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 .
Status of Claims
Claims 1-35 are pending and examined on the merits.
Priority
The instant application filed on 4/4/2022 claims the benefit of priority to U.S. Provisional Patent Application No. 63/170,180 filed on 4/2/2021. Thus, the effective filing date of the claims is 4/2/2021. The applicant is reminded that amendments to the claims and specification must comply with 35 U.S.C. § 120 and 37 C.F.R. § 1.121 to maintain priority to an earlier-filed application. Claim amendments may impact the effective filing date if new subject matter is introduced that lacks support in the originally filed disclosure. If an amendment adds limitations that were not adequately described in the parent application, the claim may no longer be entitled to the priority date of the earlier filing.
Information Disclosure Statement
The information disclosure statement (IDS) filed on 8/9/2022 has been entered and considered. A signed copy of the corresponding 1449 form has been included with this Office action.
Specification
Applicant is reminded of the proper language and format for an abstract of the disclosure.
The abstract should be in narrative form and generally limited to a single paragraph on a separate sheet within the range of 50 to 150 words in length. The abstract should describe the disclosure sufficiently to assist readers in deciding whether there is a need for consulting the full patent text for details. The abstract exceeds the 150 word limit, the current word count being 153. Appropriate action is required.
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.
Claims 1, 8, 11, and 14-15 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 applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites "the estimated likelihood that the biological material will produce a one of a successful pregnancy". It is unclear how "a successful pregnancy" is defined: fertilization of the egg and implantation of the embryo, pregnancy past the first or second trimester, or a full-term pregnancy. The instant specification only discusses the possible definitions of "producing a successful clinical outcome" in para.0082, which encompasses a successful pregnancy, which remains indefinite. The specification further goes on to lump both "a successful pregnancy" and "a live birth" together in several places, by referring to the likelihood that the biological material will produce "a successful pregnancy and/or a live birth". Therefore, to further prosecution, "a successful pregnancy" is interpreted as the achievement of a live birth.
Claim 8 recites "fluorescence photon arrival time histogram is a first fluorescence photon arrival time histogram, the estimating the likelihood that the biological material will produce a successful pregnancy and/or a live birth being further based on a second fluorescence photon arrival time histogram". It is unclear if Applicant intends to override "the likelihood" estimated using the first histogram dataset with the second histogram dataset, or if the estimation using the second histogram dataset produces a distinct "second likelihood" estimation. Additionally, the instant disclosure is silent on this matter. To further prosecution, the limitation is interpreted as "estimating a second likelihood that the biological material will produce a successful pregnancy and/or a live birth being based on a second fluorescence photon arrival time histogram".
Claim 11 recites "applying a physical model to data associated with the FLIM data set to generate an output". It is unclear what "physical" is meant to represent, or what output this model is meant to yield. Based on the instant disclosure, figures 12-13 and specification para.0104, and to further prosecution, the limitation is interpreted as a physical model of FLIM images as defined in para.0104 "a three-dimensional (3D) data structure in which the x and y values represent the pixels and z values represent fluorescence photon arrival times (for each pixel)". The resulting model being the generated output. It is also not clear if this data is intended to be used as training data to the likelihood estimation model. To further prosecution, this limitation is also interpreted as training the likelihood estimating model with the FLIM image data, then using this model for estimating the likelihood that the biological material will produce a successful pregnancy and/or a live birth.
Claims 14 and 15 recites the limitation “the intracellular region” in line 1 of each claim. There is insufficient antecedent basis for this limitation in the claims. To further prosecution: claim 14 is interpreted as depending from claim 6, where "a raw intracellular FLIM histogram or a normalized intracellular FLIM histogram" is first addressed; and claim 15 is interpreted as depending from claim 14.
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
The following is a quotation of pre-AIA 35 U.S.C. 112, fourth paragraph:
Subject to the following paragraph [i.e., the fifth paragraph of pre-AIA 35 U.S.C. 112], a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claim 12 rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends. Claim 12 recites “the estimation model includes an artificial neural network”, which does not further limit claim 1 as evidenced by "an estimation model that has been trained using artificial intelligence and labeled clinical training data" and it's interpretation in para.0076 "the AI model can be trained to classify embryos based on their viability using Naive Bayes, decision tree, random forest, support vector machines, K nearest neighbors, or any other suitable classification algorithm or combinations thereof", which are all considered either machine learning or artificial neural network models.
Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements.
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 1-35 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea of a mental process, a mathematical concept, organizing human activity, or a law of nature or natural phenomenon without significantly more. In accordance with MPEP § 2106, claims found to recite statutory subject matter (Step 1: YES) are then analyzed to determine if the claims recite any concepts that equate to an abstract idea, law of nature or natural phenomenon (Step 2A, Prong 1). In the instant application, the claims recite the following limitations that equate to an abstract idea:
Claim 1: “extracting a fluorescence photon arrival time histogram from a subset of data from the FLIM data set” provides a mathematical relationship (the relationship between number of counts per arrival time) that is considered a mathematical concept, which is an abstract idea.
“estimating a likelihood that the biological material will produce a successful pregnancy and/or a live birth based on the fluorescence photon arrival time histogram” provides a mathematical calculation (estimating a likelihood involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea.
“an estimation model that has been trained using artificial intelligence and labeled clinical training data” provides a mathematical calculation (training an estimation model with data using Naive Bayes, decision tree, random forest, support vector machines, K nearest neighbors, or any other suitable classification algorithm involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea (as interpreted above).
Claim 4: “training the estimation model using a plurality of fluorescence photon arrival time histograms of the FLIM data set” provides a mathematical calculation (training an estimation model with data using Naive Bayes, decision tree, random forest, support vector machines, K nearest neighbors, or any other suitable classification algorithm involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea (as interpreted above).
Claim 5: “using the trained model on non-training data to predict a patient’s probability of producing a successful pregnancy and/or a live birth” provides a mathematical calculation (using an estimation model to predict probabilities involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea (as interpreted above).
Claim 7: “combining multiple fluorescence photon arrival time histograms from the plurality of fluorescence photon arrival time histograms of the FLIM data set” provides a mathematical calculation (combining histogram data involves arithmetic) that is considered a mathematical concept, which is an abstract idea.
Claim 10: “parameterizing the fluorescence photon arrival time histogram using one of a decay model, phasor analysis, or principal component analysis” provides a mathematical calculation (applying a mathematical model to histogram data involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea.
Claim 11: “training the likelihood estimating model with the FLIM image data, then using this model for estimating the likelihood that the biological material will produce a successful pregnancy and/or a live birth” provides a mathematical calculation (training and applying a mathematical model involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea (as interpreted above).
Claim 13: “performing a noise correction on the FLIM data set” provides a mathematical calculation (performing noise correction on data involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea.
Claim 15: “partitioning the intracellular region to identify [] one or more sub-cellular structures of the intracellular region” provides an evaluation (identifying intracellular regions of a biological sample) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
Claim 20: “the estimating the likelihood that the biological material will produce a successful pregnancy and/or a live birth is further based on contextual data including one of patient-specific data, clinic-specific data, or a morphological image associated with the biological material” provides a mathematical calculation (training a mathematical model involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea.
Claim 21: “updating the estimation model based on feedback generated during subsequent estimations” provides a mathematical calculation (updating the model requires re-training a mathematical model which involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea.
Claim 22: “the estimating the likelihood that the biological material will produce a successful pregnancy and/or a live birth is further based on spindle imaging” provides a mathematical calculation (training a mathematical model involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea.
Claim 24: “the estimation model has been trained using supervised artificial intelligence” provides a mathematical calculation (training a mathematical model involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea.
Claim 25: “the estimation model has been trained using unsupervised artificial intelligence” provides a mathematical calculation (training a mathematical model involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea.
Claim 26: “performing a signal filtering technique on the FLIM data” provides an evaluation (performing data filtering involves evaluating values against a threshold) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
Claim 27: “processing the FLIM data set to identify a subset of data from the FLIM data set that represents an intracellular region of the biological material” provides an evaluation (identifying intracellular regions of a biological sample) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
Claim 28: “using artificial intelligence to predict whether the embryo or the gamete is aneuploid” provides a mathematical calculation (training and using an estimation model to predict probabilities involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea (as interpreted above).
Claim 29: “using artificial intelligence to predict whether the gamete has matured” provides a mathematical calculation (training and using an estimation model to predict probabilities involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea (as interpreted above).
Claim 30: “validating the output signal” provides a mathematical calculation (the validating methods involve mathematical calculations) that is considered a mathematical concept, which is an abstract idea.
Claim 31: “the validating is performed using a cross-validation method” provides a mathematical calculation (performing cross-validation involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea.
Claim 33: “comparing FLIM data of the sperm cells; and selecting a viable sperm cell from the plurality of sperm cells” provides an evaluation (comparing and selecting sperm cells) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
Claim 34: “analyzing the FLIM data of the plurality of sperm cells to determine a patient’s overall sperm health” provides an evaluation (determining sperm health) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
Claim 35: “assessing an efficacy of a preparation medium based on at least one of the fluorescence photon arrival time histogram or the estimation model” provides an evaluation (assessing a material based on data or a model) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
These recitations are similar to the concepts of collecting information, analyzing it, and displaying certain results of the collection and analysis in Electric Power Group, LLC, v. Alstom (830 F.3d 1350, 119 USPQ2d 1739 (Fed. Cir. 2016)), organizing and manipulating information through mathematical correlations in Digitech Image Techs., LLC v Electronics for Imaging, Inc. (758 F.3d 1344, 111 U.S.P.Q.2d 1717 (Fed. Cir. 2014)) and comparing information regarding a sample or test to a control or target data in Univ. of Utah Research Found. v. Ambry Genetics Corp. (774 F.3d 755, 113 U.S.P.Q.2d 1241 (Fed. Cir. 2014)) and Association for Molecular Pathology v. USPTO (689 F.3d 1303, 103 U.S.P.Q.2d 1681 (Fed. Cir. 2012)) that the courts have identified as concepts that can be practically performed in the human mind or are mathematical relationships. Therefore, these limitations fall under the “Mental process” and “Mathematical concepts” groupings of abstract ideas. As such, claims 1-35 recite an abstract idea (Step 2A, Prong 1: YES).
Claims found to recite a judicial exception under Step 2A, Prong 1 are then further analyzed to determine if the claims as a whole integrate the recited judicial exception into a practical application or not (Step 2A, Prong 2). The judicial exceptions listed above are not integrated into a practical application because the claims do not recite an additional element or elements that reflects an improvement to technology. Specifically, the claims recite the following additional elements:
Claim 1: “accessing, at a compute device, a fluorescence lifetime imaging microscopy (FLIM) data set” provides insignificant extra-solution activities (accessing data is a pre-solution activity involving data gathering and manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
“generating an output signal” provides insignificant extra-solution activities (outputting data is a post-solution activity involving data manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Claim 11: “applying a physical model to data associated with the FLIM data set to generate an output” provides insignificant extra-solution activities (outputting data is a post-solution activity involving data manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Claim 15: “sample one or more sub-cellular structures of the intracellular region” provides insignificant extra-solution activities (sampling of intracellular regions is a pre-solution activity involving data gathering steps) that do not serve to integrate the judicial exceptions into a practical application.
Claims 16 and 17: “the FLIM data set is generated by a system optimized to preferentially detect autofluorescence of nicotinamide adenine dinucleotide (NADH)” or “flavin adenine dinucleotide (FAD)” provide insignificant extra-solution activities (generating FLIM data is a pre-solution activity involving data gathering steps) that do not serve to integrate the judicial exceptions into a practical application.
Claim 23: “the spindle imaging is via second harmonic imaging microscopy, generated with a non-linear pulsed laser” provides insignificant extra-solution activities (generating spindle image data is a pre-solution activity involving data gathering steps) that do not serve to integrate the judicial exceptions into a practical application.
The steps for accessing, generating, and outputting data, and sampling (imaging) a cell with a fluorescent microscope are insignificant extra-solution activities that do not serve to integrate the recited judicial exceptions into a practical application because they are pre- and post-solution activities involving data gathering, data manipulation, and sample manipulation steps (see MPEP 2106.04(d)(2)). Therefore, claims 1-35 are directed to an abstract idea (Step 2A, Prong 2: NO).
Claims found to be directed to a judicial exception are then further evaluated to determine if the claims recite an inventive concept that provides significantly more than the judicial exception itself (Step 2B). The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the claims recite additional elements that are insignificant extra-solution activities that do not serve to integrate the recited judicial exceptions into a practical application, or equate to mere instructions to apply the recited exception in a generic way or in a generic computing environment.
The limitations for accessing, generating, and outputting data, and sampling (imaging) a cell with a fluorescent microscope are insignificant extra-solution activities that do not serve to integrate the recited judicial exceptions into a practical application. Furthermore, no inventive concept is claimed by these limitations as they are well-understood, routine, and conventional.
The additional elements do not comprise an inventive concept when considered individually or as an ordered combination that transforms the claimed judicial exception into a patent-eligible application of the judicial exception. Therefore, the claims do not amount to significantly more than the judicial exception itself (Step 2B: No). As such, claims 1-35 are not patent eligible.
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.
Claims 1-12, 19, 21-24, and 26 rejected under 35 U.S.C. 103 as being unpatentable over Ma et al. (US-20200320708).
Regarding claims 1, 12, and 24, Ma teaches accessing, at a compute device, a fluorescence lifetime imaging microscopy (FLIM) data set associated with a biological material, the biological material including one of an embryo or a gamete (Para.0059 "A method of the present invention applies the phasor-fluorescence lifetime imaging microscopy (FLIM) method and examines the dynamic endogenous biomarker changes during preimplantation embryo development" and para.0057 "the FLIM data collected from individual embryos are placed in either of two categories, the H (control/healthy group has FLIM signature from the embryos developed to the blastocyst stage) and UH (sample/unhealthy group has FLIM signature from the embryos arrested at compaction stage or even earlier)").
Ma also teaches extracting a fluorescence photon arrival time histogram from a subset of data from the FLIM data set (Para.0006 "During FLIM collection, a pulsed 2-photon laser is used to measure the intensity at short time windows (time arrival of the photons) as a function of time" and para.0057 "The distance algorithm can generate a “spectra” from the given (up to 24 parameters) of phasor FLIM distributions corresponding to individual embryos. In one embodiment, the 24 parameters include, but are not limited to, [] the total number of pixels in the phasor plot from the 4 slices of the 3D phasor histogram").
Ma also teaches (also encompassing claims 12 and 24) estimating a likelihood that the biological material will produce a successful pregnancy and/or a live birth based on the fluorescence photon arrival time histogram and an estimation model that has been trained using artificial intelligence and labeled clinical training data (as interpreted above) (Para.0056 "A system of the present invention may involve a computing device configured to process a quantity of data with a machine learning algorithm" and para.0060 "Methods of the present invention are able to calculate several different mathematical parameters that are statistically different between healthy and unhealthy pre-implantation embryos based on machine learning information", regarding claim 24 all listed modeling methods are supervised).
Ma also teaches generating an output signal representing the estimated likelihood that the biological material will produce a one of a successful pregnancy or a live birth (Abstract "calculating a viability index factor of the embryo from the set of values and the set of stored values" and para.0101 "Next, the DA data from 2-cell, 4-cell, and the early compaction stage was examined to determine the best binary classification model using receiver operating characteristic (ROC) curves (Graphs B and C in FIG. 11A, Graphs A and B in FIG. 11C)").
While the methods of Ma are not identical to claim 1, it would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify the methods of Ma for generating a likelihood estimation (beyond the used binary classification) in order to increase the likelihood of successful pregnancy by developing a more quantitative and objective means for assessing embryo quality (para.0004 "Development of more quantitative and objective means for assessing embryo quality that are simpler, safer, and faster could provide significant advantages in assisted reproduction by enabling single embryo transfers rather than the implantation of multiple embryos in order to increase the likelihood of a successful pregnancy". One skilled in the art would have a reasonable expectation of success because both methods use FLIM data for analyzing embryos for prediction of pregnancy outcome.
Regarding claims 2 and 3, Ma teaches the methods of Claim 1 on which this claim depends/these claims depend, respectively. Ma also teaches the biological material includes the gamete, and the gamete includes an oocyte or a sperm (Para.0046 "Although certain embodiments of systems and methods disclosed herein may be described in reference to determining embryo viability, it is understood that the systems and methods may be used for other processes, for example to determine properties of one or more cells, tissues, or living organisms more generally. Suitable examples include, but are not limited to, identifying changes in metabolism due to cell cycle, stress, cancer diabetes, and neurodegenerative diseases within cell, tissue, and/or blood samples", given that this work is already focused on embryo viability, it would be obvious to also apply the methods to gametes (oocytes and sperm).
Regarding claim 4, Ma teaches the methods of Claim 1 on which this claim depends/these claims depend, respectively. Ma also teaches training the estimation model using a plurality of fluorescence photon arrival time histograms of the FLIM data set (Para.0056 "a portion of data measured from embryos with known or later discerned viability metrics is used as a training set, while a second portion of data measured from embryos with known or later discerned viability metrics is used as a test set").
Regarding claim 5, Ma teaches the methods of Claim 4 on which this claim depends/these claims depend, respectively. Ma also teaches using the trained model on non-training data to predict a patient’s probability of producing a successful pregnancy and/or a live birth (para.0060 "Methods of the present invention are able to calculate several different mathematical parameters that are statistically different between healthy and unhealthy pre-implantation embryos based on machine learning information").
Regarding claim 6, Ma teaches the methods of Claim 4 on which this claim depends/these claims depend, respectively. Ma also teaches the plurality of fluorescence photon arrival time histograms includes one of a raw intracellular FLIM histogram or a normalized intracellular FLIM histogram (Para.0006 "Instead of fitting the decay curve into an exponential equation (black line in graph 201), the raw data (intensity at each pixel) is transformed into polar coordinates by plotting the sine (red line) and cosine (blue line) using Fourier transformation, for every pixel in the object").
Regarding claims 7-9, Ma teaches the methods of Claim 4 on which this claim depends/these claims depend, respectively. Ma also teaches combining multiple fluorescence photon arrival time histograms from the plurality of fluorescence photon arrival time histograms of the FLIM data set; estimating a second likelihood that the biological material will produce a successful pregnancy and/or a live birth being based on a second fluorescence photon arrival time histogram (as interpreted above); and one of the first fluorescence photon arrival time histogram or the second fluorescence photon arrival time histogram includes one of a raw intracellular FLIM histogram or a normalized intracellular FLIM histogram (Para.0054 "An imaging device 101 of the present invention may have multiple “taps”, to provide for accelerated readout of image data from the sensor by reading from multiple locations on the pixel sensor simultaneously" and para.0055 "Where multiple taps are used, the multiple taps may be acquired and combined based on the phase order in a period, i.e. in one full period measurement, two or more sets of phase images are actually acquired", multiple taps encompass a second histogram which in turn would be used in a second prediction, and the data used is normalized as evidenced by Ma, para.0006, in claim 6 above).
Regarding claims 10 and 11, Ma teaches the methods of Claim 1 on which this claim depends/these claims depend, respectively. Ma also teaches parameterizing the fluorescence photon arrival time histogram using one of a decay model, phasor analysis, or principal component analysis, prior to estimating the likelihood that the biological material will produce a successful pregnancy and/or a live birth; and applying a physical model to data associated with the FLIM data set to generate an output, prior to estimating the likelihood that the biological material will produce a successful pregnancy and/or a live birth, wherein the estimating the likelihood that the biological material will produce a successful pregnancy and/or a live birth is based on the output (as interpreted above) (Para.0100 "Using the DA algorithm, the 3D phasor histogram was separated into 4 sections based on the phasor coordinates (g, s) intensity, from which, 6 parameters were extracted from each section, generating a total of 24 parameters. The healthy embryos (H group) were used as the control set and the unhealthy embryos (UH group) were used as the sample set. Each of these sets included images from multiple embryos from each stage in development. Next, the average and variance of the training set were calculated, which includes two groups (H and UH), and weighted 20 parameters (g, s, the secondary moment a, b and angle from 4 sub-layers, intensity excluded) in each set from the 3D phasor plot").
Regarding claim 19, Ma teaches the methods of Claim 1 on which this claim depends/these claims depend, respectively. Ma also teaches the FLIM data set is generated by a system that uses one of: multiple excitation wavelengths in succession, to obtain a hyperspectral representation of autofluorescence associated with the biological material; or a wavelength-splitting optic and a spectrographic detector to obtain a multispectral representation of the autofluorescence associated with the biological material (Para.0010 "In one embodiment, the imaging device has a plurality of taps, and the instructions comprise the step of acquiring multiple images from the imaging device simultaneously using the plurality of taps" and para.0054 "In some embodiments, an imaging device of the present invention may have one tap, two taps, four taps, eight taps, or more. In some embodiments, multiple imaging devices may be used, for example with a beam splitter or other image splitting device, in order to gather more image data from a sample at higher speeds").
Regarding claim 21, Ma teaches the methods of Claim 1 on which this claim depends/these claims depend, respectively. Ma also teaches updating the estimation model based on feedback generated during subsequent estimations (Para.0058 "Using distance analysis, a training set can be generated based on the best weight set that has been chosen to separate the H and UH set embryos according to the distance from the average of each set" encompasses using data generated by the model to be used as training data).
Regarding claim 22, Ma teaches the methods of Claim 1 on which this claim depends/these claims depend, respectively. Ma also teaches the estimating the likelihood that the biological material will produce a successful pregnancy and/or a live birth is further based on spindle imaging (Para.0046 "Suitable examples include, but are not limited to, identifying changes in metabolism due to cell cycle, stress, cancer diabetes, and neurodegenerative diseases within cell, tissue, and/or blood samples" because the spindle forms during the growth phase of the cell cycle, this information would also be in the FLIM data used by the model of Ma).
Regarding claim 23, Ma teaches the methods of Claim 1 on which this claim depends/these claims depend, respectively. Ma also teaches the spindle imaging is via second harmonic imaging microscopy, generated with a non-linear pulsed laser (Para.0083 "In order to better characterize the lipid droplets distribution during embryonic development, third-harmonic generation (THG) microscopy imaging was employed (see FIG. 9) with a Deep Imaging Via Emission Recovery (DIVER) microscope").
Regarding claim 26, Ma teaches the methods of Claim 1 on which this claim depends/these claims depend, respectively. Ma also teaches performing a signal filtering technique on the FLIM data set prior to estimating the likelihood that the biological material will produce a successful pregnancy and/or a live birth (para.0077 "A dichroic filter at 690 nm was used to separate the fluorescence signal from the laser light. And the emission signal was split with 496 nm LP filter and detected in two channels using a band pass filter 460/80 and a 540/50 filter").
Claims 13 and 25 rejected under 35 U.S.C. 103 as being unpatentable over Ma et al. (US-20200320708) as applied to claims 1-12, 19, 21-24, and 26 above, and further in view of Le Marois et al. (Le Marois et al. "Noise‐Corrected Principal Component Analysis of fluorescence lifetime imaging data." Journal of biophotonics 10.9 (2017): 1124-1133).
Ma et al. are applied to claims 1-12, 19, 21-24, and 26.
Regarding claim 13, Ma teaches the method of Claim 1 on which this claim depends/these claims depend.
Ma does not explicitly teach performing a noise correction on the FLIM data set prior to estimating the likelihood that the biological material will produce a successful pregnancy and/or a live birth.
However, Le Marois teaches performing a noise correction on the FLIM data set prior to estimating the likelihood that the biological material will produce a successful pregnancy and/or a live birth (Abstract "A novel Noise-Corrected Principal Component Analysis (NC-PCA) method for time-domain FLIM data is presented here").
Therefore, it would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify the methods of Ma as taught by Le Marois in order to identify distinct microenvironments at lower photon counts (Abstract "The presence and distribution of distinct microenvironments are identified at lower photon counts than previously reported, without requiring prior knowledge of their number or of the dye’s decay kinetics"). One skilled in the art would have a reasonable expectation of success because both approaches are analyzing FLIM data sets.
Regarding claim 25, Ma teaches the method of Claim 1 on which this claim depends/these claims depend.
Ma does not explicitly teach the estimation model has been trained using unsupervised artificial intelligence.
However, Le Marois teaches the estimation model has been trained using unsupervised artificial intelligence (Page 2 col 1 paragraph 2 "PCA has been used in other fields which pro-duce dynamic imaging data [25–27] but has, to our knowledge, never been applied to FLIM data, possibly due to the complications introduced by the Pois-son noise of photon detection. We devised a noise-corrected PCA procedure (NC-PCA) adapted to the Poisson-distributed characteristic of single photon detection", PCA is a kind of unsupervised learning that may be applied to artificial intelligence models).
Claims 14-15 and 17 rejected under 35 U.S.C. 103 as being unpatentable over Ma et al. (US-20200320708) as applied to claims 1-12, 19, 21-24, and 26 above, and further in view of Okkelman et al. (Okkelman et al. "A deeper understanding of intestinal organoid metabolism revealed by combining fluorescence lifetime imaging microscopy (FLIM) and extracellular flux analyses." Redox biology 30 (2020): 101420).
Ma et al. are applied to claims 1-12, 19, 21-24, and 26.
Regarding claims 14 and 15, Ma teaches the method of Claim 1 on which this claim depends/these claims depend.
Ma does not explicitly teach the intracellular region is spatially resolved such that different areas of the biological sample can be separately sampled, nor partitioning the intracellular region to identify and sample one or more sub-cellular structures of the intracellular region.
However, Okkelman teaches the intracellular region is spatially resolved such that different areas of the biological sample can be separately sampled and partitioning the intracellular region to identify and sample one or more sub-cellular structures of the intracellular region (Page 6 col 2 paragraph 1 "Microscopy-based FLIM and PLIM methods, while rarely reported together, provided direct readouts of cell metabolism both within and outside Lgr5-GFP-labeled stem cell niches" and page 9 col 1 paragraph 2 "Future application of these methods together in multi-parametric imaging with appropriate cell type markers will allow the study of organoid stem cell metabolism with single cell and subcellular resolution").
Therefore, it would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify the methods of Ma as taught by Okkelman in order to better resolve cell fate via cell metabolism (page 9 col 1 paragraph 2 "this present and previous studies emphasize the importance of viewing cell fate regulation in organoids and regenerating tissues from the point of growth media composition and nutrient availability. Live imaging microscopy of cell metabolism is of high relevance to this emerging field of interest"). One skilled in the art would have a reasonable expectation of success because both approaches use the non-invasive FLIM for cell-specific and direct analysis of metabolism.
Regarding claim 17, Ma teaches the method of Claim 1 on which this claim depends/these claims depend. Ma also teaches using one of a one-photon excitation wavelength of between 380-500nm or a two-photon excitation wavelength of between 800-950nm (Para.0049 "An excitation source may have a spectral range, for example a broad spectral range of between 390 nm to 2000 nm. In other embodiments, a narrower or more specific spectral range may be used, for example limited to certain color bands in the visible, ultraviolet, and/or infrared spectrum. Suitable exemplary spectral ranges include, but are not limited to, 380 nm to 740 nm, 450 nm to 980 nm, 500 nm to 740 nm, or any other suitable range or combination of ranges").
Ma does not explicitly teach the FLIM data set is generated by a system optimized to preferentially detect autofluorescence of flavin adenine dinucleotide (FAD), nor using an emission bandpass filter having a lower cut-off of between 485-550nm and an upper cut-off of about 550-650nm.
However, Okkelman teaches the FLIM data set is generated by a system optimized to preferentially detect autofluorescence of flavin adenine dinucleotide (FAD) (Page 5 col 2 paragraph 1 "Frequently, this method is complemented by measuring FAD (Krebs cycle input) or other compounds [44], but its performance depends on the cell type and sensitivity of the available equipment", and Page 9 col 2 section 4.5 paragraph 1 "Two-photon excitation of NAD(P)H and GFP fluorescence was performed at excitation wavelengths of 760 nm and 920 nm, respectively").
Okkelman also teaches using an emission bandpass filter having a lower cut-off of between 485-550nm and an upper cut-off of about 550-650nm (Page 9 col 2 section 4.4 paragraph 1 "Emission was collected using 635–675 nm (405 nm excitation, O2 probe) and 512–536 nm (488 nm excitation, Lgr5-GFP) bandpass filters").
Claims 18, 27-29, and 35 rejected under 35 U.S.C. 103 as being unpatentable over Ma et al. (US-20200320708) as applied to claims 1-12, 19, 21-24, and 26 above, and further in view of McLennan et al. (McLennan et al. "Oocyte and embryo evaluation by AI and multi-spectral auto-fluorescence imaging: livestock embryology needs to catch-up to clinical practice." Theriogenology 150 (2020): 255-262).
Ma et al. are applied to claims 1-12, 19, 21-24, and 26.
Regarding claim 18, Ma teaches the method of Claim 1 on which this claim depends/these claims depend.
Ma does not explicitly teach the FLIM data set is generated by a system that does not use an emission bandpass filter.
However, McLennan teaches the FLIM data set is generated by a system that does not use an emission bandpass filter (Page 6 col 1 paragraph 2 "Adoption of these techniques, furthered with new metabolomics approaches such as FLIM or hyperspectral microscopy, will inevitably be combined to provide absolute accuracy in NQEAP assessment for every embryo, whether it be human or livestock", hyperspectral microscopy relies on post-processing of the data instead of using bandpass filters).
Regarding claims 27-29 and 35, Ma teaches the method of Claim 1 on which this claim depends/these claims depend.
Ma does not explicitly teach processing the FLIM data set to identify a subset of data from the FLIM data set that represents an intracellular region of the biological material; performing training an AI model with labeled clinical training data including FLIM datasets of aneuploid embryos, and using the model to predict whether the embryo or the gamete is aneuploid (as interpreted above); performing training an AI model with labeled clinical training data including FLIM datasets of immature and mature gamete, and using the model to predict whether the gamete has matured (as interpreted above), nor assessing an efficacy of a preparation medium based on at least one of the fluorescence photon arrival time histogram or the estimation model.
However, McLennan teaches processing the FLIM data set to identify a subset of data from the FLIM data set that represents an intracellular region of the biological material; performing training an AI model with labeled clinical training data including FLIM datasets of aneuploid embryos, and using the model to predict whether the embryo or the gamete is aneuploid (as interpreted above); performing training an AI model with labeled clinical training data including FLIM datasets of immature and mature gamete, and using the model to predict whether the gamete has matured (as interpreted above); and assessing an efficacy of a preparation medium based on at least one of the fluorescence photon arrival time histogram or the estimation model (Page 4 col 1 paragraph 1 "The power of this approach is that a spectral analysis of each cell of an embryo can be determined. In particular, it is the only metabolomics approach that can directly capture the cellular metabolic heterogeneity within the compacted cell layers of a morula or the ICM [inner cell mass] of a blastocyst. Proof of principle has shown that such an approach can identify differences in maturation and culture environment, such as the use of low O2 culture [78]. Future work aims to assess the differences in metabolism caused by aneuploidy using the same technique").
Therefore, it would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify the methods of Ma as taught by McLennan in order to achieve higher accuracy for non-invasively quantitate an embryo assessment for pregnancy (page 2 col 1 last paragraph "NQEAP [Non-invasive quantitative embryo assessment for pregnancy] is our specific term for providing a quantitative measurement of embryo quality relating to the probability of pregnancy establishment at a specific stage of pregnancy following embryo transfer" and page 6 col 1 paragraph 2 "The rapid developments of NQEAP technologies, especially around the areas of AI of images, whether they are from time-lapse or contrast microscopy techniques, is transforming clinical practices. Adoption of these techniques, furthered with new metabolomics approaches such as FLIM or hyperspectral microscopy, will inevitably be combined to provide absolute accuracy in NQEAP assessment for every embryo, whether it be human or livestock"). One skilled in the art would have a reasonable expectation of success because both approaches are concerned with prediction of pregnancy success using FLIM data.
Claims 20 and 30-32 rejected under 35 U.S.C. 103 as being unpatentable over Ma et al. (US-20200320708) as applied to claims 1-12, 19, 21-24, and 26 above, and further in view of Yao et al. (US-10438686).
Ma et al. are applied to claims 1-12, 19, 21-24, and 26.
Regarding claim 20, Ma teaches the method of Claim 1 on which this claim depends/these claims depend.
Ma does not explicitly teach the estimating the likelihood that the biological material will produce a successful pregnancy and/or a live birth is further based on contextual data including one of patient-specific data, clinic-specific data, or a morphological image associated with the biological material.
However, Yao teaches the estimating the likelihood that the biological material will produce a successful pregnancy and/or a live birth is further based on contextual data including one of patient-specific data, clinic-specific data, or a morphological image associated with the biological material (Page 42 col 2(10) paragraph 5 "In certain embodiments, the items of information relating to preselected patient variables for determining the probability of a live birth event for a post-IVF procedure patient may include blastocyst development rate, total number of embryos, total amount of gonatropins administered, endometrial thickness, flare protocol, average number of cells per embryo, type of catheter used, percentage of 8-cell embryos transferred, day 3 follicle stimulating hormone (FSH) level, body mass index, number of motile sperm before wash, number of motile sperm after wash, average grade of embryos, day of embryo transfer, season, number of spontaneous miscarriages, number of previous term deliveries, oral contraceptive pills, sperm collection, percent of unfertilized eggs, number of embryos arrested at 4-cell stage, compaction on day 3 after transfer, percent of normal fertilization, percent of abnormally fertilized eggs, percent of normal and mature oocytes, number of previous pregnancies, year, polycystic ovarian disease, unexplained female infertility, tubal disease, male infertility only, male infertility causes, endometriosis, other causes of female infertility, uterine fibroids, tubal ligation, sperm from donor, hydrosalpinx, performance of ICSI, or assisted hatching").
Regarding claims 30-32, Ma teaches the method of Claim 1 on which this claim depends/these claims depend.
Ma does not explicitly teach validating the output signal using one of the following techniques: resubstitution, hold-out, K-fold cross-validation, LOOCV, random subsampling, bootstrapping, or any other suitable validation technique or combinations thereof (as interpreted above); the validating is performed using a cross-validation method; nor the cross-validation method includes k-fold cross-validation.
However, Yao teaches performing a k-fold cross-validation (Page 50 col 1(25) paragraph 3 "The use of cross-validation and boosting in parameter selection and model assessment in MART® also preserve parsimony and prevent over-fitting. In the MART® tree constructions, the whole data set is divided into 10 subsets to achieve 10 fold cross validation for model assessment").
Therefore, it would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify the methods of Ma as taught by Yao in order to achieve robust prediction rate estimation and identify the best models (Page 50 col 1(25) paragraph 3 "The same 10 fold cross validation was repeated 1000 times to perform a robust predi