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 .
Response to Amendment
This Office Action is responsive to the amendment filed on 07/28/2026. As directed by the amendment: Claims 1, 9, and 18 have been amended, claims 2, 4, 6-8, 10, 12-13, and 15-16 have been cancelled, and no claims have been added. Thus, claims 1, 3, 5, 9, 11, 14, and 17-22 are presently under consideration in this application.
Response to Arguments
Applicant's arguments, see pages 9-10, regarding 35 U.S.C. 112(b) and 35 U.S.C. 112(a) new matter, filed 07/28/2026, regarding claims 1 and 9 have been fully considered and are persuasive. The amendments and arguments obviate the rejection and objection of record. The rejections and objections have been withdrawn.
Applicant's arguments, pages 11-15, regarding 35 U.S.C. 112(a), filed 07/28/2026, regarding the claims have been fully considered but they are not persuasive. On page 11, Applicant asserts that “The same provision, expressly recognizes amendment of the rejected claims as a means of overcoming an affirmed rejection, and Applicant has amended independent claims 1 and 9. The Board reviewed claim 1 as it recited "training an artificial neural network to at least partially compensate for electrical noise," a recitation the Board found to be functional and unsupported by a described algorithm. See Decision at 4-5, 8-9. No claim before the Board recited the loss-function computation or the gradient descent weight adjustment now recited in claims 1 and 9. As amended, the claims are confined to the particular training procedure the Specification describes. The question presented is whether that recited procedure is described in the Specification.” Applicant asserts on page 12 that “None of the amended features discussed below were before the Board.”
Applicant then argues on pages 12-13 that the amendments regarding the autoencoder “The
Specification describes the autoencoder architecture, including the encoder 92, the decoder 94, and the weights between the layers of the autoencoder, at page 23, lines 7-25 and Figure 6. The encoder 92 includes an input layer 96 and one or more hidden layers 97 that progressively compress the input to a code 98, and the decoder 94 includes one or more hidden layers 99 that progressively decompress the code 98 up to an output layer 95. The autoencoder 77 "manipulates the data received at the input layer 96 according to the values of the various weights between the layers of the autoencoder 77," and those weights are updated during training SO that the autoencoder 77 performs the data manipulation task it is trained to perform. See Specification at p. 23, 11. 13-25. As an example, the encoder 92 can include five layers that compress by a factor of two (e.g., 400, 200, 100, 50, 25), and the decoder 94 can include five layers that decompress by a factor of two. See id. at p. 23, 1. 31 to p. 24, 1. 3. The weights that are adjusted are therefore the weights of the autoencoder between the layers of the encoder and decoder, and the adjustment is directed to reducing the overall difference between the autoencoder outputs and the received first cardiac signal segments serving as desired outputs.”
Examiner disagrees because as noted in the Board Decision filed 02/25/2026, the PTAB noted that “the Examiner is correct in finding that the "[S]pecification describes adjusting weights within the encoder and the use of an Adam optimizer (page 25), but the instant [S]pecification fails to describe what these weight adjustments of the parameters would be changing, which specific weight parameters are being changed, and what exactly are these weights/parameters directed to." Ans. 5.” The instant specification fails to disclose the ways in amending the parameters or setting weights when the difference determination has been made. Instant specification describes adjusting weights within the encoder and the use of an Adam optimizer (page 25), but the instant specification fails to describe what these weight adjustments of the parameters would be changing, which specific weight parameters are being changed, and what exactly are these weights/parameters directed to.
Applicant then argues on page 13 that “the amended claims do not recite a separate noise compensation signal. Instead, the trained autoencoder itself produces the noise-compensated signal. For example, claim 1 recites "applying the trained artificial neural network to the second cardiac signal yielding the second cardiac signal with noise-compensation." The Specification describes this operation at page 26, line 6 to page 27, line 18 and Figures 9 and 10. There, the trained autoencoder 77 is applied to the cardiac signal 202 to yield the cardiac signal with noise-compensation 210. The autoencoder's mapping from a noisy input to a clean output is the noise compensation, and the noise-compensated cardiac signal is composed of the autoencoder's output values.
The Specification also describes how the compensation is included into the cardiac signal. During training, each received first cardiac signal segment is paired with the corresponding noise- added segment output by the recording apparatus cable, aligned using a synchronization signal or cross-correlation. See Specification at p. 21, 11. 6-24. The Specification states that the autoencoder 77 "is trained to remove future noise from cardiac signals." See id. at p. 23, 11. 21-25. Applying the trained network to the second cardiac signal before that signal enters the recording apparatus cable yields the second cardiac signal with noise-compensation, "which at least partially compensates for the electrical noise, which is not yet in the cardiac signal 202 but will be added to the cardiac signal 202 in the cable 84."”
Examiner disagrees because although amendments clarify where the noise compensation comes from, the claim and instant specification still fail to detail the training the model via comparing the noise-added cardiac signal and the received intracardiac signal or the ways in amending parameters and adjusting weights from the determination that a difference is not small enough, which is not defined in the instant specification. For example, regarding the training, the mere statement of comparing a difference between 150 and 152 of Fig. 7 fails to explain how the noisy signal and the normal cardiac signal are compared and what is used in the comparison to figure out the noise added.
Applicant then argues on page 14 that “Third, the amended claims define the difference, with claim 1 now reciting "computing, using a loss function, an overall difference between the autoencoder outputs and the received first cardiac signal segments serving as desired outputs." The Specification expressly describes this comparison at page 25, lines 1-4: the comparison "is generally performed using a suitable loss function, which computes the overall difference between all the outputs of the artificial neural network 75 and all the desired outputs." Specification at p. 25, 11. 1-4. The Specification illustrates the comparison with corresponding sets of segments. Outputs A, B, and C of the artificial neural network 75 are compared with corresponding received segments A', B', and C'. See id. at p. 24, 1. 28 - p. 25, 1. 1. The difference is therefore the loss-function difference between two specified signal sets. The Specification need not enumerate every signal feature on which a difference might otherwise be computed.”
Examiner disagrees because for example, the specification does not disclose what is the “small difference” of Fig. 8 and page 25 between noise-added cardiac signal and the received intracardiac signal and how this calculation or decision is made. It is also noted that the specification does not disclose what within the signal would one skilled in the art look at to observe this small difference (e.g., is the small difference relating to peak values, SNR, zero crossings, or any other feature extraction technique). Examiner notes that the Board agrees with these finding (see page 9 of the Board Decision filed 02/25/2026).
Applicant lastly argues on page 14 that “Fourth, as amended, claims 1 and 9 do not recite any threshold, stopping value, or convergence condition. The claim need not recite when training terminates, and the written description requirement does not apply to subject matter the claims do not recite.”
Examiner disagrees. It is unknown what the benchmark of the convergence criterion for when the difference is satisfied, and what the threshold must be to satisfy the criterion.
Therefore, the rejections of claims 1, 3, 5, 9, 11, 14, and 17-22 are maintained.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1, 3, 5, 9, 11, 14, and 17-22 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Original claims may lack written description when the claims define the invention in functional language specifying a desired result but the specification does not sufficiently describe how the function is performed or the result is achieved. For software, this can occur when the algorithm or steps/procedure for performing the computer function are not explained at all or are not explained in sufficient detail (simply restating the function recited in the claim is not necessarily sufficient). In other words, the algorithm or steps/procedure taken to perform the function must be described with sufficient detail so that one of ordinary skill in the art would understand how the inventor intended the function to be performed. See MPEP §§ 2163.02 and 2181, subsection IV.
When examining computer-implemented functional claims, examiners should determine whether the specification discloses the computer and the algorithm (e.g., the necessary steps and/or flowcharts) that perform the claimed function in sufficient detail such that one of ordinary skill in the art can reasonably conclude that the inventor possessed the claimed subject matter at the time of filing. An algorithm is defined, for example, as "a finite sequence of steps for solving a logical or mathematical problem or performing a task." Microsoft Computer Dictionary (5th ed., 2002). Applicant may “express that algorithm in any understandable terms including as a mathematical formula, in prose, or as a flow chart, or in any other manner that provides sufficient structure." Finisar Corp. v. DirecTV Grp., Inc., 523 F.3d 1323, 1340 (Fed. Cir. 2008) (internal citation omitted).It is not enough that one skilled in the art could write a program to achieve the claimed function because the specification must explain how the inventor intends to achieve the claimed function to satisfy the written description requirement. See, e.g., Vasudevan Software, Inc. v. MicroStrategy, Inc., 782 F.3d 671, 681-683, 114 USPQ2d 1349, 1356, 1357 (Fed. Cir. 2015).
Claims 1 and 9 fails to sufficiently describe the usage of the algorithm for the artificial neural network in enough detail for one skilled in the art to have sufficient written possession of the claimed invention. The independent claim recites “training an artificial neural network to at least partially compensate for electrical noise that will be added to cardiac signals in the cable responsively to the received first cardiac signal segments and the corresponding noise-added cardiac signal segments… applying the trained artificial neural network to the second cardiac signal yielding the second cardiac signal with noise-compensation”. The mere statement and recitation of the usage of Artificial Neural Networks for yielding noise-compensated cardiac signal (Pages 25-26) of the instant specification provides insufficient detail to the algorithm used in the artificial neural network to for noise decompensation. Specifically, there is insufficient disclosure of how the compensation is included into the noiseless cardiac signal, how the noise compensation is produced, and what is the noise compensation signal composed of. Further, there is insufficient disclosure in the instant specification detailing the training the model via comparing the noise-added cardiac signal and the received intracardiac signal or the ways in amending parameters and adjusting weights from the determination that a difference is not small enough, which is not defined in the instant specification. For example, regarding the training, the mere statement of comparing a difference between 150 and 152 of Fig. 7 fails to explain how the noisy signal and the normal cardiac signal are compared and what is used in the comparison to figure out the noise added. Further, how is the calculation to determine the compensation determined and how can this be added to the second cardiac signal. For example, the specification does not disclose what is the “small difference” of Fig. 8 and page 25 between noise-added cardiac signal and the received intracardiac signal and how this calculation or decision is made. It is also noted that the specification does not disclose what within the signal would one skilled in the art look at to observe this small difference (e.g., is the small difference relating to peak values, SNR, zero crossings, or any other feature extraction technique). Further, the instant specification fails to disclose the ways in amending the parameters or setting weights when the difference determination has been made. Instant specification describes adjusting weights within the encoder and the use of an Adam optimizer (page 25), but the instant specification fails to describe what these weight adjustments of the parameters would be changing, which specific weight parameters are being changed, and what exactly are these weights/parameters directed to.
The claims and instant specification recite the achieved result of an output of noise-compensation that is added onto the cardiac signal to cancel out the real noise and compensated [estimated] noise to obtain this original signal, but fails to describe how the noise compensation is added into the cardiac signal to yield the cardiac signal with noise compensation. It is also unknown what the benchmark of the convergence criterion for when the difference is satisfied, and what the threshold must be to satisfy the criterion.
Therefore, claims 1, 3, 5, 9, 11, 14, and 17-22 do not provide sufficient detail for one to replicate and understand the intended function that’s being performed.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MOUSSA M HADDAD whose telephone number is (571)272-6341. The examiner can normally be reached M-TH 8:00-6:00.
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, Jennifer McDonald can be reached at (571) 270-3061. 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.
/MOUSSA HADDAD/Examiner, Art Unit 3796
/Jennifer Pitrak McDonald/Supervisory Patent Examiner, Art Unit 3796
Prosecution Insights