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 (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.
Response to Arguments
Applicant's arguments filed March 23, 2026 have been fully considered but they are not persuasive.
In response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., computationally generate, synthesize, or expand a flow-volume graph from numerical indicators) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). The claims merely currently require putting the indicators through fully-connected layers to generate the graph. Trivedy currently does this as the processing of Trivedy includes the fully-connected layers and after the processing in total a graph is generated. Thus the methodology of Trivedy completes its processing and thus inputting spirometry data through fully-connected layers prior to generating the graph.
In response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., “regression-based decoder” or “reference decoding”) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
In response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., “a network architecture that takes a minimal 1D array of discrete scalar values and pushes them through a plurality of fully-connected layers”) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
Examiner recognizes that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR International Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007). Additionally, MPEP § 2145(X)(A) states that it must be recognized that any judgment on obviousness is in a sense necessarily a reconstruction based upon hindsight reasoning. But so long as it takes into account only knowledge which was within the level of ordinary skill at the time the claimed invention was made, and does not include knowledge gleaned only from the applicant's disclosure, such a reconstruction is proper. See In re McLaughlin, 443 F.2d 1392, 170 USPQ 209 (CCPA 1971). Furthermore, there is no requirement that an "express, written motivation to combine must appear in prior art references before a finding of obviousness." Ruiz v. A.B. Chance Co., 357 F.3d 1270, 1276, 69 USPQ2d 1686, 1690 (Fed. Cir. 2004). Examiner respectfully disagrees with this line of argument, in view of the reasons provided for combining the teachings of Trivedy and He provided above.
In the instant case, one of ordinary skill in the art would have been motivated to combine the teachings of Trivedy (deep learning model architecture) and He (deep residual learning network architecture, with stacked layers, and a decoder) for the purpose of improving optimization of residual networks and gaining accuracy at an increased depth, as evidenced by He (see Abstract, “…residual networks are easier to optimize and can gain accuracy from considerably increased depth”), as discussed above. The granularity of an output graph is fully within the skill of one of ordinary skill int eh art such that one can find the desired scale granularity through routine experimentation. Adjusting the granularity of an output graph would yield predictable results.
Response to Amendment
Claim Objections
Claims 17, 21-27, 29, 32, and 34 objected to because of the following informalities:
-In claim 17, “Methodology” should recite “A method”
-In claims 19, 21-27, and 34 “Methodology” should recite “The method”
-In claims 29 and 32: “the methodology” should recite “the method”
Appropriate correction is required.
Applicant is advised that should claim 29 be found allowable, claim 32 will be objected to under 37 CFR 1.75 as being a substantial duplicate thereof. When two claims in an application are duplicates or else are so close in content that they both cover the same thing, despite a slight difference in wording, it is proper after allowing one claim to object to the other as being a substantial duplicate of the allowed claim. See MPEP § 608.01(m).
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are:
-In claim 17: “a spirometry device for outputting” interpreted to be the spirometers disclosed in Paragraph 0004 of the specification and equivalents thereof
-In claim 17: “capturing…using an integral flow sensing mechanism” interpreted to be the spirometers disclosed in Paragraph 0004 of the specification and equivalents thereof
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 17, 19, 21-27, 29, 32, and 34 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 17 recites the limitation "the capability" in Lines 2 and 21. There is insufficient antecedent basis for this limitation in the claim.
The term “improved” in claim 17 is a relative term which renders the claim indefinite. The term “improved” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
The term “accurate” in claim 17 is a relative term which renders the claim indefinite. The term “accurate” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
Claim 17 recites the term “such decoder network architecture” after reciting “a decoder network architecture” making it unclear if “such decoder network architecture” is meant to refer back to “a decoder network architecture” or not. Or is anything after the term “such” meant to be exemplary and thus not part of the claimed invention (See MPEP 2173.05(d)).
Claim 17 recites the term ‘such network’ and it is unclear what ‘such network’ is meant to refer to. Or is anything after the term “such” meant to be exemplary and thus not part of the claimed invention (See MPEP 2173.05(d)).
The term “recognized” in claim 17 is a relative term which renders the claim indefinite. The term “recognized” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
Claim 17 recites ‘at least one of seven recognized key spirometry indicators’ after reciting ‘spirometry indicators’ making it unclear if each recitation refers to the same element or not.
Claim 17 recites ‘a patient user’ twice in the claim making it unclear if each recitation refers to the same element or not.
Claim 17 recites ‘at least one key spirometry indicator’ after reciting ‘at least one of seven recognized key spirometry indicators’ and after ‘spirometry indicators’ making it unclear if each recitation refers to the same element or not.
Claim 17 recites ‘such spirometry indicator numerical data’ and it is unclear if this refers to ‘at least one key spirometry indicator’ or ‘at least one of seven recognized key spirometry indicators’ or ‘spirometry indicators’. Or is anything after the term “such” meant to be exemplary and thus not part of the claimed invention (See MPEP 2173.05(d)).
Claim 17 recites the limitation "the decoder network" in Line 16. There is insufficient antecedent basis for this limitation in the claim. It is unclear if this is meant to refer to “a decoder network architecture” or not.
The term “complete” in claim 17 is a relative term which renders the claim indefinite. The term “complete” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
Claim 17 recites the limitation "said spirometry indicator" in Line 18 and “the spirometry indicator” in Line 19. There is insufficient antecedent basis for these limitations in the claim.
Claim 17 recites the limitation “said diagnostic-quality" in Line 22. There is insufficient antecedent basis for this limitation in the claim.
The term “finer-grained” in claim 17 is a relative term which renders the claim indefinite. The term “finer-grained” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
Claim 19 recites the limitation "the decoder network" in Lines 1-2. There is insufficient antecedent basis for this limitation in the claim. It is unclear if this is meant to refer to “a decoder network architecture” or not.
Claim 19 recites ‘each layer’ and it is unclear if this is meant to be part of the ‘thirteen fully-connected layers’ earlier recited in claim 19 or ‘deep stacked residual learning layers’ as recited in claim 17.
Claim 19 recites the term ‘its’, it is unclear what ‘its’ is meant to refer to.
Claim 19 recites the limitation "the compressed input" in Line 3. There is insufficient antecedent basis for this limitation in the claim.
Claim 19 recites the limitation "the abstract features" in Lines 3-4. There is insufficient antecedent basis for this limitation in the claim.
Claim 19 recites the limitation "the full flow-volume graph output" in Line 4. There is insufficient antecedent basis for this limitation in the claim.
Claim 19 recites the limitation "the decoder’s input" in Line 4. There is insufficient antecedent basis for this limitation in the claim.
Claim 21 recites the limitation "the decoder network" in Lines 1-2 and 4. There is insufficient antecedent basis for this limitation in the claim. It is unclear if this is meant to refer to “a decoder network architecture” or not.
Claim 21 recites the limitation "the stacked layers" in Line 2. There is insufficient antecedent basis for this limitation in the claim.
The term “accurate” in claim 21 is a relative term which renders the claim indefinite. The term “accurate” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
Claim 22 recites the limitation "the decoder network" in Line 1-2. There is insufficient antecedent basis for this limitation in the claim. It is unclear if this is meant to refer to “a decoder network architecture” or not.
Claim 22 recites the term ‘its’, it is unclear what ‘its’ is meant to refer to.
Claim 22 recites ‘each stacked layer’ and it is unclear what this is referring to.
Claim 23 recites the limitation "the decoder network" in Lines 1-2. There is insufficient antecedent basis for this limitation in the claim. It is unclear if this is meant to refer to “a decoder network architecture” or not.
Claim 23 recites ‘a network loss function’ and is dependent back to claim 17 which recites the same making it unclear if the recitation in claim 23 is meant to refer to that in claim 17 or not.
Claim 23 recites the limitation "the fully-connected layers’ weights" in Line 2. There is insufficient antecedent basis for this limitation in the claim.
Claim 24 recites the limitation "the average" in Line 2. There is insufficient antecedent basis for this limitation in the claim.
Claim 24 recites the limitation "the absolute difference" in Lines 2-3. There is insufficient antecedent basis for this limitation in the claim.
Claim 24 recites ‘estimated values’ and ‘real values’ and it is unclear what these values are referring to. Are they referring to the spirometry indicators?
Claim 24 recites the limitation "the architecture" in Line 1. There is insufficient antecedent basis for this limitation in the claim.
Claim 26 recites ‘seven key spirometry indicators’ twice in the claim and is dependent back to claim 17 which recites ‘‘at least one key spirometry indicator’ and ‘at least one of seven recognized key spirometry indicators’ and ‘spirometry indicators’ making it unclear if the recitations in claim 26 are meant to refer to any of those in claim 17 or not.
Claim 26 recites the limitation "the decoder network" in Line 3. There is insufficient antecedent basis for this limitation in the claim. It is unclear if this is meant to refer to “a decoder network architecture” or not.
Claim 29 recites the limitation "the capability" in Line 3. There is insufficient antecedent basis for this limitation in the claim.
The term “improved” in claim 29 is a relative term which renders the claim indefinite. The term “improved” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
The term “accurate” in claim 29 is a relative term which renders the claim indefinite. The term “accurate” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
Claim 29 refers to a ‘a programmed spirometry testing device’ and refers to claim 17 which recites ‘a spirometry device’ making it unclear if the recitation in claim 29 is meant to be the same element as that of claim 17 or not.
Claim 29 is directed to ‘a programmed spirometry testing device’ but does not set forth any structures. Claim 29 merely refers to the methodology of claim 17. Claim 29 is merely only functionally recited not structurally recited. It is therefore unclear exactly what statutory category is intended to be claimed. It is unclear what the scope of the claim is intended to be. For example as currently recited could a spirometry device that has a processor read on this claim, as any processor would be capable of accessing the methodology of claim 17?
Claim 32 is directed to ‘a spirometry testing device’ but does not set forth any structures. Claim 32 merely refers to the methodology of claim 17. Claim 32 is merely only functionally recited not structurally recited. It is therefore unclear exactly what statutory category is intended to be claimed. It is unclear what the scope of the claim is intended to be. For example as currently recited could a spirometry device that has a processor read on this claim, as any processor would be capable of accessing the methodology of claim 17?
Claim 32 recites the limitation "the capability" in Line 3. There is insufficient antecedent basis for this limitation in the claim.
The term “improved” in claim 32 is a relative term which renders the claim indefinite. The term “improved” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
The term “accurate” in claim 32 is a relative term which renders the claim indefinite. The term “accurate” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
Claim 32 refers to a ‘spirometry testing device’ and refers to claim 17 which recites ‘a spirometry device’ making it unclear if the recitation in claim 32 is meant to be the same element as that of claim 17 or not.
Claim 34 recites the limitation "the maximum flow rate" in Line 3. There is insufficient antecedent basis for this limitation in the claim.
Claim 34 recites the limitation "the total air volume" in Line 4. There is insufficient antecedent basis for this limitation in the claim.
Claim 34 recites the limitation "the air volume" in Line 5. There is insufficient antecedent basis for this limitation in the claim.
Claim 34 recites the limitation "the first second" in Lines 5-6. There is insufficient antecedent basis for this limitation in the claim.
Claim 34 recites the limitation "the test" in Line 6. There is insufficient antecedent basis for this limitation in the claim.
Claim 34 recites the limitation "the measured flow rates" in Lines 7, 9, and 11. There is insufficient antecedent basis for this limitation in the claim.
Claim 34 recites the limitation "the maximum mid-airflow rate" in Line 13. There is insufficient antecedent basis for this limitation in the claim.
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.
The factual inquiries 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.
Claims 17, 19, 21-24, 26-27, 29, and 32 are rejected under 35 U.S.C. 103 as being unpatentable over a research article entitled “Design and Development of Smart-Phone Enabled Spirometer With a Disease Classification System Using Convolutional Neural Network” by Trivedy et al. (“Trivedy”, cited in Non-Final Office Action mailed 02/26/2025) in view of a research article entitled “Deep Residual Learning for Image Recognition” by He et al. (“He”, cited in Non-Final Office Action mailed 02/26/2025), and further in view of a research article entitled “Deep Residual Inception Encoder-Decoder Network for Medical Imaging Synthesis” by Gao et al. (“Gao”, cited in Non-Final Office Action mailed 02/26/2025).
Regarding claim 17: Trivedy discloses a methodology for implementing a deep stacked residual learning model to transform the capability of at-home spirometry testing devices using improved analysis based on deep learning technology to produce accurate flow-volume graphing from spirometry indicators (see Abstract, “…the design and development of a low-cost, portable, smartphone-enabled spirometer with an automatic disease classification system based on the spirometric signal using the convolutional neural network…”), comprising:
establishing a deep learning model architecture incorporating sequential layers for patient lung function monitoring (see page 7131, Section (IV)(A), “...CNNs use multiple instances of convolutional, ReLU, and polling layers in a sequence. An FC layer is attached to the end...”. see also page 7126, “the timeseries spirometry data have been classified using deep learning models to identify lung functionality disorder”, deep learning model is applied to identify lung function disorder in patients (i.e., patient lung function monitoring), using a network architecture including sequential layers) and conducting flow-volume curve learning (see Figs. 8a-8b and page 7130 Section III B, “representative flow–volume curve is shown in Fig. 8(a) and (b) for both spirometers ...time series curve of every process is stored in the microSD card so that the classifier model can be trained by using this data set”, flow-volume curves are developed and saved for model training (i.e., curve learning)) based on spirometry indicators from a database of diverse patient lung function measures (see page 7130 Section II B, “…a total of 150 samples having 120 normal cases and 30 abnormal cases are included by considering the values of the lower limit of normal (LLN) [35] of the FEV1, the FVC, and the FEV1/FVC”, samples of normal and abnormal cases of spirometry indicators are stored (i.e., diverse measures), stored samples are interpreted as a patient database (i.e., includes lung function parameter measured values, patient groups));
providing a spirometry device (see Fig. 3 and page 7127 Section II A, Airflow tube with PCB prototype) for outputting at least one of seven recognized key spirometry indicators for a patient user (see Fig. 7 and page 7129 Section II C, “ 4) After this, the parameters (the FEV1, the FVC, their ratio, and the PEF) will be displayed”, display of key spirometry indicators FEV1, FVC, FEV1/FVC ratio, and PEF of a patient (i.e., outputting at least one key spirometry indicator)) and capturing patient-specific exhalation numerical airflow based data for a patient user using an integral flow sensing mechanism of incident airflow of a sample exhalation resulting in at least one key spirometry indicator from the spirometry device for downstream neural processing (see page 7129 Section II C, guideline of the spirometry test, specifically see “… 4) The patient should fully inhale and press the “Begin Recording” button and the “blast” of exhalation will start, and it will continue no more air can be expelled while maintaining an upright posture and then press “Stop Recording” button... Based on the values of spirometric measurements (FEV1, FVC, and FEV1/FVC), a warning message...will be shown to the patient if any value is out of the normal range...”, patient numerical exhalation data (i.e., spirometry measurements (i.e., key spirometry indicator) based on incident exhalation of a patient (i.e., incident airflow data)) are used to display a warning message to a patient (i.e., are used for downstream neural processing)); and
transforming such spirometry indicator numerical data for the patient user using the network to produce flow-volume graphing output (see page 7126, “smart Android application is designed to display spirometry measurements, such as FVC, FEV1, FEV1/FVC ratio (%), peak expiratory flow (PEF), and flow–volume and flow–time curves…”, processing of spirometry measurements (i.e., spirometry indicator numerical data for the patient) allow flow-volume and flow-time curves to be displayed), enabling automated generation of diagnostic quality graphical outputs for finer-grained, and long-term lung function tracking outside of clinical settings ((see page 7127, “... spirometer proposed in this article is inexpensive, portable, and smartphone-enabled… display spirometry measurements...and flow–volume and flow–time curves... CNN model is incorporated with the Android application for real-time classification of spirometry...been used as it extracts features automatically from the raw signal and performs better than manual feature extraction-based classification methods... with an accuracy of 98.98%”, automatic feature extraction based on spirometry measurements and display of flow-volume curves (i.e., automated generation of graphical outputs) are provided by an inexpensive and portable spirometer (i.e., enable continuous and long-term tracking) and performs real time spirometry classification with improved accuracy (i.e., finer-grained) to provide computational enhancement).
However, Trivedy fails to disclose “establishing a decoder network architecture incorporating deep stacked residual learning layers for patient lung function monitoring, such network having deep stacked residual learning architecture”.
He teaches a residual learning framework (see abstract, “... a residual learning framework...”) that reformulates layers as residual functions that learn from input layers (see abstract, “... explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions...”) including a deep residual network architecture with stacked layers (see Fig. 2 and page 2 Section 1, “…we address the degradation problem by introducing a deep residual learning framework. Instead of hoping each few stacked layers directly fit a desired underlying mapping, we explicitly let these layers fit a residual mapping”) and further including a decoder (see Fig. 3 and page 4 Section 3.3, “…When the dimensions increase (dotted line shortcuts in Fig.3),we consider two options: (A)The shortcut still performs identity mapping with extra zero entries padded for increasing dimensions…”, Examiner is interpreting a “decoder” as converting signals from one form to another , in the instant case, increasing the tensor dimensions).
Trivedy discloses establishing a deep learning model architecture incorporating sequential layers for patient lung function monitoring (see pg. 7131 Section (IV)(A) and pg. 7126), but fails to explicitly disclose incorporating a decoder and residual learning layers. He teaches a deep residual learning network architecture, with stacked layers, and a decoder. 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 modify Trivedy (to incorporate a decoder and deep stacked residual learning layers) for the purpose of improving optimization of residual networks and gaining accuracy at an increased depth, as evidence by He (see abstract).
Additionally, Trivedy fails to disclose “... conducting flow-volume curve learning with such decoder network architecture based on spirometry indicators from a database of diverse patient lung function measures”, and “transforming such spirometry indicator numerical data for the patient user using the decoder network to produce flow-volume graphing output via regression-based decoding”.
Trivedy further discloses conducting flow-volume curve learning based on spirometry indicators from a patient database (see pg. 7130, Section (III)(B)), and transforming such spirometry indicator numerical data for the patient user using the network to produce continuous flow-volume graphing output (see pg. 7126).
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 further modify Trivedy (to include the decoder network architecture incorporating deep stacked residual learning layers (of the Trivedy/He combination)) for the purpose of achieving high accuracy of spirometry signal classification, as evidence by Trivedy (see pg. 7130, Section (III)(B)).
Additionally, the Trivedy/He combination fails to disclose “…wherein said transforming uses a network loss function comprising Mean Absolute Error (MAE), from said spirometry indicator as input…”.
Gao teaches a convolutional neural network architecture using an inception encoder-decoder architecture (see abstract). Further, Gao teaches using Mean Absolute Error as a loss function (see page 44 and Equation (3), “The mean absolute error (MAE) is utilized as the loss function”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the loss function disclosed by the decoder network of the Trivedy/He combination to include the mean absolute error loss function taught by Gao with the reasonable expectation that it would improve normalizing the range of outputs and reduce the effect of outliers. Furthermore, one of ordinary skill in the art would have had predictable success combining the teachings of Trivedy/He and Gao, since their teachings relate to the same field of endeavor, i.e., training multilayer neural networks for classification.
Additionally, the Trivedy/He/Gao combination fails to explicitly disclose “…said diagnostic-quality comprising a median similarity score of at least 0.96 as compared to ground-truth flow-volume graphs using normalized cross-correlation to computationally extend the capability of the spirometry device by enabling automated generation of diagnostic-quality graphical outputs”.
The Trivedy/He/Gao combination discloses the claimed invention except for a median similarity score of 0.96 compared to ground truth flow-volume curves using normalized cross correlation. However, it would have been obvious to one having ordinary skill in the art at the time the invention was made to modify the Trivedy/He/Gao combination (to define diagnostic-quality images by comparing flow-volume graphs to ground truth flow-volume curves using a median similarity score of 0.96 using normalized cross correlation) since it has been held that where the general conditions of a claim are disclosed in the prior art, discovering the optimum or workable ranges involves only routine skill in the art. In re Aller, 105 USPQ 233.
Trivedy teaches the output from the decoder network comprises expanding the spirometry indicator input through a plurality of full-connected layers to generate the complete flow-volume graph (see Trivedy Fig. 8(b) and page 7126 Section I, “…to display spirometry measurements…and flow–volume…curves”) having resolution reported to two significant digits (see Trivedy Fig. 7, Flow Rate vs. Volume Plot Result screen shows “FEV1: 3.41 L and FVC: 3.45 L”, which are reported to two significant digits. Resolution is interpreted as measurement of the smallest detail that can be distinguished by a sensor system under specific conditions2).
However, the Trivedy/He/Gao combination fails to explicitly disclose “includes expanding the spirometry indicator input through a plurality of full-connected layers to generate the complete flow-volume graph having resolution of 0.01 L”.
The Trivedy/He/Gao combination discloses the flow-volume graph having resolution reported to two significant digits but fails to explicitly disclose a resolution of 0.01L. It would have been obvious to one having ordinary skill in the art at the time the invention was made to modify the Trivedy/He/Gao combination (to generate the complete flow-volume graph having resolution of 0.01 L), since it has been held that where the general conditions of a claim are disclosed in the prior art, discovering the optimum or workable ranges involves only routine skill in the art. In re Aller, 105 USPQ 233. The granularity of an output graph is fully within the skill of one of ordinary skill int eh art such that one can find the desired scale granularity through routine experimentation. Adjusting the granularity of an output graph would yield predictable results.
Regarding claim 18, the Trivedy/He/Gao combination teaches the methodology as in claim 17, as discussed above. The Trivedy/He combination further discloses wherein the deep stacked residual learning model architecture (deep stacked residual learning network of the Trivedy/He/Gao combination) includes a plurality of stacked layers (see He Fig. 2 and page 3 Section 3.2 Equation (1), i representing the number of layers, as the network defines “many” layers) to expand the decoder's input to output (see He Fig. 3 and page 4 Section 3.3, “…When the dimensions increase (dotted line shortcuts in Fig.3)… shortcut still performs identity mapping with extra zero entries padded for increasing dimensions…”, increasing dimensions of the smaller (compressed) input to the larger (expanded) output).
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 further modify Trivedy (to include the decoder network architecture incorporating deep stacked residual learning layers (of the Trivedy/He combination)) for the purpose of achieving high accuracy of spirometry signal classification, as evidence by Trivedy (see pg. 7130, Section (III)(B)).
Regarding claim 19: The Trivedy/He/Gao combination teaches methodology as in claim 18/17, as discussed above. The Trivedy/He/Gao combination further teaches wherein the decoder network (network disclosed by the Trivedy/He/Gao combination) includes thirteen fully- connected layers (see He Fig. 2 and page 3 Section 3.2 Equation (1), i representing the number of layers, as the network defines “many” layers, interpreted as i=13 for 13 connected layers) stacked on each other (see He Fig. 2 and page 3 Section 3.2, “We adopt residual learning to every few stacked layers”), with each layer taking input from its previous layer (see He Fig. 2 and page 2 Section 1,“the shortcut connections simply perform identity mapping, and their outputs are added to the outputs of the stacked layers”) to expand the compressed input towards the abstract features (see He Fig. 3 and page 4 Section 3.3, “…When the dimensions increase (dotted line shortcuts in Fig.3)… shortcut still performs identity mapping with extra zero entries padded for increasing dimensions…”) of the full flow- volume graph output (see Trivedy page 7126, “…display… flow–volume and flow–time curves…”), to expand the decoder's input to output (see He Fig. 3 and page 4 Section 3.3, “…When the dimensions increase (dotted line shortcuts in Fig.3)… shortcut still performs identity mapping with extra zero entries padded for increasing dimensions…”, increasing dimensions of the smaller (compressed) input to the larger (expanded) output).
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 further modify Trivedy (to include the decoder network architecture incorporating deep stacked residual learning layers (of the Trivedy/He combination)) for the purpose of achieving high accuracy of spirometry signal classification, as evidence by Trivedy (see pg. 7130, Section (III)(B)).
Regarding claim 20: The Trivedy/He/Gao combination teaches methodology as in claim 17, as discussed above. The Trivedy/He/Gao combination further teaches wherein the decoder network (network disclosed by the Trivedy/He/Gao combination) includes a multi-stage architecture, with each stage of the decoder employing a fully-connected dense layer (see He Fig. 3 and page 3 Section 3.2, “the above notations are about fully-connected layers…The element-wise addition is performed on two feature maps, channel by channel”, analysis performed channel by channel is interpreted as multi-stage architecture, with each layer being a fully connected dense layer) that expands the decoder input towards the full flow-volume graph output thereof (see He Fig. 3 and page 4 Section 3.3, “…When the dimensions increase (dotted line shortcuts in Fig.3)… shortcut still performs identity mapping with extra zero entries padded for increasing dimensions…”).
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 further modify Trivedy (to include the decoder network architecture incorporating deep stacked residual learning layers (of the Trivedy/He combination)) for the purpose of achieving high accuracy of spirometry signal classification, as evidence by Trivedy (see pg. 7130, Section (III)(B)).
Regarding claim 21: The Trivedy/He/Gao combination teaches methodology as in claim 20/17, as discussed above. The Trivedy/He/Gao combination further teaches wherein the decoder network includes skip connections between the stacked layers that enable backpropagation and learning of residual mapping between input and output, to ensure accurate flow-volume graph prediction by the decoder network (see He page 2 Section 1, “the shortcut connections simply perform identity mapping, and their outputs are added to the outputs of the stacked layers (Fig. 2). Identity shortcut connections add neither extra parameter nor computational complexity. The entire network can still be trained end-to-end by SGD with backpropagation, and can be easily implemented using common libraries”).
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 further modify Trivedy (to include the decoder network architecture incorporating deep stacked residual learning layers (of the Trivedy/He combination)) for the purpose of achieving high accuracy of spirometry signal classification, as evidence by Trivedy (see pg. 7130, Section (III)(B)).
Regarding claim 22: The Trivedy/He/Gao combination teaches methodology as in claim 21/20/17, as discussed above. The Trivedy/He/Gao combination further teaches wherein the decoder network uses ReLU activation function for its deep neural networks, with ReLU activation used for each stacked layer (see He Fig. 2 and page 3 Section 3.2, “For the example in Fig. 2 that has two layers, F = W2 (W1x) in which σ denotes ReLU”, ReLU activation function implemented in each stacked layer).
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 further modify Trivedy (to include the decoder network architecture incorporating deep stacked residual learning layers (of the Trivedy/He combination)) for the purpose of achieving high accuracy of spirometry signal classification, as evidence by Trivedy (see pg. 7130, Section (III)(B)).
Regarding claim 23: The Trivedy/He/Gao combination teaches methodology as in claim 22/21/20/17, as discussed above. The Trivedy/He/Gao combination further teaches wherein the decoder network uses a network loss function to adjust the fully-connected layers' weights (see He page 4 Section 3.4, “We use a weight decay of 0.0001 and a momentum of 0.9”, weight decay and momentum interpreted as a network loss function applied to the weights of the connected layers (i.e., to adjust the weight of the connected layers)).
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 further modify Trivedy (to include the decoder network architecture incorporating deep stacked residual learning layers (of the Trivedy/He combination)) for the purpose of achieving high accuracy of spirometry signal classification, as evidence by Trivedy (see pg. 7130, Section (III)(B)).
Regarding claim 24: The Trivedy/He/Gao combination teaches methodology as in claim 23/22/21/20/17, as discussed above. The Trivedy/He/Gao combination further teaches wherein the decoder network architecture uses a Mean Absolute Error loss function (see Trivedy page 7132 Section V, “The plot of training and testing loss”) wherein said Mean Absolute Error as the network loss function (of the Trivedy/He/Gao combination, discussed above) calculates the average of the absolute difference between estimated values and real values (see Gao page 44 and Equation (3), “The mean absolute error (MAE) is utilized as the loss function”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the loss function disclosed by the decoder network of the Trivedy/He combination to include the mean absolute error loss function taught by Gao with the reasonable expectation that it would improve normalizing the range of outputs and reduce the effect of outliers. Furthermore, one of ordinary skill in the art would have had predictable success combining the teachings of Trivedy/He and Gao, since their teachings relate to the same field of endeavor, i.e., training multilayer neural networks for classification.
Regarding claim 26: The Trivedy/He/Gao combination teaches methodology as in claim 17, as discussed above. The Trivedy/He/Gao combination further teaches wherein:
the spirometry device outputs up to seven key spirometry indicators (see Trivedy Table I and page 7126 Section I, “…to display spirometry measurements, such as FVC, FEV1, FEV1/FVC ratio (%), peak expiratory flow (PEF), and flow–volume and flow–time curves”, display is interpreted as output); and
the input to the decoder network has up to seven key spirometry indicators from the spirometry device (see Trivedy Fig. 5(a) and page 7128 Section II(B), “the data are stored in a microSD card and are also sent to the smartphone via Bluetooth to display the spirometric measurements. The data are stored in the Comma Separated Values format so that it can be analyzed”, data stored in the microSD are recorded from the spirometry device and used as input to the network of the Trivedy/He combination).
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 further modify Trivedy (to include the decoder network architecture incorporating deep stacked residual learning layers (of the Trivedy/He combination)) for the purpose of achieving high accuracy of spirometry signal classification, as evidence by Trivedy (see pg. 7130, Section (III)(B)).
Regarding claim 27: The Trivedy/He/Gao combination teaches methodology as in claim 17, as discussed above. The Trivedy/He combination further teaches the database comprises an open- source national database of lung function measures comprising data from real but anonymized patients collected over a period of time from tests on both diseased and healthy patients over different demographics (Trivedy: see page 7130 Section II B, “…a total of 150 samples having 120 normal cases and 30 abnormal cases are included by considering the values of the lower limit of normal (LLN) [35] of the FEV1, the FVC, and the FEV1/FVC”, samples of normal and abnormal cases of spirometry indicators are stored (i.e., diverse measures); see pg. 7130, Section (III)(B))
Regarding claim 29: The Trivedy/He/Gao combination teaches the methodology as in claim 17, as discussed above. The Trivedy/He combination further teaches a programmed spirometry testing device programmed with a deep stacked residual learning model operating in accordance with the methodology of claim 17 (see Trivedy page 7133 Section V, “After importing the pretrained model in the Android application... on the Redmi 4 mobile phone with the Android Nougat operating system...”, programmed spirometry testing device, programmed with deep stacked residual learning model taught by the Trivedy/He/Gao combination), to transform the capability of at-home spirometry testing devices by using improved analysis to produce accurate flow-volume graphing (see Trivedy page 7126, “Moreover, the pretrained CNN model is incorporated with the Android application for real-time classification of spirometry”) based on spirometry indicators from an associated the programmed spirometry testing device (see Trivedy page 7126, “smart Android application is designed to display spirometry measurements, such as FVC, FEV1, FEV1/FVC ratio (%), peak expiratory flow (PEF), and flow–volume and flow–time curves…”).
Regarding claim 32: The Trivedy/He/Gao combination teaches methodology as in claim 17, as discussed above. The Trivedy/He/Gao combination further teaches a spirometry testing device (see Trivedy page 7125 Section I, “a portable spirometer that can reliably extract pulmonary flow information, perform preliminary signal processing, store it in external memory...”, spirometry testing device) having access to a deep stacked residual learning model operating in accordance with the methodology of claim 17 (deep stacked residual learning model taught by the Trivedy/He combination), to transform the capability of at-home spirometry testing devices by using improved analysis to produce accurate flow-volume graphing based on spirometry indicators from the spirometry testing device (see Trivedy page 7125 Section I, “…transmit it through wireless channels for further analysis to a smartphone with higher computing capability to display spirometric measurements and diagnose lung abnormality”).
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 further modify Trivedy (to include the decoder network architecture incorporating deep stacked residual learning layers (of the Trivedy/He combination)) for the purpose of achieving high accuracy of spirometry signal classification, as evidence by Trivedy (see pg. 7130, Section (III)(B)).
Claim 25 is rejected under 35 U.S.C. 103 as being unpatentable over Trivedy in view of He, further in view of Gao, and further in view of an article entitled “Encoder-Decoder Full Residual Deep Networks for Robust Regression and Spatiotemporal Estimation” by Li et al. (“Li”, cited in Non-Final Office Action mailed 02/26/2025).
Regarding claim 25: The Trivedy/He/Gao combination teaches methodology as in claim 24/23/22/21/20//17, as discussed above. The Trivedy/He combination further teaches architecture uses learning a rate of 10-4 (see Trivedy Table II, learning rate of 0.0001), and mini-batch size of 32 (see Trivedy Fig. 9, mini-batch size of 32 for feature extraction layers).
However, the Trivedy/He combination fails to disclose “wherein the architecture uses an RMSprop optimizer, learning rate of 10-4, and mini-batch size of 32”.
Li teaches an encoder-decoder full residual deep network (see abstract) using a Root Mean Square optimizer (see page 4223 Section IV(B), “sets evaluated for root-mean-square error”). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the decoder network of the Trivedy/He combination to include the root mean square optimizer taught by Li with the reasonable expectation that it would improve stability during training.
Furthermore, one of ordinary skill in the art would have had predictable success combining the teachings of Trivedy/He and Li, since their teachings relate to the same field of endeavor, i.e., training multilayer neural networks for classification.
Claim 34 is rejected under 35 U.S.C. 103 as being unpatentable over Trivedy in view of He, further in view of Gao, and further in view of a research article entitled “Spirometric indices of early airflow impairment in individuals at risk of developing COPD: Spirometry beyond FEV1/FVC” by Hoesterey et al. (“Hoesterey”).
Regarding claim 34: The Trivedy/He/Gao combination teaches methodology as in claim 17, as discussed above. The Trivedy/He/Gao combination further teaches recognized key spirometry indicators comprise: Peak Expiratory Flow Rate (PEFR), the maximum flow rate during exhalation; Forced Vital Capacity (FVC), the total air volume exhaled; Forced Expiratory Volume - 1 second (FEV1), the air volume exhaled in the first second of the test; (see Trivedy page 7133 Section V, “Important spirometric measurements, such as FEV1, FVC, FEV1/FVC, and PEF, are calculated from the expiration half of the flow-volume loop”).
However, the Trivedy/He/Gao combination fails to disclose “...key spirometry indicators comprise...Forced Expiratory Flows (FEF25), the measure of flow rates at 25% of total capacity; Forced Expiratory Flows (FEF50), the measure of flow rates at 50% of total capacity; Forced Expiratory Flows (FEF75), the measure of flow rates at 75% of total capacity; and Maximal Mid-Expiratory Flow (MMEF), the maximum mid-airflow rate during exhalation”.
Hoesterey teaches established spirometry parameters (see abstract), including instantaneous flow based indices measured at various percentages of forced vital capacity (see Fig. 4 and pg. 62, Section 4.3, “... Instantaneous and mean flows may be derived from various points on the flow-volume curve...”, Fig. 4 displays instantaneous flow rates at 25%, 50%, and 75% of forced vital capacity (I.e., FEF25, FEF50, and FEF75)),and further teaches measuring maximum expiratory flow rate at 50% of forced vital capacity (see pg. 63, Section 4.3, “... instantaneous maximum expiratory flow at 50% of FVC (FEF50 or MEF50) is the flow where half of forced vital capacity (FVC) remains to be exhaled...”, maximum airflow rate occurring after half of forced vital capacity is exhaled (indicating a mid-airflow rate) (i.e., MMEF)).
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 modify the spirometry indicators of the Trivedy/He/Gao combination (to include the instantaneous flow measurements of FEF25, FEF50, FEF75, and MMEF50) for the purpose of capturing flow dynamics at different portions of the forced expiratory maneuver as evidence by Hoesterey (see pg. 62, Section 4.3).
Furthermore, one of ordinary skill in the art would have had predictable success combining the teachings of Trivedy/He and Gao, since their teachings relate to the same field of endeavor, i.e., utilizing spirometry indices to obtain various biometric data.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PATRICK FERNANDES whose telephone number is (571)272-7706. The examiner can normally be reached Monday-Thursday 9AM-3PM EST.
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, JASON SIMS can be reached at (571)272-7540. 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.
/PATRICK FERNANDES/Primary Examiner, Art Unit 3791
Prosecution Insights