DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claims 1-10 are pending.
Claim Rejections - 35 USC § 103
The following is a quotation of pre-AIA 35 U.S.C. 103(a) which forms the basis for all obviousness rejections set forth in this Office action:
(a) A patent may not be obtained though the invention is not identically disclosed or described as set forth in section 102 of this title, if the differences between the subject matter sought to be patented and the prior art are such that the subject matter as a whole would have been obvious at the time the invention was made to a person having ordinary skill in the art to which said subject matter pertains. Patentability shall not be negatived by the manner in which the invention was made.
Claim(s) 1-2, 8 and 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wilson et al (US20210278655) in view of Wakui et al (US20190287244A1).
Regarding claim 1, Wilson teaches a cell image analysis method comprising:
a step of acquiring a cell image including a cell by an image acquirer;
(Wilson, "accessing an optical microscopy image comprising a set of corneal endothelial cells ... the image can be obtained via a system and/or apparatus implementing the set of operations 100, or can be obtained from a separate medical imaging system.", [0043]; acquisition/accessing of optical microscopy images containing cells for downstream analysis.)
a step of generating a background component image that extracts a distribution of a brightness component of a background from the cell image by filtering the acquired cell image, by a processor;
(Wilson, "a low-pass background image was generated via the same Gaussian blur previously mentioned", [0097]; generating a low-pass background image (background component image) by applying a Gaussian blur filter to the original image to capture uneven lighting)
a step of generating a corrected cell image that is acquired by correcting the cell image based on the cell image and the background component image to reduce unevenness of brightness, by the processor;
(Wilson, "Each of the correction methods significantly flattened the image ... this background image was subtracted from the original image, wherein the flattened image was normalized", [0097]; correcting the original image by subtracting the generated background image, which "flattens" the image and corrects for shading/illumination artifacts (reducing unevenness of brightness)
a first estimation step of estimating whether the cell in the image is an undifferentiated cell or a deviated cell by using the corrected cell image and a learned model that has learned to analyze the cell, by the processor.
(Wilson, " segmenting, based at least in part on a trained deep learning (DL) model, a plurality of corneal endothelial cells of the set of corneal endothelial cells in the pre-processed optical microscopy image", [0045]; Wakui, “the evaluator 21 of the present embodiment evaluates whether the cells included in the cell image are differentiated cells or are not undifferentiated cells based on the cell image of each region R of interest”, [0052]; "the evaluator evaluates at least whether the cells are in an undifferentiated state or a differentiated state." [claim 11]; Wilson and Wakui collectively teach the limitation of using a learned model to estimate if a cell is normal or abnormal because Wilson establishes the core automated deep learning infrastructure for segmenting and analyzing cells in "pre-processed" images corrected for shading or illumination artifacts, while Wakui specifically teaches a machine-learned evaluator designed to distinguish whether cells are in an "undifferentiated state or a differentiated state". Note that the specification of the instant application expressly defines undifferentiated cells as "normal" and differentiated (deviated) cells as "abnormal," (“In this embodiment, an undifferentiated cell is referred to as a normal cell ... Also, a deviated cell is referred to as an abnormal cell”, [0034]) a person of ordinary skill in the art would find it obvious to incorporate Wakui's specific cell-state classification logic into Wilson's deep learning pipeline to enable a processor to automatically estimate cellular health in images already normalized for uneven brightness
. This synergistic combination allows for high-throughput, objective evaluation of cell populations by applying specialized maturity assessment criteria to high-quality, corrected microscopic imagery)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to incorporate the specific cell-state classification logic of Wakui into the automated deep learning framework of Wilson in order to automatically distinguish between healthy (normal) and deviated (abnormal) cells in images already normalized for lighting artifacts. The combination of Wilson and Wakui also teaches other enhanced capabilities
Regarding claim 2, the combination of Wilson and Wakui teaches its/their respective base claim(s).
The combination further teaches the cell image analysis method according to claim 1, wherein the cell image is an image including a cell that is cultivated in a cultivation solution with which the cultivation container is filled, and is located in a near-edge area of the cultivation container as the cell.
(Wakui, "the cells as the imaging targets are contained in a well plate with multiple wells." [0049]; Wilson, "however, toward the edges and some blurry areas of the original images, the borders appear more gray because the algorithm is less confident here", [0098]; Wakui teaches that cells are cultivated in containers such as well plates. Wilson recognizes that image artifacts and low algorithm confidence often occur at the "edges" of cell images. Wilson’s illumination correction method may be applied to the cells located in the near-edge area of Wakui's cultivation container to resolve known problems such as the meniscus effect causing uneven brightness for improvement of classification accuracy for cells located near container boundaries)
Regarding claim 8, the combination of Wilson and Wakui teaches its/their respective base claim(s).
The combination further teaches the cell image analysis method according to claim 1, wherein
in the step of estimating whether the cell included in the corrected cell image is an undifferentiated cell or a deviated cell, an undifferentiated area, which is an area of the undifferentiated cell, and a deviated cell area, which is an area of the deviated cell, are estimated based on an estimation result estimated by the learned model, by the processor; and
the cell image analysis method further comprises a step of displaying the undifferentiated cell area and the deviated cell area discriminatively from each other, by the processor.
(Wakui, " As the staining map, a color map in which the staining states are color-coded based on, for example, magnitudes of the predicted staining color intensities may be generated, and the generated color map may be displayed on the display device 30." [0078]; generating and displaying a color-coded "staining map" that discriminatively shows the state of cells)
Regarding claim 10, the combination of Wilson and Wakui teaches its/their respective base claim(s).
The combination further teaches the cell image analysis method according to claim 1 further comprising a step of producing the learned model by training a learning model by using corrected cell images, by the processor.
(Wilson, Fig. 2, “at 220, pre-processing each optical microscopy image of the training set to correct for at least one of shading or illumination artifacts”, [0050]; “at 230, training a model via deep learning based on the training set of images and the associated ground truth segmentations of the endothelial cells of each image of the training set”, [0051]; training a learning model using cell images that are pre-processed, i.e., corrected for shading/illumination artifacts, matching exactly the claimed “corrected cell images.”)
Claim(s) 3-5 and 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wilson et al (US20210278655) in view of Wakui et al (US20190287244A1) and further in view of Hooper (US20130022287A1).
Regarding claim 3, the combination of Wilson and Wakui teaches its/their respective base claim(s).
The combination does not expressly disclose but Hooper teaches the cell image analysis method according to claim 1, wherein the filtering is a process of applying a median filter to the cell image to generate the background component image.
(Hooper, “a modified median filter is applied to a source image, I_source, to derive a filtered image I_filter. The median filter ... is a hybrid multi-stage median filter, which is a modified version of the finite-impulse response (FIR) median hybrid filter”, [0170]; Hooper teaches that a variation of a median filter is well-suited for obtaining low-frequency local color values for use in image enhancement. Furthermore, Hooper notes that while Gaussian or weighted average filters are sensitive to the magnitude of detail, median filters are primarily sensitive only to size, allowing small but very bright or dark features to be ignored or left intact in the filtered background)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to incorporate the teachings of Hooper into the modified system or method of Wilson and Ma in order to improve the accuracy and robustness of the background extraction process by utilizing a filter that can effectively ignore localized intensity outliers—such as stray light or debris—that might otherwise distort a standard smoothing filter like the Gaussian blur used in Wilson. The combination of Wilson, Wakui and Hooper also teaches other enhanced capabilities.
Regarding claim 4, the combination of Wilson and Wakui teaches its/their respective base claim(s).
The combination of Wilson, Wakui and Hooper teaches the cell image analysis method according to claim 1 further comprising a step of reducing the cell image, by the processor, wherein
in the step of generating a background component image, a reduced background component image is generated as the background component image by filtering the reduced cell image, by the processor; and
the cell image analysis method further comprises a step of increasing the reduced background component image, by the processor.
(Hooper, “For images having color channels with more than eight bits per color, the present invention down-samples the images to eight bits per color prior to application of the filter”, [0354]; “enhancing, say, a six mega-pixel image and then sub-sampling to a one mega-pixel image produces an image that is nearly identical to the image produced by first sub-sampling and then enhancing. Such invariance to scale is an important advantage of the present invention, since enhancement can be performed on a sub-sampled image used for previewing while a user is adjusting enhancement parameters. When the user then commits the parameters, for example, by clicking on an “Apply” button, the full-resolution image can be enhanced, and the resulting enhanced image will appear as the user expects”; [0206]; “If a user employs magnification to zoom in on a photo, then the contrast-enhanced image of reduced resolution may be missing much of the detail in the photo”, [0529]; downsampling (reducing) images for preview, performing filtering/enhancement at low resolution, then applying parameters to the original full (increased) image for the final result)
Regarding claim 5, the combination of Wilson and Wakui teaches its/their respective base claim(s).
The combination of Wilson, Wakui and Hooper teaches the cell image analysis method according to claim 1 further comprising a step of accepting a user input instruction to select whether to generate the corrected cell image or not, by the processor, wherein
if the corrected cell image is to be generated, the step of generating a corrected cell image is executed, and the first estimation step is executed by using corrected cell images and the learned model, by the processor; and
the cell image analysis method further comprises a second estimation step of estimating whether the cell in the image is an undifferentiated cell or a deviated cell by using the cell image and the learned model without executing the step of generating a background component image if the corrected cell image is not to be generated, by the processor.
(Wilson, Wakui, see comments on claim 1; Hooper, “a user interface that enables a user to adjust the brightening and darkening response curves using two user parameters; namely, a brighten and a darken parameter”, [0136]; “a user interface that enables a user to directly modify the brightening and darkening response curves by dragging them upwards or downwards, or by clicking on a pixel location with the image or by clicking within a response curve visualization panel”, [0138]; enables a user to select, via GUI, whether and how to apply enhancement and corrections, including bypassing steps and directly controlling filtered/corrected result versus unprocessed image; this supports a workflow wherein user input controls the method branch)
Regarding claim 7, the combination of Wilson and Wakui teaches its/their respective base claim(s).
The combination of Wilson, Wakui and Hooper teaches the cell image analysis method according to The cell image analysis method according to wherein in the step of generating a corrected cell image, the corrected cell image is generated by subtracting the background component image from the cell image and by adding a predetermined brightness value, by the processor.
(Hooper, “The enhancement process subtracts the local offset values from color values of the original source image, and multiplies the resulting differences by the local brightening and darkening multipliers”, [0159]; eqs. 5(A) –(5D), [0210 -0213]; a process of subtracting a background component (offset), then adding a user-determined value or offset (brightness))
Allowable Subject Matter
Claim(s) 6 and 9 is/are allowed.
Response to Arguments
Applicant's arguments filed on 5/14/2026 with respect to one or more of the pending claims have been fully considered but are moot in view of the new ground(s) of rejection.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JIANXUN YANG whose telephone number is (571)272-9874. The examiner can normally be reached on MON-FRI: 8AM-5PM Pacific Time.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Amandeep Saini can be reached on (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.
/JIANXUN YANG/
Primary Examiner, Art Unit 2662 7/12/2026
Prosecution Insights