss term is a weighting factor based on the number of samples of a class relative to other classes, page 9271).
It would have been obvious to one of ordinary skill in art, having the teachings of Sarzi Amade and Rezaei-Dastjerdehei before the earliest effective filing date, to modify the neural network as disclosed by Sarzi Amade to include the bias weights as taught by Cui.
One of ordinary skill in the art would have been motivated to modify the neural network of Sarzi Amade to include the bias weights of Cui because it can help more accurately classify data in long-tailed datasets (Cui, Introduction, pages 9268-69).
In reference to claim 8, Cui further teaches the method of claim 6, wherein training the ANN comprises evaluating a loss function configured to quantify an error between prediction data generated by the ANN in response to a training spectrum and a ground truth of the training spectrum, the loss function is configured to incorporate the bias weights (sigmoid cross-entropy loss uses class balance loss term, headings 4.0-4.3, pages 9271-72).
In reference to claim 9, Cui further teaches the method of claim 8, wherein the loss function comprises a combination of a sigmoid layer and binary cross entropy between the prediction data and the ground truth (sigmoid layer with cross-entropy loss, page 9272; loss is binary because, “When using the sigmoid function, we regard multi-class visual recognition as multiple binary classification…” page 9272).
In reference to claim 14, Sarzi Amade does not explicitly teach the apparatus of claim 11, wherein nodes of the ANN comprise bias weights, the bias weights based on a mean of occurrences of respective labels within a training dataset.
Cui teaches the apparatus of claim 11, wherein nodes of the ANN comprise bias weights, the bias weights based on a mean of occurrences of respective labels within a training dataset (class-balanced loss term is a weighting factor based on the number of samples of a class relative to other classes, page 9271).
It would have been obvious to one of ordinary skill in art, having the teachings of Sarzi Amade and Rezaei-Dastjerdehei before the earliest effective filing date, to modify the neural network as disclosed by Sarzi Amade to include the bias weights as taught by Cui.
One of ordinary skill in the art would have been motivated to modify the neural network of Sarzi Amade to include the bias weights of Cui because it can help more accurately classify data in long-tailed datasets (Cui, Introduction, pages 9268-69).
In reference to claim 20, this claim is directed to a non-transitory computer-readable medium associated with the method claimed in claim 6 and is therefore rejected under a similar rationale.
In reference to claim 21, this claim is directed to a non-transitory computer-readable medium associated with the method claimed in claim 7 and is therefore rejected under a similar rationale.
In reference to claim 22, this claim is directed to a non-transitory computer-readable medium associated with the method claimed in claim 8 and is therefore rejected under a similar rationale.
In reference to claim 23, this claim is directed to a non-transitory computer-readable medium associated with the method claimed in claim 9 and is therefore rejected under a similar rationale.
Claim(s) 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sarzi Amade et al., (US 2022/0129750 A1) in view of Szandała, Review and Comparison of Commonly Used Activation Functions for Deep Neural Networks (see attached NPL).
In reference to claim 13, Sarzi Amade does not explicitly teach the apparatus of claim 11, wherein nodes of the ANN are configured to implement hyperbolic tangent activation functions (Sarzi Amade teaches sigmoid, para. 0059).
Szandala teaches the apparatus of claim 11, wherein nodes of the ANN are configured to implement hyperbolic tangent activation functions (pages 209-210).
It would have been obvious to one of ordinary skill in art, having the teachings of Sarzi Amade and Szandala before the earliest effective filing date, to modify the sigmoid activation function of Sarzi Amade to include the hyperbolic tanget function of Szandala.
One of ordinary skill in the art would have been motivated to modify the sigmoid activation function of Sarzi to include the hyperbolic tanget function of Szandala because it may more quickly minimize the cost function while training and mitigate other problems of sigmoid functions (Szandala, page 209).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See Notice of References Cited: [B], [C], [V]-[X] all teach neural networks for identifying isotopes.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Andrew T. Chiusano whose telephone number is (571)272-5231. The examiner can normally be reached M-F, 10am-6pm.
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, Tamara Kyle can be reached at 571-272-4241. 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.
/ANDREW T CHIUSANO/Primary Examiner, Art Unit 2144
Prosecution Insights