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 .
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 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.
Disposition of the Claims
Claims 1-15 are pending. Claims 1, 2, 4, 5, 6, 7, 11, 12, 14, and 15 were preliminarily amended on 8/29/2024.
Claim Rejections - 35 USC § 102
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.
Claims 1, 3, 5, 6, 8-12, and 15 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Patil (Convolution neural network and deep-belief network (DBN) based automatic detection and diagnosis of Glaucoma, of record).
Regarding claim 1, 6, Patil discloses a system (Abstract, a computer aided diagnostic system utilizing deep learning, neural network softmax classification, etc.) comprising:
a processor (p. 29490, ¶4, an Intel processor); and
an analysis engine (id., MATLAT/Simulink) coupled to the processor, wherein the analysis engine is for:
obtaining a region of interest (ROI) portion of an input eye image, wherein the input eye image corresponds to a subject eye under evaluation for detecting presence of glaucoma (p. 29485, ¶3.1-3.2);
using a detection model pipeline, wherein the detection model pipeline is trained based on training data comprising one of training characteristic information corresponding to plurality of input eye image characteristics, and images associated with glaucoma (Fig. 2, p. 29487, ¶3.4), and wherein the detection model pipeline is for:
extracting a characteristic information from the ROI portion of the input eye image to determine vertical cup-to-disc ratio (vCDR) corresponding to the subject eye in the input eye image (Figs. 2 and 3, extraction of deep features using CNN, and ¶3.3);
obtaining classification output denoting probability of presence of glaucoma in the subject eye (Fig. 2, classification of deep features using CNN, and ¶3.3); and
determining presence of glaucoma within the subject eye based on the vCDR and classification output (Fig. 2, p. 29490-29493, ¶4).
Regarding claim 3, Patil discloses the system as claimed in claim 1, and further discloses wherein the plurality of eye image characteristics comprises size, color, and integrity of the neuroretinal rim (NRR) (p. 29482, ¶1.2, “On the off chance that glaucoma is separate to fundus rim to disk area ratio, NRR, diameter of circle distance have been utilized”), size and shape of the optic cup, cup-to-disc ratio (CDR) (id., ¶1.3, “From the earliest starting point morphological characteristics of clinical parameters, like OD, OC and CDR are taken into account, which the glaucoma recognition or united order is performed in major existing systems”), shape and configuration of the vessels in the optic disc (id. “Retinal vessel detection [45] and glaucoma detection [28] initially use convolutional neural networks (CNNs).”), indicator indicating presence of the laminar dot sign in the cup, optic disc hemorrhages, structural changes in peripaillary region, and RNFL defects.
Regarding claim 5, Patil discloses the system as claimed in claim 1, and further discloses wherein the analysis engine is for further: ascertaining presence of an optic disc in the input eye image upon determining a quality score to be greater than a threshold quality score (see Fig. 1), wherein presence of the optic disc is ascertained by a neural network based machine learning (Fig. 2, ¶3.2-3.7); determining a set of coordinates of the center of the optic disc in the input eye image; and performing cropping of the input eye image based on the set of coordinates of the center of the optic disc to obtain the ROI portion of the input eye image (p. 29485, “The color fundus images have been received in RGB image pattern, then the higher intensity region-of-interest image is automatically extracted from the features of CNN. This region of interest region has optic disc, cup to disc ratio. The region of interest pixel size (150 × 150) along radius 100 is applied to extract deep features using DL models from every image”).
Regarding claim 8, Patil discloses the system as claimed in claim 1, and further discloses wherein the classification output comprises an activation map depicting salient regions within the ROI portion where optic damage is present (Fig. 2).
Regarding claim 9 and 12, Patil discloses a method (p. 29484, ¶3) comprising:
obtaining a training information comprising a training eye image and information comprising training characteristic information corresponding to plurality of input eye image characteristics, images
associated with glaucoma and retinal nerve fiber layer (RNFL) features corresponding to a training dataset (Figs. 1 and 2, p. 29485-29486, ¶3.1-3.3); and
training a detection model pipeline based on training data comprising one of training characteristic information corresponding to plurality of input eye image characteristics, images
associated with glaucoma and retinal nerve fiber layer (RNFL) features (Figs. 3 and 4, p. 29487-29490, ¶3.4-3.7).
Regarding claim 10 and 11, Patil discloses the method as claimed in claim 9, and further discloses wherein the plurality of eye image characteristics comprises size, color, and integrity of the neuroretinal rim (NRR) (p. 29482, ¶1.2, “On the off chance that glaucoma is separate to fundus rim to disk area ratio, NRR, diameter of circle distance have been utilized”), size and shape of the optic cup, cup-to-disc ratio (CDR) (id., ¶1.3, “From the earliest starting point morphological characteristics of clinical parameters, like OD, OC and CDR are taken into account, which the glaucoma recognition or united order is performed in major existing systems”, and further below, “In previous research, the researchers introduced automatic diagnosis including glaucoma classification by CDR (cup to disc ratio) extraction and texture features.”), shape and configuration of the vessels in the optic disc (id. “Retinal vessel detection [45] and glaucoma detection [28] initially use convolutional neural networks (CNNs).”), indicator indicating presence of the laminar dot sign in the cup, optic disc hemorrhages, structural changes in peripaillary region, and RNFL defects.
Regarding claim 15, Patil discloses the method as claimed in claim 9, and further discloses wherein the detection model pipeline when trained is to categorize the subject eye as one of healthy eye, glaucoma suspect eye, and urgent glaucoma eye (Figs. 1 and 2).
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 of this title, 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.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 2, 4, 7, 13, and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Patil as applied to claims 1 and 9 above, and further in view of Liu (WO 2011059409 A1, of record).
Regarding claim 2, Patil discloses the system as claim in claim 1, and further discloses the impact of RNFL degradation on cup to disk proportion (p. 29482, ¶1.4), but does not explicitly show wherein the analysis engine is for using the detection model pipeline to determine retinal nerve fiber layer (RNFL) features based on the input eye image, wherein the detection model pipeline is trained also based on retinal nerve fiber layer (RNFL) based features.
Liu drawn to automated glaucoma diagnosis explicitly shows wherein the analysis engine is for using the detection model pipeline to determine retinal nerve fiber layer (RNFL) features based on the input eye image, wherein the detection model pipeline is trained also based on retinal nerve fiber layer (RNFL) based features (p. 15, 13. Retinal Nerve Fiber Layer defect presence detection).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have utilized features known from Liu to improve the system of Patil and thus improved the efficacy of the glaucoma diagnosis.
Regarding claim 4, Patil discloses the system as claimed in claim 1, but does not explicitly show wherein the analysis engine is for: assessing a quality of the input eye image; rejecting the input eye image upon determining a quality score to be less than a threshold quality score; and prompting a user to obtain or capture new input eye image.
However, Liu drawn to automated glaucoma diagnosis explicitly shows that “texture analysis is performed on the fundus images to classify them based on their quality, and only images which are determined to meet a quality criterion are subjected to an analysis to determine if they exhibit glaucoma indicators” (Abstract).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have only utilized images of sufficient quality for which the automatic diagnostic would be effective, and to (re)obtain images as necessary, toward achieving an accurate diagnosis.
Regarding claim 7, Patil discloses the system as claimed in claim 1, but does not explicitly show wherein to categorize the input eye image as one of the health categories, the analysis engine using the trained detection model pipeline is for: cropping the ROI portion of the input eye image to obtain a set of four quadrants portions based on the determined set of coordinates of the center of the optic disc in the input eye image; processing the set of four quadrants portions to determine a Retinal Nerve Fiber Layer (RNFL) thickness value for each of the quadrant portions; determine determining an average thickness of RNFL across the quadrant portions based on the individual RNFL thickness of the quadrants; and categorizing the input eye image as one of the healthy eye, the glaucoma suspect eye, and the urgent glaucoma eye based on the average thickness of the RNFL.
Liu drawn to automatic glaucoma diagnosis explicitly shows wherein to categorize the input eye image as one of the health categories, the analysis engine using the trained detection model pipeline is for: cropping the ROI portion of the input eye image to obtain a set of four quadrants portions based on the determined set of coordinates of the center of the optic disc in the input eye image (p. 37, “Region of Interest: A ring-shaped area, as shown in Fig. 21 , is defined using the detected disc boundary, and used as the ROI which we further examine to evaluate the presence/absence of PPA. As the PPA often exists in one or several quadrants, the ROI ring is divided into several parts for examination. The enhanced disc segmentation module divides it into four quadrants (Q1 , Q2, Q3 and Q4).”). Liu further provides “automatic detection the presence or absence of RNFL based on image analysis. Making use of the special image features (color, shape, texture, etc), specific medical image processing technologies are developed to detect the presence of RNFL defects” (p. 15, e.g. ll. 23-26).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have implemented the systematic analysis of the optic disc region according to the teachings of Liu using the system of Patil toward providing a rich platform for feature generation and thus efficacious diagnostics.
The modified Patil does not explicitly show processing the set of four quadrants portions to determine a Retinal Nerve Fiber Layer (RNFL) thickness value for each of the quadrant portions; determine determining an average thickness of RNFL across the quadrant portions based on the individual RNFL thickness of the quadrants; and categorizing the input eye image as one of the healthy eye, the glaucoma suspect eye, and the urgent glaucoma eye based on the average thickness of the RNFL.
However, the prior art as has established the shape of this feature as relevant to the diagnosis of glaucoma. In view of the teachings of the modified Patil, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have utilized known features in the categorization and segmentation system of the modified Patil and thus improved the efficacy of the automated glaucoma diagnosis.
Regarding claim 13, Patil discloses the method as claimed in claim 9, but does not explicitly show wherein each training RNFL visual feature comprises a training feature value, wherein the training RNFL visual features comprises size, color, and shape of the RNFL.
Liu drawn to automated glaucoma diagnosis explicitly shows wherein the analysis engine is for using the detection model pipeline to determine retinal nerve fiber layer (RNFL) features based on the input eye image, wherein the detection model pipeline is trained also based on retinal nerve fiber layer (RNFL) based features (p. 15, 13. Retinal Nerve Fiber Layer defect presence detection, including “color, shape, texture”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have utilized features known from Liu to improve the system of Patil and thus improved the efficacy of the glaucoma diagnosis.
Regarding claim 14, Patil discloses the method as claimed in claim 9, but does not explicitly show wherein the detection model pipeline when trained is for assessing quality of one of the input eye image and region of interest (ROI) portion of an input eye image, wherein the input eye image corresponds to a subject eye under evaluation for detecting presence of glaucoma.
However, Liu drawn to automated glaucoma diagnosis explicitly shows that “texture analysis is performed on the fundus images to classify them based on their quality, and only images which are determined to meet a quality criterion are subjected to an analysis to determine if they exhibit glaucoma indicators” (Abstract).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have only utilized images of sufficient quality for which the automatic diagnostic would be effective, and to (re)obtain images as necessary, toward achieving an accurate diagnosis.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
US 12224061 B2 discloses determining levels of hypertension from retinal vasculature images
US 20200242763 A1 discloses an automated screening system using retinal imaging
US 10354384 B2 discloses systems and methods for assessing glaucoma loss
US 9757023 B2 discloses automatically detecting an optic disc in a retinal fundus autofluorescence image
US 8340437 B2 discloses determining optimal features for classifying patterns or objects.
WO 2010044459 A1 discloses automated methods for predicting glaucoma risk
WO 2009139722 A1 discloses two-dimensional retinal fundus image of the retinal fundus of an eye is processed by optic disc segmentation (2) followed by cup segmentation
WO 2009126112 A1 discloses automated analysis of retinal images, for obtaining from them information characterizing retinal blood vessels which may be useful in forming a diagnosis of a medical condition
US 7474775 B2 discloses disease state detection from eyeground images
US 20070109499 A1 discloses optic disk detection in retinal images
US 7177486 B2 discloses the details of image processing of, e.g. retinal eyeground images including optic disc
US 6053865 A discloses retinal disease analysis
US 6030079 A discloses automated image analysis of the optic disc
Any inquiry concerning this communication or earlier communications from the examiner should be directed to COLLIN X BEATTY whose telephone number is (571)270-1255. The examiner can normally be reached M - F, 10am - 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, Pinping Sun can be reached on 5712701284. 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.
/COLLIN X BEATTY/Primary Examiner, Art Unit 2872
Prosecution Insights