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 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 1-15, 17-20, and 29 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Specifically, representative Claim 1 recites:
“A system, comprising: at least one storage device including a set of instructions; at least one processor in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is configured to cause the system to perform operations including: obtaining one or more sets of reference signals collected by a coil of a magnetic resonance imaging (MRI) device in a pre-scan, the pre-scan being performed on a subject before an MRI scan of the subject; obtaining a first fault detection model, the first fault detection model being a trained machine learning model; determining whether the coil has a failure based on the one or more sets of reference signals and the first fault detection model by inputting the one or more sets of reference signals into the first fault detection model; and in response to determining that the coil has a failure, displaying a warning window via a terminal to prompt an operator whether to stop a scanning, and recording a fault detection result of the coil in a log to facilitate debugging the coil.”
The claim limitations in the abstract idea have been highlighted in bold above; the remaining limitations are “additional elements”.
Under the Step 1 of the eligibility analysis, we determine whether the claims are to a statutory category by considering whether the claimed subject matter falls within the four statutory categories of patentable subject matter identified by 35 U.S.C. 101: Process, machine, manufacture, or composition of matter. The above claim is considered to be in a statutory category (machine).
Under the Step 2A, Prong One, we consider whether the claim recites a judicial exception (abstract idea). In the above claim, the highlighted portion constitutes an abstract idea because, under a broadest reasonable interpretation, it recites limitations that fall into/recite an abstract idea exceptions. Specifically, under the 2019 Revised Patent Subject matter Eligibility Guidance, it falls into the groupings of subject matter when recited as such in a claim limitation that falls into the grouping of subject matter when recited as such in a claim limitation, that covers mathematical concepts - mathematical relationships, mathematical formulas or equations, mathematical calculations and mental processes — concepts performed in the human mind including an observation, evaluation, judgement, and/or opinion.
For example, the steps of “determining whether the coil has a failure based on the one or more sets of reference signals and the first fault detection model by inputting the one or more sets of reference signals into the first fault detection model” are treated as belonging to both math and mental process grouping.
With regards to the steps of “determining whether the coil has a failure based on the one or more sets of reference signals and the first fault detection model”, this mental step represents a process that, under its broadest reasonable interpretation, cover performance of the limitations in the mind. That is, nothing in the claim element precludes the step from practically being performed in the mind. In the context of this claim, it encompasses the user making mental decisions (evaluation/judgement) with regards to determining whether the coil has a failure and for providing training data to a model.
Next, under the Step 2A, Prong Two, we consider whether the claim that recites a judicial exception is integrated into a practical application.
In this step, we evaluate whether the claim recites additional elements that
integrate the exception into a practical application of that exception.
The above claims comprise the following additional elements:
Claim 1: A system, comprising: at least one storage device including a set of instructions; at least one processor in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is configured to cause the system to perform operations including: obtaining one or more sets of reference signals collected by a coil of a magnetic resonance imaging (MRI) device in a pre-scan, the pre-scan being performed on a subject before an MRI scan of the subject; obtaining a first fault detection model, the first fault detection model being a trained machine learning model and in response to determining that the coil has a failure, displaying a warning window via a terminal to prompt an operator whether to stop a scanning, and recording a fault detection result of the coil in a log to facilitate debugging the coil
Claim 15: A method implemented on a computing device having at least one processor and at least one storage device, comprising: obtaining one or more sets of reference signals collected by a coil of a magnetic resonance imaging (MRI) device in a pre-scan, the pre-scan being performed on a subject before an MRI scan of the subject; obtaining a first fault detection model, the first fault detection model being a trained machine learning model, displaying a warning window via a terminal to prompt an operator whether to stop a scanning, and recording a fault detection result of the coil in a log to facilitate debugging the coil, wherein the position of the failure includes a serial number of a channel that has the failure among the plurality of channels, and the output further includes the serial number when the coil has a failure
Claim 29: A non-transitory computer readable medium including executable instructions, the instructions, when executed by at least one processor, causing the at least one processor to effectuate a method comprising: obtaining one or more sets of reference signals collected by a coil of a magnetic resonance imaging (MRI) device in a pre-scan, the pre-scan being performed on a subject before an MRI scan of the subject; obtaining a first fault detection model, the first fault detection model being a trained machine learning model, displaying a warning window via a terminal to prompt an operator whether to stop a scanning, and recording a fault detection result of the coil in a log to facilitate debugging the coil
The above additional elements in Claim 1 such as a system, comprising: at least one storage device including a set of instructions; at least one processor in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is configured to cause the system to perform operations including: is recited in generality and field of use which is part of an expanded abstract idea, obtaining one or more sets of reference signals collected by a coil of a magnetic resonance imaging (MRI) device in a pre-scan, the pre-scan being performed on a subject before an MRI scan of the subject; obtaining a first fault detection model, the first fault detection model being a trained machine learning model are examples of data gathering and are generically recited and are not meaningful, and displaying a warning window via a terminal to prompt an operator whether to stop a scanning, and recording a fault detection result of the coil in a log to facilitate debugging the coil are examples of post-solution insignificant activities of outputting results. The additional elements in claims 1, 15, and 29 such a computer, a processor, and a non-transitory computer-readable medium comprising instructions that are executable by a processor for causing the processor is an example of generic computer equipment (components) that is generally recited and, therefore, is not qualified as a particular machine.
Therefore, the claims are directed to a judicial exception and require further analysis under the Step 2B.
However, the above claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception (Step 2B analysis) because these additional elements/steps are well-understood and conventional in the relevant art based on the prior art of record including references in the submitted IDS (09/02/2025) by the Applicant (Van Wieringen and Huang).
The independent claims, therefore, are not patent eligible.
With regards to the dependent claims, claims 2-14, 17-20, and 29 provide additional features/steps which are either part of an expanded abstract idea of the independent claims (additionally comprising mathematical (Claims 2-14, 17-20, and 29) or adding additional elements/steps that are not meaningful as they are recited in generality and/or not qualified as particular machine/ and/or eligible transformation and, therefore, do not reflect a practical application as well as not qualified for “significantly more” based on prior art of record.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1,3-10,12,14-20 and 29-32 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 enablement requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to enable one skilled in the art to which it pertains, or with which it is most nearly connected, to make and/or use the invention. Claim 1 limitations include “…facilitate debugging the coil…” which is not included the specification.
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 1,3-10,12,14-20 and 29-32 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.
With regards to Claim 1, the limitation “…facilitate debugging the coil…” is indefinite because it is unclear what the patentable boundaries of this limitation are. This limitation describes intended use result without clear boundaries.
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.
Claims 1-2, 10-12, and 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Van Wieringen et al. (US 20160327606), hereinafter referred to as ‘Van Wieringen' and in further view of Huang et al. (US 20120002859), hereinafter referred to as ‘Huang' and Huff et al. (US20120191383), hereinafter referred to as ‘Huff’.
Regarding Claim 1, Van Wieringen discloses a system, comprising: at least one storage device including a set of instructions; at least one processor in communication with the at least one storage device (The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A ‘computer-readable storage medium’ as used herein encompasses any tangible storage medium which may store instructions which are executable by a processor of a computing device [0006]), wherein when executing the set of instructions, the at least one processor is configured to cause the system to perform operations including (A hardware interface may allow a processor to send control signals or instructions to an external computing device and/or apparatus. A hardware interface may also enable a processor to exchange data with an external computing device and/or apparatus [0016]): obtaining one or more sets of reference signals collected by a coil of a magnetic resonance imaging (MRI) device (Magnetic Resonance (MR) data is defined herein as being the recorded measurements of radio frequency signals emitted by atomic spins by the antenna of a Magnetic resonance apparatus during a magnetic resonance imaging scan [0018]; In another embodiment execution of the instructions further causes the processor to store scanned parameter data in the measurement database. Scanned parameter data as used herein is descriptive of the usage of the gradient coil amplifier during acquisition of the magnetic resonance data. The scanned parameter data may for instance be data derived from a so called pulse sequence which describes the usage of the gradient coil amplifier during the acquisition of magnetic resonance data [0025]); obtaining a first fault detection model (Execution of the instructions further cause the processor to repeatedly calculate a probability of failure of a gradient coil amplifier of the magnetic resonance imaging system a predetermined number of days in the future by inputting the measurement vector into a trained neural network program [0020]), the first fault detection model being a trained machine learning model (Execution of the instructions further cause the processor to repeatedly calculate a probability of failure of a gradient coil amplifier of the magnetic resonance imaging system a predetermined number of days in the future by inputting the measurement vector into a trained neural network program [0020]); determining whether the coil has a failure based on the one or more sets of reference signals (The method further comprises the step of repeatedly calculating a probability of failure of a gradient coil amplifier of the magnetic resonance imaging system a predetermined number of days in the future by inputting the measurement vector into a trained neural network program [0047]).
However, Van Wieringen discloses obtaining one or more sets of reference signals collected by a coil of a magnetic resonance imaging (MRI) device in a pre-scan, the pre-scan being performed on a subject before an MRI scan of the subject; obtaining a first fault detection model, the first fault detection model being a trained machine learning model; determining whether the coil has a failure based on the one or more sets of reference signals and the first fault detection model by inputting the one or more sets of reference signals into the first fault detection model; and in response to determining that the coil has a failure, displaying a warning window via a terminal to prompt an operator whether to stop a scanning, and recording a fault detection result of the coil in a log to facilitate debugging the coil.
Nevertheless, Huang discloses obtaining one or more sets of reference signals collected by a coil of a magnetic resonance imaging (MRI) device in a pre-scan (In accordance with one disclosed aspect, a method comprises: acquiring initial sensitivity maps for a plurality of radio frequency coils using a magnetic resonance (MR) pre-scan of a subject [0006]) and the pre-scan being performed on a subject before an MRI scan of the subject (In accordance with another disclosed aspect, a method comprises: (i) acquiring sensitivity maps for a plurality of radio frequency coils using a magnetic resonance (MR) pre-scan of a subject [0007]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen with the teachings of Huang to acquire/store initial sensitivity maps and improve accuracy of the magnetic resonance scan data.
However, Van Wieringen and Huang do not explicitly disclose determining whether the coil has a failure based on the one or more sets of reference signals and the first fault detection model by inputting the one or more sets of reference signals into the first fault detection model; and in response to determining that the coil has a failure, displaying a warning window via a terminal to prompt an operator whether to stop a scanning, and recording a fault detection result of the coil in a log to facilitate debugging the coil.
Nevertheless, Huff discloses and in response to determining that the coil has a failure, displaying a warning window via a terminal to prompt an operator whether to stop a scanning, and recording a fault detection result of the coil in a log to facilitate debugging the coil (In one embodiment, a method comprises conducting circuit tests on at least one MR coil (which are typically part of a coil array) at predetermined intervals or upon the happening of predetermined events, and constructing data logs for each coil. Each data log is processed, filtered and analyzed in near real-time, and in one embodiment, the processor is configured to detect unique parametric data signatures that identify the possibility of a pending failure of the coil TR bias or related circuitry, also referred to as an output event [0012]; For purposes of data analysis, a display 34 is configured to provide graphical output to a user in the form of parametric data information, which includes alphanumeric (e.g., text, numbers, etc.) coil details, and graphical images (e.g., graphs and charts), etc. In one embodiment, display 34 is configured to also receive input from a user (e.g., touch screen, buttons located adjacent to the screen portion of display 34, etc.) [0044]).
Huff also discloses determining whether the coil has a failure based on the one or more sets of reference signals (System failures can cause a myriad of problems for their users including but limited to decreased image quality and complete inhibition of scanning. Generally, reasons for multi-coil system failures fall into one of three categories: (1) Physical damage to a coil, cable or connector, (2) T/R bias circuit failures, or (3) signal loss, noise or shadowing in images [0006]) and the first fault detection model by inputting the one or more sets of reference signals into the first fault detection model (As data logs are constructed, the CPU 28 is further configured to algorithmically filter and analyzing the data logs, and more specifically, the input events 202, to create an output 216 which ultimately predicts a failure event of the at least one coil 22. In analyzing the data logs from input data, the CPU 28 is configured to elicit a quantified relationship between the input 202 and the data logs to categorically form an output 216, such that a failure of coil 22, whether it be a critical or non-critical failure, is predicted by making a future decision/assumption that may be then forwarded to an operator 48 who is capable of intervening before a critical failure occurs, which would lead to workflow disruption [0032]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen and Huang with the teachings of Huff to predict by making a future decision/assumption that may be then forwarded to an operator who is capable of intervening before a critical failure occurs and improve accuracy of the magnetic resonance scan data.
Regarding Claim 10, Van Wieringen, Huang, and Huff disclose the claimed invention discussed in Claim 1.
Van Wieringen discloses the operations further: in response to determining the coil has a failure, determining a position of the failure using the first fault detection model (as discussed above).
However, Van Wieringen and Huang do not explicitly disclose determining a position of the failure using the first fault detection model, wherein the coil includes a plurality of channels, and the position of the failure includes a series number of a channel that has the failure among the plurality of channels.
Nevertheless, Huff discloses determining a position of the failure using the first fault detection model, wherein the coil includes a plurality of channels (A multi-coil includes any transmit/receive, or receive only coil that is placed on the patient table or on the patient and physically plugged into one or more of the ports on the Low Profile Carriage Assembly (LPCA) or table Ports P3-P5. The LPCA can have up to 4 ports 410-418, labeled "A", "B", "C", "L" (for legacy), (or P1 and P2 for MR750/450/450w products). Each port can have anywhere from 8 to 32 receive channels, channel 1 referenced by 420 through channel N referenced by 422, based on different configurations, and for each channel open circuit test data 424 and short circuit test data 426 [0051]), and the position of the failure includes a series number of a channel that has the failure among the plurality of channels (Conducting circuit tests at predetermined intervals to construct a log file for each physical coil configuration uses a set of "rules" starting at the Logical Coil Configuration, through the individual open and short circuit current data for each valid LPCA "P" port, and each channel of each port [0052]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen and Huang with the teachings of Huff to conduct circuit tests at predetermined intervals to construct a log file for each physical coil and improve accuracy of the magnetic resonance scan data.
Regarding Claim 12, Van Wieringen, Huang, and Huff disclose the claimed invention discussed in Claim 1.
Van Wieringen discloses the operations further comprising: in response to determining the coil has a failure (as discussed above), determining a type or a level of the failure using one or more second fault detection models different from the first fault detection model (In another embodiment execution of the instructions further cause the processor to train the trained neural network using the measurement database and/or historical gradient coil amplifier failure database. Using a historical record of when gradient coil amplifiers have failed measurement vectors can be constructed from the historical data [0024]).
However, Van Wieringen and Huang do not explicitly disclose the type of the failure includes at least one of a circuit disconnection, a failure of a receiving circuit, or a frequency offset of the coil.
Nevertheless, Huff discloses the type of the failure includes at least one of a circuit disconnection, a failure of a receiving circuit, or a frequency offset of the coil (System failures can cause a myriad of problems for their users including but limited to decreased image quality and complete inhibition of scanning. Generally, reasons for multi-coil system [0006]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen and Huang with the teachings of Huff to conduct circuit tests at predetermined intervals to construct a log file for each physical coil and improve accuracy of the magnetic resonance scan data.
Regarding Claim 14, Van Wieringen, Huang, and Huff disclose the claimed invention discussed in Claim 1.
Van Wieringen discloses obtaining device information of the MRI device (When a failure of a gradient amplifier occurs in an MRI system the measurements from sensors available in and around the gradient amplifier are collected [0079]); wherein the device information includes coil information or magnetic field information (Phased array multi-coils can be used in MRI to improve the signal-to-noise ratio (SNR) of images. The multi-coils allow large field of view imaging with the SNR of a small surface coil [0005]), and the coil information includes a size of the coil, a count of turns of the coil, a material of the coil, a type of the coil, or a count of channels of the coil (The multi-coil array 18 includes plurality of surface coils 22, which can be any number of surface coils N, each coil 22 being connected to the scanner via interface 20 [0023]); and determining whether the coil has a failure based on the one or more sets of reference signals, the first fault detection model, and the device information (The scanned parameter data may for instance be data derived from a so called pulse sequence which describes the usage of the gradient coil amplifier during the acquisition of magnetic resonance data [0025]; Next in step 202 a probability 118 of the failure of a gradient coil amplifier of a magnetic resonance imaging system calculated for a predetermined number of days in the future by inputting the measurement vector 114 into the trained neural network program 124 [0065]).
Regarding Claim 15, Van Wieringen discloses a method implemented on a computing device having at least one processor and at least one storage device, comprising: (The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A ‘computer-readable storage medium’ as used herein encompasses any tangible storage medium which may store instructions which are executable by a processor of a computing device [0006]), obtaining one or more sets of reference signals collected by a coil of a magnetic resonance imaging (MRI) device (Magnetic Resonance (MR) data is defined herein as being the recorded measurements of radio frequency signals emitted by atomic spins by the antenna of a Magnetic resonance apparatus during a magnetic resonance imaging scan [0018]; In another embodiment execution of the instructions further causes the processor to store scanned parameter data in the measurement database. Scanned parameter data as used herein is descriptive of the usage of the gradient coil amplifier during acquisition of the magnetic resonance data. The scanned parameter data may for instance be data derived from a so called pulse sequence which describes the usage of the gradient coil amplifier during the acquisition of magnetic resonance data [0025]); obtaining a first fault detection model (Execution of the instructions further cause the processor to repeatedly calculate a probability of failure of a gradient coil amplifier of the magnetic resonance imaging system a predetermined number of days in the future by inputting the measurement vector into a trained neural network program [0020]), the first fault detection model being a trained machine learning model (Execution of the instructions further cause the processor to repeatedly calculate a probability of failure of a gradient coil amplifier of the magnetic resonance imaging system a predetermined number of days in the future by inputting the measurement vector into a trained neural network program [0020]); and determining whether the coil has a failure based on the one or more sets of reference signals and the first fault detection model (The method further comprises the step of repeatedly calculating a probability of failure of a gradient coil amplifier of the magnetic resonance imaging system a predetermined number of days in the future by inputting the measurement vector into a trained neural network program [0047]).
However, Van Wieringen discloses obtaining one or more sets of reference signals collected by a coil of a magnetic resonance imaging (MRI) device in a pre-scan and the pre-scan being performed on a subject before an MRI scan of the subject; wherein the coil includes multiple channels, each of the multiple channels is configured to collect a portion of the one or more sets of reference signals; determining whether the coil has a failure based on the one or more sets of reference signals and the first fault detection model by inputting the one or more sets of reference signals into the first fault detection model; and in response to determining the coil has a failure, determining a position of the failure of the coil based on an output of the first fault detection model, displaying a warning window via a terminal to prompt an operator whether to stop a scanning, and recording a fault detection result of the coil in a log to facilitate debugging the coil, wherein the position of the failure includes a serial number of a channel that has the failure among the plurality of channels , and the output further includes the serial number when the coil has a failure.
Nevertheless, Huang discloses obtaining one or more sets of reference signals collected by a coil of a magnetic resonance imaging (MRI) device in a pre-scan (In accordance with one disclosed aspect, a method comprises: acquiring initial sensitivity maps for a plurality of radio frequency coils using a magnetic resonance (MR) pre-scan of a subject [0006]) and the pre-scan being performed on a subject before an MRI scan of the subject (In accordance with another disclosed aspect, a method comprises: (i) acquiring sensitivity maps for a plurality of radio frequency coils using a magnetic resonance (MR) pre-scan of a subject [0007]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen with the teachings of Huang to acquire/store initial sensitivity maps and improve accuracy of the magnetic resonance scan data.
However, Van Wieringen and Huang do not explicitly disclose wherein the coil includes multiple channels, each of the multiple channels is configured to collect a portion of the one or more sets of reference signals; determining whether the coil has a failure based on the one or more sets of reference signals and the first fault detection model by inputting the one or more sets of reference signals into the first fault detection model; and in response to determining the coil has a failure, determining a position of the failure of the coil based on an output of the first fault detection model, displaying a warning window via a terminal to prompt an operator whether to stop a scanning, and recording a fault detection result of the coil in a log to facilitate debugging the coil, wherein the position of the failure includes a serial number of a channel that has the failure among the plurality of channels, and the output further includes the serial number when the coil has a failure.
Nevertheless, Huff discloses the coil includes multiple channels, each of the multiple channels is configured to collect a portion of the one or more sets of reference signals (A multi-coil includes any transmit/receive, or receive only coil that is placed on the patient table or on the patient and physically plugged into one or more of the ports on the Low Profile Carriage Assembly (LPCA) or table Ports P3-P5. The LPCA can have up to 4 ports 410-418, labeled "A", "B", "C", "L" (for legacy), (or P1 and P2 for MR750/450/450w products). Each port can have anywhere from 8 to 32 receive channels, channel 1 referenced by 420 through channel N referenced by 422, based on different configurations, and for each channel open circuit test data 424 and short circuit test data 426 [0051]), determining a position of the failure of the coil based on an output of the first fault detection model, displaying a warning window via a terminal to prompt an operator whether to stop a scanning, and recording a fault detection result of the coil in a log to facilitate debugging the coil (In one embodiment, a method comprises conducting circuit tests on at least one MR coil (which are typically part of a coil array) at predetermined intervals or upon the happening of predetermined events, and constructing data logs for each coil. Each data log is processed, filtered and analyzed in near real-time, and in one embodiment, the processor is configured to detect unique parametric data signatures that identify the possibility of a pending failure of the coil TR bias or related circuitry, also referred to as an output event [0012]; For purposes of data analysis, a display 34 is configured to provide graphical output to a user in the form of parametric data information, which includes alphanumeric (e.g., text, numbers, etc.) coil details, and graphical images (e.g., graphs and charts), etc. In one embodiment, display 34 is configured to also receive input from a user (e.g., touch screen, buttons located adjacent to the screen portion of display 34, etc.) [0044]), wherein the position of the failure includes a serial number of a channel that has the failure among the plurality of channels (Conducting circuit tests at predetermined intervals to construct a log file for each physical coil configuration uses a set of "rules" starting at the Logical Coil Configuration, through the individual open and short circuit current data for each valid LPCA "P" port, and each channel of each port [0052]), and the output further includes the serial number when the coil has a failure (In one embodiment, a method comprises conducting circuit tests on at least one MR coil (which are typically part of a coil array) at predetermined intervals or upon the happening of predetermined events, and constructing data logs for each coil. Each data log is processed, filtered and analyzed in near real-time, and in one embodiment, the processor is configured to detect unique parametric data signatures that identify the possibility of a pending failure of the coil TR bias or related circuitry, also referred to as an output event [0012]).
Huff also discloses determining whether the coil has a failure based on the one or more sets of reference signals (System failures can cause a myriad of problems for their users including but limited to decreased image quality and complete inhibition of scanning. Generally, reasons for multi-coil system failures fall into one of three categories: (1) Physical damage to a coil, cable or connector, (2) T/R bias circuit failures, or (3) signal loss, noise, i.e., reference signals, or shadowing in images [0006]) and the first fault detection model by inputting the one or more sets of reference signals into the first fault detection model (As data logs are constructed, the CPU 28 is further configured to algorithmically filter and analyzing the data logs, and more specifically, the input events 202, to create an output 216 which ultimately predicts a failure event of the at least one coil 22. In analyzing the data logs from input data, the CPU 28 is configured to elicit a quantified relationship between the input 202 and the data logs to categorically form an output 216, such that a failure of coil 22, whether it be a critical or non-critical failure, is predicted by making a future decision/assumption that may be then forwarded to an operator 48 who is capable of intervening before a critical failure occurs, which would lead to workflow disruption [0032]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen and Huang with the teachings of Huff to predict by making a future decision/assumption that may be then forwarded to an operator who is capable of intervening before a critical failure occurs and improve accuracy of the magnetic resonance scan data.
Claims 3-4 and 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over Van Wieringen, Huang, and Huff, and further in view of Ookawa et al. (US20080231269) hereinafter referred to as ‘Ookawa’.
Regarding Claim 3, Van Wieringen, Huang, and Huff disclose the claimed invention discussed in Claim 1.
Van Wieringen discloses the one or more sets of reference signals include a set of signals collected in an acquisition that is performed on the subject (as discussed above).
However, Van Wieringen does not explicitly disclose the one or more sets of reference signals include a set of noise signals collected in an acquisition that is performed on the subject without applying an excitation pulse to the subject.
Nevertheless, Huang discloses collected in an acquisition that is performed on the subject without applying an excitation pulse to the subject (as discussed above).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen with the teachings of Huang to acquire/store initial sensitivity maps and improve accuracy of the magnetic resonance scan data.
However, the combination does not explicitly disclose the one or more sets of reference signals include a set of noise signals collected in an acquisition.
Nevertheless, Ookawa discloses the one or more sets of reference signals include a set of noise signals collected in an acquisition (However, another abnormality can be detected using the collected data. For example, an abnormality in the channel, a gradient magnetic field for readout, and the like can be identified through detection of a spike-shaped signal in the raw data of all channels, a spike-shaped signal in the raw data of only some channels, a constant noise generated in a readout direction of the reconstructed data, and the like [0072]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, and Huff with the teachings of Ookawa to obtain a signal to noise ratio to improve the accuracy of identifying abnormalities in the coil.
Regarding Claim 4, Van Wieringen, Huang, and Huff disclose the claimed invention discussed in Claim 3.
Van Wieringen discloses the determining whether the coil has a failure based on the one or more sets of reference signals and the first fault detection model includes (as discussed above).
However, Van Wieringen does not explicitly disclose determining a distribution of the set of noise signals; and determining whether the coil has a failure based on the distribution of the set of noise signals and the first fault detection model.
Nevertheless, Ookawa discloses determining a distribution of the set of noise signals (as discussed above); and determining whether the coil has a failure based on the distribution of the set of noise signals (However, another abnormality can be detected using the collected data. For example, an abnormality in the channel, a gradient magnetic field for readout, and the like can be identified through detection of a spike-shaped signal in the raw data of all channels, a spike-shaped signal in the raw data of only some channels, a constant noise generated in a readout direction of the reconstructed data, and the like [0072]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, and Huff with the teachings of Ookawa to obtain a signal to noise ratio to improve the accuracy of identifying abnormalities in the coil.
Regarding Claim 17, Van Wieringen, Huang, and Huff disclose the claimed invention discussed in Claim 15.
Van Wieringen discloses the one or more sets of signals collected in an acquisition that is performed on the subject (as discussed above).
However, Van Wieringen does not explicitly disclose the one or more sets of reference signals include a set of noise signals collected in an acquisition that is performed on the subject without applying an excitation pulse to the subject.
Nevertheless, Huang discloses collected in an acquisition that is performed on the subject without applying an excitation pulse to the subject (as discussed above).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen and Huff with the teachings of Huang to acquire/store initial sensitivity maps and improve accuracy of the magnetic resonance scan data.
However, the combination does not explicitly disclose the one or more sets of reference signals include a set of noise signals collected in an acquisition.
Nevertheless, Ookawa discloses the one or more sets of reference signals include a set of noise signals collected in an acquisition (However, another abnormality can be detected using the collected data. For example, an abnormality in the channel, a gradient magnetic field for readout, and the like can be identified through detection of a spike-shaped signal in the raw data of all channels, a spike-shaped signal in the raw data of only some channels, a constant noise generated in a readout direction of the reconstructed data, and the like [0072]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, and Huff with the teachings of Ookawa to obtain a signal to noise ratio to improve the accuracy of identifying abnormalities in the coil.
Regarding Claim 18, Van Wieringen, Huang, and Huff disclose the claimed invention discussed in Claim 17.
Van Wieringen discloses the determining whether the coil has a failure based on the one or more sets of reference signals and the first fault detection model includes (as discussed above).
However, Van Wieringen does not explicitly disclose determining a distribution of the set of noise signals; and determining whether the coil has a failure based on the distribution of the set of noise signals and the first fault detection model.
Nevertheless, Ookawa discloses determining a distribution of the set of noise signals (as discussed above); and determining whether the coil has a failure based on the distribution of the set of noise signals (as discussed above).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, and Huff with the teachings of Ookawa to obtain a signal to noise ratio to improve the accuracy of identifying abnormalities in the coil.
Claims 5-6, 8, 13, 19-20, and 29 are rejected under 35 U.S.C. 103 as being unpatentable over Van Wieringen, Huang, Huff, and Ookawa and further in view of Dagher et al. (US20170059682) hereinafter referred to as ‘Dagher’.
Regarding Claim 5, Van Wieringen, Huang, Huff, Ookawa disclose the claimed invention discussed in Claim 4.
However, Van Wieringen does not explicitly disclose the determining a distribution of the set of noise signals includes: obtaining a set of reference noise signals; and determining, based on the set of noise signals and the set of reference noise signals, a probability distribution line representing the distribution of the set of noise signals in a two-dimensional probability space.
Nevertheless, Ookawa discloses the determining a distribution of the set of noise signals includes (as discussed above).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen and Huang with the teachings of Ookawa to obtain a signal to noise ratio to improve the accuracy of identifying abnormalities in the coil.
However, the combination does not explicitly disclose the determining a distribution of the set of noise signals includes: obtaining a set of reference noise signals; and determining, based on the set of noise signals and the set of reference noise signals, a probability distribution line representing the distribution of the set of noise signals in a two-dimensional probability space.
Nevertheless, Dagher discloses the determining a distribution of the set of noise signals includes: obtaining a set of reference noise signals; and determining, based on the set of noise signals and the set of reference noise signals (Generally, there are three phase-imaging regimes that MR phase acquisition methods may operate in: (I) a regime dominated by phase-wrapping, with reduced levels of noise, (II) a regime dominated by noise, with minimal instances of phase-wrapping and (III) a regime where the original signal needs to be disambiguated from both phase-wrapping and noise contributions to MR phase measurement error [0050]), a probability distribution line representing the distribution of the set of noise signals in a two-dimensional probability space (This ratio approximates snr.sub.k,c in Eq. (10) which allows rapid computation of the noise probability distribution [9], phase noise standard deviation [25] and phase wrapping probability distribution [7] [0165]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, Huff, and Ookawa with the teachings of Dagher to process and interpret magnetic resonance data and improve filtering noise and accuracy of signal estimation.
Regarding Claim 6, Van Wieringen, Huang, Huff, and Ookawa disclose the claimed invention discussed in Claim 5.
Van Wieringen discloses the determining whether the coil has a failure based on the distribution of the set of signals and the first fault detection model includes (as discussed above): determine a feature vector (The measurement vector is constructed using data stored in the measurement database. Repeatedly acquiring and storing the environmental sensor data for both the examination room and the technical room enables the measurement vector to be constructed using current data [0023]); and determining whether the coil has a failure by inputting the feature vector into the first fault detection model (Using a historical record of when gradient coil amplifiers have failed measurement vectors can be constructed from the historical data. This may be used to train the neural network using standard neural network techniques and/or software tools [0024]).
However, Van Wieringen does not explicitly disclose the determining whether the coil has a failure based on the distribution of the set of noise signals and the first fault detection model includes: determine a feature vector representing the probability distribution line.
Nevertheless, Ookawa discloses the determining whether the coil has a failure based on the distribution of the set of noise signals (However, another abnormality can be detected using the collected data. For example, an abnormality in the channel, a gradient magnetic field for readout, and the like can be identified through detection of a spike-shaped signal in the raw data of all channels, a spike-shaped signal in the raw data of only some channels, a constant noise generated in a readout direction of the reconstructed data, and the like [0072]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, and Huff with the teachings of Ookawa to obtain a signal to noise ratio to improve the accuracy of identifying abnormalities in the coil.
However, the combination does not explicitly disclose determine a feature vector representing the probability distribution line.
Nevertheless, Dagher discloses the probability distribution line (In FIG. 6 and FIG. 7, Δβ = 0 Hz, and R.sub.max = 0, thus the likelihood is simply the noise distribution. In each of FIGs. 6 and 7, the dashed line is a Gaussian distribution with the same mean and standard deviation as the true noise distribution. Note the divergence between the noise probability distribution (solid curve and crosses) and the Gaussian approximation [00119]) ; and determining whether the coil has a failure by inputting the feature vector into the first fault detection model (In FIG. 6 and FIG. 7, Δβ = 0 Hz, and R.sub.max = 0, thus the likelihood is simply the noise distribution. In each of FIGs. 6 and 7, the dashed line is a Gaussian distribution with the same mean and standard deviation as the true noise distribution. Note the divergence between the noise probability distribution (solid curve and crosses) and the Gaussian approximation [00119]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, Huff, and Ookawa with the teachings of Dagher to process and interpret magnetic resonance data and improve filtering noise and accuracy of signal estimation.
Regarding Claim 8, Van Wieringen, Huang, Huff, and Ookawa disclose the claimed invention discussed in Claim 5.
However, Van Wieringen does not explicitly disclose the obtaining a set of reference noise signals includes: obtaining a plurality sets of reference noise signals, each set of reference noise signals being collected by a normal coil in an acquisition that is performed on a reference subject without applying an excitation pulse to the reference subject; and selecting the set of reference noise signals from the plurality sets of reference noise signals.
Nevertheless, Ookawa discloses the obtaining a set of reference noise signals includes (as discussed above): obtaining a plurality sets of reference noise signals (as discussed above), and selecting the set of reference noise signals (as discussed above).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, and Huff with the teachings of Ookawa to obtain a signal to noise ratio to improve the accuracy of identifying abnormalities in the coil.
However, the combination does not explicitly disclose obtaining a plurality sets of reference noise signals, each set of reference noise signals being collected by a normal coil in an acquisition that is performed on a reference subject without applying an excitation pulse to the reference subject; and selecting the set of reference noise signals from the plurality sets of reference noise signals.
Nevertheless, Dagher discloses obtaining a plurality sets of reference noise signals, each set of reference noise signals being collected by a normal coil in an acquisition that is performed on a reference subject without applying an excitation pulse to the reference subject; and selecting the set of reference noise signals from the plurality sets of reference noise signals (Generally, there are three phase-imaging regimes that MR phase acquisition methods may operate in: (I) a regime dominated by phase-wrapping, with reduced levels of noise, (II) a regime dominated by noise, with minimal instances of phase-wrapping and (III) a regime where the original signal needs to be disambiguated from both phase-wrapping and noise contributions to MR phase measurement error [0050]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, Huff, and Ookawa, with the teachings of Dagher to process and interpret magnetic resonance data and improve filtering noise and accuracy of signal estimation.
Regarding Claim 19, Van Wieringen, Huang, and Huff disclose the claimed invention discussed in Claim 18.
However, Van Wieringen does not explicitly disclose the determining a distribution of the set of noise signals includes: obtaining a set of reference noise signals; and determining, based on the set of noise signals and the set of reference noise signals, a probability distribution line representing the distribution of the set of noise signals in a two-dimensional probability space.
Nevertheless, Ookawa discloses the determining a distribution of the set of noise signals includes (as discussed above).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, and Huff with the teachings of Ookawa to obtain a signal to noise ratio to improve the accuracy of identifying abnormalities in the coil.
However, the combination does not explicitly disclose the determining a distribution of the set of noise signals includes: obtaining a set of reference noise signals; and determining, based on the set of noise signals and the set of reference noise signals, a probability distribution line representing the distribution of the set of noise signals in a two-dimensional probability space.
Nevertheless, Dagher discloses the determining a distribution of the set of noise signals includes: obtaining a set of reference noise signals; and determining, based on the set of noise signals and the set of reference noise signals (Generally, there are three phase-imaging regimes that MR phase acquisition methods may operate in: (I) a regime dominated by phase-wrapping, with reduced levels of noise, (II) a regime dominated by noise, with minimal instances of phase-wrapping and (III) a regime where the original signal needs to be disambiguated from both phase-wrapping and noise contributions to MR phase measurement error [0050]), a probability distribution line representing the distribution of the set of noise signals in a two-dimensional probability space (This ratio approximates snr.sub.k,c in Eq. (10) which allows rapid computation of the noise probability distribution [9], phase noise standard deviation [25] and phase wrapping probability distribution [7] [0165]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, Huff, and Ookawa with the teachings of Dagher to process and interpret magnetic resonance data and improve filtering noise and accuracy of signal estimation.
Regarding Claim 20, Van Wieringen, Huang, and Huff disclose the claimed invention discussed in Claim 19.
Van Wieringen discloses the determining whether the coil has a failure based the first fault detection model includes (as discussed above): determine a feature vector (as discussed above).
However, Van Wieringen does not explicitly disclose the determining whether the coil has a failure based on the distribution of the set of noise signals and the first fault detection model includes: determine a feature vector representing the probability distribution line; and determining whether the coil has a failure by inputting the feature vector into the first fault detection model.
Nevertheless, Ookawa discloses the determining whether the coil has a failure based on the distribution of the set of noise signals and the first fault detection model includes (However, another abnormality can be detected using the collected data. For example, an abnormality in the channel, a gradient magnetic field for readout, and the like can be identified through detection of a spike-shaped signal in the raw data of all channels, a spike-shaped signal in the raw data of only some channels, a constant noise generated in a readout direction of the reconstructed data, and the like [0072]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, and Huff with the teachings of Ookawa to obtain a signal to noise ratio to improve the accuracy of identifying abnormalities in the coil.
However, the combination does not explicitly disclose determine a feature vector representing the probability distribution line; and determining whether the coil has a failure by inputting the feature vector into the first fault detection model.
Nevertheless, Dagher discloses determine a feature vector representing the probability distribution line (In FIG. 6 and FIG. 7, Δβ = 0 Hz, and R.sub.max = 0, thus the likelihood is simply the noise distribution. In each of FIGs. 6 and 7, the dashed line is a Gaussian distribution with the same mean and standard deviation as the true noise distribution. Note the divergence between the noise probability distribution (solid curve and crosses) and the Gaussian approximation [00119]) ; and determining whether the coil has a failure by inputting the feature vector into the first fault detection model (In FIG. 6 and FIG. 7, Δβ = 0 Hz, and R.sub.max = 0, thus the likelihood is simply the noise distribution. In each of FIGs. 6 and 7, the dashed line is a Gaussian distribution with the same mean and standard deviation as the true noise distribution. Note the divergence between the noise probability distribution (solid curve and crosses) and the Gaussian approximation [00119]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, Huff and Ookawa with the teachings of Dagher to process and interpret magnetic resonance data and improve filtering noise and accuracy of signal estimation.
Regarding Claim 29, Van Wieringen discloses a non-transitory computer readable medium including executable instructions, the instructions, when executed by at least one processor, causing the at least one processor to effectuate a method comprising (The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A ‘computer-readable storage medium’ as used herein encompasses any tangible storage medium which may store instructions which are executable by a processor of a computing device [0006]); A hardware interface may allow a processor to send control signals or instructions to an external computing device and/or apparatus. A hardware interface may also enable a processor to exchange data with an external computing device and/or apparatus [0016]): obtaining one or more sets of reference signals collected by a coil of a magnetic resonance imaging (MRI) device (Magnetic Resonance (MR) data is defined herein as being the recorded measurements of radio frequency signals emitted by atomic spins by the antenna of a Magnetic resonance apparatus during a magnetic resonance imaging scan [0018]; In another embodiment execution of the instructions further causes the processor to store scanned parameter data in the measurement database. Scanned parameter data as used herein is descriptive of the usage of the gradient coil amplifier during acquisition of the magnetic resonance data. The scanned parameter data may for instance be data derived from a so called pulse sequence which describes the usage of the gradient coil amplifier during the acquisition of magnetic resonance data [0025]); obtaining a first fault detection model (Execution of the instructions further cause the processor to repeatedly calculate a probability of failure of a gradient coil amplifier of the magnetic resonance imaging system a predetermined number of days in the future by inputting the measurement vector into a trained neural network program [0020]), the first fault detection model being a trained machine learning model (Execution of the instructions further cause the processor to repeatedly calculate a probability of failure of a gradient coil amplifier of the magnetic resonance imaging system a predetermined number of days in the future by inputting the measurement vector into a trained neural network program [0020]); determining whether the coil has a failure based on the one or more sets of reference signals (The method further comprises the step of repeatedly calculating a probability of failure of a gradient coil amplifier of the magnetic resonance imaging system a predetermined number of days in the future by inputting the measurement vector into a trained neural network program [0047]).
However, Van Wieringen discloses obtaining one or more sets of reference signals collected by a coil of a magnetic resonance imaging (MRI) device in a pre-scan, wherein the one or more sets of reference signals include a set of noise signals collected in an acquisition that is performed on a subject without applying an excitation pulse to the subject, and the pre- scan is performed on the subject before an MRI scan of the subject; comprising: determining a probability distribution line representing a distribution of the set of noise signals in a two-dimensional probability space based on the set of noise signals and a set of reference noise signals; determining a distance between the probability distribution line and an ideal probability distribution line, the ideal probability distribution line representing an ideal distribution of noise signals collected by a normal coil; determining whether the coil has a failure based on the distance and in response to determining that the coil has a failure, displaying a warning window via a terminal to prompt an operator whether to stop a scanning, and recording a fault detection result of the coil in a log to facilitate debugging the coil.
Nevertheless, Huang discloses obtaining one or more sets of reference signals collected by a coil of a magnetic resonance imaging (MRI) device in a pre-scan (In accordance with one disclosed aspect, a method comprises: acquiring initial sensitivity maps for a plurality of radio frequency coils using a magnetic resonance (MR) pre-scan of a subject [0006]); wherein the one or more sets of reference signals in an acquisition that is performed on a subject without applying an excitation pulse to the subject (as discussed above) and the pre-scan being performed on a subject before an MRI scan of the subject (In accordance with another disclosed aspect, a method comprises: (i) acquiring sensitivity maps for a plurality of radio frequency coils using a magnetic resonance (MR) pre-scan of a subject [0007]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen with the teachings of Huang to acquire/store initial sensitivity maps and improve accuracy of the magnetic resonance scan data.
However, Van Wieringen and Huang do not explicitly disclose wherein the one or more sets of reference signals include a set of noise signals collected in an acquisition that is performed on a subject without applying an excitation pulse to the subject, determining a probability distribution line representing a distribution of the set of noise signals in a two-dimensional probability space based on the set of noise signals and a set of reference noise signals; determining a distance between the probability distribution line and an ideal probability distribution line, the ideal probability distribution line representing an ideal distribution of noise signals collected by a normal coil; determining whether the coil has a failure based on the distance and in response to determining that the coil has a failure, displaying a warning window via a terminal to prompt an operator whether to stop a scanning, and recording a fault detection result of the coil in a log to facilitate debugging the coil.
Nevertheless, Huff discloses the one or more sets of reference signals include a set of noise signals (as discussed above) and in response to determining that the coil has a failure, displaying a warning window via a terminal to prompt an operator whether to stop a scanning, and recording a fault detection result of the coil in a log to facilitate debugging the coil (In one embodiment, a method comprises conducting circuit tests on at least one MR coil (which are typically part of a coil array) at predetermined intervals or upon the happening of predetermined events, and constructing data logs for each coil. Each data log is processed, filtered and analyzed in near real-time, and in one embodiment, the processor is configured to detect unique parametric data signatures that identify the possibility of a pending failure of the coil TR bias or related circuitry, also referred to as an output event [0012]; For purposes of data analysis, a display 34 is configured to provide graphical output to a user in the form of parametric data information, which includes alphanumeric (e.g., text, numbers, etc.) coil details, and graphical images (e.g., graphs and charts), etc. In one embodiment, display 34 is configured to also receive input from a user (e.g., touch screen, buttons located adjacent to the screen portion of display 34, etc.) [0044]).
Huff also discloses determining whether the coil has a failure based on the one or more sets of reference signals (System failures can cause a myriad of problems for their users including but limited to decreased image quality and complete inhibition of scanning. Generally, reasons for multi-coil system failures fall into one of three categories: (1) Physical damage to a coil, cable or connector, (2) T/R bias circuit failures, or (3) signal loss, noise or shadowing in images [0006]) and the first fault detection model by inputting the one or more sets of reference signals into the first fault detection model (As data logs are constructed, the CPU 28 is further configured to algorithmically filter and analyzing the data logs, and more specifically, the input events 202, to create an output 216 which ultimately predicts a failure event of the at least one coil 22. In analyzing the data logs from input data, the CPU 28 is configured to elicit a quantified relationship between the input 202 and the data logs to categorically form an output 216, such that a failure of coil 22, whether it be a critical or non-critical failure, is predicted by making a future decision/assumption that may be then forwarded to an operator 48 who is capable of intervening before a critical failure occurs, which would lead to workflow disruption [0032]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen and Huang with the teachings of Huff to predict by making a future decision/assumption that may be then forwarded to an operator who is capable of intervening before a critical failure occurs and improve accuracy of the magnetic resonance scan data.
However, the combination does not explicitly disclose determining a probability distribution line representing a distribution of the set of noise signals in a two-dimensional probability space based on the set of noise signals and a set of reference noise signals; determining a distance between the probability distribution line and an ideal probability distribution line, the ideal probability distribution line representing an ideal distribution of noise signals collected by a normal coil.
Nevertheless, Dagher discloses determining a probability distribution line representing a distribution of the set of noise signals in a two-dimensional probability space based on the set of noise signals and a set of reference noise signals (In FIG. 6 and FIG. 7, ΔB=0 Hz, and R.sub.max=0, thus the likelihood is simply the noise distribution. In each of FIGS. 6 and 7, the dashed line is a Gaussian distribution with the same mean and standard deviation as the true noise distribution. Note the divergence between the noise probability distribution (solid curve and crosses) and the Gaussian approximation [0112]; The likelihood functions (Eq. (12) and Eq. (15)) are estimated at each echo time and channel. The SNR in each voxel, channel and echo time is approximated by computing the ratio of the magnitude signal to the noise standard deviation in the background region. This ratio approximates snr.sub.k,c in Eq. (10) which allows rapid computation of the noise probability distribution [9], phase noise standard deviation [25] and phase wrapping probability distribution [7] [0165]); determining a distance between the probability distribution line and an ideal probability distribution line, the ideal probability distribution line representing an ideal distribution of noise signals collected by a normal coil (The likelihood functions (Eq. (12) and Eq. (15)) are estimated at each echo time and channel. The SNR in each voxel, channel and echo time is approximated by computing the ratio of the magnitude signal to the noise standard deviation in the background region. This ratio approximates snr.sub.k,c in Eq. (10) which allows rapid computation of the noise probability distribution [9], phase noise standard deviation [25] and phase wrapping probability distribution [7] [0165]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, Huff and Ookawa with the teachings of Dagher to process and interpret magnetic resonance data and improve filtering noise and accuracy of signal estimation.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Van Wieringen, Huang, Huff, Ookawa, and Dagher and further in view of Shi et al. (US20210088605) hereinafter referred to as ‘Shi’.
Regarding Claim 7, Van Wieringen, Huang, Huff, Ookawa, and Dagher disclose the claimed invention discussed in Claim 5.
Van Wieringen discloses the first fault detection model comprising a support vector machine (SVM) model (as discussed above), wherein the determining whether the coil has a failure based on the distribution of the set of noise signals and the first fault detection model includes (as discussed above).
However, Van Wieringen, Huang, and Huff do not explicitly disclose the first fault detection model comprising a support vector machine (SVM) model, wherein the determining whether the coil has a failure based on the distribution of the set of noise signals and the first fault detection model includes: determining one or more decision boundaries based on the SVM model; determining a position of the probability distribution line relative to each of the one or more decision boundaries; and determining, whether the coil has a failure based on the position of the probability distribution line relative to each of the one or more decision boundaries.
Nevertheless, Ookawa discloses the set of noise signals (as discussed above).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen and Huang with the teachings of Ookawa to obtain a signal to noise ratio to improve the accuracy of identifying abnormalities in the coil.
However, the combination does not explicitly disclose the first fault detection model comprising a support vector machine (SVM) model, wherein the determining whether the coil has a failure based on the distribution of the set of noise signals and the first fault detection model includes: determining one or more decision boundaries based on the SVM model; determining a position of the probability distribution line relative to each of the one or more decision boundaries; and determining, whether the coil has a failure based on the position of the probability distribution line relative to each of the one or more decision boundaries.
Nevertheless, Dagher discloses determining a position of the probability distribution line relative to each of the one or more decision boundaries (as discussed above); and determining, whether the coil has a failure based on the position of the probability distribution line relative to each of the one or more decision boundaries (as discussed above).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, and Ookawa with the teachings of Dagher to process and interpret magnetic resonance data and improve filtering noise and accuracy of signal estimation.
However, the combination does not explicitly disclose the first fault detection model comprising a support vector machine (SVM) model, determining one or more decision boundaries based on the SVM model.
Nevertheless, Shi discloses a support vector machine (SVM) model (In some embodiments, the first cost function may include a mean squared loss function, a Sigmoid activation function, a softmax loss function, a cross entropy loss function, a support vector machine (SVM) hinge loss function, a Smooth L1 loss function, or the like, or any combination thereof [0125]), determining one or more decision boundaries based on the SVM model (In some embodiments, the first cost function may include a mean squared loss function, a Sigmoid activation function, a softmax loss function, a cross entropy loss function, a support vector machine (SVM) hinge loss function, a Smooth L1 loss function, or the like, or any combination thereof [0125]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, Ookawa, and Dagher with the teachings of Shi to identify fault detection to separate and classify regions of system performance and improve accuracy of fault detection.
Claims 9 and 32 are rejected under 35 U.S.C. 103 as being unpatentable over Van Wieringen, Huang, Huff, Ookawa, and Dagher, and further in view of Knierim et al. (US20210229946) hereinafter referred to as ‘Knierim’.
Regarding Claim 9, Van Wieringen, Huang, Huff, Ookawa, and Dagher disclose the claimed invention discussed in Claim 5.
However, Van Wieringen does not explicitly disclose the obtaining a set of reference noise signals includes: obtaining a plurality of sets of preliminary noise signals, each set of preliminary noise signals being collected by a coil in an acquisition that is performed on a reference subject without applying an excitation pulse to the reference subject; determining fitting parameters of a Weibull distribution model based on the plurality of sets of preliminary noise signals; and determining the set of reference noise signals based on the fitting parameters.
Nevertheless, Huang discloses signals being collected by a coil in an acquisition that is performed on a reference subject without applying an excitation pulse to the reference subject (as discussed above).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen and Huff with the teachings of Huang to acquire/store initial sensitivity maps and improve accuracy of the magnetic resonance scan data.
However, the combination does not explicitly disclose the obtaining a set of reference noise signals includes: obtaining a plurality of sets of preliminary noise signals, each set of preliminary noise signals being collected by a coil in an acquisition that is performed on a reference subject without applying an excitation pulse to the reference subject; determining fitting parameters of a Weibull distribution model based on the plurality of sets of preliminary noise signals; and determining the set of reference noise signals based on the fitting parameters.
Nevertheless, Ookawa discloses the obtaining a set of reference noise signals includes (as discussed above); the plurality of sets of noise signals (as discussed above); determining the set of reference noise signals based on the fitting parameters (as discussed above).
However, the combination does not explicitly disclose obtaining a plurality of sets of preliminary noise signals, each set of preliminary noise signals being collected by a coil in an acquisition that is performed on a reference subject without applying an excitation pulse to the reference subject; determining fitting parameters of a Weibull distribution model based on the plurality of sets of preliminary noise signals.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, and Huff with the teachings of Ookawa to plan the most effective path while minimizing drilling risks and control costs.
Nevertheless, Dagher discloses obtaining a plurality of sets of preliminary noise signals, each set of preliminary noise signals being collected by a coil in an acquisition that is performed on a reference subject (Generally, there are three phase-imaging regimes that MR phase acquisition methods may operate in: (I) a regime dominated by phase-wrapping, with reduced levels of noise, (II) a regime dominated by noise, with minimal instances of phase-wrapping and (III) a regime where the original signal needs to be disambiguated from both phase-wrapping and noise contributions to MR phase measurement error [0050]); and determining the set of reference noise signals based on the fitting parameters.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, Huff, Ookawa, and Dagher with the teachings of Shi to process and interpret magnetic resonance data and improve filtering noise and accuracy of signal estimation.
However, the combination does not explicitly disclose determining fitting parameters of a Weibull distribution model based on the plurality of sets of preliminary noise signals.
Nevertheless, Knierim discloses determining fitting parameters of a Weibull distribution model (In a non-contact diagnostics embodiment, the SC state is measured and processing methods, such as Gauss and Weibull statistical methods are used to determine the heterogeneous critical current distributions which leads to the quality, current carrying characteristics, and AC losses of HTS tapes [0283]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, Huff, Ookawa, and Dagher with the teachings of Knierim to model the time until failure and different failure patterns for the magnetic resonance system and improve accuracy of fault detection.
Regarding Claim 32, Van Wieringen, Huang, Huff, and Ookawa disclose the claimed invention discussed in Claim 5.
However, Van Wieringen does not explicitly disclose wherein the determining, based on the set of noise signals and the set of reference noise signals, a probability distribution line representing the distribution of the set of noise signals in a two-dimensional probability space includes: determining fitting parameters of a Weibull distribution model based on the set of noise signals and/or the set of reference noise signals; and determining the probability distribution line based on the fitting parameters.
Nevertheless, Huang and Huff disclose the set of noise signals and the set of reference noise signals (as discussed above), the set of noise signals and/or the set of reference noise signals (as discussed above).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, and Ookawa with the teachings of Huff to predict by making a future decision/assumption that may be then forwarded to an operator who is capable of intervening before a critical failure occurs and improve accuracy of the magnetic resonance scan data.
However, the combination does not explicitly disclose wherein the determining, based on the set of noise signals and the set of reference noise signals, a probability distribution line representing the distribution of the set of noise signals in a two-dimensional probability space includes: determining fitting parameters of a Weibull distribution model based on the set of noise signals and/or the set of reference noise signals; and determining the probability distribution line based on the fitting parameters.
Nevertheless, Dagher discloses a probability distribution line representing the distribution a two-dimensional probability space (as discussed above) and determining the probability distribution line (as discussed above).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, Huff, and Ookawa with the teachings of Dagher to predict by making a future decision/assumption that may be then forwarded to an operator who is capable of intervening before a critical failure occurs and improve accuracy of the magnetic resonance scan data.
However, the combination does not explicitly disclose determining fitting parameters of a Weibull distribution model based on the set of noise signals and/or the set of reference noise signals.
Nevertheless, Knierim discloses a Weibull distribution model (In a non-contact diagnostics embodiment, the SC state is measured and processing methods, such as Gauss and Weibull statistical methods are used to determine the heterogeneous critical current distributions which leads to the quality, current carrying characteristics, and AC losses of HTS tapes [0283]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, Huff, Ookawa, and Dagher with the teachings of Knierim to predict by making a future decision/assumption that may be then forwarded to an operator who is capable of intervening before a critical failure occurs and improve accuracy of the magnetic resonance scan data.
Claim 30 is rejected under 35 U.S.C. 103 as being unpatentable over Van Wieringen, Huang, and Huff, and further in view of Dagher.
Regarding Claim 30, Van Wieringen, Huang, and Huff disclose the claimed invention discussed in Claim 1.
Van Wieringen discloses the determining whether the coil has a failure (as discussed above) and the first fault detection model (as discussed above), and determining whether the coil has a failure (as discussed above).
However, Van Wieringen does not explicitly disclose the coil has a failure based on the one or more sets of reference signals and the first fault detection model, comprises: determining a probability distribution line representing a distribution of a set of noise signals in a two-dimensional probability space based on the set of noise signals and a set of reference noise signals; and determining a distance between the probability distribution line and an ideal probability distribution line, the ideal probability distribution line representing an ideal distribution of noise signals collected by a normal coil; and determining whether the coil has a failure based on the distance.
Nevertheless, Huang and Huff disclose the coil has a failure based on the one or more sets of reference signals and the first fault detection model, comprises (as discussed above): and determining whether the coil has a failure (as discussed above).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen and Huang with the teachings of Huff to predict by making a future decision/assumption that may be then forwarded to an operator who is capable of intervening before a critical failure occurs and improve accuracy of the magnetic resonance scan data.
However, Van Wieringen, Huang, and Huff do not explicitly disclose the coil has a failure based on the one or more sets of reference signals and the first fault detection model, comprises: determining a probability distribution line representing a distribution of a set of noise signals in a two-dimensional probability space based on the set of noise signals and a set of reference noise signals; and determining a distance between the probability distribution line and an ideal probability distribution line, the ideal probability distribution line representing an ideal distribution of noise signals collected by a normal coil; and determining whether the coil has a failure based on the distance.
Nevertheless, Dagher discloses determining a probability distribution line representing a distribution of a set of signals in a two-dimensional probability space based on the set of signals (as discussed above); and determining a distance between the probability distribution line by a normal coil (as discussed above); and determining whether the coil has a failure based on the distance.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, and Huff with the teachings of Dagher to process and interpret magnetic resonance data and improve filtering noise and accuracy of signal estimation.
Claim 31 is rejected under 35 U.S.C. 103 as being unpatentable over Van Wieringen, Huang, and Huff, and further in view of Sofka et al. (US20180144467) hereinafter referred to as ‘Sofka’.
Regarding Claim 31, Van Wieringen, Huang, and Huff disclose the claimed invention discussed in Claim 1.
Van Wieringen discloses the operations further comprising: obtaining environmental information of the MRI device (The multiple data values comprise examination room data descriptive of the environmental conditions of an examination room of a magnetic resonance imaging system [0046]), wherein the environmental information (as discussed above), the first fault detection model (as discussed above).
However, Van Wieringen does not explicitly disclose the operations further comprising: obtaining environmental information of the MRI device, wherein the environmental information includes information relating to electromagnetic interference; and determining whether the coil has a failure based on the one or more sets of reference signals, the first fault detection model, and the environmental information.
Nevertheless, Huang discloses the one or more sets of reference signals ( as discussed above).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen and Huang with the teachings of Huff to predict by making a future decision/assumption that may be then forwarded to an operator who is capable of intervening before a critical failure occurs and improve accuracy of the magnetic resonance scan data.
However, the combination does not explicitly disclose wherein the environmental information includes information relating to electromagnetic interference; and determining whether the coil has a failure based on the one or more sets of reference signals, the first fault detection model, and the environmental information.
Nevertheless, Sofka discloses wherein the environmental information includes information relating to electromagnetic interference (Slides 3860 include electromagnetic shielding 3865, which can be made from any suitable conductive or magnetic material, to form a moveable shield to attenuate electromagnetic noise in the operating environment of the portable MRI system to shield the imaging region from at least some electromagnetic noise, i.e. electromagnetic noise [0105]); and the environmental information (Slides 3860 include electromagnetic shielding 3865, which can be made from any suitable conductive or magnetic material, to form a moveable shield to attenuate electromagnetic noise in the operating environment of the portable MRI system to shield the imaging region from at least some electromagnetic noise [0105]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Van Wieringen, Huang, and Huff with the teachings of Sofka to form a moveable shield to attenuate electromagnetic noise in the operating environment of the portable MRI system and improve accuracy of the magnetic resonance scan data.
Response to Arguments
35 USC § 101
Applicant’s arguments with respect to claims 1, 3-10, 12, 14-15, 17-20, and 29-32 have been considered but are moot in view of new grounds of rejection.
Applicant argues (pg. 3): ” The Office Action characterizes the feature of "determining whether the coil has a failure based on the one or more sets of reference signals and the first fault detection model" as a "mental process." Applicant respectfully disagrees. Under the USPTO guidance, a claim recites a mental process only when the
claim limitations can practically be performed in the human mind or with pen and paper. That is not the case here. “
Examiner disagrees and submits “determining whether the coil has a failure based on the one or more sets of reference signals and the first fault detection model” was treated as belonging to mental process grouping can be performed in the mind because the user makes mental decisions (evaluation/judgement) regarding to determining whether the coil has a failure. According to MPEP 2106.94(a)(2) III, “a claim to "collecting information, analyzing it, and displaying certain results of the collection and analysis," where the data analysis steps are recited at a high level of generality such that they could practically be performed in the human mind, Electric Power Group v. Alstom, S.A., 830 F.3d 1350, 1353-54, 119 USPQ2d 1739, 1741-42 (Fed. Cir. 2016)”.
Applicant argues (pg. 3): “The amended claims are directed to a specific MRI hardware diagnostic workflow involving:" acquiring low-level reference signals collected from a coil of an MRI device during a pre-scan operation; processing the reference signals using a trained fault detection model;. automatically generating a warning window via a terminal to interrupt or prevent continued MRI scanning; and automatically recording fault detection results into a debugging log. A human mind cannot practically perform these operations in the context of an MRI pre-scan environment. In particular, a person cannot mentally receive and process electromagnetic reference signals from MRI coil channels in real time, execute trained machine learning model inference on such signals, automatically generate scan- interrupt warning windows on an MRI terminal, or automatically generate hardware debugging logs for the MRI system.”
Examiner submits that the amended claims include a model which is broadly recited and is treated as abstract falling under math and mental process grouping, while the “displaying a warning window…” is treated as a post solution activity. Additionally, the amended claims do not include “automatically recording…”.
Applicant argues (pg. 5): The amended claims address a concrete technical problem arising in MRI systems. Conventionally, when an MRI receiving coil develops a hardware failure, the failure is often discovered only after completion of a lengthy MRI scan and reconstruction of unusable images containing severe artifacts. This results in wasted scanner time, repeated scans, patient inconvenience, and reduced operational efficiency. The amended claims introduce a specific safeguard mechanism integrated into the MRI operational workflow. In particular, once the trained model determines that a coil failure is likely present, the system immediately triggers the terminal to display a specific warning window, actively intervening and prompting the operator to stop the current scanning action; simultaneously, a dedicated hardware log is generated for subsequent debugging. These features are not directed merely to analyzing data in the abstract. Instead, they improve the operation and reliability of a specific MRI system by preventing faulty scans from continuing and by facilitating hardware diagnosis and maintenance.”
Examiner submits that amended claim’s limitation” …displaying a warning window via a terminal to prompt an operator…” is treated as displaying results of the analysis similar to Electric Power Group and it does not indicate an improvement in technology.
Applicant argues (pg. 7): “As discussed above, Applicant's claims are not directed to an abstract idea. Thus, the "significantly more" inquiry under the Alice test does not even apply to Applicant's claims. Even assuming arguendo that the pending claims are directed to an abstract idea, which Applicant does not concede, the Office fails to satisfy the "significantly more" inquiry of Step 2B. M.P.E.P. § 2106.05 sets forth a number of examples that "the courts have found to qualify as 'significantly more' when recited in a claim with a judicial exception." The examples include "[i]mprovements to the functioning of a computer" or "[a]dding a specific limitation other than what is well-understood, routine, conventional activity in the field, or adding unconventional steps that confine the claim to a particular useful application." Applicant respectfully submits that even if the amended claims were drawn to an abstract idea, which it is not, the rejection is improper because they recite elements that qualify as "significantly more" under at least these considerations endorsed by M.P.E.P. § 2106.05.
Examiner disagrees and submits that the amended limitations are treated as abstract. Additionally, the rejection states that the additional elements are not sufficient and that they are well-understood and conventional and do not qualify as “significantly more”.
Applicant argues (pg. 7): “The Office Action asserts that the additional elements are merely generic computer components and routine data gathering activities. Applicants respectfully submit that this characterization oversimplifies the claimed invention and ignores the ordered technological combination recited in the claims.
In the MRI field, the claimed integration of pre-scan signal acquisition, machine- learning-based coil fault diagnosis, operational scan intervention, and automated debugging-log generation is not a well-understood, routine, or conventional activity.
The cited references likewise do not establish that the claimed ordered combination was conventional. At most, the cited art discusses isolated aspects of MRI monitoring or neural-network analysis. The claims, however, recite a specific coordinated MRI fault-management workflow tied to scanner operation and hardware debugging. The amended claims therefore provide significantly more than any alleged abstract idea and satisfy Step 2B of the Alice/Mayo framework”.
Examiner disagrees and submits that Claim 29 limitations include a non-transitory computer readable medium which was identified as generic computer components and is not qualified as a particular machine. Additionally, amended claims are lacking meaningful additional and/or significantly more elements and are executing by the abstract idea and they must be executed by meaningful additional elements.
35 USC § 103
Applicant’s arguments with respect to claims 1, 3-10, 12, 14-15, 17-20, and 29-32 have been considered but are moot in view of new grounds of rejection.
With regards to “Van Wieringen is directed to calculating the probability that gradient coil amplifier failure will occur. Van Wieringen, paragraph [0001].
Specifically, Van Wieringen recites: "Step 200 is to construct a measurement vector 114 which comprises multiple data values using the measurement database 116. The multiple data values comprise examination room data descriptive of the environmental conditions of an examination room of a magnetic resonance imaging system. The multiple data values further comprises technical room data descriptive of the environmental conditions of a technical room of the magnetic resonance imaging system. Next in step 202 a probability 118 of the failure of a gradient coil amplifier of a
magnetic resonance imaging system calculated for a predetermined number of days in the future by inputting the measurement vector 114 into the trained neural network program 124." Van Wieringen, paragraph [0065].”
Examiner submits that Van Wieringen is analogous art with a focus on failure of a coil and using machine learning to increase accuracy of diagnostics.
With regards to “According to the disclosure of Van Wieringen set forth above, the input of Van Wieringen trained neural network program 124 is a "measurement vector 114", which is constructed from fundamentally different types of data of amended claim 1. Specifically, the measurement vector 114 comprises environmental data (e.g., temperature, humidity) and "scanned parameter data." The scanned parameter data is expressly defined as data descriptive of the usage of the gradient coil amplifier during an MRI scan, such as the number of switching operations, total scan time, average/peak RMS current, and the pulse sequence used. Van Wieringen, paragraphs [0025]-[0026]”.
According to the specification a reference signal “may include a set of MR signals collected in an acquisition that is performed on the subject… [0006]”, “the one or more sets of reference signals may include a set of noise signals collected in an acquisition that is performed on the subject without applying an excitation pulse to the subject [0007]”, and “obtain one or more sets of reference signals (also referred to as pre-scan signals)” [0065] ‘’. The claim did not specify what type of data a reference signal represented.
With regards to “Huang does not remedy the deficiencies of Van Wieringen. Huang is directed to a method for parallel MR imaging in which initial coil sensitivity maps are acquired via a pre-scan and then corrected for subject motion before being used in the partially parallel reconstruction of subsequently acquired imaging data, thereby maintaining a high acceleration factor while improving sensitivity map accuracy and reducing motion artifacts. Huang, paragraphs [0006]-[0007]… According to the disclosure of Huang set forth above, Huang uses an MR pre- scan to acquire initial sensitivity maps for a plurality of radio frequency coils, however, the initial sensitivity maps are used for image reconstruction and motion correction. Huang uses these sensitivity maps to correct subsequently acquired diagnostic MR data by filling k-space or adjusting reconstruction weights to compensate for subject motion. Accordingly, Huang is entirely silent on any concept of coil fault detection, coil failure determination, or using a machine learning model for coil failure diagnostics.”.
The Examiner submits that Huang was used to address the limitation of a “pre-scan” and not coil fault detection or machine learning. According to MPEP 2145, “One cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. In re Keller, 642 F.2d 413, 208 USPQ 871
(CCPA 1981); In re Merck & Co., Inc., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Where a rejection of a claim is based on two or more references, a reply that is limited
to what a subset of the applied references teaches or fails to teach, or that fails to
address the combined teaching of the applied references may be considered to be an
argument that attacks the reference(s) individually. Where an applicant’s reply
establishes that each of the applied references fails to teach a limitation and addresses
the combined teachings and/or suggestions of the applied prior art, the reply as a whole
does not attack the references individually as the phrase is used in Keller and reliance
on Keller would not be appropriate. This is because "[T]he test for obviousness is what
the combined teachings of the references would have suggested to [a PHOSITA]." In re
Mouttet, 686 F.3d 1322, 1333, 103 USPQ2d 1219, 1226 (Fed. Cir. 2012).”
With regards to “In addition, Van Wieringen aims to predict hardware component failure, while Huang aims to improve MR image accuracy. A person of ordinary skill in the art would have no motivation to combine Van Wieringen and Huang to arrive at the solution of the present invention. Therefore, Applicant respectfully submits that Van Wieringen and Huang, do not teach or disclose, inter alia, "determining whether the coil has a failure based on the one or more sets of reference signals and the first fault detection model by inputting the one or more sets of reference signals into the first fault detection model" as recited in amended claim 1”.
The Examiner submits that the references in combination with Huff is used to address “determining whether the coil has a failure based on the one or more sets of reference signals and the first fault detection model by inputting the one or more sets of reference signals into the first fault detection model” above.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHARAH ZAAB whose telephone number is (571)272-4973. The examiner can normally be reached Monday - Friday 7:00 am - 4:30 pm.
/SHARAH ZAAB/Examiner, Art Unit 2857
/ALEXANDER SATANOVSKY/Primary Examiner, Art Unit 2857
Prosecution Insights