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 .
Status of Claims
Claims 1-20 were previously pending and subject to a non-final Office Action having a notification date of October 24, 2025 (“non-final Office Action”). Following the non-final Office Action, Applicant filed an amendment on January 16, 2026 (the “Amendment”), amending claims 1, 2, 11, 12, 14, 15, 17, and 18.
The present Final Office Action addresses pending claims 1-20 in the Amendment.
Response to Arguments
Response to Applicant’s Arguments Regarding Claim Rejections Under 35 USC §112
These rejections are withdrawn in view of the Amendment.
Response to Applicant’s Arguments Regarding Claim Rejections Under 35 USC §102/103
Applicant's arguments are moot in view of the new grounds of rejection set forth herein as necessitated by the Amendment.
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 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 3-6, 10, 11, 13, 14, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over NPL "Automatic 3D Surface Reconstruction of the Left Atrium From Clinically Mapped Point Clouds Using Convolutional Neural Network" to Xiong et al. ("Xiong") in view of NPL "A novel noncontact high-resolution charge density mapping system to guide ablation of complex atrial arrhythmias: overview of device technology and application" to Bala et al. ("Bala"):
Regarding claim 1, Xiong discloses a computer-implemented method (the Abstract discusses 3D surface reconstruction of the left atrium (LA) using a 3D CNN which is necessarily computer-implemented), comprising:
receiving a first dataset of points acquired from a catheter as it follows a path through a blood pool across a heart…, each point in the first dataset comprising position data acquired at a certain position along the path in the heart (section 2.1 on page 3 discusses a point-cloud recording (first dataset of points) of the LA (which necessarily includes a "blood pool" because the LA serves as a storage area where blood temporarily accumulates/pools) during clinical mapping (acquired via a catheter per the middle of right column on page 5, where such point cloud would correspond to position data at certain positions along a path in the heart in order to record the LA; also see point clouds recording during ablation procedures for Test #1 and Test #2 on page 6 and Figure 4 on page 9);
providing the first dataset to an encoder-decoder network (section 2.1 on page 3 discusses how a CNN having an encoder and decoder ("encoder-decoder network") is used to processes the point cloud input (the "first dataset"); also see how the point clouds are input to the CNN on page 6), the encoder-decoder network trained based on training data comprising (1) a dataset of points representing a shape of a known heart and (2) a dataset of points representing a known catheter path across the known heart (section 3.1.1 on page 5 discloses a paired training dataset ("training data") including LA surface geometries ("dataset of points representing a shape of a known heart") and sets of point clouds of the LA recorded with clinical mapping ("dataset of points representing a known catheter path across [a] known heart")); and
outputting, with the encoder-decoder network, a second dataset of points, the second dataset representing a predicted shape of the heart (section 2.1 on page 3 discloses predicting the 3D surface LA geometry (second dataset of points representing predicted shape of heart) using the CNN; also see output 3D mask in Figure 1 on page 3 and Figure 4 on page 9).
While Xiong discloses how the training data includes a dataset of points representing a shape of a known heart and a dataset of points representing a known catheter path across a known heart, Xiong might be silent regarding the two datasets being of the same known heart.
Nevertheless, Xiong teaches (bottom of right column on page 10) that it was known in the healthcare informatics art for future studies to utilize larger samples of clinical data involving both LGE-MRI scanning (which would result in a dataset of points representing a shape of a heart) and anatomical mapping (which would result in a dataset of points representing a known catheter path across a heart) in every patient such that both the two datasets of points would be associated with the same known heart. This approach would advantageously facilitate merging of the two datasets and therefore training and development of the model as the two datasets are associated with the same known heart as opposed to use of completely separate datasets associated with different hearts/patients from different time periods (e.g., as per the paired training data in section 3.1.1 on page 5), thereby improving accuracy of generated predictions.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention for the dataset of points representing a shape of a known heart and the dataset of points representing a known catheter path across a known heart in the system of Xiong to both be associated with the same known heart similar to as taught by Xiong to advantageously facilitate merging of the two datasets and therefore training and development of the model as the two datasets are associated with the same known heart as opposed to use of completely separate datasets associated with different hearts/patients from different time periods, thereby improving accuracy of generated predictions. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Furthermore, while Xiong discloses receiving the first dataset of points as the catheter follows a path through a blood pool across a heart as noted above, Xiong appears to be silent regarding doing so without contacting a surface of the heart.
Nevertheless, Bala teaches (section 1 on page 343, sections 2.2-2.3 on pages 344-345) that it was known in the healthcare informatics art to advance a catheter through a subject's right and left atrium without contacting the endocardium to acquire a cloud of anatomical and electrical data for generating a 3D model of the heart to advantageously provide global chamber mapping in instable rhythms (left column on page 347) and a more localized, higher resolution portrayal of global endocardial activation with improved accuracy (page 348).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention for the received first dataset of points of Xiong to be as the catheter follows a path through a blood pool across the heart without contacting a surface of the heart similar to as taught by Bala to advantageously provide global chamber mapping in instable rhythms and a more localized, higher resolution portrayal of global endocardial activation with improved accuracy. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Regarding claim 3, the Xiong/Bala combination discloses the method of claim 1, further including wherein the encoder-decoder network is a dense encoder-decoder network (page 3 of Xiong discloses how the encoder learns dense features and the CNN learns from condensed features such that the encoder-decoder network is a "dense encoder-decoder network").
Regarding claim 4, the Xiong/Bala combination discloses the method of claim 1, further including reconstructing the predicted shape of the heart based on the predicted second dataset of points in the heart (see predicted heart shape in Figure 4 on page 9 of Xiong).
Regarding claim 5, the Xiong/Bala combination discloses the method of claim 1, further including wherein the path across the heart is a path across a left atrium, wherein the known catheter path across the known heart is a path across a known left atrium, and wherein the shape of the known heart is a shape of at least a portion of the known left atrium (the Abstract, section 2.1 on page 3, and section 3.1 on page 5 of Xiong disclose how the paths/shapes are associated with the LA).
Regarding claim 6, the Xiong/Bala combination discloses the method of claim 5, further including wherein the path and the known catheter path each follow a certain trajectory through the left atrium (the manner in which the catheter is guided in relation to the above "first dataset" and "training dataset" is necessarily along some "certain trajectory" through the LA).
Regarding claim 10, the Xiong/Bala combination discloses the method of claim 1, further including wherein the encoder-decoder network comprises a first encoder (left column of page 3 of Xiong) and a first decoder (right column of page 3 of Xiong), and wherein the encoder-decoder network comprises a plurality of layers, selected from one or more of an input layer, one or more hidden layers, and an output layer (see various input, hidden, and output layers on pages 3-4 of Xiong).
Regarding claim 11, Xiong discloses a system (the Abstract discusses 3D surface reconstruction of the left atrium (LA) using a 3D CNN which is necessarily implemented by a computer system) comprising:
a memory, which is configured to store a first dataset of points acquired from a catheter as it follows a path through a blood pool across a heart…, each point in the dataset comprising position data acquired at a certain position along the path in the heart (section 2.1 on page 3 discusses a point-cloud recording (first dataset of points) of the LA (which necessarily includes a "blood pool" because the LA serves as a storage area where blood temporarily accumulates/pools) during clinical mapping (acquired via a catheter per the middle of right column on page 5, where such point cloud would correspond to position data at certain positions along a path in the heart in order to record the LA; also see point clouds recording during ablation procedures for Test #1 and Test #2 on page 6 and Figure 4 on page 9; furthermore, the top of the right column on page 10 discusses the memory cost of the point cloud data such that the "first dataset of points" is stored on the memory, notwithstanding that all data would necessarily be stored on some memory as the system is computer-implemented as already noted above); and
a processor which is configured to (computers necessarily include at least one processor):
receive, from the memory, the first dataset of points (as the processor processes/analyzes the first dataset of points as discussed below, it necessarily receives the first dataset of points from the memory);
provide the first dataset to an encoder-decoder network (section 2.1 on page 3 discusses how a CNN having an encoder and decoder ("encoder-decoder network") is used to processes the point cloud input (the "first dataset"); also see how the point clouds are input to the CNN on page 6), the encoder-decoder network trained based on training data comprising (1) a dataset of points representing a shape of a known heart and (2) a dataset of points representing a known catheter path across the known heart (section 3.1.1 on page 5 discloses a paired training dataset ("training data") including LA surface geometries ("dataset of points representing a shape of a known heart") and sets of point clouds of the LA recorded with clinical mapping ("dataset of points representing a known catheter path across [a] known heart"); furthermore, it would be the processor that is used to train and implement the "encoder-decoder network" as the system is computer-implemented);
output, with the encoder-decoder network, a second dataset of points in the heart, the second dataset representing a predicted, shape of the heart (section 2.1 on page 3 discloses predicting the 3D surface LA geometry (second dataset of points representing predicted shape of heart) using the CNN; also see output 3D mask in Figure 1 on page 3 and Figure 4 on page 9).
While Xiong discloses how the training data includes a dataset of points representing a shape of a known heart and a dataset of points representing a known catheter path across a known heart, Xiong might be silent regarding the two datasets being of the same known heart.
Nevertheless, Xiong teaches (bottom of right column on page 10) that it was known in the healthcare informatics art for future studies to utilize larger samples of clinical data involving both LGE-MRI scanning (which would result in a dataset of points representing a shape of a heart) and anatomical mapping (which would result in a dataset of points representing a known catheter path across a heart) in every patient such that both the two datasets of points would be associated with the same known heart. This approach would advantageously facilitate merging of the two datasets and therefore training and development of the model as the two datasets are associated with the same known heart as opposed to use of completely separate datasets associated with different hearts/patients from different time periods (e.g., as per the paired training data in section 3.1.1 on page 5), thereby improving accuracy of generated predictions.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention for the dataset of points representing a shape of a known heart and the dataset of points representing a known catheter path across a known heart in the system of Xiong to both be associated with the same known heart similar to as taught by Xiong to advantageously facilitate merging of the two datasets and therefore training and development of the model as the two datasets are associated with the same known heart as opposed to use of completely separate datasets associated with different hearts/patients from different time periods, thereby improving accuracy of generated predictions. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Furthermore, while Xiong discloses receiving the first dataset of points as the catheter follows a path through a blood pool across a heart as noted above, Xiong appears to be silent regarding doing so without contacting a surface of the heart.
Nevertheless, Bala teaches (section 1 on page 343, sections 2.2-2.3 on pages 344-345) that it was known in the healthcare informatics art to advance a catheter through a subject's right and left atrium without contacting the endocardium to acquire a cloud of anatomical and electrical data for generating a 3D model of the heart to advantageously provide global chamber mapping in instable rhythms (left column on page 347) and a more localized, higher resolution portrayal of global endocardial activation with improved accuracy (page 348).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention for the received first dataset of points of Xiong to be as the catheter follows a path through a blood pool across the heart without contacting a surface of the heart similar to as taught by Bala to advantageously provide global chamber mapping in instable rhythms and a more localized, higher resolution portrayal of global endocardial activation with improved accuracy. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Regarding claim 13, the Xiong/Bala combination discloses the system of claim 11, further including wherein the path across the heart is a path across a left atrium, wherein the known catheter path across the known heart is a path across a known left atrium, and wherein the shape of the known heart is a shape of at least a portion of the known left atrium (the Abstract, section 2.1 on page 3, and section 3.1 on page 5 of Xiong disclose how the paths/shapes are associated with the LA).
Regarding claim 14, the Xiong/Bala combination discloses the system of claim 11, further including wherein the path and the known catheter path each follow a certain trajectory through the left atrium (the manner in which the catheter is guided in relation to the above "first dataset" and "training dataset" is necessarily along some "certain trajectory" through the LA).
Regarding claim 19, the Xiong/Bala combination discloses the system of claim 11, further including wherein the processor is further configured to reconstruct a shape of the heart based on the predicted second dataset of points in the heart (see predicted heart shape in Figure 4 on page 9 of Xiong).
Claims 7 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over NPL "Automatic 3D Surface Reconstruction of the Left Atrium From Clinically Mapped Point Clouds Using Convolutional Neural Network" to Xiong et al. ("Xiong") in view of NPL "A novel noncontact high-resolution charge density mapping system to guide ablation of complex atrial arrhythmias: overview of device technology and application" to Bala et al. ("Bala"), and further in view of U.S. Patent App. Pub. No. 2020/0029845 to Baram et al. ("Baram"):
Regarding claim 7, the Xiong/Bala combination discloses the method of claim 6, but appears to be silent regarding wherein each trajectory includes a path starting from the septum, and continuing to left inferior, right inferior, and right superior in order.
Nevertheless, Baram teaches ([0033], [0045]-[0047]) that it was known in the healthcare informatics art to process sparse location measurements along a path starting from the septum, and continuing to left inferior, right inferior, and right superior in order followed by a catheter using an autoencoder to advantageously generate a predicted 3D shape of an LA that is substantially complete and adequately agrees with the actual shape of an LA thereby facilitating ablation of appropriate areas of a subject's heart to suppress an arrhythmia ([0054]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention for each trajectory to include a path starting from the septum, and continuing to left inferior, right inferior, and right superior in order in the system of the Xiong/Bala combination as taught by Baram to advantageously generate a predicted 3D shape of an LA that is substantially complete and adequately agrees with the actual shape of an LA thereby facilitating ablation of appropriate areas of a subject's heart to suppress an arrhythmia. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Claim 15 is rejected in view of the Xiong/Bala/Baram combination as discussed above in relation to claim 7.
Claims 8, 16, 17, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over NPL "Automatic 3D Surface Reconstruction of the Left Atrium From Clinically Mapped Point Clouds Using Convolutional Neural Network" to Xiong et al. ("Xiong") in view of NPL "A novel noncontact high-resolution charge density mapping system to guide ablation of complex atrial arrhythmias: overview of device technology and application" to Bala et al. ("Bala"), and further in view of U.S. Patent App. Pub. No. 2020/0029845 to Baram et al. ("Baram"):
Regarding claim 8, the Xiong/Bala combination discloses the method of claim 1, further including wherein the training of the encoder-decoder network comprises minimizing a loss function (the right column on page 4 of Xiong discloses minimizing a dice loss function during training), and …
However, the Xiong/Bala combination appears to be silent regarding wherein the loss function comprises a cross entropy loss term.
Nevertheless, Baram teaches ([0037]-[0038]) that it was known in the healthcare informatics and machine learning art to utilize a cross entropy loss term to advantageously facilitate reconstruction of a realistic volume of a LA from sparsely measured locations using NNs.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention for the loss function of the Xiong/Bala combination to include a cross entropy loss term as taught by Baram to advantageously facilitate reconstruction of a realistic volume of a LA from sparsely measured locations using NNs. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Claim 16 is rejected in view of the Xiong/Bala/Baram combination similar to as discussed above in relation to claim 8.
Regarding claim 17, the Xiong/Bala/Baram combination discloses the system of claim 16, further including wherein the loss function further comprises a regularization term, the regularization term configured to control the smoothness of the shape of the heart ([0038]-[0041] of Baram discloses how the loss function includes a regularization function F (regularization term) that smooths spatial weights to advantageously provide smooth reconstructions (e.g., of an LA per [0037]) with reduced noise thereby improving the accuracy of ablation procedures; it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention for the loss function of the Xiong/Bala/Baram combination to further include a regularization term configured to control the smoothness of the shape of the heart as taught by Baram to advantageously provide smooth reconstructions of the LA with reduced noise thereby improving the accuracy of ablation procedures. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.).
Regarding claim 18, the Xiong/Bala/Baram combination discloses the system of claim 17, further including wherein the regularization function comprises derivatives of weights of a first layer of the encoder-decoder network ([0008] of Baram discloses how the regularization function includes derivatives of weights of a first layer of the NN model (autoencoder/encoder-decoder network per [0047]) to advantageously result in a sufficiently smooth 3D representation of a cardiac chamber and save a need to include derivatives of weights from additional layers in the regularization function ([0041]); therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention for the regularization function of the Xiong/Bala/Baram combination to include derivatives of weights of a first layer of the encoder-decoder network as taught by Baram to advantageously result in a sufficiently smooth 3D representation of a cardiac chamber and save a need to include derivatives of weights from additional layers in the regularization function. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.), and preferably derivates of weights of the first layer and the output layer of the encoder-decoder network.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over NPL "Automatic 3D Surface Reconstruction of the Left Atrium From Clinically Mapped Point Clouds Using Convolutional Neural Network" to Xiong et al. ("Xiong") in view of NPL "A novel noncontact high-resolution charge density mapping system to guide ablation of complex atrial arrhythmias: overview of device technology and application" to Bala et al. ("Bala") and U.S. Patent App. Pub. No. 2020/0029845 to Baram et al. ("Baram"), and further in view of U.S. Patent App. Pub. No. 2023/0306725 to Wang et al. ("Wang"):
Regarding claim 9, the Xiong/Bala/Baram combination discloses the method of claim 8, but appears to be silent regarding wherein the loss function comprises a linear combination of the cross entropy loss term and a negative of a Sorenson-DICE coefficient.
Nevertheless, Wang teaches ([0037]-[0040]) that it was known in the machine learning art to train a model using a hybrid loss of a linear combination of a cross-entropy loss function and a DICE loss (which is one minus a DICE coefficient or in other words "a negative of a Sorensen-DICE coefficient") to advantageously increase continuity of segmentation and reach greater predictive accuracy of the model ([0044]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention for the loss function to include a linear combination of the cross entropy loss term and a negative of a Sorenson-DICE coefficient in the system of the Xiong/Bala/Baram combination as taught by Wang to advantageously increase continuity of segmentation and reach greater predictive accuracy of the model. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over NPL "Automatic 3D Surface Reconstruction of the Left Atrium From Clinically Mapped Point Clouds Using Convolutional Neural Network" to Xiong et al. ("Xiong") in view of NPL "A novel noncontact high-resolution charge density mapping system to guide ablation of complex atrial arrhythmias: overview of device technology and application" to Bala et al. ("Bala"), and further in view of U.S. Patent App. Pub. 2022/0061768 to Gliner ("Gliner"):
Regarding claim 20, the Xiong/Bala combination discloses the system of claim 11, but appears to be silent regarding wherein the training data dataset of points representing the known catheter path across the known heart comprises added noise and the trained encoder-decoder network is configured to remove noise from the first dataset of points.
Nevertheless, Gliner teaches ([0045]-[0050]) that it was known in the machine learning and healthcare informatics art to add noise to training cardiac signals captured by a catheter, train a neural network/autoencoder using the training signals to clean/remove noise from cardiac signals, and then use the trained NN/autoencoder to clean/remove noise from captured cardiac signals to advantageously avoid distortion of cardiac signals and useful analysis thereof ([0043]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention for the training data dataset of points representing the known catheter path across the known heart of the Xiong/Bala combination to include added noise and the trained encoder-decoder network of the Xiong/Bala combination to be configured to remove noise from the first dataset of points similar to as taught by Gliner to advantageously avoid distortion of cardiac signals and useful analysis thereof. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Allowable Subject Matter
Claims 2 and 12 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter: The Xiong/Bala combination does not further disclose or suggest, as recited in claims 2 and 12, the known catheter path of claims 1 and 11 to be synthetically generated using a graph weighted by a distance transform to favor paths close to a center of the known heart.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. The references on the attached PTO-892 disclose various manners of performing non-contact cardiac mapping and catheter path planning.
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 JONATHON A. SZUMNY whose telephone number is (303) 297-4376. The examiner can normally be reached Monday-Friday 7-5.
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 Dunham, can be reached at 571-272-8109. 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.
/JONATHON A. SZUMNY/Primary Examiner, Art Unit 3686