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 .
Allowable Subject Matter
Claims 4 and 6-14 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. Reasons for allowance will be provided in the event the application becomes in condition for allowance.
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) 1 and 5 are rejected under 35 U.S.C. 103 as being unpatentable over Iwase (U.S.P.G. Pub. No. 2021/0158525) in view of Bagherinia (U.S.P.G. Pub. No. 2023/0143051).
Regarding claim 1, Iwase (U.S.P.G. Pub. No. 2021/0158525) discloses:
An establishing method of a retinal layer auto-segmentation model, comprising:
obtaining a reference database, wherein the reference database comprises a plurality of reference optical coherence tomographic images (paragraph [0367], “image management system is an apparatus and a system that receive and save images imaged by an imaging apparatus such as the OCT apparatus… picture archiving and communication system (PACS)… image management system according to the following examples includes a database”; paragraph [0706], “retrieval… external database… plurality of images stored in the database”);
performing a reference image pre-processing step to duplicate each of the plurality of reference optical coherence tomographic images, mark a cell segmentation line of each of retinal layers so as to obtain a plurality of control label images (paragraph [0085] "training data refers to training data, and includes a pair of input data and ground truth"; Figs. 4, 5: 401, 402; paragraph [0128], “a tomographic image 401 obtained by the OCT is listed as input data, and a boundary image 402 in which the boundaries of the retina layers are specified for the tomographic image is listed as ground truth”);
performing an image feature selecting step to analyze each of the plurality of control label images by a feature selecting module, and obtain an each layer control label image feature from each of the plurality of control label images, so as to obtain a plurality of each layer control label image features (paragraph [0658], “the image features will differ according to the kind of disease… learned models used in the various examples and modifications described above may be generated and prepared for each kind of disease or each abnormal site”; paragraph [0679], “extracting (representing) a feature value of training data”; paragraph [0706], plurality of images stored in the database are already being managed in a state in which respective feature values of the plurality of images”; paragraph [0718], “in the learned models for retina layer detection and for image segmentation processing according to the various examples and modifications described above, it is conceivable for the magnitude of intensity values of a tomographic image, and the order and slope, positions, distribution, and continuity of bright sections and dark sections and the like of a tomographic image to be extracted as a part of the feature values and used for estimation processing”);
performing a data set generating step to process the reference optical coherence tomographic images and corresponding one of the control label images in a data enhancement method to obtain a data set (paragraphs [0137]-[0138], a plurality of pairs of mutually different square region images can be created from the pair; the pairs constituting the training data can be enriched by creating a large number of pairs of square region images while changing the positions of the regions to different coordinates in the original tomographic image and boundary image), and divide the data set into a training set and a validation set, wherein the data set comprises the plurality of reference optical coherence tomographic images, the plurality of control label images, a plurality of adjusted reference optical coherence tomographic images and a plurality of adjusted control label images (paragraphs [0137]-[0138], the set is divided into input data and ground truth; the produced set includes tomographic images, boundary images, and the generated pairs formed through the)
performing a training step to train the training set with the plurality of each layer control label image features through a U-net convolution neural network (see, for example, paragraph [0147]) learning classifier to reach convergence, so as to obtain the retinal layer auto-segmentation model (paragraphs [0009]-[0010], “the learned model has been obtained by using training data”; para 385: “Note that the parameters and the number of epochs of training can be set to values preferable for the utilization form of the learned model based on the training data. For example, based on the training data, the parameters and the number of epochs can be set that can output a correct imaged site label with a higher probability, that can output a more accurate region label image, or that can output an image with a higher image quality.”; paragraph [0386], “One of determination methods of such parameters and the number of epochs will be illustrated. First, 70 percent of the pairs constituting the training data are used for training, and the remaining 30 percent is randomly set for evaluation”. Training causes iterative weight adjustment resulting convergence on the suitable weights in the resultant model, paragraph [0658], “the image features will differ according to the kind of disease… learned models used in the various examples and modifications described above may be generated and prepared for each kind of disease or each abnormal site”); and
performing a confirming step to output a plurality of label reference images from the validation set using the retinal layer auto-segmentation model, and to compare each of the plurality of label reference images with corresponding one of the plurality of control label images, so as to confirm an accuracy of the retinal layer auto-segmentation model (paragraph [0085], “training data, and includes a pair of input data and ground truth. Additionally, correct answer data refers to the ground truth of training data”; paragraph [0386], “One of determination methods of such parameters and the number of epochs will be illustrated. First, 70 percent of the pairs constituting the training data are used for training, and the remaining 30 percent is randomly set for evaluation”; paragraphs [0407], [0408], [0411]-[0413], [0423], [0424], “evaluat”*; Figs. 28, 43, 44: 2805: Figs. 29, 30: s2950: Fig. 33: s3360: Fig. 41: s4150: Fig. 45: s4550: : “evaluat”*).
Iwase does not explicitly disclose:
crop each of the plurality of reference optical coherence tomographic images
Bagherinia (U.S.P.G. Pub. No. 2023/0143051) discloses:
crop each of the plurality of reference optical coherence tomographic images (paragraphs [0081], [0082], the OCT FOV is cropped to produce the reference image),
wherein the convolutional neural network is a U-net network (paragraphs [0137]-[0138], for example, a U-net)
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the system of Bagherinia with the system of Iwase such that the system would have additionally been configured to crop each of the plurality of reference optical coherence tomographic images as described in Bagherinia. The suggestion/motivation would have been in order to implement a system capable of “provid[ing] a more efficient system/method for ophthalmic motion tracking” (paragraph [0008] of the Bagherinia reference).
Regarding claim 5, the combination of Iwase and Bagherinia discloses the method of the parent claim (claim 1).
Bagherinia additionally discloses:
wherein the U-net convolution neural network learning classifier comprises 4 times of downsampling and 4 times of upsampling (paragraph [0138], the architecture has 4 encoding modules and 4 decoding modules)
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the system of Bagherinia with the system of Iwase such that the U-net convolution neural network learning classifier comprised 4 times of downsampling and 4 times of upsampling as described in Bagherinia. The suggestion/motivation would have been in order to implement a system capable of “provid[ing] a more efficient system/method for ophthalmic motion tracking” (paragraph [0008] of the Bagherinia reference).
Claim(s) 2 is rejected under 35 U.S.C. 103 as being unpatentable over Iwase in view of Bagherinia, in further view of Sidiqi (“In vivo Retinal Fluorescence Imaging With Curcumin in an Alzheimer Mouse Model”).
Regarding claim 2, the combination of Iwase and Bagherinia discloses the method of the parent claim (claim 1).
Iwase additionally discloses:
wherein the reference image pre-processing step comprises:
marking the cell segmentation line of each of retinal layers in each of the plurality of reference optical coherence tomographic images, so as to obtain a plurality of marked optical coherence tomographic images (paragraph [0085], "training data refers to training data, and includes a pair of input data and ground truth"; Figs. 4, 5: 401, 402; paragraph [0128]: “a tomographic image 401 obtained by the OCT is listed as input data, and a boundary image 402 in which the boundaries of the retina layers are specified for the tomographic image is listed as ground truth”)
Bagherinia additionally discloses:
cropping the plurality of marked optical coherence tomographic images respectively, so as to obtain the plurality of control label images (paragraphs [0081], [0082], the OCT FOV is cropped to produce the reference image)
The combination of Iwase and Bagherinia does not explicitly disclose:
performing an image quality screening on the plurality of reference optical coherence tomographic images, and retaining the plurality of reference optical coherence tomographic images meeting an image quality;
Sidiqi (“In vivo Retinal Fluorescence Imaging With Curcumin in an Alzheimer Mouse Model”) discloses:
performing an image quality screening on the plurality of reference optical coherence tomographic images, and retaining the plurality of reference optical coherence tomographic images meeting an image quality (pages 3, 6, it is generally known to remove images with poor image quality (blurriness, noise, segmentation errors) prior to conducting analysis as discussed in Sidiqi).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the system of Sidiqi with the combination of Iwase and Bagherinia such that the system would have been configured to perform an image quality screening on the plurality of reference optical coherence tomographic images, and retain the plurality of reference optical coherence tomographic images meeting an image quality as described in Sidiqi. The suggestion/motivation would have been in order to implement a system capable of “discard[ing] images that were deemed of low quality, as a result of image acquisition” (page 3 of the Sidiqi reference) to avoid errors in analysis resulting from poor images.
Claim(s) 3 is rejected under 35 U.S.C. 103 as being unpatentable over Iwase in view of Bagherinia, in further view of Liu et al. (“Shortest path with backtracking based automatic layer segmentation in pathological retinal optical coherence tomography images”).
Regarding claim 3, the combination of Iwase and Bagherinia discloses the method of the parent claim (claim 1).
Iwase additionally discloses:
wherein the image feature selecting step comprises:
performing an image layering on each of the plurality of control label images to obtain a plurality of each layer control label images, (paragraph [0658]: “the image features will differ according to the kind of disease… learned models used in the various examples and modifications described above may be generated and prepared for each kind of disease or each abnormal site”; paragraph [0679]: “extracting (representing) a feature value of training data”; paragraph [0706]: “plurality of images stored in the database are already being managed in a state in which respective feature values of the plurality of images”);
normalizing the plurality of each layer control label images, so as to obtain the plurality of each layer control label image features (paragraph [0718]: “in the learned models for retina layer detection and for image segmentation processing according to the various examples and modifications described above, it is conceivable for the magnitude of intensity values of a tomographic image, and the order and slope, positions, distribution, and continuity of bright sections and dark sections and the like of a tomographic image to be extracted as a part of the feature values and used for estimation processing”);
Iwase does not explicitly disclose:
wherein each of the plurality of each layer control label images comprises 9 retinal monolayer images
normalizing the plurality of each layer control label images, so as to obtain the plurality of each layer control label image features
Liu et al. (“Shortest path with backtracking based automatic layer segmentation in pathological retinal optical coherence tomography images”) discloses:
wherein each of the plurality of each layer control label images comprises 9 retinal monolayer images (Figure 1, page 15818, the nine layers are segmented); and
normalizing the plurality of each layer control label images, so as to obtain the plurality of each layer control label image features (Figure 5, pages 15818-15819, the boundaries between the layers are identified)
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the system of Liu et al. with the combination of Iwase and Bagherinia such that each of the plurality of each layer control label images comprise 9 retinal monolayer images and normalize the plurality of each layer control label images, so as to obtain the plurality of each layer control label image features as described in Liu et al. The suggestion/motivation would have been in order to implement a system capable of “helping experts diagnos[e] and quantify the degree of the disease “ (page 15819 of the Liu et al. reference).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOHN R WALLACE whose telephone number is (571)270-1577. The examiner can normally be reached Monday-Friday from 8:30-5 PM.
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, Benny Tieu can be reached at 571-272-7490. 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.
/JOHN R WALLACE/ Primary Examiner, Art Unit 2682