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 .
Priority
Receipt is acknowledged that application is a 371 of PCT/EP2022/070648. Applicant claims the benefit of Foreign Priority from Application No EP21189888.7, filed 08/05/2021. Claims 1-19 have been afforded the benefit of this filing date.
Information Disclosure Statement
The IDS dated 01/31/2024 have been considered and placed in the application file.
Claim Objections
Claim 11 is objected to because of the following informalities:
Claim 11 reads “said training including using training data data comprising at least one distribution of flow”. The Examiner is assuming the word “data” is not repeated purposefully. Appropriate correction is required.
Claim Interpretation
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.
Under MPEP 2143.03, "All words in a claim must be considered in judging the patentability of that claim against the prior art." In re Wilson, 424 F.2d 1382, 1385, 165 USPQ 494, 496 (CCPA 1970). As a general matter, the grammar and ordinary meaning of terms as understood by one having ordinary skill in the art used in a claim will dictate whether, and to what extent, the language limits the claim scope. Language that suggests or makes a feature or step optional but does not require that feature or step does not limit the scope of a claim under the broadest reasonable claim interpretation. In addition, when a claim requires selection of an element from a list of alternatives, the prior art teaches the element if one of the alternatives is taught by the prior art. See, e.g., Fresenius USA, Inc. v. Baxter Int’l, Inc., 582 F.3d 1288, 1298, 92 USPQ2d 1163, 1171 (Fed. Cir. 2009).
Claim 5 recite “or” then listing “3D U-Net or a 3D Deeplabv3+ or an LSTM.” Since “or” is disjunctive, any one of the elements found in the prior art is sufficient to reject the claim. While citations have been provided for completeness and rapid prosecution, only one element is required. Because, on balance, it appears the disjunctive interpretation enjoys the most specification support and for that reason the disjunctive interpretation (one of A, B OR C) is being adopted for the purposes of this Office Action. Applicant’s comments and/or amendments relating to this issue are invited to clarify the claim language and the prosecution history.
Claim 7 recite “or” then listing “either directly or indirectly,”. Since “or” is disjunctive, any one of the elements found in the prior art is sufficient to reject the claim. While citations have been provided for completeness and rapid prosecution, only one element is required. Because, on balance, it appears the disjunctive interpretation enjoys the most specification support and for that reason the disjunctive interpretation (one of A, B OR C) is being adopted for the purposes of this Office Action. Applicant’s comments and/or amendments relating to this issue are invited to clarify the claim language and the prosecution history.
Claim 11 recite “at least one ” then listing “data comprising at least one distribution of flow, pressure or resistance” Since “at least one” is disjunctive, any one of the elements found in the prior art is sufficient to reject the claim. While citations have been provided for completeness and rapid prosecution, only one element is required. Because, on balance, it appears the disjunctive interpretation enjoys the most specification support and for that reason the disjunctive interpretation (one of A, B OR C) is being adopted for the purposes of this Office Action. Applicant’s comments and/or amendments relating to this issue are invited to clarify the claim language and the prosecution history.
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 4 and 6 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 pre-AIA the applicant regards as the invention. The Examiner strongly suggested that appropriate corrections be made to clarify the claim scope.
With respect to Claim 4, the claim recites the following, each of which renders the claim indefinite:
“ said respective artery contours” on line 1-2 (unclear antecedent basis).
With respect to Claim 6, the claim recites the following, each of which renders the claim indefinite:
“ the respective artery contours” on line 4 (unclear antecedent basis).
“ respective voxel cuboids” on line 3 (unclear antecedent basis).
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.
Claims 1, 6, and 14-17 are rejected under 35 U.S.C. 103 as unpatentable over Li et al CN11680447A (using translation from espace.net, figures translated from google translate) hereafter referred to as Li) in view of Min et al. (US Patent Pub US 2021/0209757 A1 hereafter referred to as Min).
Regarding Claim 1, Li teaches a method (Li Pg 1 ¶08 discloses a method for predicting blood flow characteristics) for determining a Fractional Flow Reserve (FFR) related parameter value (Li Pg 1 ¶05 and Pg 7 ¶04 discloses characteristics including Fractional Flow Reserve (FFR), pressure, and shear force Li Pg 14 ¶06 discloses calculating the ratio for the pressure resulting in a value), comprising:
providing a computed tomography (CT) image (Li g 6 ¶17 discloses the image being a CT image) comprising coronary arteries (Li g 6 ¶17 discloses the image being a CT image of the three dimensional blood vessel)
extracting (Li Pg 1 ¶10 and Pg 2 ¶02 and Pg 6 ¶15 discloses extracting the centerline of the blood vessel), from said CT image (Li g 6 ¶17 discloses the image being a CT image) and for each of said coronary arteries (Li Pg 7 ¶03-¶04 discloses a center point for each vessel), a respective centerline (Li Pg 1 ¶10 and Pg 2 ¶02 and Pg 6 ¶15 discloses extracting the centerline of the blood vessel); and
determining, based at least on a coronary artery model (Li Pg 14 ¶04-¶06 and Pg 14 ¶07 discloses determining the mean pressure and other blood flow characteristic of the artery based on the blood flow feature prediction model in a coronary artery) comprising said respective centerlines (Li Pg 1 ¶10 and Pg 2 ¶02 and Pg 6 ¶15 discloses extracting the centerline of the blood vessel), said FFR-related parameter value (Li Pg 14 ¶04-¶06 discloses determining the mean pressure and other blood flow characteristic of the artery based on the blood flow feature prediction model in a coronary artery);
wherein said CT image is a three-dimensional (3D) CT image (Li g 6 ¶17 discloses the image being a CT image of the three dimensional blood vessel) comprising voxels (Li Pg 15 ¶06-¶07 discloses the three dimensional model being converted into pixel space representing image blocks), each voxel (Li Pg 15 ¶06-¶07 discloses the three dimensional model being converted into pixel space representing image blocks)
wherein said extracting of said respective centerlines (Li Pg 1 ¶10 and Pg 2 ¶02 and Pg 6 ¶15 discloses extracting the centerline of the blood vessel) comprises applying, on said 3D CT image (Li g 6 ¶17 discloses the image being a CT image of the three dimensional blood vessel) comprising voxels (Li Pg 15 ¶06-¶07 discloses the three dimensional model being converted into pixel space representing image blocks), a first neural network (NN) being a 3D NN (Li Pg 8 ¶11 and Pg 9 ¶05 and discloses a first neural network being composed of multiple CNN's) trained with respect to the centerline (Li Pg 10 ¶04 discloses training the first networks to become the centerline extraction model); and
wherein said determining of said FFR-related parameter value (Li Pg 1 ¶05 and Pg 7 ¶04 discloses characteristics including Fractional Flow Reserve (FFR), pressure, and shear force Li Pg 14 ¶06 discloses calculating the ratio for the pressure resulting in a value) comprises applying, on said coronary artery model (Li Pg 14 ¶04-¶06 and Pg 14 ¶07 discloses determining the mean pressure and other blood flow characteristic of the artery based on the blood flow feature prediction model in a coronary artery), a second NN (Li Pg 1 ¶13 discloses a second network, Li Pg2 ¶02 discloses predicting the feature parameters with the second network) trained with respect to FFR-related training data (Li Pg 10 ¶06 discloses the location feature parameters of the centerline and input into the second network and Li Figure 7 and Pg 11 ¶01 discloses the training of the network including iterative training using sample data Li Pg 19 ¶02 discloses sample data including feature parameters).
Li does not explicitly disclose obtained from coronary CT angiography (CCTA) and being associated with a radiodensity value.
Min is in the same field of image analysis of blood vessels. Further, Min teaches obtained from coronary CT angiography (CCTA) (Min ¶0004, ¶0114, and ¶0311 disclose using angiography, specifically coronary computed tomography angiography) being associated with a radiodensity value (Min ¶0436 discloses the use of radiodensity in the parameters of the plaque potentially narrowing the artery).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Li by including an image from a coronary CT angiography and a radiodensity value associated with the voxels and a graph NN as taught by Min, to make an invention that can and produce a graphical representation of the blood flow through the coronary artery using images from a commonly used medical imaging device; thus one of ordinary skilled in the art would be motivated to combine the references since there is a need for patients with stable heart disease to forgo invasive surgical procedures, such as angioplasty and/or heart bypass, and instead be prescribed heart medicines, such as statins, and certain lifestyle changes, such as regular exercise (Min ¶0005).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Regarding Claim 6 , Li in view of Min teaches the method of claim 1,wherein said second NN (Li Pg 1 ¶13 discloses a second network, Li Pg2 ¶02 discloses predicting the feature parameters with the second network) is applied on the combination (Li Pg 11 ¶02 discloses the input of the second network being the image block and the center point) discloses the of said coronary artery model (Li Pg 14 ¶04-¶06 and Pg 14 ¶07 discloses determining the mean pressure and other blood flow characteristic of the artery based on the blood flow feature prediction model in a coronary artery) and voxel portions (Li Pg 15 ¶06-¶07 disclose the image being segmented into images blocks) of said 3D CT image (Li g 6 ¶17 discloses the image being a CT image of the three dimensional blood vessel);
wherein said voxel portions (Li Pg 15 ¶06-¶07 disclose the image being segmented into images blocks) relate to respective voxel cuboids (Li Pg 15 ¶06-¶07 and Pg 8 ¶09 disclose the image being segmented into images blocks and the image blocks being a block of preset volume extracted from the image) extracted from said 3D CT image (Li g 6 ¶17 discloses the image being a CT image of the three dimensional blood vessel) at respective positions (Li Pg 8 ¶08, and discloses extracting the neighborhood image block of the current center point), on the extracted artery contour (Li Pg 20 ¶03 discloses a blood vessel contour extraction module is used to perform blood vessel contour extraction processing on the three-dimensional blood vessel image containing the blood vessel tree to obtain the blood vessel contour), and wherein said voxel cuboids (Li Pg 15 ¶06-¶07 and Pg 8 ¶09 disclose the image being segmented into images blocks and the image blocks being a block of preset volume extracted from the image) have a cuboid size of x by y by z voxels whereby min (x,y,z) is three or more (Li Pg 8 ¶09 discloses the cuboid image size being 25x25x25 pixels). See claim 1 for rationale, its parent claim.
Regarding Claim 14, Li in view of Min teaches a device comprising a processor and memory storing instructions (Li Pg 21 ¶03-¶04 discloses a computer comprising a non-volatile storage medium and program) which, when executed by the processor, cause the device to execute the method (Li Pg 21 ¶04 discloses a computer program executed by the processor) of claim 1. See claim 1 for rationale, its parent claim.
Regarding Claim 15, Li in view of Min teaches a non-transitory computer readable medium storing instructions (Li Pg 21 ¶04 discloses a non-volatile storage medium stores an operating system, and a computer program) which, when carried out on a processor, cause the processor to carry out the method (Li Pg 21 ¶04 discloses a computer program executed by the processor) of claim 1. See claim 1 for rationale, its parent claim.
Regarding Claim 16, Li in view of Min teaches the method of claim 1, wherein the radiodensity value (Min ¶0436 discloses the use of radiodensity in the parameters of the plaque potentially narrowing the artery) comprises a Hounsfield unit value (Min ¶0136 and ¶0155 discloses the density represented by a Hounsfield unit scale). See claim 1 for rationale, its parent claim.
Regarding Claim 17, Li in view of Min teaches the method of claim 6, wherein the voxel cuboids (Li Pg 15 ¶06-¶07 and Pg 8 ¶09 disclose the image being segmented into images blocks and the image blocks being a block of preset volume extracted from the image) have a cuboid size of x by y by z voxels whereby min(x,y,z) is five or more (Li Pg 8 ¶09 discloses the cuboid image size being 25x25x25 pixels), wherein the voxel cuboids are voxel cubes (Li Pg 15 ¶06-¶07 and Pg 8 ¶09 disclose the image being segmented into images blocks and the image blocks being a block of preset volume extracted from the image), and wherein the second NN (Li Pg 1 ¶13 discloses a second network, Li Pg2 ¶02 discloses predicting the feature parameters with the second network) is a graph NN (Min ¶0710 and ¶0719 discloses the network producing a graphical representation of the artery tree). See claim 1 for rationale, its parent claim.
Claims 2-5, 7-13, and 19 are rejected under 35 U.S.C. 103 as unpatentable over Li in view of Min in further view of Passerini et al. (US Patent Pub US 2021/0085397 A1 hereafter referred to as Passerini).
Regarding Claim 2, Li in view of Min teaches the method of claim 1, further comprising:
extracting, from said CT image (Li g 6 ¶17 discloses the image being a CT image of the three dimensional blood vessel) and for each of said coronary arteries (Li Pg 7 ¶03-¶04 discloses a center point for each vessel), a respective artery contour (Li Pg 20 ¶03 discloses a blood vessel contour extraction module is used to perform blood vessel contour extraction processing on the three-dimensional blood vessel image containing the blood vessel tree to obtain the blood vessel contour);
wherein said extracting of said respective artery contours (Li Pg 20 ¶03 discloses a blood vessel contour extraction module is used to perform blood vessel contour extraction processing on the three-dimensional blood vessel image containing the blood vessel tree to obtain the blood vessel contour) comprises applying, on said CT image (Li g 6 ¶17 discloses the image being a CT image of the three dimensional blood vessel),
with respect to a radius from the centerline (Li Pg 16 ¶08 discloses line segments of the same length radiated from the center point); and
wherein said coronary artery model (Li Pg 14 ¶04-¶06 and Pg 14 ¶07 discloses determining the mean pressure and other blood flow characteristic of the artery based on the blood flow feature prediction model in a coronary artery) from which said FFR-related parameter value (Li Pg 14 ¶04-¶06 discloses determining the mean pressure and other blood flow characteristic of the artery based on the blood flow feature prediction model in a coronary artery) is determined further comprises said respective artery contours (Li Pg 20 ¶03 discloses a blood vessel contour extraction module is used to perform blood vessel contour extraction processing on the three-dimensional blood vessel image containing the blood vessel tree to obtain the blood vessel contour Li Fig 14 discloses the contours as part of the model).
Li in view of Min does not explicitly disclose a third NN trained.
Passerini is in the same field of image analysis of blood vessels. Further, Passerini teaches a third NN trained (Passerini ¶0022 discloses a third trained machine learning model).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Li in view of Min by including a third trained neural network, a network that performs regression, and measured distribution of epicardial resistance as taught by Passerini, to make an invention that can use the third neural network in conjunction with the first two networks to more accurately predict the issue with the blood vessel based on the measured distribution of epicardial resistance; thus one of ordinary skilled in the art would be motivated to combine the references since there is a need for fast and non-invasive techniques to assess the hemodynamic significance of different portions of long diffuse/tandem lesions, as well as guide the optimal treatment strategy based on characterization of the lesion stability before and after PCI. (Passerini ¶0006)
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Regarding Claim 3, Li in view of Min teaches the method of claim 1, wherein said applying of said first NN (Li Pg 8 ¶11 and Pg 9 ¶05 and discloses a first neural network being composed of multiple CNN's) for extracting said respective centerlines (Li Pg 1 ¶10 and Pg 2 ¶02 and Pg 6 ¶15 discloses extracting the centerline of the blood vessel) comprises generating a 3D heat map (Min ¶0417-¶0418 discloses mapping using density readings from the CT image) comprising a confidence value per voxel (Min ¶0157 discloses confidently marking each pixel with a plaque likelihood) on said confidence values (Min ¶0157 discloses confidently marking each pixel with a plaque likelihood).
Li in view of Min does not explicitly disclose followed by performing a regression.
Passerini is in the same field of image analysis of blood vessels. Further, Passerini teaches followed by performing a regression (Passerini ¶0047 discloses performing a regression to estimate a location using a progression model).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Li in view of Min by including a third trained neural network, a network that performs regression, and measured distribution of epicardial resistance as taught by Passerini, to make an invention that can use the third neural network in conjunction with the first two networks to more accurately predict the issue with the blood vessel based on the measured distribution of epicardial resistance; thus one of ordinary skilled in the art would be motivated to combine the references since there is a need for fast and non-invasive techniques to assess the hemodynamic significance of different portions of long diffuse/tandem lesions, as well as guide the optimal treatment strategy based on characterization of the lesion stability before and after PCI. (Passerini ¶0006)
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Regarding Claim 4, Li in view of Min in view of Passerini teaches the method of claim 3, wherein said extracting of said respective artery contours (Li Pg 20 ¶03 discloses a blood vessel contour extraction module is used to perform blood vessel contour extraction processing on the three-dimensional blood vessel image containing the blood vessel tree to obtain the blood vessel contour) comprises determining a seed (Li Pg 19 ¶03 and Pg 19 ¶06 discloses a start point of the blood vessel for the center point for the length of the blood vessel tree) based on a maximum confidence value (Min ¶0157 discloses confidently marking each pixel with a plaque likelihood) on said 3D heat map (Min ¶0417-¶0418 discloses mapping using density readings from the CT image) corresponding to a voxel (Li Pg 15 ¶06-¶07 discloses the three dimensional model being converted into pixel space representing image blocks) not belonging to said centerline (Li Pg 8 ¶05 discloses a point classification label that can classify the center point as an end point or branch point). See claim 3 for rationale, its parent claim.
Regarding Claim 5, Li in view of Min in view of Passerini teaches the method of claim 3, wherein said first NN (Li Pg 8 ¶11 and Pg 9 ¶05 and discloses a first neural network being composed of multiple CNN's) is a 3D U-Net or a 3D Deeplabv3+ or an LSTM (Passerini ¶0062 ¶0063, ¶0087 discloses and long term short memory network, since "or" is used as a disjunctive statement here, the LSTM is used on its own to reject). See claim 3 for rationale, its parent claim.
Regarding Claim 7, Li in view of Min in view of Passerini teaches the method of claim 3, wherein said second NN is applied (Li Pg 1 ¶13 discloses a second network, Li Pg2 ¶02 discloses predicting the feature parameters with the second network), either directly or indirectly (Min ¶0138 discloses applying the network directly to the image) , on voxel portions (Li Pg 15 ¶06-¶07 disclose the image being segmented into images blocks) of said 3D CT image (Li g 6 ¶17 discloses the image being a CT image of the three dimensional blood vessel) and on the extracted centerline (Li Pg 1 ¶10 and Pg 2 ¶02 and Pg 6 ¶15 discloses extracting the centerline of the blood vessel) comprised in the coronary artery model (Li Pg 14 ¶04-¶06 and Pg 14 ¶07 discloses determining the mean pressure and other blood flow characteristic of the artery based on the blood flow feature prediction model in a coronary artery); and
wherein said voxel portions (Li Pg 15 ¶06-¶07 disclose the image being segmented into images blocks) relate to respective voxel cuboids (Li Pg 15 ¶06-¶07 and Pg 8 ¶09 disclose the image being segmented into images blocks and the image blocks being a block of preset volume extracted from the image) extracted from said 3D CT image (Li g 6 ¶17 discloses the image being a CT image of the three dimensional blood vessel) surrounding respective positions of the extracted centerline (Li Pg 8 ¶08 discloses extracting the neighborhood image block of the current center point) according to a cuboid radius larger than a maximal artery radius (Lin Pg 14 ¶07 discloses the 3D image block is the diameter of the blood vessel). See claim 3 for rationale, its parent claim.
Regarding Claim 8, Li in view of Min in view of Passerini teaches the method of claim 7, wherein said second NN (Li Pg 1 ¶13 discloses a second network, Li Pg2 ¶02 discloses predicting the feature parameters with the second network) is applied directly (Min ¶0138 discloses applying the network directly to the image) on voxel portions (Li Pg 15 ¶06-¶07 disclose the image being segmented into images blocks) of said 3D CT image (Li g 6 ¶17 discloses the image being a CT image of the three dimensional blood vessel) and on the extracted centerline (Li Pg 1 ¶10 and Pg 2 ¶02 and Pg 6 ¶15 discloses extracting the centerline of the blood vessel) comprised in the coronary artery model (Li Pg 14 ¶04-¶06 and Pg 14 ¶07 discloses determining the mean pressure and other blood flow characteristic of the artery based on the blood flow feature prediction model in a coronary artery) without requiring extraction of artery contours (Li Pg 2 ¶07-09 discloses the model being completed without using the coronary contour extraction). See claim 3 for rationale, its parent claim.
Regarding Claim 9, Li in view of Min in view of Passerini teaches the method of claim 7, wherein said second NN (Li Pg 1 ¶13 discloses a second network, Li Pg2 ¶02 discloses predicting the feature parameters with the second network) is applied indirectly (Passerini ¶0050 discloses that the medical images may receive by loading previous images not directly from the imaging device) on voxel portions (Li Pg 15 ¶06-¶07 disclose the image being segmented into images blocks) of said 3D CT image (Li g 6 ¶17 discloses the image being a CT image of the three dimensional blood vessel) and on the extracted centerline (Li Pg 1 ¶10 and Pg 2 ¶02 and Pg 6 ¶15 discloses extracting the centerline of the blood vessel) comprised in the coronary artery model (Li Pg 14 ¶04-¶06 and Pg 14 ¶07 discloses determining the mean pressure and other blood flow characteristic of the artery based on the blood flow feature prediction model in a coronary artery) without requiring extraction of artery contours (Li Pg 2 ¶07-09 discloses the model being completed without using the coronary contour extraction), said being applied indirectly (Passerini ¶0050 discloses that the medical images may receive by loading previous images not directly from the imaging device) relating to generating a multi-planar reformation (MPR) mapping (Min ¶0294 and ¶0298 discloses generating visualization of the blood vessels in a multi planar reformation format on an x and y axis) from said voxel portions (Li Pg 15 ¶06-¶07 disclose the image being segmented into images blocks); and
wherein said second NN (Li Pg 1 ¶13 discloses a second network, Li Pg2 ¶02 discloses predicting the feature parameters with the second network) is applied to said MPR mapping (Min ¶0294 and ¶0298 discloses generating visualization of the blood vessels in a multi planar reformation format on an x and y axis). See claim 3 for rationale, its parent claim.
Regarding Claim 10, Li in view of Min in view of Passerini teaches the method of claim 7, wherein the second NN (Li Pg 1 ¶13 discloses a second network, Li Pg2 ¶02 discloses predicting the feature parameters with the second network) is a transformer model (Li Pg 8 ¶02 discloses that the second network is a deep learning network based on the Transformer structure). See claim 3 for rationale, its parent claim.
Regarding Claim 11, Li in view of Min teaches the method of claim 1, further comprising the second NN (Li Pg 1 ¶13 discloses a second network, Li Pg2 ¶02 discloses predicting the feature parameters with the second network) with respect to the FFR-related training data (Li Pg 10 ¶06 discloses the location feature parameters of the centerline and input into the second network and Li Figure 7 and Pg 11 ¶01 discloses the training of the network including iterative training using sample data Li Pg 19 ¶02 discloses sample data including feature parameters), said training including using training data (Li Pg 3 ¶12 discloses the feature sequences and the parameters used in the training data) data comprising at least one distribution of flow (Li Pg 3 ¶12 discloses flow rate), pressure or resistance (Li Pg 3 ¶12 discloses pressure and shear force) at a plurality of positions along one of said coronary arteries (Li Pg 3 ¶12 and Pg 3 ¶08 discloses the parameters being taken for each center point along the centerline of the artery), wherein said at least one distribution of flow (Li Pg 3 ¶12 discloses flow rate), pressure or resistance(Li Pg 3 ¶12 discloses pressure and shear force).
Li in view of Min does not explicitly disclose comprises at least one measured distribution of epicardial resistance.
Passerini is in the same field of image analysis of blood vessels. Further, Passerini teaches comprises at least one measured distribution of epicardial resistance (Passerini ¶0049 and Fig 3 discloses an accurate FFR pullback distribution and ¶00583 discloses rest distal-to-aortic pressure ratio (Pd/Pa), computational flow reserve (CFR), hyperemic stenosis resistance (HSR), baseline stenosis resistance (BSR), index of microvascular resistance (IMR), or wall shear stress).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Li in view of Min by including a third trained neural network, a network that performs regression, and measured distribution of epicardial resistance as taught by Passerini, to make an invention that can use the third neural network in conjunction with the first two networks to more accurately predict the issue with the blood vessel based on the measured distribution of epicardial resistance; thus one of ordinary skilled in the art would be motivated to combine the references since there is a need for fast and non-invasive techniques to assess the hemodynamic significance of different portions of long diffuse/tandem lesions, as well as guide the optimal treatment strategy based on characterization of the lesion stability before and after PCI. (Passerini ¶0006)
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Regarding Claim 12, Li in view of Min teaches the method of claim 1, wherein the FFR-related parameter value (Li Pg 1 ¶05 and Pg 7 ¶04 discloses characteristics including Fractional Flow Reserve (FFR), pressure, and shear force Li Pg 14 ¶06 discloses calculating the ratio for the pressure resulting in a value) and wherein the method further comprises:
determining, by means of an automated classifier (Li Pg 18 ¶09 discloses the second network assigning classification labels) comprising a neural-network-based classifier (Min Fig 3A 322 and 0008 discloses classification of cardiovascular structures using a machine learning algorithm).
Li in view of Min does not explicitly disclose relates to a distribution of epicardial resistance values, a characteristic of said distribution indicative of the distribution being diffuse or focal.
Passerini is in the same field of image analysis of blood vessels. Further, Passerini teaches relates to a distribution of epicardial resistance values (Passerini ¶0049 and Fig 3 discloses an accurate FFR pullback distribution and ¶00583 discloses rest distal-to-aortic pressure ratio (Pd/Pa), computational flow reserve (CFR), hyperemic stenosis resistance (HSR), baseline stenosis resistance (BSR), index of microvascular resistance (IMR), or wall shear stress.)
a characteristic of said distribution (Passerini ¶0049 and Fig 3 discloses an accurate FFR pullback distribution and ¶00583 discloses rest distal-to-aortic pressure ratio (Pd/Pa), computational flow reserve (CFR), hyperemic stenosis resistance (HSR), baseline stenosis resistance (BSR), index of microvascular resistance (IMR), or wall shear stress.) indicative of the distribution being diffuse or focal (Passerini ¶0043 discloses how the FFR values help determine if the lesions are diffuse or not).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Li in view of Min by including a third trained neural network, a network that performs regression, and measured distribution of epicardial resistance as taught by Passerini, to make an invention that can use the third neural network in conjunction with the first two networks to more accurately predict the issue with the blood vessel based on the measured distribution of epicardial resistance; thus one of ordinary skilled in the art would be motivated to combine the references since there is a need for fast and non-invasive techniques to assess the hemodynamic significance of different portions of long diffuse/tandem lesions, as well as guide the optimal treatment strategy based on characterization of the lesion stability before and after PCI. (Passerini ¶0006)
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Regarding Claim 13, Li in view of Min teaches the method of claim 1, further comprising:
extracting, (Li Pg 1 ¶10 and Pg 2 ¶02 and Pg 6 ¶15 discloses extracting the centerline of the blood vessel), from said CT image (Li g 6 ¶17 discloses the image being a CT image) and for each of said coronary arteries (Li Pg 7 ¶03-¶04 discloses a center point for each vessel), a respective artery contour (Li Pg 20 ¶03 discloses a blood vessel contour extraction module is used to perform blood vessel contour extraction processing on the three-dimensional blood vessel image containing the blood vessel tree to obtain the blood vessel contour), said extracting of said respective artery contours (Li Pg 20 ¶03 discloses a blood vessel contour extraction module is used to perform blood vessel contour extraction processing on the three-dimensional blood vessel image containing the blood vessel tree to obtain the blood vessel contour) comprising applying, on said CT image (Li g 6 ¶17 discloses the image being a CT image), with respect to a radius from the centerline (Li Pg 16 ¶08 discloses line segments of the same length radiated from the center point);
determining, based on the extracted artery contour (Li Pg 20 ¶03 discloses a blood vessel contour extraction module is used to perform blood vessel contour extraction processing on the three-dimensional blood vessel image containing the blood vessel tree to obtain the blood vessel contour) and the determined FFR-related value(Li Pg 14 ¶04-¶06 discloses determining the mean pressure and other blood flow characteristic of the artery based on the blood flow feature prediction model in a coronary artery) , an artery segment associated with a narrowing (Li Pg 14 ¶06 and Pg 16 ¶02 discloses the stenosis of the coronary artery); and
generating, based on the extracted artery contour (Li Pg 20 ¶03 discloses a blood vessel contour extraction module is used to perform blood vessel contour extraction processing on the three-dimensional blood vessel image containing the blood vessel tree to obtain the blood vessel contour) and the determined artery segment (Li Pg 14 ¶06 and Pg 16 ¶02 discloses the stenosis of the coronary artery), an image comprising at least one of a visualization or heatmap of said artery contour (Li Fig 14 discloses the output of the visualization image of the artery contour) showing a position of said artery segment associated with said narrowing (Li Pg 16 ¶02 and Fig 14 discloses the output of the visualization image of the artery contour showing the condition of the blood vessel and where the stenosis exists in the blood vessel) .
Li in view of Min does not explicitly disclose a third NN trained.
Passerini is in the same field of image analysis of blood vessels. Further, Passerini teaches a third NN trained (Passerini ¶0022 discloses a third trained machine learning model).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Li in view of Min by including a third trained neural network, a network that performs regression, and measured distribution of epicardial resistance as taught by Passerini, to make an invention that can use the third neural network in conjunction with the first two networks to more accurately predict the issue with the blood vessel based on the measured distribution of epicardial resistance; thus one of ordinary skilled in the art would be motivated to combine the references since there is a need for fast and non-invasive techniques to assess the hemodynamic significance of different portions of long diffuse/tandem lesions, as well as guide the optimal treatment strategy based on characterization of the lesion stability before and after PCI. (Passerini ¶0006)
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Regarding Claim 19, Li in view of Min in view of Passerini teaches the method of claim 11, wherein the at least one measured distribution of epicardial resistance (Passerini ¶0049 and Fig 3 discloses an accurate FFR pullback distribution and ¶00583 discloses rest distal-to-aortic pressure ratio (Pd/Pa), computational flow reserve (CFR), hyperemic stenosis resistance (HSR), baseline stenosis resistance (BSR), index of microvascular resistance (IMR), or wall shear stress.) relates to a motorized FFR pullback (Passerini ¶0049, ¶0004, and Fig 3 discloses an accurate FFR pullback distribution and FFR pullback curve).See claim 11 for rationale, its parent claim.
Allowable Subject Matter
Claim 18 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.
Reference Cited
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure.
CN Patent Pub CN-111652881-A to FENG et al. discloses a coronary reconstruction and blood flow reserve fraction calculation method based on deep learning.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RACHEL LYNN ROBERTS whose telephone number is (571)272-6413. The examiner can normally be reached Monday- Friday 7:30am- 5:00pm.
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, Oneal Mistry can be reached on (313) 446-4912. 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.
/RACHEL L ROBERTS/Examiner, Art Unit 2674
/ONEAL R MISTRY/Supervisory Patent Examiner, Art Unit 2674