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 .
Priority
Acknowledgement is made of Applicant’s claim of priority from the US provisional application 63492879 filed on 03/29/2023.
Information Disclosure Statement
The information disclosure statement (“IDS”) filed on 07/12/2024 and 11/25/2024 have been reviewed and the listed references have been considered.
Drawings
The 39-page drawings have been considered and placed on record in the file.
Election/Restrictions
Applicant’s election, with traverse, of Group I (i.e., Claims 1-13 and 22-27) in the Response to Election Requirement filed on February 11, 2026 is acknowledged. Therefore, the present Office Action, only Claims 1-13 and 22-27 are being analyzed. Claims 14-21 and 28-58 have been withdrawn from consideration as non-elected claims.
Claim Objections
Claims 1, 4, and 24 are objected to because of the following informalities:
Claim 1 recites "then the boundaries of the mammalian embryos" should be "then boundaries of the mammalian embryos"
Claim 4 recites "erosion of the pixels" should be "erosion of pixels
Claim 24 recites "selected from the group consisting " should be "selected from a group consisting "
Appropriate corrections are required.
Claim Interpretation
Claim 7 has been given the following interpretation under broadest reasonable interpretation in light of the specification. Claim 7 recites an arbitrary value of channels for the U-Net and hyperparameters for the ridge regression model. The specification does not provide the significance of the value of “a U-Net with 512 features and a ridge regression model that utilizes a λ of 2”. One of ordinary skill in the art may consider any number of features such as 512, 1024, etc. and a λ of 0, 0.2, 0.3, 0.6, 0.8, 1, and 2. For completeness and compact prosecution Examiner has interpretated claim 7 as a U-Net contain channels and ridge regression model with hyperparameters.
Under MPEP 2143.03, "All words in a claim must be considered in judging the patentability of that claim against the prior art." In re Wilson, 424 F.2d 1382, 1385, 165 USPQ 494, 496 (CCPA 1970). As a general matter, the grammar and ordinary meaning of terms as understood by one having ordinary skill in the art used in a claim will dictate whether, and to what extent, the language limits the claim scope. Language that suggests or makes a feature or step optional but does not require that feature or step does not limit the scope of a claim under the broadest reasonable claim interpretation. In addition, when a claim requires selection of an element from a list of alternatives, the prior art teaches the element if one of the alternatives is taught by the prior art. See, e.g., Fresenius USA, Inc. v. Baxter Int’l, Inc., 582 F.3d 1288, 1298, 92 USPQ2d 1163, 1171 (Fed. Cir. 2009).
Claim 24 recites "from the group consisting of" then lists “a deep neural network image classification,” and “ridge regression models.” Since “from the group consisting of” separated by “or” is disjunctive, any one of the elements found in the prior art is sufficient to reject the claim. While citations have been provided for completeness and rapid prosecution, only one element is required. Because, on balance, it appears the disjunctive interpretation enjoys the most specification support and for that reason the disjunctive interpretation (one of A, B OR C) is being adopted for the purposes of this Office Action. Similarly, for claim 25, the disjunctive interpretation (one of A, B OR C) is being adopted for the purposes of this Office Action Applicant’s comments and/or amendments relating to this issue are invited to clarify the claim language and the prosecution history.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
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.
Claims 1, 3-5, 8, 11, 13, and 22-23 are rejected under 35 U.S.C. 103 as being unpatentable over Hall et al. (US 2022/0198657 A1) in view of Letterie et al. (US 10,902,334 B2).
Regarding claim 1, Hall teaches “A system for predicting a pregnancy outcome in a mammalian embryo (Hall paragraph [0082] "computation system 1 configured to computationally generate and use an Artificial Intelligence (AI) model 100 configured to estimate an embryo viability score from a single image of an embryo"), which system comprises:
(a) a microscope for observing a plurality of mammalian embryos (Hall paragraph [0091] "Imaging systems are typically light microscopes configured to capture single phase contrast images embryos");
(b) a camera mounted to the microscope for obtaining a plurality of digital images of mammalian embryos (Hall paragraph [0091] "Images may be captured using a conventional optical microscope fitted with a camera or image sensor, or the image may be captured by a camera with an integrated
optical system capable of taking a high resolution or high magnification image, including smart phone syst"); and
(c) a processor (Hall paragraph [0267] "The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two, including cloud based systems") electrically connected to the camera for receiving the plurality of digital images of mammalian embryos (Hall paragraph [0095] "The model monitor 21 allows a user 40 to provide image data and metadata 14 to a data management platform which includes a data repository. A data preparation step is performed, for example to move the images to specific folder, and to rename and perform pre-processing on the image such as objection detection, segmentation, alpha channel removal, padding, cropping/localising, normalising, scaling, etc"), wherein (Hall paragraph [0106] "Object Detection/Cropping the image to localise the image on the embryo and ensure that there are no artefacts around the edges of the image"), which is then followed by the plurality of digital images of mammalian embryos being isolated (Hall paragraph [0107] "Extracting the geometric properties of the boundaries using an elliptical Hough transform of the image contours, for example the best ellipse fit from an elliptical Hough transform calculated on the binary threshold map of the image. This method acts by selecting the hard boundary of the embryo in the image, and by cropping the square boundary of the new image so that the longest radius of the new ellipse is encompassed by the new image width and height, and so that the center of the ellipse is the center of the new image") for utilization in pregnancy prediction (Hall paragraph [0128] "Each of the individual models are configured to estimate an embryo viability score of an embryo in an image, and the AI model combines selected models to produce an overall embryo viability score that is returned by the AI model").
However, Hall is not relied on to teach “the plurality of digital images of mammalian embryos are converted from RGB to greyscale”.
Letterie teaches “the plurality of digital images of mammalian embryos are converted from RGB to greyscale (Letterie column 6 line 53 "converting color images to grayscale")”.
It would have been obvious to a person having ordinary skill in the art before
effective filing date of the claimed invention of the instant application to combine a system for predicting embryo pregnancy viability as taught by Hall to include pre-processing step of converting a colored image to grayscale as taught by Letterie.
The suggestion/motivation for doing so would have been "Manual oocyte scoring may provide useful clinical information. However, manual assessment of oocytes and embryos remains standard of care and has not changed significantly since inception of human embryology techniques. Thus, there remains a need for better tools to assess the reproductive potential of oocytes and pronuclear embryos to identify those with a high likelihood of developing into blastocysts and ultimately a live birth" as noted by the Letterie disclosure in column 1 lines 31-38.
Therefore, it would have been obvious to combine the disclosure of Hall with
the Letterie disclosure to obtain the invention as specified in claim 1 as there is a
reasonable expectation of success and/or because doing so merely combines prior art
elements according to known methods to yield predictable results.
Regarding claim 3, the combination of Hall and Letterie teaches “The system for predicting a pregnancy outcome in a mammalian embryo, according to Claim 1, further comprising suppression of light structures connected to the boundaries of the mammalian embryo in the plurality of digital images of mammalian embryos with the processor prior to the plurality of digital images of mammalian embryo being isolated (Hall paragraph [0104] "Normalizing the RGB (red-green-blue) or grayscale images to a fixed mean value for all the images […] This step ensured that color biases among the images were suppressed, and that the brightness of each image was normalized").”
Regarding claim 4, the combination of Hall and Letterie teaches “The system for predicting a pregnancy outcome in a mammalian embryo, according to Claim 3, further comprising erosion of the pixels from the boundaries of the mammalian embryos in the plurality of digital images with the processor after the suppression of the light structures connected to the boundaries of the mammalian embryos in the plurality of digital images (Hall paragraph [0105] "Thresholding images using binary, Otsu, or adaptive methods. Includes morphological processing of the image using dilation ( opening), erosion ( closing) and scale gradients, and using a scaled mask to extract the outer and inner boundaries of a shape").”
Regarding claim 5, the combination of Hall and Letterie teaches “The system for predicting a pregnancy outcome in a mammalian embryo, according to Claim 1, further comprising a deep neural network segmenter trained on the isolated plurality of digital images of mammalian embryos (Hall paragraph [0116] "One approach is Region-Convolutional Neural Net (or R-CNN) which uses an expensive search process is applied to search for image patch proposals (potential bounding boxes). These bounding boxes are then used to crop the regions of the image of interest. The cropped images are then run through a classifying model to classify the contents of the image region") for predicting mammalian embryo pregnancy status with a deep neural network image classification with the processor (Hall paragraph [0084] "At least one Zona Deep Leaming model is trained on a set of Zona Pellucida images 103 in order to generate the Artificial Intelligence (AI) model 100 configured to generate an embryo viability score from an input image 104").”
Regarding claim 8, the combination of Hall and Letterie teaches “The system for predicting a pregnancy outcome in a mammalian embryo, according to Claim 1, wherein the deep neural network segmenter trained on the plurality of isolated digital images of mammalian embryos for determining mammalian embryo pregnancy status (Hall paragraph [0128] "Each of the individual models are configured to estimate an embryo viability score of an embryo in an image, and the AI model combines selected models to produce an overall embryo viability score that is returned by the AI model" is performed using ResNet 18 (Hall paragraph [0124] "The main difference between FCN style models and U-Net style models is that in the FCN model, the encoder is responsible for predicting a low resolution label map that is then upsampled (possibly progressively). Whereas, the U-Net model does not have a fully complete label map prediction until the final layer. Ultimately, there do exist many variants of these models that trade off the differences between them (e.g. Hybrids). U-net architectures may also use pre-trained weights, such as ResNet-18 or ResNet-50, for use in cases where there is insufficient data to train models from scratch").”
Regarding claim 11, the combination of Hall and Letterie teaches “The system for predicting a pregnancy outcome in a mammalian embryo, according to Claim 1, further comprising a deep neural network for determining mammalian embryo pregnancy status with the processor (Hall paragraph [0085] "one or more additional AI models are trained on the pre-processed images 106. These may be additional deep learning models trained directly on the embryo image, and/or on a set of IZC images in which all regions of the image apart from the IZC are masked, or Computer Vision (CV) models trained to combine computer vision features/descriptors generating in the pre-processing step 102 to generate an embryo viability score from an image").”
Regarding claim 13, the combination of Hall and Letterie teaches “The system for predicting a pregnancy outcome in a mammalian embryo, according to Claim 11, wherein the deep neural network utilizes ResNet 18 (Hall paragraph [0124] "The main difference between FCN style models and U-Net style models is that in the FCN model, the encoder is responsible for predicting a low resolution label map that is then upsampled (possibly progressively). Whereas, the U-Net model does not have a fully complete label map prediction until the final layer. Ultimately, there do exist many variants of these models that trade off the differences between them (e.g. Hybrids). U-net architectures may also use pre-trained weights, such as ResNet-18 or ResNet-50, for use in cases where there is insufficient data to train models from scratch").”
Claim 22 recites a method with steps corresponding to the system with elements
recited in claim 1. Therefore, the recited steps of this claim are mapped to the
proposed combination in the same manner as the corresponding elements of system
claim 1. Additionally, the rationale and motivation to combine the Hall and Letterie
references, presented in rejection of claim 1 apply to this claim. The combination of Hall and Letterie teaches “(e) dilating the boundaries of the mammalian embryo in the plurality of digital images with the processor (Hall paragraph [0105] "Thresholding images using binary, Otsu, or adaptive methods. Includes morphological processing of the image using dilation ( opening), erosion ( closing) and scale
gradients, and using a scaled mask to extract the outer and inner boundaries of a shape");
(f) expanding the boundaries of the mammalian embryo in the plurality of digital images with the processor (Hall paragraph [0105] "Thresholding images using binary, Otsu, or adaptive methods. Includes morphological processing of the image using dilation ( opening), erosion ( closing) and scale
gradients, and using a scaled mask to extract the outer and inner boundaries of a shape");
(g) segmenting the plurality of digital images of mammalian embryos with the processor (Hall paragraph [0107] "Extracting the geometric properties of the boundaries using an elliptical Hough transform of the image contours, for example the best ellipse fit from an elliptical Hough transform calculated on the binary threshold map of the image. This method acts by selecting the hard boundary of the embryo in the image, and by cropping the square boundary of the new image so that the longest radius of the new ellipse is encompassed by the new image width and height, and so that the center of the ellipse is the center of the new image");
(h) cropping the plurality of digital images of mammalian embryos with the processor (Hall paragraph [0107] "This method acts by selecting the hard boundary of the embryo in the image, and by cropping the square boundary of the new image so that the longest radius of the new ellipse is encompassed by the new image width and height, and so that the center of the ellipse is the center of the new image"); and
(i) isolating the plurality of digital images of mammalian embryos with the processor (Hall paragraph [0108] "Zooming the image by ensuring a consistently centred image with a consistent border size around the elliptical region").”
Regarding claim 23, the combination of Hall and Letterie teaches “The system for predicting a pregnancy outcome in a mammalian embryo, according to Claim 1, further comprising suppression of light structures connected to the boundaries of the mammalian embryo in the plurality of digital images of mammalian embryos with the processor prior to the plurality of digital images of mammalian embryo being isolated (Hall paragraph [0104] "Normalizing the RGB (red-green-blue) or grayscale images to a fixed mean value for all the images […] This step ensured that color biases among the images were suppressed, and that the brightness of each image was normalized").”
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Hall and Letterie in view of Chan et al. (US 2020/0125818 A1), in further view of Yan et al. (US 2007 /0002275 A1).
Regarding claim 2, the combination of Hall and Letterie teaches “The system for predicting a pregnancy outcome in a mammalian embryo, according to Claim 1, wherein the boundaries of the mammalian embryos in the plurality of digital images are detected (Hall paragraph [0116] "One approach is Region-Convolutional Neural Net (or R-CNN) which uses an expensive search process is applied to search for image patch proposals (potential bounding boxes). These bounding boxes are then used to crop the regions of the image of interest. The cropped images are then run through a classifying model to classify the contents of the image region") with
However, the combination of Hall and Letterie is not relied on to teach “a Sobel filter and convolutional process utilizing the processor with the plurality of digital images of mammalian embryos being transformed into a symmetric linear structuring element for dilation”.
Chan teaches “a Sobel filter (Chan paragraph [0022] "the edge enhancement requires detecting the areas of high-frequency and large gradient magnitudes, and the traditional solutions thereof are based on differential operation such as Sobel operator") and convolutional process utilizing the processor with
It would have been obvious to a person having ordinary skill in the art before
effective filing date of the claimed invention of the instant application to combine a system for predicting embryo pregnancy viability as taught by Hall and Letterie to include a Sobel filter for detecting boundaries as taught by Chan.
The suggestion/motivation for doing so would have been “"In in vitro fertilisation (IVF), only a minority of the in vitro generated embryos have the ability to implant and to give a viable pregnancy, probably because of intrinsic characteristics of the zygotes. To increase the probability of implantation, the transfer of a single embryo with high implantation potential would be the ideal strategy. Identifying embryos with high implantation potential remains a challenge in IVF and different approaches have been adopted for that purpose. The most widely supported strategy to choose viable embryos is to rely on the grade of the embryos at the time of embryo transfer. Furthermore, legal constraints in some countries prevent the use of approaches involving embryo selection, identification of potentially viable embryos there is thus limited either to oocytes prior to fertilisation or to pronuclear stage zygotes" as noted by the Chan disclosure in paragraph 3.
However, the combination of Hall, Letterie, and Chan is not relied on to teach “the plurality of digital images of mammalian embryos being transformed into a symmetric linear structuring element for dilation”.
In an analogous field of endeavor, Yan teaches “the plurality of digital images of mammalian embryos being transformed into a symmetric linear structuring element for dilation (Yan paragraph [0047-0048] "Dilation of an image I in the gray value domain is a mapping function from R to R in R2 space. Given an image I and a structuring element B, the dilation operation D can be defined as: […] where B defines the neighboring region for (i,j). For MAs detection, a flat linear structuring element is used")”.
It would have been obvious to a person having ordinary skill in the art before
effective filing date of the claimed invention of the instant application to combine a system for predicting embryo pregnancy viability by detecting boundaries with a Sobel filter as taught by Hall, Letterie, and Chan to include a linear structuring for dilation as taught by Yan.
The suggestion/motivation for doing so would have been In order to address the above-described problem, a local adaptive algorithm is proposed for automatic detection of MAs, where multiple subregions of each image are automatically analyzed to adapt to local intensity variations and properties. A priori structural features and pathology, such as region and location information of vessels, optic disk and hard exudates, are further incorporated to improve the detection accuracy. The method effectively improves the specificity of MA detection in digital fundus images, without sacrificing sensitivity” as noted by the Yan disclosure in paragraph 18.
Therefore, it would have been obvious to combine the disclosure of Hall, Letterie, and Chan with the Yan disclosure to obtain the invention as specified in claim 2 as there is a reasonable expectation of success and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Claims 6-7 and 24 are rejected under 35 U.S.C. 103 as being unpatentable over Hall and Letterie in view of Bell et al. (US 2021/0172024 A1).
Regarding claim 6, the combination of Hall and Letterie teaches “The system for predicting a pregnancy outcome in a mammalian embryo, according to Claim 1, further comprising a deep neural network segmenter trained on the plurality of isolated digital images of mammalian embryos for (Hall paragraph [0084] "At least one Zona Deep Leaming model is trained on a set of Zona Pellucida images 103 in order to generate the Artificial Intelligence (AI) model 100 configured to generate an embryo viability score from an input image 104").”
However, the combination of Hall and Letterie is not relied on to teach “determining mammalian embryo pregnancy status with ridge regression models”.
In an analogous field of endeavor Bell teaches “determining mammalian embryo pregnancy status with ridge regression models (Bell paragraph [0312] "logistic RIDGE regression model trained to predict a binarized promoter methylation status based on specimen RNA datasets")”.
It would have been obvious to a person having ordinary skill in the art before
effective filing date of the claimed invention of the instant application to combine a system for predicting embryo pregnancy viability as taught by Hall and Letterie to include ridge regression model for predicting binary outcomes as taught by Bell.
The suggestion/motivation for doing so would have been " the trained RIDGE regression model exhibits >80% accuracy in withheld testing data and are well powered to discriminate BRCA-deficient (HRD+,biallelic genetic BRCAl/2 inactivation or deletion) from BRCA-intact (generally HRD-, BRCAl/2 wildtype) specimens" as noted by the Bell disclosure in paragraph 131.
Therefore, it would have been obvious to combine the disclosure of Hall and Letterie with the Bell disclosure to obtain the invention as specified in claim 6 as there is a reasonable expectation of success and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Regarding claim 7, the combination of Hall, Letterie, and Bell teaches “The system for predicting a pregnancy outcome in a mammalian embryo, according to Claim 1, wherein the deep neural network segmenter trained on the plurality isolated digital images of mammalian embryos for determining mammalian embryo pregnancy status (Hall paragraph [0128] "Each of the individual models are configured to estimate an embryo viability score of an embryo in an image, and the AI model combines selected models to produce an overall embryo viability score that is returned by the AI model") is performed on a U-Net with 512 features (Hall paragraph [0123] "an alternative U-Net architecture may be used that instead uses skip connections between the symmetric components of the encoder and decoder. Simply put, every encoding block has a corresponding block in the decoder. The features at each stage are then passed to the decoder alongside the lowest resolution feature representation. For each of the decoding blocks, the input feature representation is upsampled to match the resolution of its corresponding encoding block. The feature representation from the encoding block and the upsampled lower resolution features are then concatenated and passed through a 2D convolution layer. By concatenating the features in this way, the decoder can learn to refine the inputs at each block, choosing which details to integrate (low-res details or high-res details) depending on its input") and a ridge regression model that utilizes a [lambda] of 2 (Bell paragraph [0312] "logistic RIDGE regression model trained to predict a binarized promoter methylation status based on specimen RNA datasets").”
The proposed combination as well as the motivation for combining Hall, Letterie, and Bell references presented in the rejection of claim 6, applies to claim 7. Finally the system recited in claim 7 is met by Hall, Letterie, and Bell.
Regarding claim 24, the combination of Hall, Letterie, and Bell “The method for predicting a pregnancy outcome in a mammalian embryo, according to Claim 22, further comprising: utilizing a deep neural network segmenter trained on the segmented, cropped, and isolated plurality of digital images of mammalian embryos selected from the group consisting of a deep neural network image classification (Hall paragraph [0116] "One approach is Region-Convolutional Neural Net (or R-CNN) which uses an expensive search process is applied to search for image patch proposals (potential bounding boxes). These bounding boxes are then used to crop the regions of the image of interest. The cropped images are then run through a classifying model to classify the contents of the image region") or ridge regression models, with the processor (Bell paragraph [0312] "logistic RIDGE regression model trained to predict a binarized promoter methylation status based on specimen RNA datasets").”
The proposed combination as well as the motivation for combining Hall, Letterie, and Bell references presented in the rejection of claim 6, applies to claim 24. Finally the method recited in claim 24 is met by Hall, Letterie, and Bell.
Claims 9-10, 12, and 25-27 are rejected under 35 U.S.C. 103 as being unpatentable over Hall and Letterie in view of Saltz et al. (US 2020/0388029 A1).
Regarding claim 9, the combination of Hall and Letterie teaches “The system for predicting a pregnancy outcome in a mammalian embryo, according to Claim 1, further comprising (Hall paragraph [0128] "Each of the individual models are configured to estimate an embryo viability score of an embryo in an image, and the AI model combines selected models to produce an overall embryo viability score that is returned by the AI model").”
However, the combination of Hall and Letterie is not relied on to teach “an autoencoder for extracting features from the plurality of digital images”.
In an analogous field of endeavor Saltz teaches “an autoencoder for extracting features from the plurality of digital images (Saltz paragraph [0080] "a Convolutional Autoencoder (CAE) for fully unsupervised, simultaneous nucleus detection and feature extraction in histopathology tissue images")”.
It would have been obvious to a person having ordinary skill in the art before
effective filing date of the claimed invention of the instant application to combine a system for predicting embryo pregnancy viability as taught by Hall and Letterie to include autoencoder for feature extracting as taught by Saltz.
The suggestion/motivation for doing so would have been "Convolutional Autoencoder (CAE) for fully unsupervised, simultaneous nucleus detection and feature extraction in histopathology tissue images that is proven useful for the pipeline of digital image pathology analysis, including the quantification of TILs used in the classification and prognosis of cancer cells" as noted by the Saltz disclosure in paragraph 123.
Therefore, it would have been obvious to combine the disclosure of Hall and Letterie with the Saltz disclosure to obtain the invention as specified in claim 9 as there is a reasonable expectation of success and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Regarding claim 10, the combination of Hall, Letterie, and Saltz teaches “The system for predicting a pregnancy outcome in a mammalian embryo, according to Claim 9, wherein the extracted features are processed with a random forest classifier for determining mammalian embryo pregnancy status with the processor (Hall paragraph [0133] "Computer vision models rely on identifying key features of the image and expressing them in terms of descriptors. These descriptors may encode qualities such as pixel variation, gray level, roughness of texture, fixed comer points or orientation of image gradients, which are implemented in the OpenCV or similar libraries. By selection on such feature to search for in each image, a model can be built by finding which arrangement of the features is a good indicator for embryo viability. This procedure is best carried out by machine learning processes such as Random Forest or Support Vector Machines, which are able to separate the images in terms of their descriptions from the computer vision analysis").”
Regarding claim 12, the combination of the Hall, Letterie, and Saltz teaches “The system for predicting a pregnancy outcome in a mammalian embryo, according to Claim 11, wherein the deep neural network is a VGG16 network (Saltz paragraph [0365] "the system implements CNN-VGG and a Comparison of Experiment results was performed. The VGG 16-layer network was fine-tuned, which was pretrained on ImageNet. Fine-tuning the VGG16 network has been shown to be robust for pathology image classification").”
The proposed combination as well as the motivation for combining Hall, Letterie, and Saltz references presented in the rejection of claim 9, applies to claim 12. Finally the system recited in claim 12 is met by Hall, Letterie, and Saltz.
Regarding claim 25, the combination of Hall, Letterie, and Saltz “The method for predicting a pregnancy outcome in a mammalian embryo, according to Claim 22, further comprising: predicting a pregnancy outcome in a mammalian embryo with a methodology selected from a group consisting of a deep neural network segmenter with U-Net (Hall paragraph [0123] "an alternative U-Net architecture may be used that instead uses skip connections between the symmetric components of the encoder and decoder. Simply put, every encoding block has a corresponding block in the decoder. The features at each stage are then passed to the decoder alongside the lowest resolution feature representation. For each of the decoding blocks, the input feature representation is upsampled to match the resolution of its corresponding encoding block. The feature representation from the encoding block and the upsampled lower resolution features are then concatenated and passed through a 2D convolution layer. By concatenating the features in this way, the decoder can learn to refine the inputs at each block, choosing which details to integrate (low-res details or high-res details) depending on its input"), or
an autoencoder for extracting features from the plurality of digital images (Saltz paragraph [0080] "a Convolutional Autoencoder (CAE) for fully unsupervised, simultaneous nucleus detection and feature extraction in histopathology tissue images") of mammalian embryos (Hall paragraph [0091] "Imaging systems are typically light microscopes configured to capture single phase contrast images embryos").”
The proposed combination as well as the motivation for combining Hall, Letterie, and Saltz references presented in the rejection of claim 9, applies to claim 25. Finally the system recited in claim 25 is met by Hall, Letterie, and Saltz.
Regarding claim 26, the combination of Hall, Letterie, and Saltz teaches “The method for predicting a pregnancy outcome in a mammalian embryo, according to Claim 25, further comprising a per frame prediction of pregnancy (Hall paragraph [0092] "the image used in embodiments described herein may be a single image extracted from a video stream or a time lapse sequence of images of an embryo").”
Regarding claim 27, the combination of Hall, Letterie, and Saltz teaches “The method for predicting a pregnancy outcome in a mammalian embryo, according to Claim 25, further comprising a majority voting schema (Hall paragraph [0088] "based on the pregnancy outcome information or multiple AI models may be combined using an ensemble model which selects AI models and generates an outcome based on a voting strategy") of the per frame prediction of pregnancy (Hall paragraph [0128] "Each of the individual models are configured to estimate an embryo viability score of an embryo in an image, and the AI model combines selected models to produce an overall embryo viability score that is returned by the AI model").”
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JASPREET KAUR whose telephone number is (571)272-5534. The examiner can normally be reached Monday - Friday 7:30 am - 4:00 PST.
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, Amandeep Saini can be reached at (571)272-3382. 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.
/JASPREET KAUR/Examiner, Art Unit 2662
/AMANDEEP SAINI/Supervisory Patent Examiner, Art Unit 2662
Prosecution Insights