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 .
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, 8-10, 14, 15, and 17-20 are rejected under 35 U.S.C. 103 as being unpatentable over Sammak et al. (US Pub. 2001/0041347), hereinafter Sammak, in view of Cleary et al. (US Pub. 2020/0152289), hereinafter Cleary.
Regarding claim 1, Sammak discloses a method of generating artificial images for medical evaluation of eukaryotic cells, comprising: extracting each instance of single-cells in an image of eukaryotic cells (Paragraph [0181]: original cytoplasm image was thresholded, creating a cytoplasmic mask image. Local regions containing cells were defined around the nuclei. The limits of the cells in those regions were then defined by a local dynamic threshold operation on the same region in the fluorescent antibody image. A sequence of erosions and dilations was used to separate slightly touching cells and a set of cytoplasm morphological descriptors was used to identify single cells. The area of the individual cells was tabulated in order to define the distribution of cell sizes for comparison with size data from normal and hypertrophic cells; Paragraphs [0216]-[0218]: cytoplasmic objects that are identified as distinct may contain one or more nucleus ("nucleus object") within the area defined by the cytoplasmic object. Such nucleus objects may be colonies of cells instead of single cells, which can be accounted for by adjusting the maximum number of nucleus objects in a valid cytoplasmic object. This parameter can be set to 1 (i.e.: all objects studied will be single cells) if mono-disperse cells are plentiful in the images or if analysis of only single cells is desired. Otherwise, the parameter can be set higher, and the size and/or morphology of colonies can also be analyzed by this approach…Cells touching the edge of the field of view can optionally be excluded, since their area and shape measurements may be incomplete. Cells that are in large clumps can also be excluded if desired. The morphology of clumps depends on cell-cell contact more than cell-substrate contact, while single cells and small colonies are more dependent on cell-substrate adhesion. Thus, the method allows a user to select cell subpopulations that will report more selectively on agents that affect spreading of cells on defined substrates…cell spreading assay processes the nuclear and cytoplasmic images to generate nuclear and cytoplasmic masks and single cell data is generated from the masks and raw images. Processing of the nuclear and cytoplasmic images optionally includes an initial background compensation step, involving the removal of small bright spots and gradual variations in background across the field. Further processing of the nuclear and cytoplasmic images comprises the creation of the nuclear mask and the cytoplasmic mask); extracting each instance of multi-cells in the image of eukaryotic cells (Paragraph [0088]: the present invention provides a method for analyzing cells comprising providing an array of locations which contain multiple cells wherein the cells contain one or more fluorescent reporter molecules; scanning multiple cells in each of the locations containing cells to obtain fluorescent signals from the fluorescent reporter molecule in the cells; converting the fluorescent signals into digital data; and utilizing the digital data to determine the distribution, environment or activity of the fluorescent reporter molecule within the cells; Paragraph [0212]: the cells to be analyzed further possess at least a second luminescent reporter molecules to identify individual cells in the population by the presence of a bright luminescent spot, scanning multiple cells in each of the locations to acquire a spot image from the second luminescent reporter molecule, creating a spot mask from the spot image, and using the spot mask and the cytoplasmic mask to automatically calculate one or more morphological features that provide a measure of cell spreading; Paragraph [0341]: present method provides high-content and combined high throughput-high content cell-based screens for anti-microtubule drugs, particularly as one parameter in a multi-parametric cancer target screen. The EGFP-MAP4 construct used herein can also be used as one of the components of a high-content screen that measures multiple signaling pathways or physiological events. In a preferred embodiment, a combined high throughput and high content screen is employed, wherein multiple cells in each of the locations containing cells are analyzed in a high throughput mode, and only a subset of the locations containing cells are analyzed in a high content mode. The high throughput screen can be any screen that would be useful to identify those locations containing cells that should be further analyzed, including, but not limited to, identifying locations with increased luminescence intensity, those exhibiting expression of a reporter gene, those undergoing calcium changes, and those undergoing pH change); generating a background image from the image of eukaryotic cells (Paragraph [0102]: images are acquired of a primary marker 105 (FIG. 9) (typically cell nuclei counterstained with DAPI or PI fluorescent dyes) which are segmented ("identified") using an adaptive thresholding procedure. The adaptive thresholding procedure 106 is used to dynamically select the threshold of an image for separating cells from the background. The staining of cells with fluorescent dyes can vary to an unknown degree across cells in a microtiter plate sample as well as within images of a field of cells within each well of a microtiter plate. This variation can occur as a result of sample preparation and/or the dynamic nature of cells. A global threshold is calculated for the complete image to separate the cells from background and account for field to field variation Paragraph [0218]: cell spreading assay processes the nuclear and cytoplasmic images to generate nuclear and cytoplasmic masks and single cell data is generated from the masks and raw images. Processing of the nuclear and cytoplasmic images optionally includes an initial background compensation step, involving the removal of small bright spots and gradual variations in background across the field. Further processing of the nuclear and cytoplasmic images comprises the creation of the nuclear mask and the cytoplasmic mask); selecting a set of cells from the extracted single-cells and the extracted multi-cells (Paragraph [0217]: Cells touching the edge of the field of view can optionally be excluded, since their area and shape measurements may be incomplete. Cells that are in large clumps can also be excluded if desired. The morphology of clumps depends on cell-cell contact more than cell-substrate contact, while single cells and small colonies are more dependent on cell-substrate adhesion. Thus, the method allows a user to select cell subpopulations that will report more selectively on agents that affect spreading of cells on defined substrates).
Sammak does not explicitly disclose applying at least one augmentation technique to each cell in the set of cells to generate augmented cells; and generating an artificial image of eukaryotic cells using the augmented cells and the background image.
However, Cleary teaches cell imaging (Abstract), further comprising applying at least one augmentation technique to each cell in the set of cells to generate augmented cells (Paragraphs [0690]-[0691]: the current approach does not require resolving individual spots, a current fundamental limitation to scaling existing IT, or on cell segmentation. To scale up the workflow, computational methods for identifying co-expression pattern; novel experimental techniques for generating composite images at scale; and a scalable composite image processing and decompression pipeline are investigated…address challenges in IT to drastically scale up both throughput and information content by integrating compressed sensing and optimization methods with advanced optics, building on the interdisciplinary team of compressed sensing, optimization, optics, and biological experts); and generating an artificial image of eukaryotic cells using the augmented cells and the background image (Paragraph [0663]: Applicants ran a series of image processing steps to normalize, stitch, align, and segment the images in each color, field of view, round, and tissue. Applicants first took a maximum projection across the z-axis, and then used the DAPI channel to stitch the fields of view within each round of imaging (using ImageJ software (Abramoff et al., 2004)). Applicants applied the stitching coordinates from the DAPI channel to each of the other channels. Applicants then smoothed the image for each channel using a median filter (with a width of 8 pixels). (If spot-level resolution is needed, this step may not be advised. Since Applicants do not need this resolution, Applicants use this step to make autoencoder reconstruction an easier task.) From each smoothed image, Applicants aligned and subtracted background signal, obtained by imaging after stripping the final round of fluorescent probes. Applicants then adjusted brightness and contrast by rescaling according to upper and lower thresholds determined using auto-adjust in ImageJ. The same rescaling parameters for each channel (determined from the maximum upper threshold and minimum lower threshold) were applied to all tissues and rounds. After rescaling, Applicants applied a flat field correction to each field of view, by normalizing (dividing) each pixel by the median smoothed pixel intensity across all images (with smoothing by a Gaussian filter with a width ⅛ of the image dimension). Each round of the flat field-corrected images in a given tissue was then aligned using ImageJ. These images were used in the remainder of downstream analysis; Paragraph [0721]: First, Applicants will confirm the expected patterns for genes known to correlate with morphological or gross features (e.g., genes expressed only in outer cortical layers). Second, Applicants will confirm correlation across the image for genes known to be expressed in the same cells. Third, in each experiment Applicants will generate images with probes for a subsets of individual genes as internal controls… Use molecular normalization to reduce signal in proportion to expected abundances (Aim 1.2); (2) Apply the mathematics of compressed sensing to super resolve individual spots from low resolution data in which spots appear merged (Aim 3); and (3) Leverage the fact that the decompression algorithm does not depend on the resolution of individual spots, but only on the net signal of composite measurements in entire cells. Applicants can therefore use alternative protocols that do not rely on combinatorial labeling (e.g., in situ HCR′). Noise and bias in scRNA-Seq training data. The scRNA-Seq data Applicants use in training, can be compromised by noise (including zero-inflation) and by cell composition biases introduced during tissue dissociation or nuclei preps. To address noise, Applicants will model the noise process in scRNA-Seq, as has been previously done.sup.24. For cell type composition biases, Applicants will first rely on the fact that the decompression methods operate cell-by-cell, and do not require assumptions on the overall abundance of any given cell type. In case that the gene modules (e.g., U in matrix factorization) are biased in favor of certain cell types, Applicants will apply methods of correcting for sampling bias.sup.25 when training gene modules. Finally, Applicants will assess the benefit of foregoing training altogether by adapting methods of Blind Compressed Sensing (BCS), for which Applicants (Eldar) developed the theory.sup.26, and Applicants (Cleary, Regev) have shown the application to gene expression.sup.17. This, however, requires a greater number of composite images to be generated). Cleary teaches that this will allow for accurate and high-throughput cell detection, quantification and/or sorting, exploiting a variety of physical principles (Paragraph [0339]), Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Sammak with the features of above as taught by Cleary so as to allow for accurate cell detection as presented by Cleary.
Regarding claim 8, Sammak, in view of Cleary teaches the method of claim 1, Cleary discloses wherein generating the artificial image of eukaryotic cells using the augmented cells and the background image comprises: placing a selection of the augmented cells on the background image (Paragraph [0663]: Applicants ran a series of image processing steps to normalize, stitch, align, and segment the images in each color, field of view, round, and tissue. Applicants first took a maximum projection across the z-axis, and then used the DAPI channel to stitch the fields of view within each round of imaging (using ImageJ software (Abramoff et al., 2004)). Applicants applied the stitching coordinates from the DAPI channel to each of the other channels. Applicants then smoothed the image for each channel using a median filter (with a width of 8 pixels). (If spot-level resolution is needed, this step may not be advised. Since Applicants do not need this resolution, Applicants use this step to make autoencoder reconstruction an easier task.) From each smoothed image, Applicants aligned and subtracted background signal, obtained by imaging after stripping the final round of fluorescent probes. Applicants then adjusted brightness and contrast by rescaling according to upper and lower thresholds determined using auto-adjust in ImageJ. The same rescaling parameters for each channel (determined from the maximum upper threshold and minimum lower threshold) were applied to all tissues and rounds. After rescaling, Applicants applied a flat field correction to each field of view, by normalizing (dividing) each pixel by the median smoothed pixel intensity across all images (with smoothing by a Gaussian filter with a width ⅛ of the image dimension). Each round of the flat field-corrected images in a given tissue was then aligned using ImageJ. These images were used in the remainder of downstream analysis; Paragraph [0721]: First, Applicants will confirm the expected patterns for genes known to correlate with morphological or gross features (e.g., genes expressed only in outer cortical layers). Second, Applicants will confirm correlation across the image for genes known to be expressed in the same cells. Third, in each experiment Applicants will generate images with probes for a subsets of individual genes as internal controls… Use molecular normalization to reduce signal in proportion to expected abundances (Aim 1.2); (2) Apply the mathematics of compressed sensing to super resolve individual spots from low resolution data in which spots appear merged (Aim 3); and (3) Leverage the fact that the decompression algorithm does not depend on the resolution of individual spots, but only on the net signal of composite measurements in entire cells. Applicants can therefore use alternative protocols that do not rely on combinatorial labeling (e.g., in situ HCR′). Noise and bias in scRNA-Seq training data. The scRNA-Seq data Applicants use in training, can be compromised by noise (including zero-inflation) and by cell composition biases introduced during tissue dissociation or nuclei preps. To address noise, Applicants will model the noise process in scRNA-Seq, as has been previously done.sup.24. For cell type composition biases, Applicants will first rely on the fact that the decompression methods operate cell-by-cell, and do not require assumptions on the overall abundance of any given cell type. In case that the gene modules (e.g., U in matrix factorization) are biased in favor of certain cell types, Applicants will apply methods of correcting for sampling bias.sup.25 when training gene modules. Finally, Applicants will assess the benefit of foregoing training altogether by adapting methods of Blind Compressed Sensing (BCS), for which Applicants (Eldar) developed the theory.sup.26, and Applicants (Cleary, Regev) have shown the application to gene expression.sup.17. This, however, requires a greater number of composite images to be generated).
Regarding claim 9, Sammak, in view of Cleary teaches the method of claim 8, Sammak discloses wherein the selection of the augmented cells mimics a distribution of the eukaryotic cells in the image of eukaryotic cells (Paragraphs [0075]-[0078]: An optical system that can acquire images of single cell layers in multilayer preparations is required for use with cell lines that tend to form layers. The large depth of field of wide field microscopes produces an image that is a projection through the many layers of cells, making analysis of subcellular spatial distributions extremely difficult in layer-forming cells. Alternatively, the very shallow depth of field that can be achieved on a confocal microscope, (about one micron), allows discrimination of a single cell layer at high resolution, simplifying the determination of the subcellular spatial distribution. Similarly, confocal imaging is preferable when detection modes such as fluorescence lifetime imaging are required…microplate chamber 42 serves as a microfluidic delivery system for the addition of compounds to cells. The microplate 41 in the microplate chamber 42 is placed in an XY microplate reader 43. Digital data is processed as described above. The small size of this microplate system increases throughput, minimizes reagent volume and allows control of the distribution and placement of cells for fast and precise cell-based analysis. Processed data can be displayed on a PC screen 11 and made part of a bioinformatics data base 44. This data base not only permits storage and retrieval of data obtained through the methods of this invention, but also permits acquisition and storage of external data relating to cells. FIG. 5 is a PC display which illustrates the operation of the software).
Regarding claim 10, Sammak, in view of Cleary teaches the method of claim 8, Cleary discloses wherein the selected augmented cells are placed randomly on the background image (Paragraph [0267]: the sparse coding solving process comprises sparse module activity factorization (SMAF) for the matrix factorization step and blind compressed sensing (BCS) to learn the System Matrix S. SMAF may be used to find the initial sample clusters and modules for BCS. Given the SMAF approximation, the dictionary may be updated using standard algorithms, then the module activity levels may be updated, and then all three steps may be iterated. For example, noisy composite measurements may be simulated across a randomly selected subset of genes; Paragraph [0656]: Applicants varied the total number of measurements (from 8 to 12), and the maximum number of measurements in which each gene appeared (either 2, 3, or 4). Each gene was then randomly assigned to a randomly chosen number of measurements (up to the maximum). Final assignments resulting in either two or more genes being perfectly co-assigned or in large measurement imbalance (any gene appearing more than 4 times more frequently than any other gene) were excluded. Applicants then iterated steps (i)-(v) 2,000 times, selected the 50 composition matrices resulting in the top correlations, and evaluated (steps (ii)-(v)) in testing data. The correlations in testing data were then used to compare different numbers of measurements, and maximum assignments per gen).
Regarding claim 14, Sammak, in view of Cleary teaches the method of claim 1, Cleary discloses wherein the at least one augmentation technique applied to each cell corresponds to a particular augmentation policy of a pre-determined selection of a set of augmentation techniques (Paragraphs [0690]-[0691]: the current approach does not require resolving individual spots, a current fundamental limitation to scaling existing IT, or on cell segmentation. To scale up the workflow, computational methods for identifying co-expression pattern; novel experimental techniques for generating composite images at scale; and a scalable composite image processing and decompression pipeline are investigated…address challenges in IT to drastically scale up both throughput and information content by integrating compressed sensing and optimization methods with advanced optics, building on the interdisciplinary team of compressed sensing, optimization, optics, and biological experts).
Regarding claim 15, Sammak, in view of Cleary teaches the method of claim 14, Cleary wherein augmentation techniques of the pre-determined selection of the set of augmentation techniques are selected from FlipLR, FlipUD, AutoContrast, Equalize, Rotate, Posterize, Contrast, Brightness, Sharpness, Smooth, and Resize (Paragraphs [0690]-[0691]: the current approach does not require resolving individual spots, a current fundamental limitation to scaling existing IT, or on cell segmentation. To scale up the workflow, computational methods for identifying co-expression pattern; novel experimental techniques for generating composite images at scale; and a scalable composite image processing and decompression pipeline are investigated…address challenges in IT to drastically scale up both throughput and information content by integrating compressed sensing and optimization methods with advanced optics, building on the interdisciplinary team of compressed sensing, optimization, optics, and biological experts).
Regarding claim 17, Sammak, in view of Cleary teaches the method of claim 1, Sammak discloses wherein extracting each instance of single-cells includes identifying each instance of single-cells in the image of eukaryotic cells, labelling each instance of single-cells as a single-cell, and storing each instance of single-cells in a single-cell resource (Paragraph [0088]: the present invention provides a method for analyzing cells comprising providing an array of locations which contain multiple cells wherein the cells contain one or more fluorescent reporter molecules; scanning multiple cells in each of the locations containing cells to obtain fluorescent signals from the fluorescent reporter molecule in the cells; converting the fluorescent signals into digital data; and utilizing the digital data to determine the distribution, environment or activity of the fluorescent reporter molecule within the cells; Paragraph [0212]: the cells to be analyzed further possess at least a second luminescent reporter molecules to identify individual cells in the population by the presence of a bright luminescent spot, scanning multiple cells in each of the locations to acquire a spot image from the second luminescent reporter molecule, creating a spot mask from the spot image, and using the spot mask and the cytoplasmic mask to automatically calculate one or more morphological features that provide a measure of cell spreading; Paragraph [0341]: present method provides high-content and combined high throughput-high content cell-based screens for anti-microtubule drugs, particularly as one parameter in a multi-parametric cancer target screen. The EGFP-MAP4 construct used herein can also be used as one of the components of a high-content screen that measures multiple signaling pathways or physiological events. In a preferred embodiment, a combined high throughput and high content screen is employed, wherein multiple cells in each of the locations containing cells are analyzed in a high throughput mode, and only a subset of the locations containing cells are analyzed in a high content mode. The high throughput screen can be any screen that would be useful to identify those locations containing cells that should be further analyzed, including, but not limited to, identifying locations with increased luminescence intensity, those exhibiting expression of a reporter gene, those undergoing calcium changes, and those undergoing pH change).
Regarding claim 18, Sammak, in view of Cleary teaches the method of claim 1, Sammak discloses wherein extracting each instance of multi-cells includes identifying each instance of multi-cell groupings in the image of eukaryotic cells, labelling each instance of multi-cells as a multi-cell, and storing each instance of multi-cells in a multi-cell resource (Paragraph [0088]: the present invention provides a method for analyzing cells comprising providing an array of locations which contain multiple cells wherein the cells contain one or more fluorescent reporter molecules; scanning multiple cells in each of the locations containing cells to obtain fluorescent signals from the fluorescent reporter molecule in the cells; converting the fluorescent signals into digital data; and utilizing the digital data to determine the distribution, environment or activity of the fluorescent reporter molecule within the cells; Paragraph [0212]: the cells to be analyzed further possess at least a second luminescent reporter molecules to identify individual cells in the population by the presence of a bright luminescent spot, scanning multiple cells in each of the locations to acquire a spot image from the second luminescent reporter molecule, creating a spot mask from the spot image, and using the spot mask and the cytoplasmic mask to automatically calculate one or more morphological features that provide a measure of cell spreading; Paragraph [0341]: present method provides high-content and combined high throughput-high content cell-based screens for anti-microtubule drugs, particularly as one parameter in a multi-parametric cancer target screen. The EGFP-MAP4 construct used herein can also be used as one of the components of a high-content screen that measures multiple signaling pathways or physiological events. In a preferred embodiment, a combined high throughput and high content screen is employed, wherein multiple cells in each of the locations containing cells are analyzed in a high throughput mode, and only a subset of the locations containing cells are analyzed in a high content mode. The high throughput screen can be any screen that would be useful to identify those locations containing cells that should be further analyzed, including, but not limited to, identifying locations with increased luminescence intensity, those exhibiting expression of a reporter gene, those undergoing calcium changes, and those undergoing pH change).
Regarding claim 19, Sammak, in view of Cleary teaches the method of claim 1, Cleary discloses wherein selecting the set of cells from the extracted single-cells and the extracted multi-cells comprises randomly selecting the cells (Paragraph [0267]: the sparse coding solving process comprises sparse module activity factorization (SMAF) for the matrix factorization step and blind compressed sensing (BCS) to learn the System Matrix S. SMAF may be used to find the initial sample clusters and modules for BCS. Given the SMAF approximation, the dictionary may be updated using standard algorithms, then the module activity levels may be updated, and then all three steps may be iterated. For example, noisy composite measurements may be simulated across a randomly selected subset of genes; Paragraph [0656]: Applicants varied the total number of measurements (from 8 to 12), and the maximum number of measurements in which each gene appeared (either 2, 3, or 4). Each gene was then randomly assigned to a randomly chosen number of measurements (up to the maximum). Final assignments resulting in either two or more genes being perfectly co-assigned or in large measurement imbalance (any gene appearing more than 4 times more frequently than any other gene) were excluded. Applicants then iterated steps (i)-(v) 2,000 times, selected the 50 composition matrices resulting in the top correlations, and evaluated (steps (ii)-(v)) in testing data. The correlations in testing data were then used to compare different numbers of measurements, and maximum assignments per gen).
Regarding claim 20, Sammak, in view of Cleary teaches the method of claim 1, Sammak discloses wherein selecting the set of cells from the extracted single-cells and the extracted multi-cells comprises mimicking a distribution of the eukaryotic cells in the original image of eukaryotic cells (Paragraphs [0075]-[0078]: An optical system that can acquire images of single cell layers in multilayer preparations is required for use with cell lines that tend to form layers. The large depth of field of wide field microscopes produces an image that is a projection through the many layers of cells, making analysis of subcellular spatial distributions extremely difficult in layer-forming cells. Alternatively, the very shallow depth of field that can be achieved on a confocal microscope, (about one micron), allows discrimination of a single cell layer at high resolution, simplifying the determination of the subcellular spatial distribution. Similarly, confocal imaging is preferable when detection modes such as fluorescence lifetime imaging are required…microplate chamber 42 serves as a microfluidic delivery system for the addition of compounds to cells. The microplate 41 in the microplate chamber 42 is placed in an XY microplate reader 43. Digital data is processed as described above. The small size of this microplate system increases throughput, minimizes reagent volume and allows control of the distribution and placement of cells for fast and precise cell-based analysis. Processed data can be displayed on a PC screen 11 and made part of a bioinformatics data base 44. This data base not only permits storage and retrieval of data obtained through the methods of this invention, but also permits acquisition and storage of external data relating to cells. FIG. 5 is a PC display which illustrates the operation of the software).
Allowable Subject Matter
Claims 2-7, 11-13, and 16 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Claim 2 is allowable over the prior art of record since the cited references taken individually or in combination fails to particularly disclose or suggest a method comprising replacing values of the inside pixels with values corresponding to certain pixels found outside of the bounding box that are similar in values as bordering pixels of the bounding box to remove the at least one instance of the eukaryotic cell in the image of eukaryotic cells, wherein the certain pixels found outside of the bounding box are outside pixels, as presented in the environment of the remaining limitations of claim 2. It is noted that the closest prior art, Sammak, shows the limitations of claim 1, and generating a bounding box around at least one instance of a eukaryotic cell in the image of eukaryotic cells, wherein pixels of the image of eukaryotic cells inside the bounding box are inside pixels. However, the Sammak fails to disclose or suggest replacing values of the inside pixels with values corresponding to certain pixels found outside of the bounding box that are similar in values as bordering pixels of the bounding box to remove the at least one instance of the eukaryotic cell in the image of eukaryotic cells, wherein the certain pixels found outside of the bounding box are outside pixels.
Claim 11 is allowable over the prior art of record since the cited references taken individually or in combination fails to particularly disclose or suggest a method comprising wherein placing the selection of the augmented cells on the background image comprises: comparing pixels from four corners of the bounding box to pixels in the background image to determine a target location, wherein the target location is an area of the background image where the pixels in the background image have a highest degree of similarity to the pixels in the four corners of the bounding box; placing the at least one of the selection of the augmented single-cells and the augmented multi-cells in the target location; creating a cell masking image, wherein the cell masking image includes a black color background and a white area in the middle, wherein the white area is substantially the same shape as the at least one cell from the selection of the augmented single-cells and the augmented multi- cells; and applying a Gaussian filter to smooth a transition between texture of the background image and texture of the at least one cell from the selection of the augmented single-cells and the augmented multi-cells, as presented in the environment of the remaining limitations of claim 11. It is noted that the closest prior art, Sammak, shows the limitations of claim 8, and generating a bounding box around at least one cell from the selection of the augmented cells. However, the Sammak fails to disclose or suggest wherein placing the selection of the augmented cells on the background image comprises: comparing pixels from four corners of the bounding box to pixels in the background image to determine a target location, wherein the target location is an area of the background image where the pixels in the background image have a highest degree of similarity to the pixels in the four corners of the bounding box; placing the at least one of the selection of the augmented single-cells and the augmented multi-cells in the target location; creating a cell masking image, wherein the cell masking image includes a black color background and a white area in the middle, wherein the white area is substantially the same shape as the at least one cell from the selection of the augmented single-cells and the augmented multi- cells; and applying a Gaussian filter to smooth a transition between texture of the background image and texture of the at least one cell from the selection of the augmented single-cells and the augmented multi-cells.
Claim 16 is allowable over the prior art of record since the cited references taken individually or in combination fails to particularly disclose or suggest a method comprising identifying the particular augmentation policy used for the at least one augmentation technique applied to each cell, wherein identifying the particular augmentation policy used for the at least one augmentation technique applied to each cell comprises: applying potential policies of combinations of augmentation techniques to a cell; scoring results of the application of the potential policies; ranking the scored results; and selecting a highest ranking one or more potential policies as the particular augmentation policy, as presented in the environment of the remaining limitations of claim 16. It is noted that the closest prior art, Sammak, shows the limitations of claim 14. However, the Sammak fails to disclose or suggest identifying the particular augmentation policy used for the at least one augmentation technique applied to each cell, wherein identifying the particular augmentation policy used for the at least one augmentation technique applied to each cell comprises: applying potential policies of combinations of augmentation techniques to a cell; scoring results of the application of the potential policies; ranking the scored results; and selecting a highest ranking one or more potential policies as the particular augmentation policy.
Claims 3-7 and 12-13 each depend from one of the above claims and would accordingly be allowable.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Sherman et al. (US Pub. 2024/0426737) teaches super-resolution imaging of cells.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MATTHEW D SALVUCCI whose telephone number is (571)270-5748. The examiner can normally be reached M-F: 7:30-4:00PT.
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, XIAO WU can be reached at (571) 272-7761. 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.
/MATTHEW SALVUCCI/Primary Examiner, Art Unit 2613
Prosecution Insights