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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 06/18/2026 has been entered.
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.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claims 1-2, 4-10, 12-16, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Sahlsten et al. NPL “Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading” in view of Abou Shousha et al. (US 10468142 B1) herein after Abou, and further in view of Staurenghi et al. MPL “Impact of baseline Diabetic Retinopathy Severity Scale scores on visual outcomes in the VIVID-DME and VISTA-DME studies”.
Regarding claim 1, Sahlsten et al. teaches a method for evaluating diabetic retinopathy (DR) severity, the method comprising: determining one or more DR severity scores, each score associated with a DR severity level (see Abstract; “including state-of-the-art results for accurately classifying images according to clinical five-grade diabetic retinopathy” see also page 7th para; “Here the neural network can be constructed in such a way, that it receives an input which is used in calculating an output12, such as class or grade of diabetic retinopathy”); determining a plurality of DR severity classifications, each classification denoted by a range or a set of DR severity threshold scores (see Abstract; “ We also provide novel results for five different screening and clinical grading systems for diabetic retinopathy and macular edema classification”, see also page 2, 4th para; “The NRDR/ RDR system considers the cases with no diabetic retinopathy and mild diabetic retinopathy as nonreferable diabetic retinopathy, and the cases with moderate or worse diabetic retinopathy as referable diabetic retinopathy”); receiving input data comprising at least color fundus imaging data for an eye of a subject (see page 2, 1st para; “Two 45 degree color fundus photographs, centered on fovea and optic disc were taken from the patient’s both eyes”); and classifying the eye of the received input data into a DR severity classification of the plurality of DR severity classifications based on the metric (see Abstract; “including state-of-the-art results for accurately classifying images according to clinical five-grade diabetic retinopathy”). However, Sahlsten et al. des not teach wherein at least one DR severity classification denotes a moderate to moderately severe DR, a moderately severe to severe DR, or a moderate to severe DR, determining, from the received input data, a metric indicating a probability that a score for DR severity in the eye of the subject falls within a selected range.
In the same field of endeavor Abou teaches determining, from the received input data, and the one or more DR severity scores, a metric indicating a probability that a score for DR severity in the eye of the subject falls within a selected range (see col. 27, lines 21-23; “the predictions may be made through a single AI model 12 comprising a CNN wherein the probability score is used to correlate a severity. For example, a first threshold probability may lead to a predicted condition and additional thresholds in the probability score may be set to indicate severity as the probability score increases” see also col. 29, lines 30-36; “the analysis subsystem utilizes the probability score to correlate a severity score, …. the analysis subsystem analyzes probability scores and applies a weighted algorithm to determine a severity score”). Accordingly, it would have been obvious to one of ordinary skill in the art at the time of the invention to modify a deep learning fundus image analysis for diabetic retinopathy and macular edema grading of Sahlsten et al. in view of the use of a method of predicting a disease or condition of a cornea or an anterior segment of an eye of Abou in order to identify and monitor corneal conditions (see col. 27, lines 21-23). However, the combination of Sahlsten et al. and Abou as a whole does not teach wherein at least one DR severity classification denotes a moderate to moderately severe DR, a moderately severe to severe DR, or a moderate to severe DR.
In the same field of endeavor, Staurenghi et al. teaches wherein at least one DR severity classification denotes a moderate to moderately severe DR, a moderately severe to severe DR, or a moderate to severe DR (see page 955, Table 1
PNG
media_image1.png
829
464
media_image1.png
Greyscale
).
Accordingly, it would have been obvious to one of ordinary skill in the art at the time of the invention to modify a deep learning fundus image analysis for diabetic retinopathy and macular edema grading of Sahlsten et al. in view of the use of a method of predicting a disease or condition of a cornea or an anterior segment of an eye of Abou and further in view of impact of baseline diabetic retinopathy severity scale scores on visual outcomes in the VIVID-DME and VISTA-DME studies of Staurenghi et al. in order to demonstrate consistent treatment benefit across various baseline levels of retinopathy (see page 955 Table 1).
Regarding claim 2, the rejection of claim 1 is incorporated herein.
Staurenghi et al. in the combination further teach further comprising: determining the range or set of DR severity threshold scores, each DR severity threshold score indicating a minimum or maximum score corresponding to a DR severity classification of the plurality of DR severity classifications (see page 955, Table 1; “ Severity categories for characteristics graded in multiple fields are of the form ‘maximum severity/extent’, where maximum severity can be absent (A), questionable (Q), definitely present (D), moderate (M), severe (S), or very severe (VS), and extent is the number of fields at that severity level. For example, M/2–3 means that there are two or three fields from fields 3 to 7 with moderate severity, and none with higher severity”).
Regarding claim 4, the rejection of claim 1 is incorporated herein.
Staurenghi et al. in the combination further teach wherein the at least one range or set of DR severity threshold scores comprises a portion of a Diabetic Retinopathy Severity Scale (DRSS) between and including 43 and 47, between and including 47 and 53, or between and including 43 and 53 (see page 955, 1st para; “with a DRSS score ≤43, moderate (26.3%) in patients with a DRSS score of 47, and high (50.2%) in patients with a DRSS score ≥53”).
Regarding claim 5, the rejection of claim 1 is incorporated herein.
Abou in the combination further teach wherein the input data further comprises one or more of: baseline demographic characteristics associated with the subject and baseline clinical characteristics associated with the subject (see col. 11, lines 39-44; “input data may include patient data such as demographic data or medical data, e.g., data relating to a condition of a patient's other cornea or prior condition of state of the imaged cornea. Herein, the terms condition and disease, with respect to the cornea or anterior segment, may be used interchangeably”, see also col. 16, lines 35-42; “the AI model 12 configured generating predictions based on input data comprising one or more input images and other patient data. In various embodiments, the other patient data may include, for example, medical data, demographical data, or both. Medical data may include, for example, corneal curvature, central corneal thickness, eye pressures, visual fields, or visual acuity, among others. Demographical data may include, for example, age, gender, ethnicity, past medical history, family history, or occupation, among others”); and wherein the generating the output further comprises generating the output using one or more of the baseline demographic characteristics and the baseline clinical characteristics (see col. 16, lines 35-42; “the AI model 12 configured generating predictions based on input data comprising one or more input images and other patient data. In various embodiments, the other patient data may include, for example, medical data, demographical data, or both. Medical data may include, for example, corneal curvature, central corneal thickness, eye pressures, visual fields, or visual acuity, among others. Demographical data may include, for example, age, gender, ethnicity, past medical history, family history, or occupation, among others”).
Regarding claim 6, the rejection of claim 1 is incorporated herein.
Sahlsten et al. in the combination further teach wherein the generating the metric (see page 3 2nd para; “Also, we calculate the confusion matrices for the multi-class classification tasks. For each metric in the binary classification tasks”) comprises generating the metric using a neural network system (see page 2, 7th para; “Here the neural network can be constructed in such a way, that it receives an input which is used in calculating an output12, such as class or grade of diabetic retinopathy”).
Regarding claim 7, the rejection of claim 6 is incorporated herein.
Sahlsten et al. in the combination further teach further comprising: training the neural network system using a training dataset comprising at least graded color fundus imaging data associated with a plurality of training subjects (see page 2, 1st para; “provided a non-open, anonymized retinal image dataset of patients with diabetes, including 41122 graded retinal color images from 14624 patient” see also page 3 7th para; “In order to distinguish features related to diabetic retinopathy and macular edema in the color images of patients’ fundi we chose to use a deep convolutional neural network….Here the neural network can be constructed in such a way, that it receives an input which is used in calculating an output1”).
Regarding claim 8, the rejection of claim 7 is incorporated herein.
Sahlsten et al. in the combination further teach wherein the training the neural network system further comprises training the neural network using one or more of: baseline demographic characteristics associated with the plurality of training subjects and baseline clinical characteristics associated with the plurality of training subjects (see para [0014]; “the machine learning procedure comprises training a machine learning algorithm using outcome classified patient data comprising macular sensitivity, axial length, best corrected visual acuity (BCVA), bivariate contour ellipse area (BCEA), or any combination hereof. In some non-limiting embodiments, the patient data is classified according to at least four categories of myopic maculopathy”).
Regarding claim 9, the scope of claim 9 is fully encompassed by the scope of claim 1, accordingly, the rejection analysis of claim 1 is equally applicable (see also Abou claim 19; [ “One or more non-transitory computer-readable media comprising computer program instructions that, when executed by one or more processors, cause operations”).
Regarding claim 10, the rejection of claim 9 is incorporated herein.
Sahlsten et al. in the combination further teach wherein the operations further comprise: receiving a determination of the range or set of DR severity threshold scores, each DR severity threshold score indicating a minimum or maximum score corresponding to a DR severity classification of the plurality of DR severity classifications (see page 955, Table 1; “ Severity categories for characteristics graded in multiple fields are of the form ‘maximum severity/extent’, where maximum severity can be absent (A), questionable (Q), definitely present (D), moderate (M), severe (S), or very severe (VS), and extent is the number of fields at that severity level. For example, M/2–3 means that there are two or three fields from fields 3 to 7 with moderate severity, and none with higher severity”).
Regarding claim 11, the rejection of claim 9 is incorporated herein.
Sahlsten et al. in the combination further teach wherein the at least one DR severity classification denotes a moderate to moderately severe DR, a moderately severe to severe DR, or a moderate to severe DR (see page 2, 4th para; “The NRDR/ RDR system considers the cases with no diabetic retinopathy and mild diabetic retinopathy as nonreferable diabetic retinopathy, and the cases with moderate or worse diabetic retinopathy as referable diabetic retinopathy”).
Regarding claim 12, the rejection of claim 9 is incorporated herein.
Staurenghi et al. in the combination further teach wherein the at least one range or set of DR severity threshold scores comprises a portion of a Diabetic Retinopathy Severity Scale (DRSS) between and including 43 and 47, between and including 47 and 53, or between and including 43 and 53 (see page 955, 1st para; “with a DRSS score ≤43, moderate (26.3%) in patients with a DRSS score of 47, and high (50.2%) in patients with a DRSS score ≥53”).
Regarding claim 13, the rejection of claim 9 is incorporated herein.
Abou in the combination further teach wherein the input data further comprises one or more of: baseline demographic characteristics associated with the subject and baseline clinical characteristics associated with the subject; and wherein the generating the output further comprises generating the output using one or more of the baseline demographic characteristics and the baseline clinical characteristic (see col. 11, lines 39-44; “input data may include patient data such as demographic data or medical data, e.g., data relating to a condition of a patient's other cornea or prior condition of state of the imaged cornea. Herein, the terms condition and disease, with respect to the cornea or anterior segment, may be used interchangeably”, see also col. 16, lines 35-42; “the AI model 12 configured generating predictions based on input data comprising one or more input images and other patient data. In various embodiments, the other patient data may include, for example, medical data, demographical data, or both. Medical data may include, for example, corneal curvature, central corneal thickness, eye pressures, visual fields, or visual acuity, among others. Demographical data may include, for example, age, gender, ethnicity, past medical history, family history, or occupation, among others”).
Regarding claim 14, the rejection of claim 9 is incorporated herein.
Sahlsten et al. in the combination further teach wherein the generating the metric (see page 3 2nd para; “Also, we calculate the confusion matrices for the multi-class classification tasks. For each metric in the binary classification tasks”) comprises generating the metric using a neural network system (see page 2, 7th para; “Here the neural network can be constructed in such a way, that it receives an input which is used in calculating an output12, such as class or grade of diabetic retinopathy”).
Regarding claim 15, the scope of claim 15 is fully encompassed by the scope of claim 1, accordingly, the rejection analysis of claim 1 is equally applicable.
Regarding claim 16, the rejection of claim 15 is incorporated herein.
Staurenghi et al. in the combination further teach wherein the operations further comprise: receiving a determination of the range or set of DR severity threshold scores, each DR severity threshold score indicating a minimum or maximum score corresponding to a DR severity classification of the plurality of DR severity classifications (see page 955, Table 1; “ Severity categories for characteristics graded in multiple fields are of the form ‘maximum severity/extent’, where maximum severity can be absent (A), questionable (Q), definitely present (D), moderate (M), severe (S), or very severe (VS), and extent is the number of fields at that severity level. For example, M/2–3 means that there are two or three fields from fields 3 to 7 with moderate severity, and none with higher severity”).
Regarding claim 17, the rejection of claim 15 is incorporated herein.
Sahlsten et al. in the combination further teach wherein the at least one DR severity classification denotes a moderate to moderately severe DR, a moderately severe to severe DR, or a moderate to severe DR (see page 2, 4th para; “The NRDR/ RDR system considers the cases with no diabetic retinopathy and mild diabetic retinopathy as nonreferable diabetic retinopathy, and the cases with moderate or worse diabetic retinopathy as referable diabetic retinopathy”).
Regarding claim 18, the rejection of claim 15 is incorporated herein.
Staurenghi et al. in the combination further teach wherein the at least one range or set of DR severity threshold scores comprises a portion of a Diabetic Retinopathy Severity Scale (DRSS) between and including 43 and 47, between and including 47 and 53, or between and including 43 and 53 (see page 955, 1st para; “with a DRSS score ≤43, moderate (26.3%) in patients with a DRSS score of 47, and high (50.2%) in patients with a DRSS score ≥53”).
Regarding claim 19, the rejection of claim 15 is incorporated herein.
Zhang et al. in the combination further teach wherein the input data further comprises one or more of: baseline demographic characteristics associated with the subject and baseline clinical characteristics associated with the subject; and wherein the generating the output further comprises generating the output using one or more of the baseline demographic characteristics and the baseline clinical characteristic (see col. 11, lines 39-44; “input data may include patient data such as demographic data or medical data, e.g., data relating to a condition of a patient's other cornea or prior condition of state of the imaged cornea. Herein, the terms condition and disease, with respect to the cornea or anterior segment, may be used interchangeably”, see also col. 16, lines 35-42; “the AI model 12 configured generating predictions based on input data comprising one or more input images and other patient data. In various embodiments, the other patient data may include, for example, medical data, demographical data, or both. Medical data may include, for example, corneal curvature, central corneal thickness, eye pressures, visual fields, or visual acuity, among others. Demographical data may include, for example, age, gender, ethnicity, past medical history, family history, or occupation, among others”).
Regarding claim 20, the rejection of claim 15 is incorporated herein.
Sahlsten et al. in the combination further teach wherein the generating the metric (see page 3 2nd para; “Also, we calculate the confusion matrices for the multi-class classification tasks. For each metric in the binary classification tasks”) comprises generating the metric using a neural network system (see page 2, 7th para; “Here the neural network can be constructed in such a way, that it receives an input which is used in calculating an output12, such as class or grade of diabetic retinopathy”).
Claims 21-23 are rejected under 35 U.S.C. 103 as being unpatentable over Sahlsten et al. and Staurenghi et al. in view of Abou as applied in claims 1, 9, and 15 above, and further in view of NPL Arcadu et al. “Deep learning algorithm predicts diabetic retinopathy progression in individual patients”.
Regarding claim 21, the rejection of claim 1 is incorporated herein. The combination of Sahlsten et al., Staurenghi et al. and Abou does not teach wherein the color fundus imaging data for the eye of the subject comprises a plurality of field of view color fundus images; and wherein determining the metric comprises pooling predictions from the plurality of field of view color fundus images.
In the same field of endeavor, Arcadu et al. teaches wherein the color fundus imaging data for the eye of the subject comprises a plurality of field of view color fundus images (); and wherein determining the metric comprises pooling predictions from the plurality of field of view color fundus images (see page 2, Fig. 1; “In phase II, the probabilities independently generated by the field-specific DCNNs are aggregated by means of random forest”, see also page 7, left col. 5th para; “DCNNs were separately trained for each type of CFP field to form the “pillars”; and (2) the probabilities provided by the individual pillars are then aggregated by means of RFs”, and page 4, left col. 1st para; “the probabilities of DR progression generated by all individual DCNNs) for the final prediction” Note; aggregated is direct technical equivalent of the claimed “pooling prediction”).
Regarding claim 22, the rejection of claim 9 is incorporated herein.
Arcadu in the combination further teach wherein the color fundus imaging data for the eye of the subject comprises a plurality of field of view color fundus images; and wherein determining the metric comprises pooling predictions from the plurality of field of view color fundus images (see page 2, Fig. 1; “In phase II, the probabilities independently generated by the field-specific DCNNs are aggregated by means of random forest”, see also page 7, left col. 5th para; “DCNNs were separately trained for each type of CFP field to form the “pillars”; and (2) the probabilities provided by the individual pillars are then aggregated by means of RFs”, and page 4, left col. 1st para; “the probabilities of DR progression generated by all individual DCNNs) for the final prediction” Note; aggregated is direct technical equivalent of the claimed “pooling prediction”).
Regarding claim 23, the rejection of claim 15 is incorporated herein.
Arcadu in the combination further teach wherein the color fundus imaging data for the eye of the subject comprises a plurality of field of view color fundus images; and wherein determining the metric comprises pooling predictions from the plurality of field of view color fundus images (see page 2, Fig. 1; “In phase II, the probabilities independently generated by the field-specific DCNNs are aggregated by means of random forest”, see also page 7, left col. 5th para; “DCNNs were separately trained for each type of CFP field to form the “pillars”; and (2) the probabilities provided by the individual pillars are then aggregated by means of RFs”, and page 4, left col. 1st para; “the probabilities of DR progression generated by all individual DCNNs) for the final prediction” Note; aggregated is direct technical equivalent of the claimed “pooling prediction”).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WINTA GEBRESLASSIE whose telephone number is (571)272-3475. The examiner can normally be reached Monday-Friday9:00-5:00.
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, Andrew Bee can be reached at 571-270-5180. 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.
/WINTA GEBRESLASSIE/Examiner, Art Unit 2677
Prosecution Insights