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 .
Claims 1-17 and 21-23 are pending in the application. Claims 12-17 have been withdrawn from consideration, claims 18-20 have been canceled, and claims 21-23 have been added.
Response to Arguments
Claims 12-17 have been withdrawn from further consideration pursuant to 37 CFR 1.142(b), as being drawn to a nonelected invention, there being no allowable generic or linking claim. Applicant timely traversed the restriction (election) requirement in the reply filed on 7/23/26.
Applicant's election with traverse of Invention I in the reply filed on 7/23/26 is acknowledged. The traversal is on the ground(s) that Invention II recites a specific manner of generating training data sets while claim 7 generally defines training datasets and therefore the two inventions pertain to the same inventive concept and it would not impose an undue examination burden. Examiner respectfully disagrees. Claims 12-17 recite a method of generating training datasets by manipulating scan fan angles and generating raw data through forward projection and backward projection etc. Examining claims 12-17 will involve search in a different field.
The requirement is still deemed proper and is therefore made FINAL.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-6 and 21 is/are rejected under 35 U.S.C. 102 (a)(1) as being anticipated by Wang et al. (CN1720861A, published 2006-01-18, hereafter Wang).
As per claim 1, Wang teaches a method (Abstract) for data processing, implemented on a computing device (Fig. 1 #6) having at least one storage device storing a set of instructions, and at least one processor in communication with the at least one storage device (para. [0042] “The control panel 6 has a data processing device 60. The data processing device 60 is, for example, composed of a computer”), the method comprising:
obtaining first data of a subject acquired by an imaging device (Fig. 1 #2 X-ray scanner; Fig. 4; Fig. 5 #503, 507; para. [0059]-[0060]), the first data relating to a truncation artifact (Fig. 6 inner circle represents a ring-shaped artifacts; para. [0062] “The reconstructed image shows an example of ring-shaped artifacts inside the body surface contour. Ring artifacts are ring-shaped artifacts centered at isocenter point O”; Since the ring-shaped artifacts occlude partial pixels in the reconstructed image, they are considered truncation artifacts);
transforming the first data from a first form to a second form (Fig. 7 #601; para. [0065] “As shown in the figure, polar coordinate transformation is performed in step 601. Perform polar coordinate transformation on each pixel of the reconstructed image”; Fig. 9; See original Chinese document page 7 of 9 eqn. (1)); and
generating, based on the first data in the second form, truncation artifact corrected data using a data processing model (Fig. 7 #605; Fig. 9-13; para. [0072]-[0073]).
As per claim 2, dependent upon claim 1, Wang teaches wherein the generating, based on the first data in the second form, truncation artifact corrected data using a data processing model includes:
generating, based on the first data in the second form, truncation artifact corrected data in the second form using the data processing model (Fig. 7 #605; Fig. 9-13; para. [0072]-[0073]); and
transforming the truncation artifact corrected data from the second form to the first form (Fig. 7 #607; Fig. 14; para. [0088]; See original Chinese document page 8 of 9 eqn. (2)).
As per claim 3, dependent upon claim 1, Wang teaches wherein the generating, based on the first data in the second form, truncation artifact corrected data using a data processing model further includes:
obtaining, based on the first data in the second form, second data of a region corresponding to the truncation artifact (Fig. 8 the region inside the eclipse corresponds to a region of the second data); and
generating, based on the first data and the second data, the truncation artifact corrected data using the data processing model (Fig. 9-11; para. [0072]-[0085]).
As per claim 4, dependent upon claim 1, Wang teaches wherein the first form includes a Cartesian coordinate form, and the second form includes a polar coordinate form (Fig. 6 the reconstructed image is in Cartesian coordinate (x,y); Fig. 9 the converted image is in polar coordinate (r,
θ
)).
As per claim 5, dependent upon claim 3, Wang teaches wherein the generating, based on the first data and the second data, the truncation artifact corrected data using the data processing model includes:
generating, based on the second data, intermediate data in the second form, the intermediate data being configured to correct the truncation artifact (para. [0081] Ring＝|(Souter+Scenter)/7-Image(i,j)|); and
generating the truncation artifact corrected data by combining the first data and the intermediate data (para. [0082]-[0083]).
As per claim 6, dependent upon claim 5, Wang teaches wherein the generating the truncation artifact corrected data by combining the first data and the intermediate data includes:
determining weighted intermediate data based on a weight;
transforming the weighted intermediate data from the second form to the first form; and
determining the truncation artifact corrected data by combining the first data and the weighted intermediate data in the first form (para. [0082]-[0083] setting different weight for “Ring” based on if (Souter+Scenter)/7-Image(i,j)＜0 or (Souter+Scenter)/7-Image(i,j)＞0, and combines image data and the weighted intermediate data by mage(i,j)＝Image(i,j)-Ring or Image(i,j)＝Image(i,j)+Ring. Fig. 7 #607; para. [0088]; Note Wang combines the two data in second form and then converts the corrected data into first form. This treatment is equivalent to the recited acts “transforming the weighted intermediate data from the second form to the first form; and determining the truncation artifact corrected data by combining the first data and the weighted intermediate data in the first form”).
As per claim 21, dependent upon claim 3, Wang teaches wherein the first data in the second form is in a form of an image (Abstract; Fig. 6), and the obtaining, based on the first data in the second form, second data of a region corresponding to the truncation artifact includes:
determining a first region inside a truncated region;
determining a difference region between a boundary of the first region and a boundary of the image; and
designating the difference region as the region corresponding to the truncation artifact and designating image data of the difference region as the second data (See below annotated Fig. 6).
PNG
media_image1.png
648
697
media_image1.png
Greyscale
Claim(s) 7 is/are rejected under 35 U.S.C. 102 (a)(2) as being anticipated by Litwiller et al. (US 20220198725 A1, hereafter Litwiller).
As per claim 7, Litwiller teaches a method for generating a data processing model (Abstract), implemented on a computing device (FIG. 1/10) having at least one storage device storing a set of instructions (FIG. 1/10), and at least one processor (FIG. 1/10) in communication with the at least one storage device, the method comprising:
obtaining a training sample set including a plurality of training data pairs, wherein each of the plurality of training data pairs includes sample data and reference data of a same sample subject, and the sample data relates to a sample truncation artifact (FIG. 3A; Abstract “The method also includes analyzing the crude image using a neural network model trained with a pair of pristine images and corrupted images. The corrupted images are based on partial k-space data from partial k-spaces truncated in one or more partial sampling patterns. The pristine images are based on full k-space data corresponding to the partial k-space data of the corrupted images, and target output images of the neural network model are the pristine images”; para. [0039], [0041]);
for each of the plurality of training data pairs, transforming sample data and reference data of the training data pair from a first form to a second form (FIG. 2B #256; para. [0043] “reconstructing 256 a crude image based on the partial k-space data … The full k-space data for the crude image may be reconstructed by methods other than zero-filling, such as interpolation. Reconstructing 256 the crude image may be carried out outside the neural network model 204 and the crude image is inputted into the neural network model”; That says crude image pair is reconstructed based on full-partial k-space pair. The reconstruction transforms training data from first form into a second form; FIG. 3B-3D showing that corrupted crude images are reconstructed from partial-k space data using zero-filling.); and
generating the data processing model by training, based on the training sample set including a plurality of training data pairs in the second form, a preliminary machine learning model, the data processing model being configured to generate truncation artifact corrected data (FIG. 2B “neural network model”; FIG. 3A-3D showing trained machine learning model; para. [0044] “FIGS. 3A-3D are schematic diagrams of exemplary neural network model 204. The neural network model 204 may include a convolutional neural network 302. The neural network 302 is trained with corrupted images 304 as inputs and output pristine images 306”).
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.
Claim(s) 8-9 and 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Litwiller et al. (US 20220198725 A1, hereafter Litwiller), in view of SONG et al. (US 20220058426 A1, hereafter SONG).
As per claim 8, Litwiller teaches training the machine learning model based on the training sample set including a plurality of training data pairs in the second form (See rejections applied to claim 7), but does not teach the training details recited in claim 8.
SONG in the same field of endeavor discloses a method for restoring occluded region of an object in an image (Abstract). Specifically, SONG teaches:
the training, based on the training sample set including a plurality of training data pairs in the second form, a preliminary machine learning model includes one or more iterations (FIG. 4 #101; FIG. 8; para. [0060] “Step 101. Construct a training sample set including object image sample pairs for different position numbers based on an object image database. The object image sample pairs include object image samples and object image samples subjected to occlusion processing”; para. [0079] “The following operations are performed during each iteration of training the object recognition model”), at least one current iteration of which includes:
for each of at least one training data pair in the training sample set, generating, based on sample data of the training data pair, predicted data using the preliminary machine learning model or an intermediate machine learning model determined in a prior iteration (para. [0079], [0156], [0160]);
determining, based on the predicted data and reference data of the training data pair, a value of a loss function (FIG. 8 “Difference loss”; FIG. 8 x.sup.i representing a clean non-occlusion human face and x.sub.j.sup.i representing an occlusion human face (para. [0122]); para. [0124] eqn. (1) “Difference loss”
PNG
media_image2.png
43
144
media_image2.png
Greyscale
representing feature difference between predicted data and reference data);
determining, based on the value of the loss function, whether a termination condition is satisfied in the current iteration (para. [0067] “to determine the parameter of the mask generation model when or in response to determining that the loss function takes a minimum value; and updating the PDSN model according to the determined parameter of the mask generation model”); and
in response to determining that the termination condition is satisfied in the current iteration, designating the preliminary machine learning model or the intermediate machine learning model as the data processing model (para. [0067]).
It would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of Litwiller to incorporate the teaching of SONG to include the steps in claim 8 for training the machine learning model. The motivation for performing the above steps is to provide an object recognition system that is robust to occlusions based on a deep convolutional network having a good performance in general recognition scenarios (no occlusion or less occlusion) (SONG para. [0039]).
As per claim 9, dependent upon claim 7, Litwiller in view of SONG teaches wherein the generating the data processing model by training, based on the training sample set including a plurality of training data pairs in the second form, a preliminary machine learning model includes:
for each of the plurality of training data pairs, obtaining, based on sample data of the training data pair in the second form, second sample data of a region corresponding to the sample truncation artifact (SONG FIG. 7 the face image is segmented into 25 blocks); and
obtaining, based on reference data of the training data pair in the second form, second reference data corresponding to the second sample data (SONG para. [0063]; para. [0121]);
determining a second training sample set including a plurality of second training data pairs corresponding to the plurality of training data pairs, wherein each of the plurality of second training data pairs includes second sample data and corresponding second reference data (SONG FIG. 4 #101; para. [0060] “Step 101. Construct a training sample set including object image sample pairs for different position numbers based on an object image database. The object image sample pairs include object image samples and object image samples subjected to occlusion processing”); and
generating the data processing model by training, based on the second training sample set, the preliminary machine learning model (SONG FIG. 4 #103; para. [0067]).
As per claim 11, dependent upon claim 9, Litwiller in view of SONG teaches wherein the training, based on the second training sample set, the preliminary machine learning model includes one or more iterations (SONG para. [0079] “The following operations are performed during each iteration of training the object recognition model”), and at least one current iteration of the one or more iterations includes:
for each of at least one second training data pair in the second training sample set, generating, based on second sample data of the second training data pair, intermediate data in the second form using the preliminary machine learning model or an intermediate machine learning model determined in a prior iteration, the intermediate data being configured to correct the sample truncation artifact (SONG para. [0070] “performing, by the mask generation model in the PDSN model, mask generation processing on an absolute value of a difference between the first feature and the second feature, to obtain a mask for the position number; and multiplying the first feature and the second feature with the mask respectively, to obtain the input sample feature”; The mask is considered an intermediate data); and
generating predicted data by combining the second sample data and the intermediate data (para. [0070] “performing, by the mask generation model in the PDSN model, mask generation processing on an absolute value of a difference between the first feature and the second feature, to obtain a mask for the position number; and multiplying the first feature and the second feature with the mask respectively, to obtain the input sample feature”);
determining, based on the predicted data and second reference data of the second training data pair, a value of a loss function (SONG FIG. 8 “Difference loss”; para. [0124]);
determining, based on the value of the loss function, whether a termination condition is satisfied in the current iteration (SONG para. [0067] “to determine the parameter of the mask generation model when or in response to determining that the loss function takes a minimum value; and updating the PDSN model according to the determined parameter of the mask generation model”); and
in response to determining that the termination condition is satisfied in the current iteration, designating the preliminary machine learning model or the intermediate machine learning model as the data processing model (SONG para. [0067] “to determine the parameter of the mask generation model when or in response to determining that the loss function takes a minimum value; and updating the PDSN model according to the determined parameter of the mask generation model”).
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Litwiller et al. (US 20220198725 A1, hereafter Litwiller), in view of SONG et al. (US 20220058426 A1, hereafter SONG), as applied above to claim 9, and further in view of Wang et al. (CN1720861A, published 2006-01-18, hereafter Wang).
As per claim 10, Litwiller mentions training data could be in the form of Cartesian coordinate system, a 2D/3D non-Cartesian coordinate system such as a polar, spherical, or cylindrical coordinate system, or a combination thereof (para. [0040]), but does not teach wherein the first form includes a Cartesian coordinate form, and the second form includes a polar coordinate form.
Wang in the same field of endeavor discloses a method for eliminating annular artifact in X-ray data (Abstract). Before performing artifact elimination, Wang transform captured X-ray data in Cartesian coordinate form into a polar coordinate form (Fig. 7 #601; para. [0065] “As shown in the figure, polar coordinate transformation is performed in step 601. Perform polar coordinate transformation on each pixel of the reconstructed image”; Fig. 9; See original Chinese document page 7 of 9 eqn. (1)).
It would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of Litwiller and SONG to incorporate the teaching of Wang to transfer training sample data from Cartesian coordinate form into a polar coordinate form. By doing so the annular artifact can be transformed into a linear artifact, which can be effectively eliminated by using a 1D filter (Wang FIG. 9; para. [0072]).
Allowable Subject Matter
Claims 22-23 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.
Conclusion
Prior art searched but not cited is recorded in PTO-892.
Additional LIU et al. (US 20220101028 A1) disclose a method for occlusion detection. The method includes: after an image is captured by a camera, obtaining the image as an image to be detected; inputting the image to be detected into a trained occluded-image detection model, the occluded-image detection model is trained based on original occluded images and non-occluded images by using a trained data feature augmentation network; determining whether the image to be detected is an occluded image based on the occluded-image detection model; and outputting an image detection result. See Abstract; FIG. 1-5; para. [0050]-[0068].
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to XUEMEI G CHEN whose telephone number is (571)270-3480. The examiner can normally be reached Monday-Friday 9am-6pm.
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, John M Villecco can be reached at (571) 272-7319. 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.
/XUEMEI G CHEN/Primary Examiner, Art Unit 2661
Prosecution Insights