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 1-5, 8-17, 20 are rejected under 35 U.S.C. 103 as being unpatentable over Matsumoto et al. (US20130163809A1, hereinafter referred to as Matsumoto) in view of Jawahar et al. (US20220230733A1, hereinafter referred to as Jawahar).
Regarding claim 1, Matsumoto teaches a method for measuring a thickness (met by pipe thickness measuring device and method). This is read in (Paragraph [0066]).
PNG
media_image1.png
76
506
media_image1.png
Greyscale
Matsumoto fails to teach training neural networks, by a learning part, generating a pipe image that distinguishes a pipe from a non-pipe object in a radiographic image. However, Jawahar amends this deficiency.
Jawahar teaches training a neural network by generating segmented images as well as using these images to further train the model.
PNG
media_image2.png
191
417
media_image2.png
Greyscale
PNG
media_image3.png
578
417
media_image3.png
Greyscale
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Matsumoto to incorporated the teachings of Jawahar in order to provide a system and method for generating an optimized medical image using a machine learning model (Abstract).
Regarding distinguishing a pipe from a non-pipe object in a radiographic image, Matsumoto teaches a luminance profile divided into two sectors, or in a given example, three regions: a region inside the two outer diameter inputs and regions outside the two outer diameter points. This is read in (Paragraph [0091]).
PNG
media_image4.png
174
510
media_image4.png
Greyscale
By being able to incorporate neural network based image segmentation, and determining regions of a pipe against regions outside of the pipe, the combination of Matsumoto and Jawahar meets generating, by a recognition part, the pipe image using the neural networks.
Matsumoto further teaches measuring, by a measuring part, a pipe thickness as a distance between a first pixel on a first outer circumferential surface of the pipe and a second pixel on an inner circumferential surface of the pipe, the inner circumferential surface being closest to the first pixel (met by a difference (number of pixels) in coordinate position between the inner diameter point (which may be interpreted as the coordinate position of a second pixel) and its corresponding outer diameter point (which may be interpreted as the coordinate point of a first pixel) is calculated; further met by coordinate positions of the outer diameter point and the inner diameter point and their differences (corresponding to a pipe thickness)). This is read in (Paragraph [0098]).
PNG
media_image5.png
241
511
media_image5.png
Greyscale
The above reading in (Paragraph [0091]) also meets a total pipe thickness as a distance between the first pixel and a third pixel on a second outer circumferential surface of the pipe, the second outer circumferential surface being closest to the first pixel, by analyzing the pipe image (met by two outer diameter points; further met by outer diameter point estimation).
Regarding claim 2, Matsumoto as read in (Paragraph [0091]) in the rejection of claim 1, incorporated herein meets wherein the measuring includes: specifying, by a measurement line-based measuring part, a detection area through a window moving along the pipe of the pipe image (met by dividing luminance profile into two sectors, regions inside the outer diameter of the pipe and regions outside of it).
Matsumoto further teaches estimating, by the measurement line-based measuring part, a center line parallel to the inner circumferential surface and the first outer circumferential surface of the pipe and located between the inner circumferential surface and the first outer circumferential surface of the pipe in the detection area using a linear regression model (met by an intermediate position between the two estimated outer diameter points corresponds to the center position of the pipe). This is read in (Paragraph [0092]).
PNG
media_image6.png
236
512
media_image6.png
Greyscale
See also (Paragraph [0121]), meeting the measurement line limitation of the claim.
PNG
media_image7.png
200
511
media_image7.png
Greyscale
Regarding linear regression, this is a specific form of machine learning model that is well known to the art.
The prior art meets detecting, by the measurement line-based measuring part, a measurement line orthogonal to the center line (met by ability to determine center point as well as a diameter of the outer and inner portions of the pipe); and measuring, by the measurement line-based measuring part, the pipe thickness and the total pipe thickness according to pixel values changing along the measurement line (met also by the ability to determine the inner and outer diameters of the pipe).
Regarding claim 3, Matsumoto as read in the rejections of claims 1 and 2, incorporated herein, meets specifying, by the measurement line-based measuring part, the first pixel, the second pixel, and the third pixel through the pixel values changing along the measurement line (met by the nature of the inner and outer diameter points being different by virtue of their usage to determine the thickness measurements of a pipe); determining, by the measurement line-based measuring part, the distance between the first pixel and the second pixel on the measurement line as the pipe thickness (met also by the aforementioned usage of inner and outer diameter points to determine the thickness of a pipe); and determining, by the measurement line-based measuring part, the distance between the first pixel and the third pixel on the measurement line as the total pipe thickness (met also by the aforementioned usage of inner and outer diameter points to determine the thickness of a pipe).
Regarding claim 4, Matsumoto teaches extracting, by a contour-based measuring part, contours of the pipe from the pipe image; dividing, by the contour-based measuring part, the contours into a plurality of inner circumferential contours and a plurality of outer circumferential contours (met by an approximate curve calculating unit which calculates an approximate curve by approximating a second order differential profile of the set zero cross region with a predetermined function). This is read in (Claim 4).
PNG
media_image8.png
573
519
media_image8.png
Greyscale
The limitations pertaining to determining, by the contour-based measuring part, a distance between a fourth pixel on a first outer circumferential contour of the plurality of outer circumferential contours and a fifth pixel on an inner circumferential contour of the plurality of inner circumferential contours, the inner circumferential contour being closest to the fourth pixel, as the pipe thickness; and determining, by the contour-based measuring part, a distance between the fourth pixel and a sixth pixel on a second outer circumferential contour of the plurality of outer circumferential contours, the second outer circumferential contour being closest to the fourth pixel, as the total pipe thickness, are all enabled by the prior art’s ability to establish inner and outer diameter points, which may be used to determine pipe thickness and are not limited to straight pipes and can easily be used to measure the curvature or contour of a pipe.
Regarding claim 5, Matsumoto as read in the rejection of claims 1-4, incorporated herein, meets estimating, by the contour-based measuring part, a center line passing between two nearby contours of the pipe along a flow direction of the pipe using a polynomial fitting algorithm (enabled by the prior art’s ability to determine a center line as well as estimate the curvature of a pipe); and determining, by the contour-based measuring part, each of the contours as one of an inner circumferential outline and an outer circumferential outline according to a position of each of the contours relative to the center line (enabled by the prior art’s ability to determine an outer and inner diameter point and determine pipe thickness).
Regarding claim 8, Matsumoto teaches converting, by an actual measurement conversion part, the pipe thickness into an actual measurement value based on a ratio of the total pipe thickness to a pre-stored actual measurement value of an entire pipe (met by pipe thickness can be calculated from the number of pixels based on the actual dimensions per pixel). This is read in (Paragraph [0099]).
PNG
media_image9.png
170
511
media_image9.png
Greyscale
Regarding claim 9, Matsumoto as read in (Paragraph [0091]) in the rejection of claim 1, incorporated herein, meets detecting, by the recognition part, an area occupied by an object other than the pipe through a bounding box in the pipe image using the neural networks comprising a detection model; and specifying, by the recognition part, a remaining area excluding the bounding box as a measurement target area (enabled by the ability to separate the image into regions comprising the pipe and regions not comprising the pipe, effectively achieving the same desired function as a bounding box).
Regarding claim 10, Jawahar teaches performing, by the generation model, a plurality of operations applying weights learned for the radiographic image to generate the pipe image which distinguishes pixels occupied by the pipe from pixels occupied by the non-pipe object (met by the transformed medical image is a segmented output that is generated based on pre-defined weights (w); further met by modifying, using the machine learning model, the pre-defined weights (w) based on a derivative of the loss function with respect to the pre-defined weights (w)). This is read in (Paragraph [0049]).
PNG
media_image10.png
503
523
media_image10.png
Greyscale
PNG
media_image11.png
432
519
media_image11.png
Greyscale
Regarding claim 11, Jawahar as read in (Paragraph [0039]) in the rejection of claim 1, incorporated herein, meets providing, by a learning part, training data which includes the pipe image including the non-pipe object and the pipe and a target image displaying a target bounding box representing an area occupied by the non-pipe object in the pipe image (met by The medical image segmentation server (106) trains the machine learning model (108)); inputting, by the learning part, the pipe image into the neural networks comprising a detection model (met implicitly by the aforementioned training based on images; further met by the machine learning model (108) gets trained while processing the user-provided scribblings or markings); detecting, by the detection model, a bounding box representing the area occupied by the non-pipe object included in the pipe image through a plurality of operations applying weights which have not been completely trained for the pipe image (met by the machine learning model (108) need not be necessarily get pre-trained by any specific data set).
Jawahar as read in (Paragraph [0049]) in the rejection of claim 10, incorporated herein, further meets calculating, by the learning part, a loss representing a difference between the target bounding box and the detected bounding box through a loss function (met by loss function is computed for a location of pixels where the target element is located on the transformed medical image); and updating, by the learning part, the weights of the detection model so that the loss is minimized through optimization, before the generating of the pipe image (met by modifying, using the machine learning model, the pre-defined weights (w) based on a derivative of the loss function with respect to the pre-defined weights (w)).
Regarding claim 12, Jawahar as read in (Paragraph [0049]) in the rejection of claims 1 and 11, incorporated herein, meets a coordinate loss representing a difference between coordinates of the target bounding box and coordinates of the detected bounding box (met by loss function is computed for a location of pixels where the target element is located on the transformed medical image); and a classification loss representing a probability that an object within the detected bounding box is the non-pipe object (met by determining that the segmentation output whether matched with the target element on the transformed medical image)
Jawahar as read in (Paragraph [0040]) meets repeating, by the learning part, the detecting of the bounding box, the calculating of the loss, and the updating of the weights until a degree of overlapping between the detected bounding box and the target bounding box is equal to or greater than a predetermined percentage and each of the coordinate loss and the classification loss converges to a value equal to or less than a preset target value (met by the medical image segmentation server (106) again trains the machine learning model (108) with optimized medical images from the learnings of the ML module and the scribblings). See also (Paragraph [0049]) which teaches the optimized medical image is generated if the segmentation output is matched with the target element on the transformed medical image.
Regarding claim 13, the claim is substantially identical to claim 1, the analysis of which is incorporated herein.
Regarding claim 14, the claim is substantially identical to claim 2, the analysis of which is incorporated herein.
Regarding claim 15, the claim is substantially identical to claim 3, the analysis of which is incorporated herein.
Regarding claim 16, the claim is substantially identical to claim 4, the analysis of which is incorporated herein.
Regarding claim 17, the claim is substantially identical to claim 5, the analysis of which is incorporated herein.
Regarding claim 20, the claim is substantially identical to claim 8, the analysis of which is incorporated herein.
Allowable Subject Matter
Claims 6-7 and 18-19 are is 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 6 pertains to determining a center line passing between two nearby contours of the pipe along a flow direction of the pipe using a polynomial fitting algorithm, dividing two contour points into an inner circumferential contour and an outer circumferential contour. These features are not taught by the prior art.
Claim 7 pertains to determining a final pipe thickness and a final total pipe thickness by averaging or interpolating the pipe thickness and the total pipe thickness measured by the measurement line-based measuring part and the pipe thickness and the total pipe thickness measured by the contour-based measuring part. This feature is not taught by the prior art.
Claim 18 is substantially identical to claim 6, the grounds for objection of which are incorporated herein.
Claim 19 is substantially identical to claim 7, the grounds for objection of which are incorporated herein.
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MATTHEW JAMES BODNARK whose telephone number is (703)756-5378. The examiner can normally be reached 8a-5p.
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, Vu Le can be reached at (571) 272-7332. 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 JAMES BODNARK/Examiner, Art Unit 2668
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights