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 .
Claims Pending
Applicant's arguments, filed 07/20/2025, have been fully considered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
Applicants have amended their claims, filed 07/20/2025, and therefore rejections newly made in the instant office action have been necessitated by amendment.
Applicant’s cancellation of claim 2 in the response filed 07/20/2025 and previous cancellation of claims 4 and 6 is acknowledged.
Claims 1, 3, 5, and 7-12 are the current claims hereby under examination.
Claim Interpretation - Withdrawn
The applicant’s amendments, filed 10/27/2024, have been fully considered and the previous interpretation withdrawn.
Claim Rejections - 35 USC § 112 - Withdrawn
The applicant’s amendments, filed 07/20/2025, have been fully considered and the previous interpretation withdrawn
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1, 3, 5, and 7-12 are rejected under 35 U.S.C. 101 because the claimed invention is directed towards a judicial exception without significantly more. These claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception or that are sufficient to amount to significantly more than the judicial exception.
Step 1 of the subject matter eligibility test
Claims 1 and 9 are directed towards a method and a system, respectively, which each describes one of the four statutory categories of patentable subject matter.
Step 2A of the subject matter eligibility test
Prong 1: Claim 1 recites the abstract idea of a mental process as follows:
“output a value of a stenosis significance parameter by means of a training data set comprising a plurality of records of prior clinically examined stenosis cases, each training record comprising: data representing dimensional parameters, data representing blood flow parameters calculated using computational fluid dynamics (CPD) methods, including at least one of: relative fractional flow reserve (FFR_VCAST), energy flow reference index (EFR_VCAST), vascular resistance (R), turbulent kinetic energy, pressure drop (∆P), wall shear stress, oscillatory shear index, and relative residence time, and data representing clinical measurement parameters of the prior clinically examined blood vessel containing the stenosis”, “numerical simulation comparing a personalized model and a reference model of the blood vessel, the numerical simulation comprising determining conditions of blood flow at an inlet to the blood vessels model and calculating blood flow energy for the inlet and all outlets of the blood vessels model, and comparing the blood flow energy measured for the personalized model and for the reference model to determine blood flow energy change indexes”, “inputting…” “…an examination record comprising data representing the dimensional parameters of the currently examined blood vessel containing the stenosis and data representing blood flow parameters calculated using CFD methods, including at least one of: relative fractional flow reserve (FFR_VCAST), energy flow reference index (EFR_VCAST), vascular resistance (R), turbulent kinetic energy, pressure drop (AP), wall shear stress, oscillatory shear index, and relative residence time, wherein the examination record contains less input data than the training records, and does not contain clinical measurement parameters”, “instructing…” “…to output the value of the stenosis significance parameter based on the examination record, wherein the value of the stenosis significance parameter is selected from the group consisting of Significant (S), Non-Significant (NS), and Borderline (B).”
The outputting a value of a stenosis significance parameter by means of a training data set comprising a plurality of records of prior clinically examined stenosis cases, each training record comprising: data representing dimensional parameters, data representing blood flow parameters calculated using computational fluid dynamics (CPD) methods, including at least one of: relative fractional flow reserve (FFR_VCAST), energy flow reference index (EFR_VCAST), vascular resistance (R), turbulent kinetic energy, pressure drop (∆P), wall shear stress, oscillatory shear index, and relative residence time, and data representing clinical measurement parameters of the prior clinically examined blood vessel containing the stenosis, numerical simulation comparing a personalized model and a reference model of the blood vessel, the numerical simulation comprising determining conditions of blood flow at an inlet to the blood vessels model and calculating blood flow energy for the inlet and all outlets of the blood vessels model, and comparing the blood flow energy measured for the personalized model and for the reference model to determine blood flow energy change indexes, inputting an examination record comprising data representing the dimensional parameters of the currently examined blood vessel containing the stenosis and data representing blood flow parameters calculated using CFD methods, including at least one of: relative fractional flow reserve (FFR_VCAST), energy flow reference index (EFR_VCAST), vascular resistance (R), turbulent kinetic energy, pressure drop (AP), wall shear stress, oscillatory shear index, and relative residence time, wherein the examination record contains less input data than the training records, and does not contain clinical measurement parameters, and instructing to output the value of the stenosis significance parameter based on the examination record, wherein the value of the stenosis significance parameter is selected from the group consisting of Significant (S), Non-Significant (NS), and Borderline (B) can be practically performed by the human mind, with the aid of a pen and paper, but for performance on a generic processor, in a computer environment, or merely using the computer as a tool to perform the steps.
Prong 1: Claim 9 recites the abstract idea of a mental process as follows:
“output a value of a stenosis significance parameter by means of a training data set comprising a plurality of records of prior clinically examined stenosis cases, each training record comprising: data representing dimensional parameters, data representing blood flow parameters calculated using computational fluid dynamics (CPD) methods, including at least one of: relative fractional flow reserve (FFR_VCAST), energy flow reference index (EFR_VCAST), vascular resistance (R), turbulent kinetic energy, pressure drop (∆P), wall shear stress, oscillatory shear index, and relative residence time, and data representing clinical measurement parameters of the prior clinically examined blood vessel containing the stenosis”, “numerical simulation comparing a personalized model and a reference model of the blood vessel, the numerical simulation comprising determining conditions of blood flow at an inlet to the blood vessels model and calculating blood flow energy for the inlet and all outlets of the blood vessels model, and comparing the blood flow energy measured for the personalized model and for the reference model to determine blood flow energy change indexes”, “receive an examination record comprising data representing the dimensional parameters of the currently examined blood vessel containing the stenosis and data representing blood flow parameters calculated using CFD methods, including at least one of: relative fractional flow reserve (FFRVCAST), energy flow reference index (EFRVCAST), vascular resistance (R), turbulent kinetic energy, pressure drop (AP), wall shear stress, oscillatory shear index, and relative residence time, wherein the examination record contains less input data than the training records, and does not contain clinical measurement parameters”, and “provide the value of the stenosis significance parameter based on the examination record, wherein the value of the stenosis significance parameter is selected from the group consisting of Significant (S), Non-Significant (NS), and Borderline (B).”.
The outputting a value of a stenosis significance parameter by means of a training data set comprising a plurality of records of prior clinically examined stenosis cases, each training record comprising: data representing dimensional parameters, data representing blood flow parameters calculated using computational fluid dynamics (CPD) methods, including at least one of: relative fractional flow reserve (FFR_VCAST), energy flow reference index (EFR_VCAST), vascular resistance (R), turbulent kinetic energy, pressure drop (∆P), wall shear stress, oscillatory shear index, and relative residence time, and data representing clinical measurement parameters of the prior clinically examined blood vessel containing the stenosis, numerical simulation comparing a personalized model and a reference model of the blood vessel, the numerical simulation comprising determining conditions of blood flow at an inlet to the blood vessels model and calculating blood flow energy for the inlet and all outlets of the blood vessels model, and comparing the blood flow energy measured for the personalized model and for the reference model to determine blood flow energy change indexes, receiving an examination record comprising data representing the dimensional parameters of the currently examined blood vessel containing the stenosis and data representing blood flow parameters calculated using CFD methods, including at least one of: relative fractional flow reserve (FFRVCAST), energy flow reference index (EFRVCAST), vascular resistance (R), turbulent kinetic energy, pressure drop (AP), wall shear stress, oscillatory shear index, and relative residence time, wherein the examination record contains less input data than the training records, and does not contain clinical measurement parameters, providing the value of the stenosis significance parameter based on the examination record, wherein the value of the stenosis significance parameter is selected from the group consisting of Significant (S), Non-Significant (NS), and Borderline (B) can be practically performed by the human mind, with the aid of a pen and paper, but for performance on a generic processor, in a computer environment, or merely using the computer as a tool to perform the steps.
A person of ordinary skill in the art could reasonably output a value of a stenosis significance parameter based on being handed a piece of paper with dimensional parameters and blood flow parameters with a generic computer. A person of ordinary skill in the art could reasonably receive an examination record by being handed a piece of paper. A person of ordinary skill in the art could reasonably compare a personalized model and reference model of a blood vessel based on being handed a piece of paper with reference and personalized blood flow data with a generic computer. A person of ordinary skill in the art could reasonably determine conditions of blood flow and calculate blood flow energy based on being handed a piece of paper with a blood vessel model with a generic computer. A person of ordinary skill in the art could reasonably output and provide a value of stenosis significance verbally or with a generic computer. A person of ordinary skill in the art could reasonably input an examination record with a generic computer.
There is currently nothing to suggest an undue level of complexity in the comparing, determining, calculating, inputting, receiving, outputting, and providing steps. Therefore, a person would be able to practically be able to perform the comparing, determining, calculating, inputting, receiving, outputting, and providing steps mentally or with the aid of pen and paper.
Prong Two: Claims 1 and 9 do not recite additional elements that integrate the mental process into a practical application. Therefore, the claims are “directed to” the mental process. The additional elements merely:
Recite the words “apply it” or an equivalent with the judicial exception, or include instructions to implement the abstract idea on a computer, or merely use the computer as a tool to perform the abstract idea (e.g., a computer, a non-transitory, computer-readable memory, and processor).
For claims 1 and 9. The additional elements merely serve to gather data to be used by the abstract idea. The computer is merely used as a pre-solution step of necessary data gathering to be used by the abstract idea. There is no practical application because the abstract idea is not applied, relied on, or used in a meaningful way. The processing that is performed remains in the abstract realm, i.e. the gathered data is not used for a treatment or meaningful purpose. Additionally, there is no overall improvement to existing technology present. The mental process merely functions on generic computer elements that do not change the functionality of the device itself. Therefore, the additional elements, alone or in combination, do not integrate the abstract idea into a practical application.
Step 2B of the subject matter eligibility test for Claims 1 and 9:
Per the Berkheimer requirement, the additional elements are well-understood, routine, and conventional. For example,
a computer and a non-transitory, computer-readable memory, and processor as disclosed by Yang (US Pub. No. 20180260957) hereinafter Yang, “The above-described methods for automated liver segmentation in 3D medical images may be implemented on a computer using well-known computer processors, memory units, storage devices, computer software, and other components.” (Par. 43) and Itu (US Pub. No. 20180315505) hereinafter Itu “Systems, apparatuses, and methods described herein may be implemented using digital circuitry, or using one or more computers using well-known computer processors, memory units, storage devices, computer software, and other components.” (Par. 85)
are all well-understood, routine, and conventional.
Claims 3, 5-8, and 10-12 do not include additional elements, alone or in combination that are sufficient to amount to significantly more than the judicial exception (i.e., an inventive concept) as all of the elements are directed to the further describing of the abstract idea, pre-solution activities, and computer implementation.
The dependent claims merely further define the abstract idea and are, therefore, directed to an abstract idea for similar reasons: they merely further describe the abstract idea:
the dimensional parameters of the prior clinically examined blood vessel and/or of the currently examined blood vessel include at least one of: a length of the stenosis, a thickness of the stenosis, a shape index of the stenosis, a symmetry index of the stenosis, a cross-section area of a lesion coronary, an area severity of the stenosis, a stenosed vessel volume, a reconstructed vessel volume lumen, a volume severity of the stenosis, an aggregate volume of the stenosis, an aggregate volume severity of the stenosis, a coronary score lesion grade, a vascular index, an extent score, a calcium score, a density factor, a localization of the stenosis (Claim 3),
the clinical measurement parameters of the prior clinically examined blood vessel include at least one of: a fractional flow reserve (FFR), an instantaneous wave-free ratio (iFR), a resting full-cycle ratio or relative flow reserve (RFR) (Claim 5),
process input CT imaging data and to output a 3D segmented model containing description of blood vessels arrangement within the imaged volume, including at least the location and dimensions of the vessels (Claim 7)(Examiners note: a person of ordinary skill in the art could reasonably output a segmented model based on receiving CT imaging data using a generic computer),
prediction of output binary mask based on the input CT imaging data (Claim 7) (Examiner's Note: A person of ordinary skill in the art could reasonably make a prediction based on receiving CT imaging data using a generic computer),
computation of the difference between the ground truth mask and the predicted mask (Claim 7) (Examiner's Note: A person of ordinary skill in the art could calculate a difference between a ground truth mask and predicted mask based on having each data value using a generic computer),
update of weights according to the gradient backpropagation method (Claim 7) (Examiner's Note: A person of ordinary skill in the art could reasonably updated weights using the gradient backpropagation method using a generic computer),
process input image data and to output a 3D segmented model containing description of blood vessels arrangement within the imaged volume, including at least the location and dimensions of the vessels by use of at least one of the following half-automated or fully-automated methods: - region growing from seed,- active shapes and active contours, - segmentation based on graph cuts,- adaptive thresholding,- segmentation based on rough sets,- watershed segmentation,- vesselness filters, and- connectedness methods (Claim 8) (Examiners note: a person of ordinary skill in the art could reasonably process data and output a segmented model based on receiving image data using a generic computer),
generating a borderline classification for the stenosis significance parameter (Claim 10) (Examiners note: a person of ordinary skill in the art could reasonably generate a borderline classification with a generic computer based on having a piece of paper with blood vessel data),
outputting a reliability parameter for the stenosis significance parameter (Claim 11),
wherein the dimensional parameters of the currently examined blood vessel containing the stenosis include a shape index and a symmetry index, the shape index defining a ratio of stenosis length to stenosis thickness, and the symmetry index defining a ratio of stenosis perimeter lying on a reconstructed wall to a total circumference of the vessel (Claim 12).
Further describe the pre-solution activity (or structure used for such activity):
A computer (Claims 7, 8, 10, and 11).
Per the Berkheimer requirement, the additional elements are well-understood, routine, and conventional. For example,
A computer as disclosed by Yang and Itu above
are all well-understood, routine, and conventional.
Taken alone or in combination, the additional elements do not integrate the judicial exception into a practical application at least because the abstract idea is not applied, relied on, or used in a meaningful way. The additional elements do not add anything significantly more than the abstract idea. The collective functions of the additional elements merely provide computer/electronic implementation and processing, data gathering, and no additional elements beyond those of the abstract idea. There is no indication that the combination of elements improves the functioning of a mobile device, output device, improves technology other than the technical field of the claimed invention, etc. Therefore, the claims are rejected as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 102 - Withdrawn
The applicant’s amendments, filed 10/27/2024, have been fully considered and the previous 102 rejection withdrawn.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The claims are generally directed towards the determination of stenosis in a blood vessel. This is done through training a convolutional neural network with known stenosis cases, and then inputting unknown data into the trained neural network which then outputs the stenosis significance for that unknown data.
Claim(s) 1, 3, 5, and 9-10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Isgum (US Pub. No. 20190318476) hereinafter Isgum, and further in view of Yagi (US Pub. No. 20140316758) hereinafter Yagi and Koo (US Pat. No. 10692608) hereinafter Koo.
Regarding claim 1, Isgum discloses A method for determining a significance of a stenosis in a currently examined blood vessel (Abstract (assessing vessel obstruction)), the method comprising:
providing a pre-trained convolutional neural network reasoning module that has been trained (Par. 15, “The machine learning-based VOA model may be based on a recurrent convolutional neural network (RCNN)”) (Par. 60, “The operations of FIG. 2 (as well as the operations of any other methods, algorithms and processes described herein) are implemented by one or more processors, while executing program instructions.”) (Par. 77, “Within step 204 of FIG. 2, the coronary parameters are extracted by utilizing a machine learning based Vessel Obstruction Assessment (VOA) model.” (model of step 204)) to output a value of a stenosis significance parameter (Par. 79, Fig. 2, step 206)) by means of a training data set comprising a plurality of records of prior clinically examined stenosis cases (Fig. 2, step 205, Par. 77), each training record comprising:
data representing dimensional parameters (Par. 77, 82 (anatomical stenosis severity)),
data representing blood flow parameters (Par. 77, “index of microcirculatory resistance and pressure drop along a coronary artery”), including at least one of: relative fractional flow reserve (FFR_VCAST), energy flow reference index (EFR_VCAST), vascular resistance (R) (Par. 77, “index of microcirculatory resistance and pressure drop along a coronary artery”), turbulent kinetic energy, pressure drop (ΔP), wall shear stress, oscillatory shear index, and relative residence time, and
data representing clinical measurement parameters (Par. 77, (fractional flow reserve)) of the prior clinically examined blood vessel containing the stenosis (Par. 77, “The reference standard is a database which contains data of multiple patients…” “… index of microcirculatory resistance and pressure drop along a coronary artery.”),
inputting (Fig. 2, Step 201), to the pre-trained convolutional neural network reasoning module (Par. 15, “The machine learning-based VOA model may be based on a recurrent convolutional neural network (RCNN)”) (Par. 60, “The operations of FIG. 2 (as well as the operations of any other methods, algorithms and processes described herein) are implemented by one or more processors, while executing program instructions.”) (Par. 77, “Within step 204 of FIG. 2, the coronary parameters are extracted by utilizing a machine learning based Vessel Obstruction Assessment (VOA) model.” (model of step 204)), an examination record (Par. 78 (unseen data)) comprising:
data representing dimensional parameters of the currently examined blood vessel containing the stenosis (Par. 78, “After training the machine learning model, step 204 of FIG. 2 is configured to predict the coronary plaque type, and/or anatomical stenosis severity and/or the functional significance of the coronary of interest based on analysis of the MPR image as a result of step 204. Within the prediction phase, unseen image data is used (201) and step 205 of FIG. 2 is detached”) and
instructing (Par. 60, “The operations of FIG. 2 (as well as the operations of any other methods, algorithms and processes described herein) are implemented by one or more processors, while executing program instructions.”) the pre-trained convolutional neural network reasoning module (Par. 15, “The machine learning-based VOA model may be based on a recurrent convolutional neural network (RCNN)”) (Par. 60, “The operations of FIG. 2 (as well as the operations of any other methods, algorithms and processes described herein) are implemented by one or more processors, while executing program instructions.”) to output the value of the stenosis significance parameter based on the examination record (Par. 78 (unseen image data used for the model)) (Par. 79, “The output (step 206 of FIG. 2) is a prediction of the coronary plaque type, and/or anatomical stenosis severity and/or the functional significance of lesion(s) within the coronary of interest.”).
Isgum fails to explicitly disclose data representing blood flow parameters calculated using computational fluid dynamics (CFD) methods, wherein the blood flow parameters are determined through numerical simulation comparing a personalized model and a reference model of the blood vessel, the numerical simulation comprising determining conditions of blood flow at an inlet to the blood vessels model and calculating blood flow energy for the inlet and all outlets of the blood vessels model, and comparing the blood flow energy measured for the personalized model and for the reference model to determine blood flow energy change indexes.
However, Isgum does disclose wherein the blood flow parameters are determined through numerical simulation comparing a personalized model and a reference model of the blood vessel (Par. 77, “The reference standard is a database which contains data of multiple patients. Each set within the database contains for each patient a) contrast enhanced CT image datasets (201 represents reference image sets during the training phase) and corresponding b) CAD related reference values…”)(Par. 80, “the processor may obtain a training database that includes volumetric imaging datasets for multiple patients and corresponding coronary artery disease (CAD) related reference values. The volumetric image data sets may be for a target organ that includes a vessel of interest…”).
Yagi teaches data representing blood flow parameters calculated using computational fluid dynamics (CFD) methods (Par. 200)(Par. 202, “The energy loss calculation unit computes the energy of the blood flow at the inlet and the outlet of the model under investigation and the energy loss by using the state quantities that the fluid dynamics analysis unit calculated. The energy loss is then converted to the anastomotic stenosis rate (or the degree of stenosis) by normalizing it for the cross-section and the length of the blood vessel.”), wherein the blood flow parameters are determined through numerical simulation comparing a personalized model and a reference model of the blood vessel (Par. 200, “the blood flow analysis for a vascular anastomosis model is carried out but at the same time, it is preferable for a user itself to edit the morphology of the anastomotic part in order to conduct a simulation to investigate the procedure of vascular anastomosis or the loss of energy…”) (Par. 202), the numerical simulation comprising determining conditions of blood flow at an inlet to the blood vessels model and calculating blood flow energy for the inlet and all outlets of the blood vessels model (Par. 202, “The energy loss calculation unit computes the energy of the blood flow at the inlet and the outlet of the model under investigation and the energy loss by using the state quantities that the fluid dynamics analysis unit calculated. The energy loss is then converted to the anastomotic stenosis rate (or the degree of stenosis) by normalizing it for the cross-section and the length of the blood vessel.”), and comparing the blood flow energy measured for the personalized model and for the reference model to determine blood flow energy change indexes (Par. 202, “The energy loss calculation unit computes the energy of the blood flow at the inlet and the outlet of the model under investigation and the energy loss by using the state quantities that the fluid dynamics analysis unit calculated. The energy loss is then converted to the anastomotic stenosis rate (or the degree of stenosis) by normalizing it for the cross-section and the length of the blood vessel…”).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Isgum with that of Yagi to include data representing blood flow parameters calculated using computational fluid dynamics (CFD) methods, wherein the blood flow parameters are determined through numerical simulation comparing a personalized model and a reference model of the blood vessel, the numerical simulation comprising determining conditions of blood flow at an inlet to the blood vessels model and calculating blood flow energy for the inlet and all outlets of the blood vessels model, and comparing the blood flow energy measured for the personalized model and for the reference model to determine blood flow energy change indexes through the substitution of the blood flow parameters of Isgum for that of Yagi as it would have yielded the predictable result of improving stenosis treatment (Yagi (Par. 203,204)).
Modified Isgum fails to explicitly disclose an examination record comprising data representing blood flow parameters calculated using CFD methods, including at least one of: relative fractional flow reserve (FFR_VCAST), energy flow reference index (EFR_VCAST), vascular resistance (R), turbulent kinetic energy, pressure drop (ΔP), wall shear stress, oscillatory shear index, and relative residence time, wherein the examination record contains less input data than the training records, and does not contain clinical measurement parameters.
However, Koo teaches an examination record comprising data representing blood flow parameters calculated using CFD methods (Col. 16, lines 40-64), including at least one of: relative fractional flow reserve (FFR_VCAST), energy flow reference index (EFR_VCAST), vascular resistance (R), turbulent kinetic energy, pressure drop (ΔP), wall shear stress (Col. 16, lines 40 – 64 (wall shear stress)), oscillatory shear index, and relative residence time,
wherein the examination record contains less input data than the training records (Col. 16, lines 9-14, “FIG. 8 depicts an exemplary method 800 of applying a trained machine learning algorithm to predict hemodynamic characteristics using a non-invasively acquired geometric model of a target patient. The trained machine learning algorithm may be that obtained from method 700 of FIG. 7.”)(Fig. 7, Fig. 8, Col. 15, lines 46-59 (the training record of Fig. 7 further involves additional data that is used to generate the machine learning model)) (Col. 14, lines 56-65, “FIG. 7 depicts an exemplary method 700 for training a machine learning algorithm for estimating hemodynamic forces, using non-invasive imaging and computational fluid dynamics. In another embodiment, the patient-specific geometric model may be acquired invasively (e.g., through IVUS, OCT, pull-back, pressure wire, etc.), for the purposes of training a machine learning algorithm. In yet another embodiment, step 702 may include receiving a database of geometric models from a plurality of patients for the purpose of training a machine learning algorithm.”), and does not contain clinical measurement parameters (Col. 16, lines 40-64 (non-invasive)).
Isgum, Yagi, and Koo are considered to be analogous art to the claimed invention as they are involved with blood vessel measurements.
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Isgum and Yagi with that of Koo to include an examination record of Isgum comprising data representing blood flow parameters calculated using CFD methods, including at least one of: relative fractional flow reserve (FFR_VCAST), energy flow reference index (EFR_VCAST), vascular resistance (R), turbulent kinetic energy, pressure drop (ΔP), wall shear stress, oscillatory shear index, and relative residence time, wherein the examination record contains less input data than the training records, and does not contain clinical measurement parameters through the combination of references as non-invasive and invasive measurements are known in the art (Koo (Col. 14, lines 39-61)) and it would have yielded the predictable result of assessing patient hemodynamic characteristics non-invasively (Koo (Col. 16, lines 40-64)) and improve patient treatment strategies (Koo (Col. 17, lines 21-31)).
Modified Isgum fails to explicitly disclose wherein the value of the stenosis significance parameter is selected from the group consisting of Significant (S), Non-Significant (NS), and Borderline (B).
However, Isgum does teach in an alternate embodiment wherein the value of the stenosis significance parameter is selected from the group consisting of Significant (S), Non-Significant (NS), and Borderline (B) (Par. 131-134, “Hence, the FFR classifier (1810, FIG. 18) can be trained to recognize multiple classes, for example “no functionally significant stenosis present”, “mild functionally significant stenosis present” or “severe functionally significant stenosis present”, or any categories chosen based on the reference value (step 1802 of FIG. 18). When the reference value (FIG. 18, 1802) is an invasive FFR measurement, above classification can be achieved using for instance the following invasive FFR threshold values: [0132] i) Invasive FFR>0.9—“no functionally significant stenosis present” [0133] ii) Invasive FFR between 0.7 and 0.8—“mild functionally significant stenosis present” [0134] iii) Invasive FFR<0.7—“severe functionally significant stenosis present”).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the method of Isgum, Yagi, and Koo with an alternate embodiment of Isgum to include wherein the value of the stenosis significance parameter is selected from the group consisting of Significant (S), Non-Significant (NS), and Borderline (B) through the combination of references as differing classification types are known in the art (Isgum (Par. 131-134)) and it would have yielded the predictable result of providing additional output data to the user regarding the functional significance of the stenosis (Isgum (Par. 131-134)).
Regarding claim 3, modified Isgum further discloses wherein the dimensional parameters of the prior clinically examined blood vessel and/or of the currently examined blood vessel include at least one of: a length of the stenosis, a thickness of the stenosis, a shape index of the stenosis (Par. 77, 82 (anatomical stenosis severity)), a symmetry index of the stenosis, a cross-section area of a lesion coronary, an area severity of the stenosis, a stenosed vessel volume, a reconstructed vessel volume lumen, a volume severity of the stenosis, an aggregate volume of the stenosis, an aggregate volume severity of the stenosis, a coronary score lesion grade, a vascular index, an extent score, a calcium score, a density factor, a localization of the stenosis.
Regarding claim 5, modified Isgum further discloses wherein the clinical measurement parameters of the prior clinically examined blood vessel include at least one of: a fractional flow reserve (FFR) (Par. 77, (fractional flow reserve)), an instantaneous wave-free ratio (iFR), a resting full-cycle ratio or relative flow reserve (RFR).
Regarding claim 9, Isgum discloses a computer-operated system (Par. 60, “The operations of FIG. 2 (as well as the operations of any other methods, algorithms and processes described herein) are implemented by one or more processors, while executing program instructions.”) configured for determining a significance of a stenosis in a currently examined blood vessel (Abstract (assessing vessel obstruction)) , the system comprising:
a pre-trained convolutional neural network reasoning module that is stored in a non-transitory, computer-readable memory and executed by at least one processor (Par. 69, 246 (implementation)), that has been trained (Par. 15, “The machine learning-based VOA model may be based on a recurrent convolutional neural network (RCNN)”) (Par. 60, “The operations of FIG. 2 (as well as the operations of any other methods, algorithms and processes described herein) are implemented by one or more processors, while executing program instructions.”) (Par. 77, “Within step 204 of FIG. 2, the coronary parameters are extracted by utilizing a machine learning based Vessel Obstruction Assessment (VOA) model.” (model of step 204)) to output a value of a stenosis significance parameter (Par. 79, Fig. 2, step 206)) by means of a training data set comprising a plurality of records of prior clinically examined stenosis cases (Fig. 2, step 205, Par. 77), each training record comprising:
data representing dimensional parameters (Par. 77, 82 (anatomical stenosis severity)),
data representing blood flow parameters (Par. 77, “index of microcirculatory resistance and pressure drop along a coronary artery”) blood flow parameters (Par. 77, “index of microcirculatory resistance and pressure drop along a coronary artery”), including at least one of: relative fractional flow reserve (FFR_VCAST), energy flow reference index (EFR_VCAST), vascular resistance (R) (Par. 77, “index of microcirculatory resistance and pressure drop along a coronary artery”), turbulent kinetic energy, pressure drop (ΔP), wall shear stress, oscillatory shear index, and relative residence time, and
data representing clinical measurement parameters (Par. 77, (fractional flow reserve)) of the prior clinically examined blood vessel containing the stenosis (Par. 77, “The reference standard is a database which contains data of multiple patients…” “… index of microcirculatory resistance and pressure drop along a coronary artery.”);
wherein the pre-trained convolutional neural network reasoning module (Par. 15, “The machine learning-based VOA model may be based on a recurrent convolutional neural network (RCNN)”) (Par. 60, “The operations of FIG. 2 (as well as the operations of any other methods, algorithms and processes described herein) are implemented by one or more processors, while executing program instructions.”) (Par. 77, “Within step 204 of FIG. 2, the coronary parameters are extracted by utilizing a machine learning based Vessel Obstruction Assessment (VOA) model.” (model of step 204)) has:
an input (Fig. 2, Step 201) configured to receive an examination record comprising:
data representing (Par. 78 (unseen data)) the dimensional parameters of the currently examined blood vessel containing the stenosis (Par. 78, “After training the machine learning model, step 204 of FIG. 2 is configured to predict the coronary plaque type, and/or anatomical stenosis severity and/or the functional significance of the coronary of interest based on analysis of the MPR image as a result of step 204. Within the prediction phase, unseen image data is used (201) and step 205 of FIG. 2 is detached”), and
an output configured (Par. 60, “The operations of FIG. 2 (as well as the operations of any other methods, algorithms and processes described herein) are implemented by one or more processors, while executing program instructions.”) to provide the value of the stenosis significance parameter based on the examination record (Par. 78 (unseen image data)) (Par. 79, “The output (step 206 of FIG. 2) is a prediction of the coronary plaque type, and/or anatomical stenosis severity and/or the functional significance of lesion(s) within the coronary of interest.”).
Isgum fails to explicitly disclose data representing blood flow parameters calculated using computational fluid dynamics (CFD) methods, wherein the blood flow parameters are determined through numerical simulation comparing a personalized model and a reference model of the blood vessel, the numerical simulation comprising determining conditions of blood flow at an inlet to the blood vessels model and calculating blood flow energy for the inlet and all outlets of the blood vessels model, and comparing the blood flow energy measured for the personalized model and for the reference model to determine blood flow energy change indexes.
However, Isgum does disclose wherein the blood flow parameters are determined through numerical simulation comparing a personalized model and a reference model of the blood vessel (Par. 77, “The reference standard is a database which contains data of multiple patients. Each set within the database contains for each patient a) contrast enhanced CT image datasets (201 represents reference image sets during the training phase) and corresponding b) CAD related reference values…”)(Par. 80, “the processor may obtain a training database that includes volumetric imaging datasets for multiple patients and corresponding coronary artery disease (CAD) related reference values. The volumetric image data sets may be for a target organ that includes a vessel of interest…”).
Yagi teaches data representing blood flow parameters calculated using computational fluid dynamics (CFD) methods (Par. 200)(Par. 202, “The energy loss calculation unit computes the energy of the blood flow at the inlet and the outlet of the model under investigation and the energy loss by using the state quantities that the fluid dynamics analysis unit calculated. The energy loss is then converted to the anastomotic stenosis rate (or the degree of stenosis) by normalizing it for the cross-section and the length of the blood vessel.”), wherein the blood flow parameters are determined through numerical simulation comparing a personalized model and a reference model of the blood vessel (Par. 200, “the blood flow analysis for a vascular anastomosis model is carried out but at the same time, it is preferable for a user itself to edit the morphology of the anastomotic part in order to conduct a simulation to investigate the procedure of vascular anastomosis or the loss of energy…”) (Par. 202), the numerical simulation comprising determining conditions of blood flow at an inlet to the blood vessels model and calculating blood flow energy for the inlet and all outlets of the blood vessels model (Par. 202, “The energy loss calculation unit computes the energy of the blood flow at the inlet and the outlet of the model under investigation and the energy loss by using the state quantities that the fluid dynamics analysis unit calculated. The energy loss is then converted to the anastomotic stenosis rate (or the degree of stenosis) by normalizing it for the cross-section and the length of the blood vessel.”), and comparing the blood flow energy measured for the personalized model and for the reference model to determine blood flow energy change indexes (Par. 202, “The energy loss calculation unit computes the energy of the blood flow at the inlet and the outlet of the model under investigation and the energy loss by using the state quantities that the fluid dynamics analysis unit calculated. The energy loss is then converted to the anastomotic stenosis rate (or the degree of stenosis) by normalizing it for the cross-section and the length of the blood vessel…”).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the system of Isgum with that of Yagi to include data representing blood flow parameters calculated using computational fluid dynamics (CFD) methods, wherein the blood flow parameters are determined through numerical simulation comparing a personalized model and a reference model of the blood vessel, the numerical simulation comprising determining conditions of blood flow at an inlet to the blood vessels model and calculating blood flow energy for the inlet and all outlets of the blood vessels model, and comparing the blood flow energy measured for the personalized model and for the reference model to determine blood flow energy change indexes through the substitution of the blood flow parameters of Isgum for that of Yagi as it would have yielded the predictable result of improving stenosis treatment (Yagi (Par. 203,204)).
Modified Isgum fails to explicitly disclose an examination record comprising data representing blood flow parameters calculated using CFD methods, including at least one of: relative fractional flow reserve (FFR_VCAST), energy flow reference index (EFR_VCAST), vascular resistance (R), turbulent kinetic energy, pressure drop (ΔP), wall shear stress, oscillatory shear index, and relative residence time, wherein the examination record contains less input data than the training records, and does not contain clinical measurement parameters.
However, Koo teaches an examination record comprising data representing blood flow parameters calculated using CFD methods (Col. 16, lines 40-64), including at least one of: relative fractional flow reserve (FFR_VCAST), energy flow reference index (EFR_VCAST), vascular resistance (R), turbulent kinetic energy, pressure drop (ΔP), wall shear stress (Col. 16, lines 40 – 64 (wall shear stress)), oscillatory shear index, and relative residence time,
wherein the examination record contains less input data than the training records (Col. 16, lines 9-14, “FIG. 8 depicts an exemplary method 800 of applying a trained machine learning algorithm to predict hemodynamic characteristics using a non-invasively acquired geometric model of a target patient. The trained machine learning algorithm may be that obtained from method 700 of FIG. 7.”)(Fig. 7, Fig. 8, Col. 15, lines 46-59 (the training record of Fig. 7 further involves additional data that is used to generate the machine learning model)) (Col. 14, lines 56-65, “FIG. 7 depicts an exemplary method 700 for training a machine learning algorithm for estimating hemodynamic forces, using non-invasive imaging and computational fluid dynamics. In another embodiment, the patient-specific geometric model may be acquired invasively (e.g., through IVUS, OCT, pull-back, pressure wire, etc.), for the purposes of training a machine learning algorithm. In yet another embodiment, step 702 may include receiving a database of geometric models from a plurality of patients for the purpose of training a machine learning algorithm.”), and does not contain clinical measurement parameters (Col. 16, lines 40-64 (non-invasive)).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the system of Isgum and Yagi with that of Koo to include an examination record of Isgum comprising data representing blood flow parameters calculated using CFD methods, including at least one of: relative fractional flow reserve (FFR_VCAST), energy flow reference index (EFR_VCAST), vascular resistance (R), turbulent kinetic energy, pressure drop (ΔP), wall shear stress, oscillatory shear index, and relative residence time, wherein the examination record contains less input data than the training records, and does not contain clinical measurement parameters through the combination of references as non-invasive and invasive measurements are known in the art (Koo (Col. 14, lines 39-61)) and it would have yielded the predictable result of assessing patient hemodynamic characteristics non-invasively (Koo (Col. 16, lines 40-64)) and improve patient treatment strategies (Koo (Col. 17, lines 21-31)).
Modified Isgum fails to explicitly disclose wherein the value of the stenosis significance parameter is selected from the group consisting of Significant (S), Non-Significant (NS), and Borderline (B).
However, Isgum does teach in an alternate embodiment wherein the value of the stenosis significance parameter is selected from the group consisting of Significant (S), Non-Significant (NS), and Borderline (B) (Par. 131-134, “Hence, the FFR classifier (1810, FIG. 18) can be trained to recognize multiple classes, for example “no functionally significant stenosis present”, “mild functionally significant stenosis present” or “severe functionally significant stenosis present”, or any categories chosen based on the reference value (step 1802 of FIG. 18). When the reference value (FIG. 18, 1802) is an invasive FFR measurement, above classification can be achieved using for instance the following invasive FFR threshold values: [0132] i) Invasive FFR>0.9—“no functionally significant stenosis present” [0133] ii) Invasive FFR between 0.7 and 0.8—“mild functionally significant stenosis present” [0134] iii) Invasive FFR<0.7—“severe functionally significant stenosis present”).
Therefore, it would have been obvious to a person of ordinary skill in the art to modify the system of Isgum, Yagi, and Koo with an alternate embodiment of Isgum to include wherein the value of the stenosis significance parameter is selected from the group consisting of Significant (S), Non-Significant (NS), and Borderline (B) through the combination of references as differing classification types are known in the art (Isgum (Par. 131-134)) and it would have yielded the predictable result of providing additional output data to the user regarding the functional significance of the stenosis (Isgum (Par. 131-134)).
Regarding claim 10, modified Isgum further discloses further comprising generating a borderline classification for the stenosis significance parameter (Par. 79, “The output (step 206 of FIG. 2) is a prediction of the coronary plaque type, and/or anatomical stenosis severity and/or the functional significance of lesion(s) within the coronary of interest”), wherein the borderline classification indicates that the