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 .
Claim Objections
Claims 1 and 11 are objected to because of the following informalities:
In claim 1, line 4; “of CT imaging system” should be changed to “of the CT imaging system” for grammar.
In claim 11, line 4; the extra period should be deleted after the word range.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Regarding claims 1, 15, and 19, the claims set forth that values "predicting an upper threshold value and a lower threshold value of a heart rate (HR) of a patient" are extracted based on an desired confidence level. This is understood to be a computer-implemented functional limitation which requires disclosure of the underlying algorithm(s) for obtaining the result in order to comply with the written description requirement. See MPEP § 2161.01(1). While the specification provides literal support for extracting values " predicting an upper threshold value and a lower threshold value of a heart rate (HR) of a patient" as in [0004], [0048], [0049], [0053-0093] (paragraphs as numbered in applicant's pre-grant publication, US20250166793A1), there is no description as to how the HR data is converted to an upper threshold value and a lower threshold value based on a desired confidence other than generic high level steps describing that machine learning is used and what the inputs and outputs are. Therefore, the specification is tantamount to a black box, rather than showing possession of a particular implementation. For this reason, applicant has failed to comply with the written description requirement for this computer-implemented function.
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 5-9 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 applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claim 5, claim 5 recites “a patient”. This limitation has unclear antecedent basis. It is unclear how this patient relates to the patient previously set forth.
Regarding claim 7, claim 7 requires “wherein the classification is based on the classification model detecting an abnormal heart rhythm in the stored HR time series data” however, the claim does not actually require “a classification of a sample performed by a classification model of the CT imaging system” since the claim only requires “wherein the one or more statistical features […] includes at least one of” emphasis added”. Therefore, it is unclear what claim 7 is requiring in situations where one of the other statistical features is extracted.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception of an abstract idea in the form of a mental process without significantly more.
Claim 1 is directed to a method for a CT imaging system, claim 15 is directed to a CT imaging system, and claim 19 is directed to a method comprising steps that are substantially similar to the processing steps of claim 15.
Regarding claim 1, claim 1 is considered to be directed towards an abstract idea because it recites a mental process of calculating predicting an upper threshold value and a lower threshold value of a heart rate (HR) of a patient of the CT imaging system, based on HR time series data collected from the patient over a duration and estimating an appropriate time to perform a cardiac scan during a cardiac phase range, based on the upper threshold value and the lower threshold value. Specifically, the limitation of predicting an upper threshold value and a lower threshold value of a heart rate (HR) of a patient of the CT imaging system, based on HR time series data and determining an appropriate time to perform a cardiac scan during a cardiac phase range, based on the upper threshold value and the lower threshold value is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. That is, nothing in the claim element precludes the step from practically being performed in the mind. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind, then it falls within the “mental processes” grouping of abstract ideas. Examples of this type of concept include diagnosing an abnormal condition by performing clinical tests and analyzing the results, In re Grams, 888 F.2d 835, 840, 12 USPQ2d 1824, 1828 (Fed. Cir. 1989); see CyberSource, 654 F.3d at 1372 n.2, 99 USPQ2d at 1695 n.2 (describing the abstract idea in Grams), and collecting information, analyzing it, and displaying certain results of the collection and analysis, Electric Power Group, LLC v. Alstom, S.A., 830 F.3d 1350, 1351, 119 USPQ2d 1739, 1739 (Fed. Cir. 2016). See MPEP § 2106.04(a)(2).III. A-B.
The judicial exceptions enumerated above (i.e., mathematical formula, mental process, and law of nature) are not integrated into a practical application. Specifically, the additional limitations of claim 1 directed towards acquiring, reconstructing, and displaying the image are merely extra-solution activity that would be required in any form of data gathering and analysis to implement the judicial exceptions. Consequently, these additional elements do not integrate the judicial exceptions into a practical application because they do not impose any meaningful limits on practicing the judicial exceptions.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. For example, as explained above, the additional limitations of claim 1 directed towards acquiring, reconstructing, and displaying the image are merely extra-solution activity. Mere extra-solution activity does not add significantly more to the judicial exceptions.
The limitations do not improve a computer or another technology or technical field. The limitations do not apply or use the judicial exceptions to effect a particular treatment or prophylaxis for a disease or medical condition. The limitations do not apply or use the judicial exceptions with, or by use of, a particular machine. The limitations do not effect a transformation or reduction of a particular article to a different state or thing. In addition, the claims do not include other meaningful limitations beyond generally linking the use of the judicial exception to a particular technological environment.
Therefore, when considered separately and in combination, the additional limitations of claim 1 do not add significantly more (also known as an “inventive concept”) to the judicial exceptions.
Turning to the dependent claims:
Claims 2-11, and 13 recite additional elements directed towards further details of the abstract idea, specifying particular calculations, inputs, outputs, variables, or details about the machine learning algorithm to be used to implement the abstract idea of calculating the recommended position. These elements do not integrate the judicial exceptions into a practical application and are insufficient to amount to “significantly more” than the abstract idea because they too are directed towards the abstract idea.
Claims 12 and 14 recite additional elements directed towards further details of the extra-solution activity, specifying particular details about acquiring cardiac scan data which are merely extra-solution activity that would be required in any form of data gathering and analysis to implement the judicial exceptions. These elements do not integrate the judicial exceptions into a practical application and are insufficient to amount to “significantly more” than the abstract idea because they amount to no more than mere extra-solution activity.
The limitations of the dependent claims do not improve a computer or another technology or technical field. The limitations do not apply or use the judicial exceptions to effect a particular treatment or prophylaxis for a disease or medical condition. The limitations do not apply or use the judicial exceptions with, or by use of, a particular machine. The limitations do not effect a transformation or reduction of a particular article to a different state or thing. In addition, the claims do not include other meaningful limitations beyond generally linking the use of the judicial exception to a particular technological environment. Therefore, when considered separately and in combination, the additional limitations of the dependent claims do not add significantly more (also known as an “inventive concept”) to the judicial exceptions.
Regarding claims 15 and 19, claims 15 and 19 are considered to be directed towards an abstract idea because they recites a mental process of calculating predicting an upper threshold value and a lower threshold value of a heart rate (HR) of a patient of the CT imaging system, based on HR time series data collected from the patient over a duration and estimating an appropriate time to perform a cardiac scan during a cardiac phase range, based on the upper threshold value and the lower threshold value. Specifically, the limitation of predicting an upper threshold value and a lower threshold value of a heart rate (HR) of a patient of the CT imaging system, based on HR time series data and determining an appropriate time to perform a cardiac scan during a cardiac phase range, based on the upper threshold value and the lower threshold value is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. That is, nothing in the claim element precludes the step from practically being performed in the mind. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind, then it falls within the “mental processes” grouping of abstract ideas. Examples of this type of concept include diagnosing an abnormal condition by performing clinical tests and analyzing the results, In re Grams, 888 F.2d 835, 840, 12 USPQ2d 1824, 1828 (Fed. Cir. 1989); see CyberSource, 654 F.3d at 1372 n.2, 99 USPQ2d at 1695 n.2 (describing the abstract idea in Grams), and collecting information, analyzing it, and displaying certain results of the collection and analysis, Electric Power Group, LLC v. Alstom, S.A., 830 F.3d 1350, 1351, 119 USPQ2d 1739, 1739 (Fed. Cir. 2016). See MPEP § 2106.04(a)(2).III. A-B.
The judicial exceptions enumerated above (i.e., mathematical formula, mental process, and law of nature) are not integrated into a practical application. Specifically, the additional limitations of claims 15 and 19 directed towards collecting HR data and extracting one or more statistical features and acquiring, reconstructing, and displaying the image are merely extra-solution activity that would be required in any form of data gathering and analysis to implement the judicial exceptions. Consequently, these additional elements do not integrate the judicial exceptions into a practical application because they do not impose any meaningful limits on practicing the judicial exceptions.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. For example, as explained above, the additional limitations of claims 15 and 19 directed towards collecting HR data and extracting one or more statistical features and acquiring, reconstructing, and displaying the image are merely extra-solution activity. Mere extra-solution activity does not add significantly more to the judicial exceptions.
The limitations do not improve a computer or another technology or technical field. The limitations do not apply or use the judicial exceptions to effect a particular treatment or prophylaxis for a disease or medical condition. The limitations do not apply or use the judicial exceptions with, or by use of, a particular machine. The limitations do not effect a transformation or reduction of a particular article to a different state or thing. In addition, the claims do not include other meaningful limitations beyond generally linking the use of the judicial exception to a particular technological environment.
Therefore, when considered separately and in combination, the additional limitations of claim 1 do not add significantly more (also known as an “inventive concept”) to the judicial exceptions.
Turning to the dependent claims:
Claims 16-18 recite additional elements directed towards further details of the abstract idea, specifying particular calculations, inputs, outputs, variables, or details about the machine learning algorithm to be used to implement the abstract idea of calculating the recommended position. These elements do not integrate the judicial exceptions into a practical application and are insufficient to amount to “significantly more” than the abstract idea because they too are directed towards the abstract idea.
Claim 20 recites additional elements directed towards further details of the extra-solution activity, specifying particular details about acquiring cardiac scan data which are merely extra-solution activity that would be required in any form of data gathering and analysis to implement the judicial exceptions. These elements do not integrate the judicial exceptions into a practical application and are insufficient to amount to “significantly more” than the abstract idea because they amount to no more than mere extra-solution activity.
The limitations of the dependent claims do not improve a computer or another technology or technical field. The limitations do not apply or use the judicial exceptions to effect a particular treatment or prophylaxis for a disease or medical condition. The limitations do not apply or use the judicial exceptions with, or by use of, a particular machine. The limitations do not effect a transformation or reduction of a particular article to a different state or thing. In addition, the claims do not include other meaningful limitations beyond generally linking the use of the judicial exception to a particular technological environment. Therefore, when considered separately and in combination, the additional limitations of the dependent claims do not add significantly more (also known as an “inventive concept”) to the judicial exceptions.
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.
Claims 1 and 10-14 are rejected under 35 U.S.C. 103 as being unpatentable over Jackson et al. (US20210093277, hereafter Jackson) and Bhatia et al. (US20220277176, hereafter Bhatia).
Regarding claim 1, Jackson discloses a method for a computed tomography (CT) imaging system, the method comprising:
predicting an upper threshold value and a lower threshold value of a heart rate (HR) of a patient of the CT imaging system, based on HR time series data collected from the patient over a duration (Jackson, Para 48; "By basing scan timing/data acquisition on a patient's heart rate, the radiation dose may be reduced by acquiring CT imaging information only over a duration wherein a predetermined or pre-selected phase or range of phases having minimal motion is guaranteed to be imaged. For example, scanning so that the end of systole or mid-diastole, as determined by a patient's heart rate range, is included within the projection data may ensure that a diagnostic image having little or no motion is generated. Accordingly, scanning may be performed to ensure at least one of a phase of 45% or a phase of 75% is included in the acquired projection data");
configuring the CT imaging system to perform a cardiac scan during a cardiac phase range, based on the upper threshold value and the lower threshold value (Jackson, Para 15; "scanning may be performed to ensure at least the end of systole or middle of diastole is included within the acquired projection data. The timing of end-systole and mid-diastole may be specifically determined based on a patient's heart rate range ") (Jackson, Para 56; "As previously described with respect to FIGS. 3A and 3B, the least amount of cardiac motion happens within ventricular diastole which generally occurs during an R-R interval phase ranging from 45% to 100%. Thus, by acquiring projection data for a sufficient amount of time that either the end of systole or mid-diastole of an R-R interval will fall within the scan range regardless of when in the patient's cardiac cycle scanning commences it may be assumed that the exposure duration may robustly generate a diagnostic image.");
performing the cardiac scan (Jackson, Para 12; "Thus, by targeting x-ray exposure to a particular time window relative to the ECG R-wave, the radiation dose may be reduced by only acquiring data sufficient to ensure, with reasonable confidence, at least one image set with minimal motion.");
reconstructing an image based on data acquired during the cardiac scan; and displaying the image on a display device of the CT imaging system and/or storing the image in a memory of the CT imaging system (Jackson, Para 14; "the CT scan may be performed with an x-ray exposure that is longer than a minimum x-ray exposure duration demanded to reconstruct a single image and less than an x-ray duration demanded to acquire and reconstruct images depicting a full heartbeat. The use of this duration to scan and reconstruct a cardiac image may result in an image with minimal motion, or an amount of motion that does not significantly impede the intended clinical diagnosis, while minimizing radiation exposure to the patient").
Jackson does not clearly and explicitly disclose predicting based on a confidence level specified by an operator of the CT imaging system.
In an analogous machine learning for prediction of events field of endeavor Bhatia discloses predicting based on a confidence level specified by an operator of CT imaging system (Bhatia, Para 56; " A determination is made whether the confidence score of the log source type exceeds a predetermined threshold. This is illustrated at step 240. The predetermined threshold is set by an administrator to allow for the normalization of the log based on the confidence score achieving the predetermined threshold. The predetermined threshold may represent a percentage the confidence score must achieve in order for the log source type prediction to be used for normalization purposes.") (Bhatia, Para 54; "The confidence score can reflect a decimal number between zero and one interpreting a percentage of confidence of the log source type prediction. For example, the confidence score can be produced as a range from 0% to 100%, with 100% being an absolute certainty for a given log source type prediction. While typically shown as a percentage, the confidence score can vary based on the accuracy, recall, precession, and preference requested. In some embodiments, the confidence score can be produced as a set of expressions. For example, the set of expressions be expressions such as “low”, “medium”, and “high”.").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson to include predicting based on a confidence level specified by an operator of the CT imaging system as taught by Bhatia in order to streamline review of by a user and allow customization by a user as needed.
Regarding claim 10, Jackson as modified by Bhatia above discloses all of the limitations of claim 1 as discussed above.
Jackson does not clearly and explicitly disclose wherein the confidence level is specified as a percentage indicating a threshold probabilistic certainty of the predicted the upper and lower threshold values of the HR being sufficiently accurate to configure the cardiac scan to be performed during the cardiac phase range.
Bhatia further discloses wherein the confidence level is specified as a percentage indicating a threshold probabilistic certainty of being sufficiently accurate (Bhatia, Para 54; "The confidence score can reflect a decimal number between zero and one interpreting a percentage of confidence of the log source type prediction. For example, the confidence score can be produced as a range from 0% to 100%, with 100% being an absolute certainty for a given log source type prediction. While typically shown as a percentage, the confidence score can vary based on the accuracy, recall, precession, and preference requested. In some embodiments, the confidence score can be produced as a set of expressions. For example, the set of expressions be expressions such as “low”, “medium”, and “high”.").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson wherein the confidence level is specified as a percentage indicating a threshold probabilistic certainty of the predicted the upper and lower threshold values of the HR being sufficiently accurate to configure the cardiac scan to be performed during the cardiac phase range in order to streamline review of by a user and allow customization by a user as needed.
Regarding claim 11, Jackson as modified by Bhatia above discloses all of the limitations of claim 1 as discussed above.
Jackson does not clearly and explicitly disclose wherein the confidence level is specified by selecting a category of a plurality of categories corresponding to gradations between a lowest threshold probabilistic certainty of the predicted the upper and lower threshold values of the HR being sufficiently accurate to configure the cardiac scan to be performed during the cardiac phase range and a highest threshold probabilistic certainty of the predicted the upper and lower threshold values of the HR being sufficiently accurate to configure the cardiac scan to be performed during the cardiac phase range.
Bhatia further discloses wherein the confidence level is specified by selecting a category of a plurality of categories corresponding to gradations between a lowest threshold probabilistic certainty of the predicted values being sufficiently accurate (Bhatia, Para 54; "The confidence score can reflect a decimal number between zero and one interpreting a percentage of confidence of the log source type prediction. For example, the confidence score can be produced as a range from 0% to 100%, with 100% being an absolute certainty for a given log source type prediction. While typically shown as a percentage, the confidence score can vary based on the accuracy, recall, precession, and preference requested. In some embodiments, the confidence score can be produced as a set of expressions. For example, the set of expressions be expressions such as “low”, “medium”, and “high”.").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson wherein the confidence level is specified by selecting a category of a plurality of categories corresponding to gradations between a lowest threshold probabilistic certainty of the predicted the upper and lower threshold values of the HR being sufficiently accurate to configure the cardiac scan to be performed during the cardiac phase range and a highest threshold probabilistic certainty of the predicted the upper and lower threshold values of the HR being sufficiently accurate to configure the cardiac scan to be performed during the cardiac phase range in order to streamline review of by a user and allow customization by a user as needed.
Regarding claim 12, Jackson as modified by Bhatia above discloses all of the limitations of claim 1 as discussed above.
Jackson further discloses wherein configuring the CT imaging system to perform the cardiac scan based on the upper threshold value and the lower threshold value further comprises scheduling a start of an X-ray exposure based on the upper threshold value, and scheduling an end of the X-ray exposure based on the lower threshold value (Jackson, Para 15; “scanning may be performed to ensure at least the end of systole or middle of diastole is included within the acquired projection data. The timing of end-systole and mid-diastole may be specifically determined based on a patient's heart rate range”) (Jackson, Para 56; "As previously described with respect to FIGS. 3A and 3B, the least amount of cardiac motion happens within ventricular diastole which generally occurs during an R-R interval phase ranging from 45% to 100%. Thus, by acquiring projection data for a sufficient amount of time that either the end of systole or mid-diastole of an R-R interval will fall within the scan range regardless of when in the patient's cardiac cycle scanning commences it may be assumed that the exposure duration may robustly generate a diagnostic image. As previously described with respect to FIG. 3B, for a patient with systole ending at 45% and mid-diastole at 75%, in a worst case scenario, the longest duration between cardiac phases that will generate a diagnostic image is 70% of an R-R interval. Further, as the effect of heart rate on diastolic duration is predictable from kinematic modeling and known cellular physiology, a model of cardiac motion may be used to more precisely determine diastolic/systolic event times, with these precise event times then used for exposure time determinations. For example, based on heart rate range and kinematic modeling, mid-diastole may be found to occur at 85% for a patient rather than a generalized 75%. Thus, the longest duration between cardiac phases that may generate a diagnostic image would be from 85% to 145% rather than 75% to 145% and, as such, the required window of acquisition during scanning may be 60% of an R-R interval (as opposed to 70% when diastolic/systolic event times are not precisely determined)") (Jackson, Para 12; "Thus, by targeting x-ray exposure to a particular time window relative to the ECG R-wave, the radiation dose may be reduced by only acquiring data sufficient to ensure, with reasonable confidence, at least one image set with minimal motion.").
Regarding claim 13, Jackson as modified by Bhatia above discloses all of the limitations of claim 1 as discussed above.
Jackson further discloses wherein the cardiac phase range is prescribed by the operator, and the cardiac phase range is one of a middle of diastole of a cardiac cycle and an end of systole of the cardiac cycle (Jackson, Para 15; “scanning may be performed to ensure at least the end of systole or middle of diastole is included within the acquired projection data. The timing of end-systole and mid-diastole may be specifically determined based on a patient's heart rate range”) (Jackson, Para 35; the computing device 216 controls system operations based on operator input. The computing device 216 receives the operator input, for example, including commands and/or scanning parameters via an operator console 220 operatively coupled to the computing device 216. The operator console 220 may include a keyboard (not shown) or a touchscreen to allow the operator to specify the commands and/or scanning parameters).
Regarding claim 14, Jackson as modified by Bhatia above discloses all of the limitations of claim 1 as discussed above.
Jackson further discloses updating a prediction of the upper threshold value and the lower threshold value of the HR of the patient immediately prior to performing the cardiac scan (Jackson, Para 46; “For ECG gated imaging, the CT scanner monitors the patient's ECG and is set to scan at a particular point in the cardiac cycle which is typically during diastole as the heart is moving the least. The CT scanner may interpret the ECG and determine a delay after a QRS complex to begin scanning. Once that point of delay has occurred, the ECG may trigger the CT scanner to start scanning. For”).
Claims 2, 4-6, 8-9 are rejected under 35 U.S.C. 103 as being unpatentable over Jackson and Bhatia as applied to claim 1 above, and in further view of Man et al. (US20200163639, hereafter Man).
Regarding claim 2, Jackson as modified by Bhatia above discloses all of the limitations of claim 1 as discussed above.
Jackson does not clearly and explicitly disclose predicting the upper threshold value and the lower threshold value of the HR of the patient based on the HR time series data and the confidence level using an HR prediction model, where the HR prediction model comprises a machine learning (ML) model trained on stored HR time series data acquired from a plurality of human subjects.
In an analogous diagnostic imaging classification field of endeavor Man discloses predicting based on HR time series data and confidence level using an HR prediction model (Man, Para 22; "the cardiac motion is monitored by an electrocardiogram (ECG) device to find end-diastole or end-systole stage for each cardiac cycle. Then, the scan (e.g., a cardiac CT scan) is triggered such that the diagnostic scan data is acquired when the heart is in a phase with relatively little motion") (Man, Para 25; "If the answer is no (e.g., since the bolus contrast is not sufficiently high for diagnostic imaging, or the confidence in the current cardiac phase estimate is not very high), in some instances the monitoring scan will continue to acquire and analyze more projection data until such time as a projection data is acquired that meets the criteria to trigger diagnostic acquisition.") (Man, Para 54; “the cardiac phase estimation 200 determines the quiescent phase of the heart cycle”), where the HR prediction model comprises a machine learning (ML) model trained on stored HR time series data acquired from a plurality of human subjects (Man, Para 25; "Thus, as projection data from a monitoring scan is acquired, it may be analyzed, such as using a machine learning model as discussed herein, to evaluate whether or not to trigger a transition to the diagnostic scan (or when to trigger the transition to the diagnostic scan). If the answer is no (e.g., since the bolus contrast is not sufficiently high for diagnostic imaging, or the confidence in the current cardiac phase estimate is not very high), in some instances the monitoring scan will continue to acquire and analyze more projection data until such time as a projection data is acquired that meets the criteria to trigger diagnostic acquisition.") (Man, Para 28; "Neural networks as discussed herein may encompass deep neural networks, fully connected networks, convolutional neural networks (CNNs), perceptrons, auto encoders, recurrent networks, wavelet filter banks based neural networks, or other machine learning models. These techniques are referred to herein as deep learning techniques, though this terminology may also be used specifically in reference to the use of deep neural networks, which is a neural network having a plurality of layers").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson to include predicting the upper threshold value and the lower threshold value of the HR of the patient based on the HR time series data and the confidence level using an HR prediction model, where the HR prediction model comprises a machine learning (ML) model trained on stored HR time series data acquired from a plurality of human subjects in order to improve clinical workflow as well as improve accuracy as taught by Man as taught by Man (Man, Para 66 and 51).
Regarding claim 4, Jackson as modified by Bhatia and Man above discloses all of the limitations of claim 2 as discussed above.
Jackson does not clearly and explicitly disclose wherein the HR prediction model comprises one of a convolutional neural network (CNN) and a recurrent neural network (RNN).
Man further discloses wherein the HR prediction model comprises one of a convolutional neural network (CNN) and a recurrent neural network (RNN) (Man, Para 25; "Thus, as projection data from a monitoring scan is acquired, it may be analyzed, such as using a machine learning model as discussed herein, to evaluate whether or not to trigger a transition to the diagnostic scan (or when to trigger the transition to the diagnostic scan). If the answer is no (e.g., since the bolus contrast is not sufficiently high for diagnostic imaging, or the confidence in the current cardiac phase estimate is not very high), in some instances the monitoring scan will continue to acquire and analyze more projection data until such time as a projection data is acquired that meets the criteria to trigger diagnostic acquisition.") (Man, Para 28; "Neural networks as discussed herein may encompass deep neural networks, fully connected networks, convolutional neural networks (CNNs), perceptrons, auto encoders, recurrent networks, wavelet filter banks based neural networks, or other machine learning models. These techniques are referred to herein as deep learning techniques, though this terminology may also be used specifically in reference to the use of deep neural networks, which is a neural network having a plurality of layers") (Man, Para 54; “the cardiac phase estimation 200 determines the quiescent phase of the heart cycle”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson wherein the HR prediction model comprises one of a convolutional neural network (CNN) and a recurrent neural network (RNN) in order to improve clinical workflow as well as improve accuracy as taught by Man as taught by Man (Man, Para 66 and 51).
Regarding claim 5, Jackson as modified by Bhatia and Man above discloses all of the limitations of claim 2 as discussed above.
Jackson does not clearly and explicitly disclose wherein the stored HR time series data used to train the HR prediction model includes at least one of: one or more statistical features extracted from samples of the stored HR time series data; one or more parameters of the CT imaging system associated with the stored HR time series data; patient history, test results, and/or demographic data of a patient of the stored HR time series data.
Man further discloses wherein the stored HR time series data used to train the HR prediction model includes at least one of: one or more statistical features extracted from samples of the stored HR time series data; one or more parameters of the CT imaging system associated with the stored HR time series data; patient history, test results, and/or demographic data of a patient of the stored HR time series data (Man, Para 31; "As part of the initial training of deep learning processes to solve a particular problem, training data sets may be employed that have known input values (e.g., input images, projection data, emission data, magnetic resonance data, and so forth) and known or desired values for a final output associated with the input data (e.g., cardiac motion state or phase, respiratory motion state or phase, combined cardiac and respiratory motion state, start timing of diagnostic scan, and so forth) of the deep learning process”) (Man, Para 54; “the cardiac phase estimation 200 determines the quiescent phase of the heart cycle. The cardiac phase may be estimated in various ways. In a phase based approach, the cardiac phase is determined relative to the ECG R-R interval (i.e., peak to peak interval) for each view acquisition (shown as the output of phase estimation 200 of FIG. 3). This can be done as a % of the R-R interval or using a fixed delay after the R-peak. It is generally accepted that the least cardiac motion occurs during the diastole stage (50%-60%), therefore this interval can be used to predict the optimal acquisition timing in a future heartbeat. In one embodiment estimating the cardiac phase comprises directly estimating the timing of a quiescent cardiac phase, which is then used for triggering the acquisition of the diagnostic scan data”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson wherein the stored HR time series data used to train the HR prediction model includes at least one of: one or more statistical features extracted from samples of the stored HR time series data; one or more parameters of the CT imaging system associated with the stored HR time series data; patient history, test results, and/or demographic data of a patient of the stored HR time series data in order to improve clinical workflow as well as improve accuracy as taught by Man as taught by Man (Man, Para 66 and 51).
Regarding claim 6, Jackson as modified by Bhatia and Man above discloses all of the limitations of claim 5 as discussed above.
Jackson does not clearly and explicitly disclose wherein the one or more statistical features extracted from the samples of the stored HR time series data includes at least one of an amplitude and/or time of an R-wave (R-peak), an amplitude and/or time of a p-wave, an amplitude and/or time of a t-wave, a slope of a QRS complex, a quantification of electrocardiograph (EKG) noise, and a classification of a sample performed by a classification model of the CT imaging system.
Man further discloses wherein the one or more statistical features extracted from the samples of the stored HR time series data includes at least one of an amplitude and/or time of an R-wave (R-peak), an amplitude and/or time of a p-wave, an amplitude and/or time of a t-wave, a slope of a QRS complex, a quantification of electrocardiograph (EKG) noise, and a classification of a sample performed by a classification model of the CT imaging system (Man, Para 31; "As part of the initial training of deep learning processes to solve a particular problem, training data sets may be employed that have known input values (e.g., input images, projection data, emission data, magnetic resonance data, and so forth) and known or desired values for a final output associated with the input data (e.g., cardiac motion state or phase, respiratory motion state or phase, combined cardiac and respiratory motion state, start timing of diagnostic scan, and so forth) of the deep learning process”) (Man, Para 54; “the cardiac phase estimation 200 determines the quiescent phase of the heart cycle. The cardiac phase may be estimated in various ways. In a phase based approach, the cardiac phase is determined relative to the ECG R-R interval (i.e., peak to peak interval) for each view acquisition (shown as the output of phase estimation 200 of FIG. 3). This can be done as a % of the R-R interval or using a fixed delay after the R-peak. It is generally accepted that the least cardiac motion occurs during the diastole stage (50%-60%), therefore this interval can be used to predict the optimal acquisition timing in a future heartbeat. In one embodiment estimating the cardiac phase comprises directly estimating the timing of a quiescent cardiac phase, which is then used for triggering the acquisition of the diagnostic scan data”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson wherein the one or more statistical features extracted from the samples of the stored HR time series data includes at least one of an amplitude and/or time of an R-wave (R-peak), an amplitude and/or time of a p-wave, an amplitude and/or time of a t-wave, a slope of a QRS complex, a quantification of electrocardiograph (EKG) noise, and a classification of a sample performed by a classification model of the CT imaging system in order to improve clinical workflow as well as improve accuracy as taught by Man as taught by Man (Man, Para 66 and 51).
Regarding claim 8, Jackson as modified by Bhatia and Man above discloses all of the limitations of claim 5 as discussed above.
Jackson does not clearly and explicitly disclose wherein the one or more parameters of the CT imaging system associated with the stored HR time series data includes at least one of an indication of whether a contrast agent was administered during a collection of samples of the stored HR time series data, one or more contrast injection parameters, and/or a breath hold duration/parameters of a patient during the collection of samples.
Man further discloses wherein the one or more parameters of the CT imaging system associated with the stored HR time series data includes at least one of an indication of whether a contrast agent was administered during a collection of samples of the stored HR time series data, one or more contrast injection parameters, and/or a breath hold duration/parameters of a patient during the collection of samples (Man, Para 53; "In other embodiments, other parameters may also be estimated, such as blood flow, contrast flow speed, flow path, and so forth.") (Man, Para 31; "As part of the initial training of deep learning processes to solve a particular problem, training data sets may be employed that have known input values (e.g., input images, projection data, emission data, magnetic resonance data, and so forth) and known or desired values for a final output associated with the input data (e.g., cardiac motion state or phase, respiratory motion state or phase, combined cardiac and respiratory motion state, start timing of diagnostic scan, and so forth) of the deep learning process”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson wherein the one or more parameters of the CT imaging system associated with the stored HR time series data includes at least one of an indication of whether a contrast agent was administered during a collection of samples of the stored HR time series data, one or more contrast injection parameters, and/or a breath hold duration/parameters of a patient during the collection of samples in order to improve clinical workflow as well as improve accuracy as taught by Man as taught by Man (Man, Para 66 and 51).
Regarding claim 9, Jackson as modified by Bhatia and Man above discloses all of the limitations of claim 5 as discussed above.
Jackson further discloses predicting the upper threshold value and the lower threshold value of the HR of the patient based on the HR time series data collected from the patient over the duration (Jackson, Para 48; "By basing scan timing/data acquisition on a patient's heart rate, the radiation dose may be reduced by acquiring CT imaging information only over a duration wherein a predetermined or pre-selected phase or range of phases having minimal motion is guaranteed to be imaged. For example, scanning so that the end of systole or mid-diastole, as determined by a patient's heart rate range, is included within the projection data may ensure that a diagnostic image having little or no motion is generated. Accordingly, scanning may be performed to ensure at least one of a phase of 45% or a phase of 75% is included in the acquired projection data").
Jackson does not clearly and explicitly disclose extracting the one or more statistical features from the HR time series data collected from the patient, and predicting based on the specified confidence level, and one or more of an extracted statistical feature and a parameter of the CT imaging system associated with the HR time series data.
Bhatia further discloses predicting based on a confidence level specified by an operator of CT imaging system (Bhatia, Para 56; " A determination is made whether the confidence score of the log source type exceeds a predetermined threshold. This is illustrated at step 240. The predetermined threshold is set by an administrator to allow for the normalization of the log based on the confidence score achieving the predetermined threshold. The predetermined threshold may represent a percentage the confidence score must achieve in order for the log source type prediction to be used for normalization purposes.") (Bhatia, Para 54; "The confidence score can reflect a decimal number between zero and one interpreting a percentage of confidence of the log source type prediction. For example, the confidence score can be produced as a range from 0% to 100%, with 100% being an absolute certainty for a given log source type prediction. While typically shown as a percentage, the confidence score can vary based on the accuracy, recall, precession, and preference requested. In some embodiments, the confidence score can be produced as a set of expressions. For example, the set of expressions be expressions such as “low”, “medium”, and “high”.").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson to include predicting based on a confidence level specified by an operator of the CT imaging system as taught by Bhatia in order to streamline review of by a user and allow customization by a user as needed.
Man further discloses extracting the one or more statistical features from the HR time series data collected from the patient, and predicting based on one or more of an extracted statistical feature and a parameter of the CT imaging system associated with the HR time series data (Man, Para 31; "As part of the initial training of deep learning processes to solve a particular problem, training data sets may be employed that have known input values (e.g., input images, projection data, emission data, magnetic resonance data, and so forth) and known or desired values for a final output associated with the input data (e.g., cardiac motion state or phase, respiratory motion state or phase, combined cardiac and respiratory motion state, start timing of diagnostic scan, and so forth) of the deep learning process”) (Man, Para 54; “the cardiac phase estimation 200 determines the quiescent phase of the heart cycle. The cardiac phase may be estimated in various ways. In a phase based approach, the cardiac phase is determined relative to the ECG R-R interval (i.e., peak to peak interval) for each view acquisition (shown as the output of phase estimation 200 of FIG. 3). This can be done as a % of the R-R interval or using a fixed delay after the R-peak. It is generally accepted that the least cardiac motion occurs during the diastole stage (50%-60%), therefore this interval can be used to predict the optimal acquisition timing in a future heartbeat. In one embodiment estimating the cardiac phase comprises directly estimating the timing of a quiescent cardiac phase, which is then used for triggering the acquisition of the diagnostic scan data”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson to include extracting the one or more statistical features from the HR time series data collected from the patient, and predicting based on one or more of an extracted statistical feature and a parameter of the CT imaging system associated with the HR time series data in order to improve clinical workflow as well as improve accuracy as taught by Man as taught by Man (Man, Para 66 and 51).
Claims 3 and 7 are rejected under 35 U.S.C. 103 as being unpatentable over Jackson, Bhatia, and Man as applied to claims 2 and 6 above, and in further view of Banerjee et al. (US20220384049, hereafter Banerjee).
Regarding claim 3, Jackson as modified by Bhatia and Man above discloses all of the limitations of claim 2 as discussed above.
Jackson does not clearly and explicitly disclose wherein the plurality of human subjects includes subjects having a healthy heart and subjects suffering from a heart condition.
In an analogous cardiac modeling field of endeavor Banerjee discloses training a machine learning model on stored HR time series data acquired from a plurality of human subjects, wherein the plurality of human subjects includes subjects having a healthy heart and subjects suffering from a heart condition (Banerjee, Para 6; "there is provided a processor implemented method comprising the steps of: receiving as input, via one or more hardware processors, (i) a first set of real numbers selected randomly from a unit Gaussian distribution and (ii) a second set of reference training data comprising time series data representing a biomedical signal corresponding to a cardiovascular disease condition, each time series data including a plurality of complete cardiac cycles; training an ensemble Generative Adversarial Network (GAN) comprising a pair of GANs, via the one or more hardware processors, using the received input, wherein the pair of GANs includes (i) a Long Short-Term Memory GAN (LSTM-GAN) configured to generate a Heart Rate Variability (HRV) pattern associated with the cardiovascular disease condition and (ii) a Deep Convolutional GAN (DCGAN) configured to create a morphology of a representative cardiac cycle from the plurality of complete cardiac cycles, and wherein each GAN in the pair of GANs includes a generator and a discriminator; and simulating, via the one or more hardware processors, a time series data representing the biomedical signal by combining an output from each GAN in the pair of GANs") (Banerjee, Para 9; "by the generator of the LSTM-GAN, using the first set of real numbers by mapping the first set of real numbers to a time series and classifying the generated R-R interval time-series as belonging to the cardiovascular disease condition or not").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson wherein the plurality of human subjects includes subjects having a healthy heart and subjects suffering from a heart condition in order to improve the algorithm as taught by Banerjee (Banerjee, Para 53).
Regarding claim 7, Jackson as modified by Bhatia and Man above discloses all of the limitations of claim 6 as discussed above.
Jackson does not clearly and explicitly disclose wherein the classification is based on the classification model detecting an abnormal heart rhythm in the stored HR time series data.
In an analogous cardiac modeling field of endeavor Banerjee discloses classification is based on the classification model detecting an abnormal heart rhythm in the stored HR time series data (Banerjee, Para 9; "there is provided a processor implemented method comprising the steps of: receiving as input, via one or more hardware processors, (i) a first set of real numbers selected randomly from a unit Gaussian distribution and (ii) a second set of reference training data comprising time series data representing a biomedical signal corresponding to a cardiovascular disease condition, each time series data including a plurality of complete cardiac cycles; training an ensemble Generative Adversarial Network (GAN) comprising a pair of GANs, via the one or more hardware processors, using the received input, wherein the pair of GANs includes (i) a Long Short-Term Memory GAN (LSTM-GAN) configured to generate a Heart Rate Variability (HRV) pattern associated with the cardiovascular disease condition and (ii) a Deep Convolutional GAN (DCGAN) configured to create a morphology of a representative cardiac cycle from the plurality of complete cardiac cycles, and wherein each GAN in the pair of GANs includes a generator and a discriminator; and simulating, via the one or more hardware processors, a time series data representing the biomedical signal by combining an output from each GAN in the pair of GANs") (Banerjee, Para 9; "by the generator of the LSTM-GAN, using the first set of real numbers by mapping the first set of real numbers to a time series and classifying the generated R-R interval time-series as belonging to the cardiovascular disease condition or not").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson wherein the classification is based on the classification model detecting an abnormal heart rhythm in the stored HR time series data in order to improve the algorithm as taught by Banerjee (Banerjee, Para 53).
Claims 15-20 are rejected under 35 U.S.C. 103 as being unpatentable over Jackson et al. (US20210093277, hereafter Jackson), Bhatia et al. (US20220277176, hereafter Bhatia), and Man et al. (US20200163639, hereafter Man).
Regarding claim 15, Jackson discloses a computed tomography (CT) imaging system comprising:
an electrocardiograph (EKG) (Jackson, Para 8; “FIG. 3A depicts an example electrocardiogram (ECG) waveform that may be used for imaging system gating;”);
a processor; and a memory storing instructions that when executed (Jackson, Para 41; “The various methods and processes described further herein may be stored as executable instructions in non-transitory memory on a computing device in imaging system 200. In one embodiment, image reconstructor 230 may include such executable instructions in non-transitory memory, and may apply the methods described herein to reconstruct an image from scanning data. In another embodiment, computing device 216 may include the instructions in non-transitory memory, and may apply the methods described herein, at least in part, to a reconstructed image after receiving the reconstructed image from image reconstructor 230. In yet another embodiment, the methods and processes described herein may be distributed across image reconstructor 230 and computing device 216”), cause the processor to:
collect heart rate (HR) time series data from a patient of the CT imaging system over a duration, via the EKG (Jackson, Para 46; “For ECG gated imaging, the CT scanner monitors the patient's ECG and is set to scan at a particular point in the cardiac cycle which is typically during diastole as the heart is moving the least. The CT scanner may interpret the ECG and determine a delay after a QRS complex to begin scanning. Once that point of delay has occurred, the ECG may trigger the CT scanner to start scanning”);
extract one or more statistical features of the collected HR time series data (Jackson, Para 46; "For ECG gated imaging, the CT scanner monitors the patient's ECG and is set to scan at a particular point in the cardiac cycle which is typically during diastole as the heart is moving the least. The CT scanner may interpret the ECG and determine a delay after a QRS complex to begin scanning. Once that point of delay has occurred, the ECG may trigger the CT scanner to start scanning. For example, in FIG. 3A, t5 may represent a point of delay after QRS complex 324 that triggers CT scanning so that the scan data includes some range of diastole for a given cardiac cycle.");
receive a cardiac phase range specified by the operator for performing a cardiac scan of the patient using the CT imaging system (Jackson, Para 15; “scanning may be performed to ensure at least the end of systole or middle of diastole is included within the acquired projection data. The timing of end-systole and mid-diastole may be specifically determined based on a patient's heart rate range”) (Jackson, Para 35; the computing device 216 controls system operations based on operator input. The computing device 216 receives the operator input, for example, including commands and/or scanning parameters via an operator console 220 operatively coupled to the computing device 216. The operator console 220 may include a keyboard (not shown) or a touchscreen to allow the operator to specify the commands and/or scanning parameters);
predict an upper threshold value and a lower threshold value of a heart rate (HR) of a patient of the CT imaging system, based on HR time series data and the extracted one or more statistical features (Jackson, Para 48; "By basing scan timing/data acquisition on a patient's heart rate, the radiation dose may be reduced by acquiring CT imaging information only over a duration wherein a predetermined or pre-selected phase or range of phases having minimal motion is guaranteed to be imaged. For example, scanning so that the end of systole or mid-diastole, as determined by a patient's heart rate range, is included within the projection data may ensure that a diagnostic image having little or no motion is generated. Accordingly, scanning may be performed to ensure at least one of a phase of 45% or a phase of 75% is included in the acquired projection data") (Jackson, Para 46; "For ECG gated imaging, the CT scanner monitors the patient's ECG and is set to scan at a particular point in the cardiac cycle which is typically during diastole as the heart is moving the least. The CT scanner may interpret the ECG and determine a delay after a QRS complex to begin scanning. Once that point of delay has occurred, the ECG may trigger the CT scanner to start scanning. For example, in FIG. 3A, t5 may represent a point of delay after QRS complex 324 that triggers CT scanning so that the scan data includes some range of diastole for a given cardiac cycle.");
adjust a dose of radiation and a timing of a CT scan performed using the CT imaging system based on the received cardiac phase range and the predicted upper threshold value and lower threshold value; perform the cardiac scan on the patient at the adjusted timing using the adjusted dose (Jackson, Para 15; "scanning may be performed to ensure at least the end of systole or middle of diastole is included within the acquired projection data. The timing of end-systole and mid-diastole may be specifically determined based on a patient's heart rate range ") (Jackson, Para 56; "As previously described with respect to FIGS. 3A and 3B, the least amount of cardiac motion happens within ventricular diastole which generally occurs during an R-R interval phase ranging from 45% to 100%. Thus, by acquiring projection data for a sufficient amount of time that either the end of systole or mid-diastole of an R-R interval will fall within the scan range regardless of when in the patient's cardiac cycle scanning commences it may be assumed that the exposure duration may robustly generate a diagnostic image.") (Jackson, Para 12; "Thus, by targeting x-ray exposure to a particular time window relative to the ECG R-wave, the radiation dose may be reduced by only acquiring data sufficient to ensure, with reasonable confidence, at least one image set with minimal motion."); and
reconstruct an image based on data acquired during the cardiac scan; and display the image on a display device of the CT imaging system and/or store the image in a memory of the CT imaging system (Jackson, Para 14; "the CT scan may be performed with an x-ray exposure that is longer than a minimum x-ray exposure duration demanded to reconstruct a single image and less than an x-ray duration demanded to acquire and reconstruct images depicting a full heartbeat. The use of this duration to scan and reconstruct a cardiac image may result in an image with minimal motion, or an amount of motion that does not significantly impede the intended clinical diagnosis, while minimizing radiation exposure to the patient").
Jackson does not clearly and explicitly disclose receiving a confidence level specified by an operator of the CT imaging system, the confidence level a desired probabilistic certainty that a prediction of an HR of the patient generated by the CT imaging system is accurate; and predicting an upper threshold value and a lower threshold value of the HR of the patient, using a machine learning (ML) model, and based on the confidence level specified by an operator of the CT imaging system.
In an analogous machine learning for prediction of events field of endeavor Bhatia discloses receiving a confidence level specified by an operator, the confidence level a desired probabilistic certainty that a prediction is accurate and predicting based on a confidence level specified by an operator of CT imaging system (Bhatia, Para 56; " A determination is made whether the confidence score of the log source type exceeds a predetermined threshold. This is illustrated at step 240. The predetermined threshold is set by an administrator to allow for the normalization of the log based on the confidence score achieving the predetermined threshold. The predetermined threshold may represent a percentage the confidence score must achieve in order for the log source type prediction to be used for normalization purposes.") (Bhatia, Para 54; "The confidence score can reflect a decimal number between zero and one interpreting a percentage of confidence of the log source type prediction. For example, the confidence score can be produced as a range from 0% to 100%, with 100% being an absolute certainty for a given log source type prediction. While typically shown as a percentage, the confidence score can vary based on the accuracy, recall, precession, and preference requested. In some embodiments, the confidence score can be produced as a set of expressions. For example, the set of expressions be expressions such as “low”, “medium”, and “high”.").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson to include receiving a confidence level specified by an operator of the CT imaging system, the confidence level a desired probabilistic certainty that a prediction of an HR of the patient generated by the CT imaging system is accurate; and predicting an upper threshold value and a lower threshold value of the HR of the patient and based on the confidence level specified by an operator of the CT imaging system as taught by Bhatia in order to streamline review of by a user and allow customization by a user as needed.
In an analogous diagnostic imaging classification field of endeavor Man discloses predicting based on HR time series data and confidence level using an HR prediction model (Man, Para 22; "the cardiac motion is monitored by an electrocardiogram (ECG) device to find end-diastole or end-systole stage for each cardiac cycle. Then, the scan (e.g., a cardiac CT scan) is triggered such that the diagnostic scan data is acquired when the heart is in a phase with relatively little motion") (Man, Para 25; "If the answer is no (e.g., since the bolus contrast is not sufficiently high for diagnostic imaging, or the confidence in the current cardiac phase estimate is not very high), in some instances the monitoring scan will continue to acquire and analyze more projection data until such time as a projection data is acquired that meets the criteria to trigger diagnostic acquisition.") (Man, Para 54; “the cardiac phase estimation 200 determines the quiescent phase of the heart cycle”), where the HR prediction model comprises a machine learning (ML) model (Man, Para 25; "Thus, as projection data from a monitoring scan is acquired, it may be analyzed, such as using a machine learning model as discussed herein, to evaluate whether or not to trigger a transition to the diagnostic scan (or when to trigger the transition to the diagnostic scan). If the answer is no (e.g., since the bolus contrast is not sufficiently high for diagnostic imaging, or the confidence in the current cardiac phase estimate is not very high), in some instances the monitoring scan will continue to acquire and analyze more projection data until such time as a projection data is acquired that meets the criteria to trigger diagnostic acquisition.") (Man, Para 28; "Neural networks as discussed herein may encompass deep neural networks, fully connected networks, convolutional neural networks (CNNs), perceptrons, auto encoders, recurrent networks, wavelet filter banks based neural networks, or other machine learning models. These techniques are referred to herein as deep learning techniques, though this terminology may also be used specifically in reference to the use of deep neural networks, which is a neural network having a plurality of layers").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson to include predicting the upper threshold value and the lower threshold value of the HR of the patient based on the HR time series data and the confidence level using an HR prediction model, where the HR prediction model comprises a machine learning (ML) model in order to improve clinical workflow as well as improve accuracy as taught by Man as taught by Man (Man, Para 66 and 51).
Regarding claim 16, Jackson as modified by Bhatia and Man above discloses all of the limitations of claim 15 as discussed above.
Jackson does not clearly and explicitly disclose an HR prediction system, wherein the upper threshold value and the lower threshold value of the HR of the patient are predicted by an HR time series prediction model of the HR prediction system.
In an analogous diagnostic imaging classification field of endeavor Man discloses an HR prediction system, wherein an upper threshold value and lower threshold value of the HR of the patient are predicted by an HR time series prediction model of the HR prediction system (Man, Para 22; "the cardiac motion is monitored by an electrocardiogram (ECG) device to find end-diastole or end-systole stage for each cardiac cycle. Then, the scan (e.g., a cardiac CT scan) is triggered such that the diagnostic scan data is acquired when the heart is in a phase with relatively little motion") (Man, Para 25; "If the answer is no (e.g., since the bolus contrast is not sufficiently high for diagnostic imaging, or the confidence in the current cardiac phase estimate is not very high), in some instances the monitoring scan will continue to acquire and analyze more projection data until such time as a projection data is acquired that meets the criteria to trigger diagnostic acquisition.") (Man, Para 54; “the cardiac phase estimation 200 determines the quiescent phase of the heart cycle”) (Man, Para 25; "Thus, as projection data from a monitoring scan is acquired, it may be analyzed, such as using a machine learning model as discussed herein, to evaluate whether or not to trigger a transition to the diagnostic scan (or when to trigger the transition to the diagnostic scan). If the answer is no (e.g., since the bolus contrast is not sufficiently high for diagnostic imaging, or the confidence in the current cardiac phase estimate is not very high), in some instances the monitoring scan will continue to acquire and analyze more projection data until such time as a projection data is acquired that meets the criteria to trigger diagnostic acquisition.") (Man, Para 28; "Neural networks as discussed herein may encompass deep neural networks, fully connected networks, convolutional neural networks (CNNs), perceptrons, auto encoders, recurrent networks, wavelet filter banks based neural networks, or other machine learning models. These techniques are referred to herein as deep learning techniques, though this terminology may also be used specifically in reference to the use of deep neural networks, which is a neural network having a plurality of layers").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson to include an HR prediction system, wherein the upper threshold value and the lower threshold value of the HR of the patient are predicted by an HR time series prediction model of the HR prediction system in order to improve clinical workflow as well as improve accuracy as taught by Man as taught by Man (Man, Para 66 and 51).
Regarding claim 17, Jackson as modified by Bhatia and Man above discloses all of the limitations of claim 16 as discussed above.
Jackson does not clearly and explicitly disclose wherein the extracted one or more statistical features include at least one of an amplitude and/or time of an R-wave (R-peak), an amplitude and/or time of a p-wave, an amplitude and/or time of a t-wave, a slope of a QRS complex, a quantification of electrocardiograph (EKG) noise, and a classification of the HR time series data performed by a classification model of the CT imaging system.
Man further discloses wherein the extracted one or more statistical features include at least one of an amplitude and/or time of an R-wave (R-peak), an amplitude and/or time of a p-wave, an amplitude and/or time of a t-wave, a slope of a QRS complex, a quantification of electrocardiograph (EKG) noise, and a classification of the HR time series data performed by a classification model of the CT imaging system (Man, Para 31; "As part of the initial training of deep learning processes to solve a particular problem, training data sets may be employed that have known input values (e.g., input images, projection data, emission data, magnetic resonance data, and so forth) and known or desired values for a final output associated with the input data (e.g., cardiac motion state or phase, respiratory motion state or phase, combined cardiac and respiratory motion state, start timing of diagnostic scan, and so forth) of the deep learning process”) (Man, Para 54; “the cardiac phase estimation 200 determines the quiescent phase of the heart cycle. The cardiac phase may be estimated in various ways. In a phase based approach, the cardiac phase is determined relative to the ECG R-R interval (i.e., peak to peak interval) for each view acquisition (shown as the output of phase estimation 200 of FIG. 3). This can be done as a % of the R-R interval or using a fixed delay after the R-peak. It is generally accepted that the least cardiac motion occurs during the diastole stage (50%-60%), therefore this interval can be used to predict the optimal acquisition timing in a future heartbeat. In one embodiment estimating the cardiac phase comprises directly estimating the timing of a quiescent cardiac phase, which is then used for triggering the acquisition of the diagnostic scan data”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson wherein the extracted one or more statistical features include at least one of an amplitude and/or time of an R-wave (R-peak), an amplitude and/or time of a p-wave, an amplitude and/or time of a t-wave, a slope of a QRS complex, a quantification of electrocardiograph (EKG) noise, and a classification of the HR time series data performed by a classification model of the CT imaging system in order to improve clinical workflow as well as improve accuracy as taught by Man as taught by Man (Man, Para 66 and 51).
Regarding claim 18, Jackson as modified by Bhatia and Man above discloses all of the limitations of claim 16 as discussed above.
Jackson does not clearly and explicitly disclose wherein the HR prediction model comprises one of a convolutional neural network (CNN) and a recurrent neural network (RNN).
Man further discloses wherein the HR prediction model comprises one of a convolutional neural network (CNN) and a recurrent neural network (RNN) (Man, Para 25; "Thus, as projection data from a monitoring scan is acquired, it may be analyzed, such as using a machine learning model as discussed herein, to evaluate whether or not to trigger a transition to the diagnostic scan (or when to trigger the transition to the diagnostic scan). If the answer is no (e.g., since the bolus contrast is not sufficiently high for diagnostic imaging, or the confidence in the current cardiac phase estimate is not very high), in some instances the monitoring scan will continue to acquire and analyze more projection data until such time as a projection data is acquired that meets the criteria to trigger diagnostic acquisition.") (Man, Para 28; "Neural networks as discussed herein may encompass deep neural networks, fully connected networks, convolutional neural networks (CNNs), perceptrons, auto encoders, recurrent networks, wavelet filter banks based neural networks, or other machine learning models. These techniques are referred to herein as deep learning techniques, though this terminology may also be used specifically in reference to the use of deep neural networks, which is a neural network having a plurality of layers") (Man, Para 54; “the cardiac phase estimation 200 determines the quiescent phase of the heart cycle”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson wherein the HR prediction model comprises one of a convolutional neural network (CNN) and a recurrent neural network (RNN) in order to improve clinical workflow as well as improve accuracy as taught by Man as taught by Man (Man, Para 66 and 51).
Regarding claim 19, Jackson discloses a method for a computed tomography (CT) imaging system, the method comprising:
collecting heart rate (HR) time series data from a patient of the CT imaging system over a duration (Jackson, Para 46; “For ECG gated imaging, the CT scanner monitors the patient's ECG and is set to scan at a particular point in the cardiac cycle which is typically during diastole as the heart is moving the least. The CT scanner may interpret the ECG and determine a delay after a QRS complex to begin scanning. Once that point of delay has occurred, the ECG may trigger the CT scanner to start scanning”);
extracting statistical features from the HR time series data (Jackson, Para 46; "For ECG gated imaging, the CT scanner monitors the patient's ECG and is set to scan at a particular point in the cardiac cycle which is typically during diastole as the heart is moving the least. The CT scanner may interpret the ECG and determine a delay after a QRS complex to begin scanning. Once that point of delay has occurred, the ECG may trigger the CT scanner to start scanning. For example, in FIG. 3A, t5 may represent a point of delay after QRS complex 324 that triggers CT scanning so that the scan data includes some range of diastole for a given cardiac cycle.");
predicting an upper threshold value and a lower threshold value of a heart rate (HR) of a patient of the CT imaging system, based on HR time series data and the extracted one or more statistical features (Jackson, Para 48; "By basing scan timing/data acquisition on a patient's heart rate, the radiation dose may be reduced by acquiring CT imaging information only over a duration wherein a predetermined or pre-selected phase or range of phases having minimal motion is guaranteed to be imaged. For example, scanning so that the end of systole or mid-diastole, as determined by a patient's heart rate range, is included within the projection data may ensure that a diagnostic image having little or no motion is generated. Accordingly, scanning may be performed to ensure at least one of a phase of 45% or a phase of 75% is included in the acquired projection data") (Jackson, Para 46; "For ECG gated imaging, the CT scanner monitors the patient's ECG and is set to scan at a particular point in the cardiac cycle which is typically during diastole as the heart is moving the least. The CT scanner may interpret the ECG and determine a delay after a QRS complex to begin scanning. Once that point of delay has occurred, the ECG may trigger the CT scanner to start scanning. For example, in FIG. 3A, t5 may represent a point of delay after QRS complex 324 that triggers CT scanning so that the scan data includes some range of diastole for a given cardiac cycle.");
adjusting a dose of radiation and a timing of a cardiac scan of the patient based on the predicted upper threshold value and lower threshold value; performing the cardiac scan on the patient at the adjusted timing using the adjusted dose (Jackson, Para 15; "scanning may be performed to ensure at least the end of systole or middle of diastole is included within the acquired projection data. The timing of end-systole and mid-diastole may be specifically determined based on a patient's heart rate range ") (Jackson, Para 56; "As previously described with respect to FIGS. 3A and 3B, the least amount of cardiac motion happens within ventricular diastole which generally occurs during an R-R interval phase ranging from 45% to 100%. Thus, by acquiring projection data for a sufficient amount of time that either the end of systole or mid-diastole of an R-R interval will fall within the scan range regardless of when in the patient's cardiac cycle scanning commences it may be assumed that the exposure duration may robustly generate a diagnostic image.") (Jackson, Para 12; "Thus, by targeting x-ray exposure to a particular time window relative to the ECG R-wave, the radiation dose may be reduced by only acquiring data sufficient to ensure, with reasonable confidence, at least one image set with minimal motion."); and
displaying an image reconstructed from data acquired during the cardiac scan and/or storing the image in a memory of the CT imaging system (Jackson, Para 14; "the CT scan may be performed with an x-ray exposure that is longer than a minimum x-ray exposure duration demanded to reconstruct a single image and less than an x-ray duration demanded to acquire and reconstruct images depicting a full heartbeat. The use of this duration to scan and reconstruct a cardiac image may result in an image with minimal motion, or an amount of motion that does not significantly impede the intended clinical diagnosis, while minimizing radiation exposure to the patient").
Jackson does not clearly and explicitly disclose performing a classification of the HR time series data using a classification model of the CT imaging system, receiving a confidence level specified by an operator of the CT imaging system, the confidence level a desired probabilistic certainty that a prediction of an HR of the patient generated by the CT imaging system is accurate; and predicting an upper threshold value and a lower threshold value of the HR of the patient, using a machine learning (ML) model, and based on the confidence level specified by an operator of the CT imaging system.
In an analogous machine learning for prediction of events field of endeavor Bhatia discloses
performing a classification based on a classification model (Banerjee, Para 9; "there is provided a processor implemented method comprising the steps of: receiving as input, via one or more hardware processors, (i) a first set of real numbers selected randomly from a unit Gaussian distribution and (ii) a second set of reference training data comprising time series data representing a biomedical signal corresponding to a cardiovascular disease condition, each time series data including a plurality of complete cardiac cycles; training an ensemble Generative Adversarial Network (GAN) comprising a pair of GANs, via the one or more hardware processors, using the received input, wherein the pair of GANs includes (i) a Long Short-Term Memory GAN (LSTM-GAN) configured to generate a Heart Rate Variability (HRV) pattern associated with the cardiovascular disease condition and (ii) a Deep Convolutional GAN (DCGAN) configured to create a morphology of a representative cardiac cycle from the plurality of complete cardiac cycles, and wherein each GAN in the pair of GANs includes a generator and a discriminator; and simulating, via the one or more hardware processors, a time series data representing the biomedical signal by combining an output from each GAN in the pair of GANs") (Banerjee, Para 9; "by the generator of the LSTM-GAN, using the first set of real numbers by mapping the first set of real numbers to a time series and classifying the generated R-R interval time-series as belonging to the cardiovascular disease condition or not"); and
receiving a confidence level specified by an operator, the confidence level a desired probabilistic certainty that a prediction is accurate and predicting based on a confidence level specified by an operator of CT imaging system (Bhatia, Para 56; " A determination is made whether the confidence score of the log source type exceeds a predetermined threshold. This is illustrated at step 240. The predetermined threshold is set by an administrator to allow for the normalization of the log based on the confidence score achieving the predetermined threshold. The predetermined threshold may represent a percentage the confidence score must achieve in order for the log source type prediction to be used for normalization purposes.") (Bhatia, Para 54; "The confidence score can reflect a decimal number between zero and one interpreting a percentage of confidence of the log source type prediction. For example, the confidence score can be produced as a range from 0% to 100%, with 100% being an absolute certainty for a given log source type prediction. While typically shown as a percentage, the confidence score can vary based on the accuracy, recall, precession, and preference requested. In some embodiments, the confidence score can be produced as a set of expressions. For example, the set of expressions be expressions such as “low”, “medium”, and “high”.").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson to include performing a classification of the HR time series data using a classification model of the CT imaging system; receiving a confidence level specified by an operator of the CT imaging system, the confidence level a desired probabilistic certainty that a prediction of an HR of the patient generated by the CT imaging system is accurate; and predicting an upper threshold value and a lower threshold value of the HR of the patient and based on the confidence level specified by an operator of the CT imaging system as taught by Bhatia in order to streamline review of by a user and allow customization by a user as needed.
In an analogous diagnostic imaging classification field of endeavor Man discloses predicting based on HR time series data and confidence level using an HR prediction model (Man, Para 22; "the cardiac motion is monitored by an electrocardiogram (ECG) device to find end-diastole or end-systole stage for each cardiac cycle. Then, the scan (e.g., a cardiac CT scan) is triggered such that the diagnostic scan data is acquired when the heart is in a phase with relatively little motion") (Man, Para 25; "If the answer is no (e.g., since the bolus contrast is not sufficiently high for diagnostic imaging, or the confidence in the current cardiac phase estimate is not very high), in some instances the monitoring scan will continue to acquire and analyze more projection data until such time as a projection data is acquired that meets the criteria to trigger diagnostic acquisition.") (Man, Para 54; “the cardiac phase estimation 200 determines the quiescent phase of the heart cycle”), where the HR prediction model comprises a machine learning (ML) model (Man, Para 25; "Thus, as projection data from a monitoring scan is acquired, it may be analyzed, such as using a machine learning model as discussed herein, to evaluate whether or not to trigger a transition to the diagnostic scan (or when to trigger the transition to the diagnostic scan). If the answer is no (e.g., since the bolus contrast is not sufficiently high for diagnostic imaging, or the confidence in the current cardiac phase estimate is not very high), in some instances the monitoring scan will continue to acquire and analyze more projection data until such time as a projection data is acquired that meets the criteria to trigger diagnostic acquisition.") (Man, Para 28; "Neural networks as discussed herein may encompass deep neural networks, fully connected networks, convolutional neural networks (CNNs), perceptrons, auto encoders, recurrent networks, wavelet filter banks based neural networks, or other machine learning models. These techniques are referred to herein as deep learning techniques, though this terminology may also be used specifically in reference to the use of deep neural networks, which is a neural network having a plurality of layers").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Jackson to include predicting the upper threshold value and the lower threshold value of the HR of the patient based on the HR time series data and the confidence level using an HR prediction model, where the HR prediction model comprises a machine learning (ML) model in order to improve clinical workflow as well as improve accuracy as taught by Man as taught by Man (Man, Para 66 and 51).
Regarding claim 20, Jackson as modified by Bhatia and Man above discloses all of the limitations of claim 19 as discussed above.
Jackson further discloses wherein adjusting the dose of radiation and the timing of the cardiac scan of the patient based on the predicted upper threshold value and lower threshold value further comprises timing a start of an X-ray exposure based on the upper threshold value, and timing an end of the X-ray exposure based on the lower threshold value (Jackson, Para 15; “scanning may be performed to ensure at least the end of systole or middle of diastole is included within the acquired projection data. The timing of end-systole and mid-diastole may be specifically determined based on a patient's heart rate range”) (Jackson, Para 56; "As previously described with respect to FIGS. 3A and 3B, the least amount of cardiac motion happens within ventricular diastole which generally occurs during an R-R interval phase ranging from 45% to 100%. Thus, by acquiring projection data for a sufficient amount of time that either the end of systole or mid-diastole of an R-R interval will fall within the scan range regardless of when in the patient's cardiac cycle scanning commences it may be assumed that the exposure duration may robustly generate a diagnostic image. As previously described with respect to FIG. 3B, for a patient with systole ending at 45% and mid-diastole at 75%, in a worst case scenario, the longest duration between cardiac phases that will generate a diagnostic image is 70% of an R-R interval. Further, as the effect of heart rate on diastolic duration is predictable from kinematic modeling and known cellular physiology, a model of cardiac motion may be used to more precisely determine diastolic/systolic event times, with these precise event times then used for exposure time determinations. For example, based on heart rate range and kinematic modeling, mid-diastole may be found to occur at 85% for a patient rather than a generalized 75%. Thus, the longest duration between cardiac phases that may generate a diagnostic image would be from 85% to 145% rather than 75% to 145% and, as such, the required window of acquisition during scanning may be 60% of an R-R interval (as opposed to 70% when diastolic/systolic event times are not precisely determined)") (Jackson, Para 12; "Thus, by targeting x-ray exposure to a particular time window relative to the ECG R-wave, the radiation dose may be reduced by only acquiring data sufficient to ensure, with reasonable confidence, at least one image set with minimal motion.").
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to John Li whose telephone number is (313)446-4916. The examiner can normally be reached Monday to Thursday; 5:30 AM to 3:30 PM Eastern.
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, Pascal Bui-Pho can be reached at (571) 272-2714. 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.
/JOHN D LI/Primary Examiner, Art Unit 3798
Prosecution Insights