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 .
DETAILED ACTION
Response to Amendment
Claims 1-20 are pending in this application.
Claims 2, 14 and 17 have been amended [1/26/2026].
Response to Arguments
Applicant's arguments filed 1/26/2026 have been fully considered but they are not persuasive. On pages 7-8 of Applicant’s Arguments, Applicant argues the reference ‘Thibault fails to teach generating one or more FEM-mimic simulations by applying a first deep learning model to one or more pre-stent label volumes and one or more treatment variables, as recited in claim 1’, because Thibault teaches that the simulation module 112 comprises finite element models that are used in conjunction with (e.g., together with) separate machine learning models.
In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Further, Itu teaches simulating a blood flow and pressure for placement of the stent in the vessel in pre-stent anatomical model of coronary arteries to compute lumen and calcification post-stent flow and pressure related metrics including balloon force and using a modified pressure-drop model for a coronary artery stenosis based on CFD computations or a finite-element method and a post stenting pressure-drop for the stenosis to calculate base on the simulated blood flow using the modified pressure-drop model [par 0019, 0026, 0028, 0039, 0041], while Thibault teaches simulation module may include trained and/or untrained neural networks and may further include training routines, or parameters (e.g., weights and biases), associated with one or more deep learning methods (e.g., machine learning models) and finite element models for interventional imaging [par 0014, 0018-0019, 0026, 0048, 0058]. Thus, the combination of Itu in view of Thibault teaches modeling a stent and/or the vessel lumen as a deformable object and using techniques from computed mechanics, such as the finite element method (FEM), by implementing deep learning networks of machine learning models.
Therefore, Itu in view of Thibault does teach generating one or more FEM-mimic simulations by applying a first deep learning model to one or more pre-stent label volumes and one or more treatment variables, as recited in claim 1 [similar limitations of independent claims 9 and 17].
The above response is applied to those dependent therefrom.
Applicant’s arguments, see pages 8-10, filed 1/26/2026, with respect to claim 2 have been fully considered and are persuasive. The 35 USC 103 Rejection of claim 2 (and those dependent therefrom) has been withdrawn.
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.
Claim(s) 1 and 7 are rejected under 35 U.S.C. 103 as being unpatentable over Itu et al. (US-2015/0374243) in view of Thibault et al. (US-2023/0187054).
As to Claim 1, Itu teaches ‘A method of determining a stent effectiveness, comprising: accessing a pre-stent intravascular image of a blood vessel of a patient [par 0019-0021 – pre-stenting medical image data of a patient is received, such as PCI for a coronary artery stenosis and computed tomography (CT)]; determining one or more pre-stent label volumes of the blood vessel [par 0023, 0025 – pre-stenting patient-specific anatomical model of the coronary arteries is extracted, where each stenosis can also be extracted using similar algorithms which includes the quantification of the proximal vessel diameter and area, distal vessel diameter and area, minimal lumen diameter and area, and length of stenosis]; determining one or more treatment variables associated with the pre-stent intravascular image [par 0026, 0037-0040 – selecting a stenosis for virtual stenting treatment prediction (e.g., virtual PCI), to perform treatment prediction for multiple possible treatment scenarios]; generating one or more FEM-mimic simulations by applying a model to the one or more pre-stent label volumes and the one or more treatment variables; and utilizing the one or more FEM-mimic simulations to determine a stent effectiveness metric [par 0019, 0026, 0028, 0039, 0041 – simulating a blood flow and pressure for placement of the stent in the vessel in pre-stent anatomical model of coronary arteries to compute lumen and calcification post-stent flow and pressure related metrics including balloon force and using a modified pressure-drop model for a coronary artery stenosis based on CFD computations or a finite-element method and a post stenting pressure-drop for the stenosis to calculate base on the simulated blood flow using the modified pressure-drop model]’.
Itu does not disclose expressly ‘a first deep learning model’.
Thibault in the proposed combination teaches ‘a first deep learning model [par 0014, 0018-0019, 0026, 0048, 0058 – simulation module may include trained and/or untrained neural networks and may further include training routines, or parameters (e.g., weights and biases), associated with one or more deep learning methods (e.g., machine learning models) and finite element models for interventional imaging]’.
Itu and Thibault are analogous art because they are from the same field of endeavor, namely image simulations for medical images. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include one or more deep learning methods, as taught by Thibault. The motivation for doing so would have been to performing simulated studies based on an imaging intent, in order to more efficiently and accurately optimize image acquisition settings. Therefore, it would have been obvious to combine Thibault with Itu to obtain the invention as specified in claim 1.
As to Claim 7, Itu teaches ‘wherein the one or more FEM-mimic simulations are generated for a center frame using inputs collected from surrounding frames within a distance of the center frame [Fig 4, par 0026, 0030-0033 – simulating using a finite-element method for pressure-drop models by computing a minimum cross-sectional area along the stenosis with relation to cross-section area at the top of stenosed segment and cross-section area at the bottom of the stenosed segment]’.
Claim(s) 5-6 and 8, 9, 11, 14-16 are rejected under 35 U.S.C. 103 as being unpatentable over Itu et al. (US-2015/0374243) in view of Thibault et al. (US-2023/0187054) and further in view of Schmitt et al. (US-2015/0297373).
As to Claim 5, Itu teaches ‘further comprising: accessing segmented parts of the pre-stent intravascular image; extracting a plurality of image features from the segmented parts and a plurality of FEM-mimic features from the one or more FEM-mimic simulations; determining a lumen area from one or more of the plurality of image features and the plurality of FEM-mimic features [par 0019, 0023, 0026 – pre-stenting patient-specific anatomical model of the coronary arteries is extracted from the pre-stenting medical image data by segmenting the 3D medical image data using an automated coronary artery centerline extraction algorithm including proximal vessel diameter and area, distal vessel diameter and area, minimal lumen diameter and area, and length of stenosis, and simulating pre-stenting anatomical model using finite-element method to generate a post-stenting anatomical model of the lumen after the stent is placed in a vessel]’.
Itu in view of Thibault does not disclose expressly ‘determining a stent expansion index (SEI) or a minimum expansion index (MEI) from the lumen area’.
Schmitt in the proposed combination teaches ‘determining a stent expansion index (SEI) or a minimum expansion index (MEI) from the lumen area [Figs 11a, 11b, 12, par 0027, 0071-0078 – calculating stent expansion index by creating a partition or segmentation of a frame to compare a lumen diameter to determine an index value that provides a measure of error or deviation between a computed ideal profile and current lumen profile including walls of a vessel lumen]’.
Itu in view of Thibault are analogous art with Schmitt because they are from the same field of endeavor, namely medical imaging. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include stent expansion index, as taught by Schmitt. The motivation for doing so would have been to sizing and adjusting a stent of a narrowed vessel. Therefore, it would have been obvious to combine Schmitt with Itu in view of Thibault to obtain the invention as specified in claim 5.
As to Claim 6, Schmitt in the proposed combination teaches ‘selecting discriminative features from the plurality of image features and the plurality of FEM-mimic features; and providing the discriminative features to a regression model configured to determine the SEI or the MEI [Figs 11a, 11b, 12, par 0027, 0068, 0071-0078 – calculating stent expansion index by creating a partition or segmentation of a frame to compare a lumen diameter to determine an index value that provides a measure of error or deviation between a computed ideal profile and current lumen profile including walls of a vessel lumen based on a selected set of parameters]’.
Itu in view of Thibault are analogous art with Schmitt because they are from the same field of endeavor, namely medical imaging. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include stent expansion index, as taught by Schmitt. The motivation for doing so would have been to sizing and adjusting a stent of a narrowed vessel. Therefore, it would have been obvious to combine Schmitt with Itu in view of Thibault to obtain the invention as specified in claim 6.
As to Claim 8, Schmitt teaches ‘wherein the pre-stent intravascular image comprises one or more optical coherence tomography (IVOCT) images [par 0034, 0040 – OCT and IVUS are important methodologies for pre-interventional stent planning]’.
Itu in view of Thibault are analogous art with Schmitt because they are from the same field of endeavor, namely medical imaging. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include OCT and IVUS, as taught by Schmitt. The motivation for doing so would have been to sizing and adjusting a stent of a narrowed vessel. Therefore, it would have been obvious to combine Schmitt with Itu in view of Thibault to obtain the invention as specified in claim 8.
As to Claim 9, Itu teaches ‘A non-transitory computer-readable medium storing computer-executable instructions that, when executed, cause a processor to perform operations, comprising: accessing an intravascular optical coherence tomography (IVOCT) image of a blood vessel [par 0019-0021 – pre-stenting medical image data of a patient is received, such as PCI for a coronary artery stenosis and computed tomography (CT)]; determining one or more pre-stent label volumes associated with the blood vessel [par 0023, 0025 – pre-stenting patient-specific anatomical model of the coronary arteries is extracted, where each stenosis can also be extracted using similar algorithms which includes the quantification of the proximal vessel diameter and area, distal vessel diameter and area, minimal lumen diameter and area, and length of stenosis]; determining one or more treatment variables associated with the blood vessel [par 0026, 0037-0040 – selecting a stenosis for virtual stenting treatment prediction (e.g., virtual PCI), to perform treatment prediction for multiple possible treatment scenarios]; generating one or more FEM-mimic simulations by applying a model to the one or more pre-stent label volumes and the one or more treatment variables [par 0019, 0026, 0028, 0039, 0041 – simulating a blood flow and pressure for placement of the stent in the vessel in pre-stent anatomical model of coronary arteries to compute lumen and calcification post-stent flow and pressure related metrics including balloon force and using a modified pressure-drop model for a coronary artery stenosis based on CFD computations or a finite-element method and a post stenting pressure-drop for the stenosis to calculate base on the simulated blood flow using the modified pressure-drop model], wherein the one or more FEM-mimic simulations include a displacement field and one or more inflated label volumes formed using the displacement field and the one or more pre-stent label volumes; and generating one or more stress/strain maps from one or more of the displacement field and the one or more inflated label volumes [par 0019, 0028, 0038, 0042, 0046 – selecting a type of the pressure-drop model, such as the fully analytical model or the semi-empirical model, or the type of pressure-drop model can be preset and not selectable by a user when evaluating different stenting strategies for treating coronary artery stenoses to determine which stenting strategies are effective and/or select a best stenting strategy, where it is important to note that the determination of partially successful treatment or fully successful treatment is not based on modification of the anatomical model of the coronary arteries to estimate the actual enlargement of the geometry due to stent placement]’.
Itu does not disclose expressly ‘an intravascular optical coherence tomography (IVOCT) image; a first deep learning model’.
Thibault teaches ‘a first deep learning model [par 0014, 0018-0019, 0026, 0048, 0058 – simulation module may include trained and/or untrained neural networks and may further include training routines, or parameters (e.g., weights and biases), associated with one or more deep learning methods (e.g., machine learning models) and finite element models for interventional imaging]’.
Itu and Thibault are analogous art because they are from the same field of endeavor, namely image simulations for medical images. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include one or more deep learning methods, as taught by Thibault. The motivation for doing so would have been to performing simulated studies based on an imaging intent, in order to more efficiently and accurately optimize image acquisition settings. Therefore, it would have been obvious to combine Thibault with Itu to obtain the invention as specified.
Itu in view of Thibault does not disclose expressly ‘an intravascular optical coherence tomography (IVOCT) image’.
Schmitt teaches ‘an intravascular optical coherence tomography (IVOCT) image [par 0034, 0040 – OCT and IVUS are important methodologies for pre-interventional stent planning]’.
Itu in view of Thibault are analogous art with Schmitt because they are from the same field of endeavor, namely medical imaging. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include OCT and IVUS, as taught by Schmitt. The motivation for doing so would have been to sizing and adjusting a stent of a narrowed vessel. Therefore, it would have been obvious to combine Schmitt with Itu in view of Thibault to obtain the invention as specified in claim 9.
As to Claim 10, Itu in view of Schmitt teaches ‘wherein the operations further comprise: extracting one or more image features from the IVOCT image; extracting one or more FEM-mimic features from the one or more FEM-mimic simulations; and predicting a stent effectiveness from the one or more image features and the one or more FEM-mimic features [Itu: par 0019, 0023, 0026 – pre-stenting patient-specific anatomical model of the coronary arteries is extracted from the pre-stenting medical image data by segmenting the 3D medical image data using an automated coronary artery centerline extraction algorithm including proximal vessel diameter and area, distal vessel diameter and area, minimal lumen diameter and area, and length of stenosis, and simulating pre-stenting anatomical model using finite-element method to generate a post-stenting anatomical model of the lumen after the stent is placed in a vessel; Schmitt: par 0034, 0040 – OCT and IVUS are important methodologies for pre-interventional stent planning]’.
Itu in view of Thibault are analogous art with Schmitt because they are from the same field of endeavor, namely medical imaging. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include OCT and IVUS, as taught by Schmitt. The motivation for doing so would have been to sizing and adjusting a stent of a narrowed vessel. Therefore, it would have been obvious to combine Schmitt with Itu in view of Thibault to obtain the invention as specified in claim 10.
As to Claim 11, Itu teaches ‘wherein the one or more FEM-mimic features comprise lumen features, vessel wall strain features, and vessel wall stress features [par 0019, 0023, 0027 – requiring many assumptions, such as flow/pressure computation in the lumen, material property of the vessel lumen/wall, accurate geometry and material properties of the stent, the balloon force (or the pre-stress in case of self-expanding stents), etc.]’.
As to Claim 14, Thibault teaches simulation module may include trained and/or untrained neural networks and may further include training routines, or parameters (e.g., weights and biases), associated with one or more deep learning methods (e.g., machine learning models) and finite element models for interventional imaging [par 0014, 0018-0019, 0026, 0048, 0058].
While Schmitt teaches calculating stent expansion index by creating a partition or segmentation of a frame to compare a lumen diameter to determine an index value that provides a measure of error or deviation between a computed ideal profile and current lumen profile including walls of a vessel lumen for OCT and IVUS [Figs 11a, 11b, 12, par 0027, 0034, 0040, 0071-0078]’.
Thibault and Schmitt in the proposed combination of Itu teaches ‘wherein the operations further comprise: determining a plurality of features from the IVOCT images and from the one or more FEM-mimic simulations; operating a machine learning model on the plurality of features to determine a lumen area from one or more of the plurality of features; and determining a stent effectiveness from the lumen area [Thibault: par 0014, 0018-0019, 0026, 0048, 0058; Schmitt: Figs 11a, 11b, 12, par 0027, 0071-0078]’.
Itu in view of Thibault are analogous art with Schmitt because they are from the same field of endeavor, namely medical imaging. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include OCT and IVUS, as taught by Schmitt. The motivation for doing so would have been to sizing and adjusting a stent of a narrowed vessel. Therefore, it would have been obvious to combine Schmitt with Itu in view of Thibault to obtain the invention as specified in claim 14.
As to Claim 15, Itu in view of Thibault teaches ‘wherein the operations further comprise: training the first deep learning model by comparing the displacement field to training and testing data generated by a finite element model [Itu: par 0019, 0028, 0038, 0042, 0046 – selecting a type of the pressure-drop model, such as the fully analytical model or the semi-empirical model, or the type of pressure-drop model can be preset and not selectable by a user when evaluating different stenting strategies for treating coronary artery stenoses to determine which stenting strategies are effective and/or select a best stenting strategy, where it is important to note that the determination of partially successful treatment or fully successful treatment is not based on modification of the anatomical model of the coronary arteries to estimate the actual enlargement of the geometry due to stent placement; Thibault: par 0014, 0018-0019, 0026, 0048, 0058 – simulation module may include trained and/or untrained neural networks and may further include training routines, or parameters (e.g., weights and biases), associated with one or more deep learning methods (e.g., machine learning models) and finite element models for interventional imaging]’.
Itu and Thibault are analogous art because they are from the same field of endeavor, namely image simulations for medical images. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include one or more deep learning methods, as taught by Thibault. The motivation for doing so would have been to performing simulated studies based on an imaging intent, in order to more efficiently and accurately optimize image acquisition settings. Therefore, it would have been obvious to combine Thibault with Itu to obtain the invention as specified in claim 15.
As to Claim 16, Thibault in the proposed combination teaches ‘wherein a loss function is used to compare the displacement field to the training and testing data [par 0018, 0049-0050 – simulation module including loss functions based on patient information including prior images and anatomical features for training routines]’.
Itu and Thibault are analogous art because they are from the same field of endeavor, namely image simulations for medical images. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include one or more deep learning methods using loss functions, as taught by Thibault. The motivation for doing so would have been to performing simulated studies based on an imaging intent, in order to more efficiently and accurately optimize image acquisition settings. Therefore, it would have been obvious to combine Thibault with Itu to obtain the invention as specified in claim 16.
Claim(s) 12 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Itu et al. (US-2015/0374243) in view of Thibault et al. (US-2023/0187054) and further in view of Schmitt et al. (US-2015/0297373) and further in view of Rozen (US-2024/0156529).
As to Claim 12, Itu in view of Thibault and further in view of Schmitt teaches all of the claimed elements/features as recited in independent claim 9. Itu in view of Thibault and Schmitt does not disclose expressly ‘wherein the one or more stress/strain maps are formed using a second deep learning model’.
Rozen in the proposed combination teaches ‘wherein the one or more stress/strain maps are formed using a second deep learning model [par 0064-0065, 0081 – employing a second deep learning model that takes a 3D multi-class segmentation to generate one or more stress maps]’.
Itu in view of Thibault are analogous art with Rozen because they are from the same field of endeavor, namely medical imaging. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include finite element analysis to create stress maps, as taught by Rozen. The motivation for doing so would have been to predicting multi-labeled masks and/or stress maps for anatomical elements. Therefore, it would have been obvious to combine Rozen with Itu in view of Thibault and Schmitt to obtain the invention as specified in claim 12.
As to Claim 13, Rozen in the proposed combination teaches ‘wherein the operations further comprise: comparing stress values or strain values obtained from the one or more stress/strain maps to a predetermined stress/strain threshold to predict potential damage to the blood vessel [par 0057, 0063-0065, 0081 – employing a second deep learning model that takes a 3D multi-class segmentation to generate one or more stress maps to simulate stresses on anatomical element based on the highest amount of stress for potential stenosis]’.
Itu in view of Thibault and Schmitt are analogous art with Rozen because they are from the same field of endeavor, namely medical imaging. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include finite element analysis to create stress maps, as taught by Rozen. The motivation for doing so would have been to predicting multi-labeled masks and/or stress maps for anatomical elements. Therefore, it would have been obvious to combine Rozen with Itu in view of Thibault and Schmitt to obtain the invention as specified in claim 13.
Claim(s) 17-20 are rejected under 35 U.S.C. 103 as being unpatentable over Itu et al. (US-2015/0374243) in view of Thibault et al. (US-2023/0187054) and further in view of Rozen (US-2024/0156529).
As to Claim 17, Itu teaches ‘A stent prediction apparatus, comprising: a memory configured to store a pre-stent intravascular image of a blood vessel of a patient [par 0018-0021 – pre-stenting medical image data of a patient is received, such as PCI for a coronary artery stenosis and computed tomography (CT), where medical image data may be received by loading previously stored medical image data for a patient], one or more treatment variables relating to the pre-stent intravascular image [par 0018, 0026, 0037-0040 – selecting a stenosis for virtual stenting treatment prediction (e.g., virtual PCI) using data stored within the computer system, to perform treatment prediction for multiple possible treatment scenarios], and one or more pre-stent label volumes of the pre-stent intravascular image [par 0018, 0023, 0025 – pre-stenting patient-specific anatomical model of the coronary arteries is extracted using data stored within computer system, where each stenosis can also be extracted using similar algorithms which includes the quantification of the proximal vessel diameter and area, distal vessel diameter and area, minimal lumen diameter and area, and length of stenosis]; a model configured to generate one or more FEM-mimic simulations from the one or more treatment variables and the one or more pre-stent label volumes [par 0019, 0026, 0028, 0039, 0041 – simulating a blood flow and pressure for placement of the stent in the vessel in pre-stent anatomical model of coronary arteries to compute lumen and calcification post-stent flow and pressure related metrics including balloon force and using a modified pressure-drop model for a coronary artery stenosis based on CFD computations or a finite-element method and a post stenting pressure-drop for the stenosis to calculate base on the simulated blood flow using the modified pressure-drop model]’.
Itu does not disclose expressly ‘a first deep learning model; a second deep learning model configured to generate one or more stress/strain maps from the one or more FEM-mimic simulations’.
Thibault teaches ‘a first deep learning model [par 0014, 0018-0019, 0026, 0048, 0058 – simulation module may include trained and/or untrained neural networks and may further include training routines, or parameters (e.g., weights and biases), associated with one or more deep learning methods (e.g., machine learning models) and finite element models for interventional imaging]’.
Itu and Thibault are analogous art because they are from the same field of endeavor, namely image simulations for medical images. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include one or more deep learning methods using loss functions, as taught by Thibault. The motivation for doing so would have been to performing simulated studies based on an imaging intent, in order to more efficiently and accurately optimize image acquisition settings. Therefore, it would have been obvious to combine Thibault with Itu to obtain the invention as specified.
Itu in view of Thibault does not disclose expressly ‘a second deep learning model configured to generate one or more stress/strain maps from the one or more FEM-mimic simulations [par 0064-0065, 0081 – employing a second deep learning model that takes a 3D multi-class segmentation to generate one or more stress maps]’.
Rozen in the proposed combination teaches ‘a second deep learning model configured to generate one or more stress/strain maps from the one or more FEM-mimic simulations [par 0064-0065, 0081 – employing a second deep learning model that takes a 3D multi-class segmentation to generate one or more stress maps]’.
Itu in view of Thibault are analogous art with Rozen because they are from the same field of endeavor, namely medical imaging. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include finite element analysis to create stress maps, as taught by Rozen. The motivation for doing so would have been to predicting multi-labeled masks and/or stress maps for anatomical elements. Therefore, it would have been obvious to combine Rozen with Itu in view of Thibault to obtain the invention as specified in claim 17.
As to Claim 18, Itu teaches pre-stenting patient-specific anatomical model of the coronary arteries is extracted from the pre-stenting medical image data by segmenting the 3D medical image data using an automated coronary artery centerline extraction algorithm including proximal vessel diameter and area, distal vessel diameter and area, minimal lumen diameter and area, and length of stenosis, and simulating pre-stenting anatomical model using finite-element method to generate a post-stenting anatomical model of the lumen after the stent is placed in a vessel [par 0019, 0023, 0026].
Rozen teaches employing a second deep learning model that takes a 3D multi-class segmentation to generate one or more stress maps [par 0064-0065, 0081].
Itu in view of Thibault and further in view of Rozen teaches ‘further comprising: a feature extraction circuit configured to extract a plurality of image features from the pre-stent intravascular image and to further extract a plurality of FEM-mimic features from the one or more FEM-mimic simulations and the one or more stress/strain maps; and a machine learning circuit configured to operate upon the plurality of image features and the plurality of FEM-mimic features to generate a lumen area [Itu: par 0019, 0023, 0026; Rozen: par 0064-0065, 0081]’.
Itu in view of Thibault are analogous art with Rozen because they are from the same field of endeavor, namely medical imaging. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include finite element analysis to create stress maps, as taught by Rozen. The motivation for doing so would have been to predicting multi-labeled masks and/or stress maps for anatomical elements. Therefore, it would have been obvious to combine Rozen with Itu in view of Thibault to obtain the invention as specified in claim 18.
As to Claim 19, Itu teaches ‘further comprising: a stent effectiveness circuit configured to utilize the lumen area to generate a stent effectiveness metric [par 0019, 0026, 0028, 0039, 0041 – simulating a blood flow and pressure for placement of the stent in the vessel in pre-stent anatomical model of coronary arteries to compute lumen and calcification post-stent flow and pressure related metrics including balloon force and using a modified pressure-drop model for a coronary artery stenosis based on CFD computations or a finite-element method and a post stenting pressure-drop for the stenosis to calculate base on the simulated blood flow using the modified pressure-drop model]’.
As to Claim 20, Rozen in the proposed combination teaches ‘further comprising: a comparison circuit configured to utilize the one or more stress/strain maps to predict potential damage to the blood vessel [par 0057, 0063-0065, 0081 – employing a second deep learning model that takes a 3D multi-class segmentation to generate one or more stress maps to simulate stresses on anatomical element based on the highest amount of stress for potential stenosis]’.
Itu in view of Thibault are analogous art with Rozen because they are from the same field of endeavor, namely medical imaging. Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to include finite element analysis to create stress maps, as taught by Rozen. The motivation for doing so would have been to predicting multi-labeled masks and/or stress maps for anatomical elements. Therefore, it would have been obvious to combine Rozen with Itu in view of Thibault to obtain the invention as specified in claim 20.
Allowable Subject Matter
Claim 2 (claims 3-4 based on dependency) 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: Itu in view of Thibault, Schmitt, Rozen and further in view of the prior art searched and/or cited does not teach nor render obvious the combination of limitations including “applying the first deep learning model to the one or more pre-stent label volumes and the one or more treatment variables to form a displacement field showing changes in position of blood vessel components in response to insertion and expansion of a stent at the one or more treatment variables; determining one or more inflated label volumes using the displacement field and the one or more pre-stent label volumes; and generating one or more stress/strain maps from one or more of the displacement field and the one or more inflated label volumes” as recited in dependent claim 2.
Conclusion
THIS ACTION IS MADE FINAL. 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 MIYA J CATO whose telephone number is (571)270-3954. The examiner can normally be reached M-F, 830-530.
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, Akwasi Sarpong can be reached at 571.270.3438. 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.
/MIYA J CATO/Primary Examiner, Art Unit 2681