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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 11/19/2024 was filed in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Specification
The disclosure is objected to because of the following informalities:
[0027]: As written it reads “Usually, ultrasound systems implement hardware to reduce the amount of EM emissions caused by the ultrasound systems, such as Faraday cages in the chassis of the ultrasound system, shields over IC’s and/or PCBs, cable shielding, ground clamps, and the like”. However, this is the first indication of the terms “IC” and “PCB” therefore, the terms should be spelled out to provide clarity.
[0028]: As written it reads “The detector can automatically determine whether a noise process (e.g., EM emissions, or another noise process) is at is at an acceptable level and the controller 105 can take a corrective action to reduce the noise process prior to and/or during using the ultrasound system”. However, to correct the typo the second instance of “is at” should be deleted.
[0037]: As written it reads “In at least some embodiments, the current generator generates an AC current at 100 MHz or a harmonic of 100MHz for impedance measurement”. However, this is the first indication of the term “AC” therefore the term should be spelled out to provide clarity.
[0039]: As written it reads “If “yes” for the FPGA, then controller105 can move to the ADC and enable its indirect detector to measure grounding impedance”. However, to correct the typo “controller105” should be “controller 105”.
[0050]: As written it reads “enabling a calibration routine (e.g., reconfigured a digital filter’s notch level or cutoff frequency, redistribute gain throughout an amplifier chain, etc., to match a target parameter, such as, for example, SNR)”. However, this is the first indication of the term “SNR”, therefore, the term should be spelled out to provide clarity.
[0086]: As written it reads “such as a non-transitory machine readable storage media, such as volatile DRAM or nonvolatile flash memory”. However, this is the first indication of the term “DRAM” therefore, the term should be spelled out to provide clarity.
Appropriate correction is required.
Claim Objections
Claim 2 is objected to because of the following informalities:
Regarding claim 2, the claim reads “wherein the sensor data includes at least one of an amount of RF content […]”. However, this is the first instance of the term “RF”, therefore, the term should be spelled out to provide clarity.
Appropriate correction is required.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-4, 6, 11-15, 17 and 20 is/are rejected under 35 U.S.C. 103 as being anticipated by Ziv-Ari et al. US 2012/0065509 A1 “Ziv-Ari” and further in view of Lundberg et al. US 2020/0088862 A1 “Lundberg”.
Regarding claims 1 and 12, Ziv-Ari teaches “An ultrasound machine comprising:” (Claim 1) (“FIG. 1 is a schematic diagram of an ultrasound imaging system 100. The ultrasound imaging system 100 includes an ultrasound probe 109, a user interface 115, a processor 116, a memory 120 and a display 118” [0021]. Therefore, an ultrasound machine is described.);
“A method implemented by an ultrasound machine comprising an image processor, at least one sensor implemented at least partially in hardware that is coupled to the image processor, and a circuit coupled to the image processor, the method comprising:” (Claim 12) (“FIG. 4 is a flowchart illustrating a method 250 in accordance with an embodiment. An ultrasound imaging system such as the ultrasound imaging system 100 (shown in FIG. 1) may be used to perform the method 250” [0031]; “According to an embodiment, the ultrasound probe 109 of ultrasound imaging system 100 may optionally include a sensor 121. Other embodiments may include probes with multiple sensors. The sensor 121 may be connected to the processor 116 by an electrical connection 122. The sensor 121 is adapted to detect an electromagnetic noise signal while the transducer array 106 is detecting ultrasonic energy” [0023]. As shown in FIG, 1, the ultrasound imaging system 100 (i.e. ultrasound machine) comprises: 1) an image processor (i.e. a processor 116), 2) at least one sensor (i.e. sensor 121) implemented at least partially in hardware (i.e. within ultrasound probe 109) that is coupled to the image processor (i.e. connected to the processor 116), and 3) a circuit (i.e. probe/SAP electronics 107) coupled to the image processor (i.e. 116). Therefore, the method shown in FIG. 4 is implemented by an ultrasound machine comprising an image processor, at least one sensor implemented at least partially in hardware that is coupled to the image processor, and a circuit coupled to the image processor.); and
“an image processor configured to generate an ultrasound image based on ultrasound data received from an ultrasound scanner as part of an ultrasound examination” (Claim 1); “generating, by the image processor, an ultrasound image based on ultrasound data received from an ultrasound scanner as part of an ultrasound examination” (Claim 12) (“The ultrasound probe 109 includes a plurality of transducer elements 104 arranged in a transducer array 106, and probe/sub-aperture processor (SAP) electronics 107, hereinafter probe/SAP electronics 107. […] The transducer elements 104 in the transducer array 106 emit ultrasonic signals into the tissue of the patient being examined. The ultrasonic signals are backscattered from structures in the body, like blood cells or muscular tissue, to produce echoes that return to the elements 104. The echoes are converted into electrical signals, or ultrasound data, by the elements 104 and the electrical signals are received by the processor 116” [0021]; “The processor 116 may also be used to process the ultrasound data and prepare frames of ultrasound information for display on the display 118. The processor 116 may be adapted to perform one or more processing operations on the ultrasound information according to a plurality of selectable ultrasound modalities” [0022]. Additionally, step 260 of FIG. 4 involves generating an image. Therefore, the ultrasound machine includes an image processor (i.e. 116) configured to generate an ultrasound image (see [0022]) based on ultrasound data received from an ultrasound scanner (i.e. ultrasound probe 109) as part of an ultrasound examination. Furthermore, the method involves generating, by the image processor, an ultrasound image based on ultrasound data received from an ultrasound scanner as part of an ultrasound examination.);
“at least one sensor configured to generate, during the ultrasound examination, sensor data indicative of an operating environment within the ultrasound machine” (Claim 1); “generating, by the at least one sensor during the ultrasound examination, sensor data indicative of an operating environment within the ultrasound machine” (Claim 12) (See [0023] above and “Referring to FIG. 4, at step 254, the processor 116 (shown in FIG. 1) analyzes the ultrasound data. According to an embodiment, the processor 116 may analyze the ultrasound data in order to identify coherent noise, such as electromagnetic noise” [0033]. Therefore, the ultrasound machine includes at least one sensor (i.e. 121) configured to generate, during the ultrasound examination, sensor data indicative of an operating environment (i.e. electromagnetic noise signal) within the ultrasound machine. Furthermore, the method involves generating, by the at least one sensor (i.e. 121) during the ultrasound examination, sensor data indicative of an operating environment (i.e. electromagnetic noise signal) within the ultrasound machine.); and
Although Ziv-Ari discloses analyzes ultrasound data in order to identify coherent noise, such as electromagnetic noise (see [0033]) and “the processor 116 removes the estimated electromagnetic noise signal from the ultrasound data” [0035], Ziv-Ari does not teach “a circuit configured to generate, during the ultrasound examination and based on at least one of the sensor data and the ultrasound image, a probability that the ultrasound image includes artifacts from electromagnetic emissions” (Claim 1); “generating, by the circuit during the ultrasound examination, and based on at least one of the ultrasound image and the sensor data, a probability that the ultrasound image includes artifacts from the electromagnetic emissions” (Claim 12).
Lundberg is within the same field of endeavor as the claimed invention because it involves an ultrasound system which identifies faults and errors (see [Abstract]).
Lundberg teaches “a circuit configured to generate, during the ultrasound examination and based on at least one of the sensor data and the ultrasound image, a probability that the ultrasound image includes artifacts from electromagnetic emissions” (Claim 1); “generating, by the circuit during the ultrasound examination, and based on at least one of the ultrasound image and the sensor data, a probability that the ultrasound image includes artifacts from the electromagnetic emissions” (Claim 12) (“FIG. 2A shows a representative ultrasound image 80 taken from a fully operation ultrasound imaging system, while FIG. 2B shows an image 82 having noise problems and malfunctioning receive channels. The image 82 has a number of artifacts such as a pattern of dark beam lines 84 corresponding to the malfunctioning receive channels and a pattern of white streaks having increase noise. To a trained ultrasound technician such artifacts suggest where the faults or error conditions in the ultrasound imaging system are occurring. By detecting these types of errors, the processor in the ultrasound system of the disclosed technology can compensate for the artifacts” [0018]; “During use, the trained neural network 170 is configured to receive input image data of the same size with which the neural network was trained (e.g. 256×128×1) and to produce an output data indicating the probability of the image having been obtained with an imaging system or transducer having a particular fault or error condition. In one embodiment, the output from the neural network (return values from the trained neural network) is a list of faults or error conditions that the neural network 170 has been trained to detect and a probability or likelihood that an input image was captured by a transducer or imaging system having a particular fault/error condition. For example, in one embodiment, the system is trained to detect 200 known faults or error conditions. The neural network 170 therefore returns a 200 element array or a list with the probability (e.g. percentage) that an image is obtained with a transducer or imaging system having one or more of the known 200 faults/error conditions” [0034].
As shown in FIG. 2B, the image includes artifacts/noise problems (i.e. caused by electromagnetic emissions) which need to be compensated for. These artifacts are present due to a particular fault or error within the ultrasound system. In this case, since the trained neural network 170 receives an input image and outputs data indicating the probability that the image has been obtained with an imaging system or transducer having a particular fault or error (i.e. causing electromagnetic emissions/noise within the image), the trained neural network 170 is a circuit configured to generate, during the ultrasound examination and based on at least one of the sensor data and the ultrasound image (i.e. specifically the ultrasound image), a probability that the ultrasound image includes artifacts (i.e. noise, see FIG. 2B) from electromagnetic emissions. Additionally, the method involves generating, by the circuit during the ultrasound examination, and based on at least one of the ultrasound image and the sensor data, a probability that the ultrasound image includes artifacts from the electromagnetic emissions.).
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 ultrasound machine and the method of Ziv-Ari so as to include a circuit configured to perform the step of generating, based on at least one of the sensor data and the ultrasound image, a probability that the ultrasound image includes artifacts from electromagnetic emissions as disclosed in Lundberg in order to detect faults or errors caused by electromagnetic emissions (i.e. noise) such that they can be compensated for (see Lundberg: [0015]). Outputting a probability that the ultrasound image includes artifacts from electromagnetic emissions (i.e. noise) is one of a finite number of techniques which can be used to verify whether there is a need compensate for faults/errors in an imaging system with a reasonable expectation of success. Thus, modifying the ultrasound machine and the method of Ziv-Ari so as to include a circuit configured to perform the step of generating, based on at least one of the sensor data and the ultrasound image, a probability that the ultrasound image includes artifacts from electromagnetic emissions as disclosed in Lundberg would yield the predictable result of facilitating the identification of faults or errors caused by electromagnetic emissions (i.e. noise) such that they can be compensated for (see Lundberg: [0015]).
Regarding claims 2 and 13, Ziv-Ari in view of Lundberg discloses all features of the claimed invention as discussed with respect to claims 1 and 12 above, and Ziv-Ari further teaches "wherein the sensor data includes as least one of an amount of RF content, an impedance, a temperature, a torque, a strain, and an amount of light” (Claim 2); “wherein the sensor data includes as least one of an amount of RF content, an impedance, a temperature, a torque, a strain, an amount of light, or a number of open/close cycles of a display of the ultrasound machine” (Claim 13) (“FIG. 7 is a schematic representation of a sensor 160 that could be used in place of the sensor 121 according to an embodiment. […] The resistor 162 and the capacitor 164 are connected in an RC circuit designed to have an electrical impedance similar to that of a transducer element in the transducer array 148 (shown in FIG. 6) […] The sensor 160 is designed to approximate the electrical impedance of a transducer element 104 (shown in FIG. 1)” [0042]. Therefore, since the sensor 160 (i.e. used in place of sensor 121) is designed to approximate the electrical impedance of a transducer element 104, the at least one sensor includes an impedance sensor (i.e. sensor 160). Furthermore, the sensor data includes an impedance.).
Regarding claims 3 and 14, Ziv-Ari in view of Lundberg discloses all features of the claimed invention as discussed with respect to claims 1 and 12 above, and Lundberg further teaches “wherein the circuit is implemented to generate the probability based on a comparison of the ultrasound image and an additional ultrasound image that lacks the artifacts from electromagnetic emissions” (Claim 3); “further comprising: generating, by the circuit, the probability based on a comparison of the ultrasound image and an additional ultrasound image that lacks the artifacts from electromagnetic emissions” (Claim 14) (See Lundberg: [0018], [0034] as discussed with respect to claims 1 and 12 above and “The neural network 170 should identify the fault based on changes in the ultrasound image data versus image data from a normally operating transducer/ultrasound system” [0033]. In this case, since the neural network 170 identifies the fault based on changes in the ultrasound image data (i.e. ultrasound system functioning with a particular fault or error condition) versus image data from a normally operating transducer/ultrasound system, the circuit is implemented to generate the probability based on a comparison of the ultrasound image and an additional ultrasound image that lacks the artifacts from electromagnetic emissions (i.e. noise, representing a particular fault or error condition).).
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 ultrasound machine and the method of Ziv-Ari so as to include a circuit configured to perform the step of generating the probability based on a comparison of the ultrasound image and an additional ultrasound image that lacks the artifacts from electromagnetic emissions (i.e. noise) as disclosed in Lundberg in order to detect faults or errors caused by electromagnetic emissions (i.e. noise) such that they can be compensated for (see Lundberg: [0015]). Outputting a probability that the ultrasound image includes artifacts from electromagnetic emissions (i.e. noise) is one of a finite number of techniques which can be used to verify whether there is a need compensate for faults/errors in an imaging system with a reasonable expectation of success. Thus, modifying the ultrasound machine and the method of Ziv-Ari so as to include a circuit configured to perform the step of generating, the probability based on a comparison of the ultrasound image and an additional ultrasound image that lacks the artifacts from electromagnetic emissions (i.e. noise) as disclosed in Lundberg would yield the predictable result of facilitating the identification of faults or errors caused by electromagnetic emissions (i.e. noise) such that they can be compensated for (see Lundberg: [0015]).
Regarding claims 4 and 15, Ziv-Ari in view of Lundberg discloses all features of the claimed invention as discussed with respect to claims 1 and 12 above, and Ziv-Ari further teaches “further comprising: a controller implemented to, based on the probability, take a corrective action to reduce the electromagnetic emissions” (Claim 4); “wherein the ultrasound machine further comprises a controller, and the method further comprises: taking, by the controller and based on the probability, a corrective action to reduce the electromagnetic emissions” (Claim 15) (“At step 304, the sensor 121 is used to detect an electromagnetic noise signal while the transducer array 104 is acquiring ultrasound data. At step 306, the processor 116 removes the electromagnetic noise signal from each of the plurality of signals of the ultrasound data. For example, the processor may subtract the electromagnetic noise signal from each of the plurality of signals. According to an embodiment, the processor 116 may process the electromagnetic noise signal with one or more of the following: filtering the electromagnetic noise signal, scaling the electromagnetic noise signal, and applying a phase delay to the electromagnetic noise signal” [0039]. In this case, since the processor 116 removes the electromagnetic noise signal (i.e. detected by sensor 121), the processor 116 acts as a controller implemented to take a corrective action to reduce electromagnetic emissions (i.e. remove electromagnetic noise signal). Therefore, the ultrasound machine further comprises a controller, implemented to, based on the probability, take a corrective action to reduce the electromagnetic emissions. Furthermore, the method comprises: taking, by the controller and based on the probability, a corrective action to reduce the electromagnetic emissions.).
Regarding claims 6 and 17, Ziv-Ari in view of Lundberg discloses all features of the claimed invention as discussed with respect to claims 1 and 12 above, and Ziv-Ari further teaches “wherein the at least one sensor includes an impedance sensor, and the sensor data includes an impedance” (Claim 6); “wherein the at least one sensor includes at least one of an impedance sensor, or a light sensor” (Claim 17) (See [0042] as discussed with respect to claims 2 and 13 above. Therefore, since the sensor 160 (i.e. used in place of sensor 121) is designed to approximate the electrical impedance of a transducer element 104, the at least one sensor includes an impedance sensor (i.e. sensor 160), and the sensor data includes an impedance. Furthermore, the at least one sensor includes at least one of an impedance sensor, or a light sensor, specifically an impedance sensor.).
Regarding claims 11 and 20, Ziv-Ari in view of Lundberg discloses all features of the claimed invention as discussed with respect to claims 1 and 12 above, and Lundberg further teaches “further comprising: an additional circuit configured to determine a source circuit of the electromagnetic emissions within the ultrasound machine; and a controller coupled to the additional circuit and configured to disable the source circuit; and enable an additional source circuit that is redundant to the source circuit” (Claim 11); “wherein the ultrasound machine further comprises an additional circuit coupled to the circuit, and a controller coupled to the circuit, and the method further comprises: determining, by the additional circuit, a source circuit of the electromagnetic emissions within the ultrasound machine; disabling, by the controller, the source circuit; and enabling, by the controller, an additional source circuit that is redundant to the source circuit” (Claim 20) (“In one embodiment, beamforming circuitry for a number of transmit/receive channels is connected to transducer elements through a programmable multiplexer. A processor controls a self-test in which the multiplexer is set to disconnect one or more transducer probes from the beamforming circuitry. A test pulse is generated while the transducer(s) are disconnected. Faults are detected based on the measured current drawn from the power supply with the test pulse. If current is detected, transmit pulsers could be selectively disabled to isolate the channel with a fault. Depending upon the extent of the fault, the processor can compensate thereafter” [0004]; “If the processor determines that the fault causing the artifact may further damage the imaging system, then the processor may disable further imaging until the fault can be repaired” [0018].
In this case, the processor controls a self-test in which the multiplexer disconnects one or more transducer probes (i.e. connected to channels) from the beamforming circuitry to selectively disable the channel(s) with a fault (i.e. electromagnetic emissions/noise). Therefore, the ultrasound machine further comprises an additional circuit (i.e. beamforming circuitry in combination with the processor) configured to determine a source circuit of the electromagnetic emissions (i.e. channel with a fault resulting in electromagnetic emissions/noise) within the ultrasound machine, and a controller coupled to the additional circuit and configured to disable the source circuit (i.e. disconnect the channel with a fault resulting in electromagnetic emissions/noise) and enable an additional source circuit (i.e. channel connected to transducer probe) that is redundant to the source circuit. Additionally, the ultrasound machine further comprises an additional circuit (i.e. beamforming circuity, in combination with the processor) coupled to the circuit, and a controller coupled to the circuit, and the method further comprises: determining, by the additional circuit, a source circuit of the electromagnetic emissions within the ultrasound machine (i.e. channel with a fault resulting in electromagnetic emissions/noise); disabling, by the controller, the source circuit (i.e. with the fault); and enabling, by the controller, an additional source circuit (i.e. a channel connected to a transducer probe without faults) that is redundant to the source circuit.).).
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 ultrasound machine and method of Ziv-Ari such that it includes an additional circuit configured to determine a source circuit of the electromagnetic emissions within the ultrasound machine and a controller coupled to the additional circuit and configured to disable the source circuit and enable an additional source circuit that is redundant to the source circuit as disclosed in Lundberg in order to disable faulty channels (i.e. connected to transducer probes) such that the imaging can be performed using channels (i.e. transducer probes) without faults or errors. When faulty transducers/channels (i.e. circuits) are used to obtain imaging data, that imaging data will not be as reliable as imaging data obtained with normally operating transducers/channels (i.e. circuits). Thus, modifying the ultrasound machine such that it includes an additional circuit configured to determine a source circuit of the electromagnetic emissions within the ultrasound machine and a controller coupled to the additional circuit and configured to disable the source circuit and enable an additional source circuit that is redundant to the source circuit as disclosed in Lundberg would yield the predictable result of obtaining ultrasound imaging data which is less subject to fault due to electromagnetic emissions/noise.
Claim(s) 5, 9, 16 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ziv-Ari et al. US 2012/0065509 A1 “Ziv-Ari” and Lundberg et al. US 2020/0088862 A1 “Lundberg” as applied to claims 1 and 12 above, and further in view of Gao et al. US 2021/0145393 A1 “Gao”.
Regarding claims 5 and 16, Ziv-Ari in view of Lundberg discloses all features of the claimed invention as discussed with respect to claims 1 and 12 above, and Lundberg further teaches “wherein the circuit includes a neural network to generate the probability” (Claims 5 and 16) (See Lundberg: [0018] and [0034] as discussed with respect to claims 1 and 12 above. Therefore, the circuit includes a neural network to generate the probability.).
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 ultrasound machine and the method of Ziv-Ari so as to include a circuit which includes a neural network configured to perform the step of generating the probability that the ultrasound image includes artifacts from electromagnetic emissions as disclosed in Lundberg in order to detect faults or errors caused by electromagnetic emissions (i.e. noise) such that they can be compensated for (see Lundberg: [0015]). Outputting a probability that the ultrasound image includes artifacts from electromagnetic emissions (i.e. noise) is one of a finite number of techniques which can be used to verify whether there is a need compensate for faults/errors in an imaging system with a reasonable expectation of success. Thus, modifying the ultrasound machine and the method of Ziv-Ari so as to include a circuit configured to perform the step of generating, based on at least one of the sensor data and the ultrasound image, a probability that the ultrasound image includes artifacts from electromagnetic emissions as disclosed in Lundberg would yield the predictable result of facilitating the identification of faults or errors caused by electromagnetic emissions (i.e. noise) such that they can be compensated for (see Lundberg: [0015]).
However, the combination does not teach “and a classifier coupled to the neural network to determine, based on the at least one of the sensor data and the ultrasound image, a classification of the electromagnetic emissions” (Claims 5 and 16).
Gao is within a related field of endeavor to the claimed invention because it involves utilizing a neural network model for reducing or cancelling row-correlated noise artifacts in acquired images (see [0051]).
Gao teaches “a classifier coupled to the neural network to determine, based on the at least one of the sensor data and the ultrasound image, a classification of the electromagnetic emissions” (Claims 5 and 16) (“In embodiments disclosed herein, a neural network model, such as the neural network model depicted in FIGS. 3 and 4, is trained with pairs of noisy images and clean, target images, such as the pair of images depicted in FIG. 5, such that the neural network model accepts an image with EMI noise as input and outputs the image with the EMI noise substantially reduced. As depicted in FIG. 6, such a neural network model is particularly effective at eliminating image noise artifacts caused by EMI” [0014]; “The noise frequency is usually associated with the row spatial distribution and external electromagnetic sources” [0031]; “Thus the neural network model 320 may be configured as the neural network model 400 for reducing or cancelling row-correlated noise artifacts in acquired images. Further, in some examples, the neural network model 400 may include one or more noise filters such as a filter 482 and a filter 484. The filters 482 and 484 may comprise bandpass filters, for example, with a frequency band centered on noise frequencies caused by electromagnetic interference endemic to digital x-ray detectors such as the digital x-ray detector 222. For example, if the noise frequency is one Hertz, the filters 482 and 484 may provide a noise reduction filter around this noise frequency” [0051]. Therefore, since the neural network (i.e. such as neural network model 320) is trained with pairs of noisy images and clean target images, such that the model accepts an image with EMI noise and outputs an image with the EMI noise substantially reduced, the neural network 400 constitutes a classifier which is configured to determine a classification of the electromagnetic emissions (i.e. the EMI noise artifacts based on the noise filters). EMI emission frequencies correspond to different electromagnetic sources. Therefore, since the neural network model 400, includes one or more noise filters (i.e. filters 482, 484) such that electromagnetic interference noise frequencies caused by external electromagnetic sources can be reduced or cancelled, the neural network determines, based on the classification of the electromagnetic emission (i.e. the frequency of the EMI emission) and a list of sources and signatures of their emissions (i.e. corresponding to the frequency of EMI emissions), a source of the electromagnetic emissions.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to modify the ultrasound machine and method of Ziv-Ari in view of Lundberg so as to include a classifier (i.e. neural network 400 of Gao) configured to determine a classification of the electromagnetic emissions as disclosed in Gao in order to effectively eliminate image noise artifacts caused by EMI (see Gao: [0014]). Utilizing a neural network/classifier is one of a finite number of techniques which can be used to determine whether images have a specific frequency band of electromagnetic noise and remove it with a reasonable expectation of success therefore it would be obvious to try. Although Gao involves embodiments related to X-ray imaging, it would be obvious to one of ordinary skill in the art to train the neural network of Gao with the ultrasound images obtained by Ziv-Ari in order to identify the classifications of electromagnetic emissions/noise, and thereby reduce the amount of electromagnetic noise present within the ultrasound images.
Regarding claims 9 and 19, Ziv-Ari in view of Lundberg discloses all features of the claimed invention as discussed with respect to claims 1 and 12 above, however, the combination does not teach “wherein the circuit is further configured to: determine, based on a property of the sensor data, a source of the electromagnetic emissions by correlating the property with properties known to be associated with the electromagnetic emissions” (Claim 9); “further comprising: determining, by the circuit and based on a property of the sensor data, a source of the electromagnetic emissions by correlating the property with properties known to be associated with the electromagnetic emissions” (Claim 19).
Gao teaches “wherein the circuit is further configured to: determine, based on a property of the sensor data, a source of the electromagnetic emissions by correlating the property with properties known to be associated with the electromagnetic emissions” (Claim 9); “further comprising: determining, by the circuit and based on a property of the sensor data, a source of the electromagnetic emissions by correlating the property with properties known to be associated with the electromagnetic emissions” (Claim 19) (“In embodiments disclosed herein, a neural network model, such as the neural network model depicted in FIGS. 3 and 4, is trained with pairs of noisy images and clean, target images, such as the pair of images depicted in FIG. 5, such that the neural network model accepts an image with EMI noise as input and outputs the image with the EMI noise substantially reduced. As depicted in FIG. 6, such a neural network model is particularly effective at eliminating image noise artifacts caused by EMI” [0014]; “The noise frequency is usually associated with the row spatial distribution and external electromagnetic sources” [0031]; “Thus the neural network model 320 may be configured as the neural network model 400 for reducing or cancelling row-correlated noise artifacts in acquired images. Further, in some examples, the neural network model 400 may include one or more noise filters such as a filter 482 and a filter 484. The filters 482 and 484 may comprise bandpass filters, for example, with a frequency band centered on noise frequencies caused by electromagnetic interference endemic to digital x-ray detectors such as the digital x-ray detector 222. For example, if the noise frequency is one Hertz, the filters 482 and 484 may provide a noise reduction filter around this noise frequency” [0051].
In this case, the neural network (i.e. such as neural network model 320) is trained with pairs of noisy images and clean target images, such that the model accepts an image with EMI noise (i.e. from a source of electromagnetic emissions) and outputs an image with the EMI noise substantially reduced. Therefore, the neural network 320 acts as a classifier which is configured to determine a classification of the electromagnetic emissions (i.e. the EMI noise artifacts). EMI emission frequencies correspond to different electromagnetic sources. Therefore, since the neural network model 400, includes one or more noise filters (i.e. filters 482, 484) such that electromagnetic interference noise frequencies caused by external electromagnetic sources can be reduced or cancelled, the neural network determines, based on a property of the sensor data (i.e. the frequency of the EMI emission/noise), a source of the electromagnetic emissions by correlating (i.e. comparing) the property (i.e. frequency of the EMI emission/noise) with properties (i.e. frequencies) known to be associated with the electromagnetic emissions. Additionally, the method further comprises determining, by the circuit and based on a property of the sensor data (i.e. the frequency of the EMI emission/noise), a source of the electromagnetic emissions by correlating the property (i.e. frequency of the EMI emission/noise) with properties (i.e. frequencies) known to be associated with the electromagnetic emissions.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to modify the ultrasound machine of Ziv-Ari in view of Lundberg so as to include a classifier (i.e. neural network) configured to determine a source of the electromagnetic emissions as disclosed in Gao in order to effectively eliminate image noise artifacts caused by EMI (see Gao: [0014]). Utilizing a neural network is one of a finite number of techniques which can be used to determine whether images have a specific frequency band of electromagnetic noise, associated with a source of electromagnetic emissions, and remove it with a reasonable expectation of success therefore it would be obvious to try. Although Gao involves embodiments related to X-ray imaging, it would be obvious to one of ordinary skill in the art to train the neural network of Gao with the ultrasound images obtained by Ziv-Ari in order to identify the source(s) of electromagnetic emissions/noise, and thereby reduce the amount of electromagnetic noise present within the ultrasound images.
Claim(s) 7 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ziv-Ari et al. US 2012/0065509 A1 “Ziv-Ari” and Lundberg et al. US 2020/0088862 A1 “Lundberg”. as applied to claims 1 and 12 above, and further in view of Wang WO 02/43801 A2 “Wang”.
Regarding claims 7 and 18, Ziv-Ari in view of Lundberg discloses all features of the claimed invention as discussed with respect to claims 1 and 12 above, and Ziv-Ari further teaches “wherein the at least one sensor includes impedance sensors located within the ultrasound machine (Claims 7 and 18) (“According to an embodiment, the ultrasound probe 109 of ultrasound imaging system 100 may optionally include a sensor 121. Other embodiments may include probes with multiple sensors” [0023]; “FIG. 7 is a schematic representation of a sensor 160 that could be used in place of the sensor 121 according to an embodiment. […] The sensor 160 is designed to approximate the electrical impedance of a transducer element 104 (shown in FIG. 1). […] Therefore, it is possible to use the signal from the sensor 160 as an estimate of the electromagnetic noise signal that would be affecting the other transducer elements in the transducer array 148” [0042]. Therefore, since the ultrasound probe 109 may include multiple sensors and the sensor 160 can be used in place of sensor 121 for estimating the electrical impedance of a transducer element 104 and estimate the electromagnetic noise signal, the at least one sensor includes impedance sensors (i.e. sensors 160) located within the ultrasound machine (i.e. within the probe 109 connected to the processor 116).).
However, Ziv-Ari does not teach that the impedance sensors are “configured to generate an impedance matrix including impedances between the impedance sensors, and the circuit is configured to generate the probability based on the impedance matrix” (Claim 7) or that “the method further comprises: generating, by the circuit, an impedance matrix including impedances between the impedance sensors; and generating, by the circuit, the probability based on the impedance matrix” (Claim 18).
Wang is within a related field of endeavor to the claimed invention because is discloses constructing a 3-dimensional acoustic impedance matrix from a plurality of two-dimensional ultrasound planes (see Page 13, Lines 4-8]).
Wang teaches that the impedance sensors are “configured to generate an impedance matrix including impedances between the impedance sensors, and the circuit is configured to generate the probability based on the impedance matrix” (Claim 7) and that “the method further comprises: generating, by the circuit, an impedance matrix including impedances between the impedance sensors; and generating, by the circuit, the probability based on the impedance matrix” (Claim 18) (“FIG. 3 illustrates a diagram corresponding to steps 110 and 112 of FIG. 1, in particular a conceptual diagram of 3-dimensional breast volume reconstruction and ultrasound image slice interpolation in accordance with a preferred embodiment. FIG. 3 conceptually shows a 3-dimensional acoustic impedance matrix 302 constructed from the plurality of two-dimensional ultrasound planes. […] The 3-dimensional acoustic impedance matric 302 may be constructed from the ultrasound planes nj using any of a variety of known 3-dimensional volume formation algorithms” [Page 13, Lines 4-10]; and “The latter algorithm is usually preferable because more data within the 3-dimensional acoustic impedance matrix is used to compute the actual result, and less data is “discarded” by the projection algorithm. In accordance with a preferred embodiment, the successive ultrasound image slices mj correspond to planes in the breast volume that are no greater than a predetermined spacing distance apart. The predetermined spacing distance is selected to reduce the probability of missed lesions due to undersampling along an axis perpendicular to the x-ray mammogram view plane (e.g. the x-axis in FIGS. 2 and 3)” [Page 13, Lines 21-29]. Therefore, an impedance matrix is generated which includes impedances between the impedance sensors (i.e. for example, sensors 208, 210 forming the electromagnetic position sensing system along with the electromagnetic transmitter embedded into ultrasound probe 202, see [Page 11, Lines 17-19]). As shown in FIG. 3, the impedance matrix 302 and the ultrasound image slice 304 are displayed together, thereby facilitating comparison between the two for identification of image features (i.e. such as lesions). Furthermore, since the latter algorithm utilizes the 3-dimensional acoustic impedance matrix to compute the actual result and successive ultrasound image slices corresponding to planes in the breast volume are acquired at a predetermined spacing distance to reduce the probability of missing lesions in the breast due to undersampling along the x-axis (i.e. shown in FIG. 3), under broadest reasonable interpretation, probability that the ultrasound image includes artifacts from the electromagnetic emissions is generated based at least in part on the impedance matrix.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to modify the ultrasound machine and method of Ziv-Ari in view of Lundberg such that the impedance sensors are configured to generate an impedance matrix as disclosed in Wang in order to allow characteristics of the tissue, such as lesions, to be identified within the ultrasound images acquired by the system. Generating an impedance matrix is one of a finite number of techniques which can be used to identify characteristics of the tissue being analyzed with a reasonable expectation of success. Therefore, it would be obvious to modify the impedance sensor of Ziv-Ari such that it is configured to generate an impedance matrix as disclosed in Wang in order to identify locations in ultrasound images where there is a change in impedance (i.e. such as lesions).
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ziv-Ari et al. US 2012/0065509 A1 “Ziv-Ari” and Lundberg et al. US 2020/0088862 A1 “Lundberg” as applied to claim 1 above, and further in view of Urano et al. US 2015/0305712 A1 “Urano”.
Regarding claim 8, Ziv-Ari in view of Lundberg discloses all features of the claimed invention as discussed with respect to claim 1, however the combination does not teach “wherein the at least one sensor includes a light sensor, and the sensor data includes an amount of light”.
Urano is within a similar field of endeavor to the claimed invention because it discloses an ultrasonic diagnostic apparatus which includes a plurality of light detection units arranged around the ultrasonic transmitting and receiving surface and detect the light of the specific wavelength reflected inside the subject (See [Abstract]).
Urano teaches “wherein the at least one sensor includes a light sensor, and the sensor data includes an amount of light” (“FIG. 1 is a block diagram of a biomedical light measuring apparatus 4 including a light probe 40 and an optical measurement processing unit 42. FIG. 2 is a block diagram of an ultrasonic diagnosis apparatus 1 into which the biomedical light measuring apparatus 4 according to the present embodiment is incorporated” [0039]; “The light probe 40 includes at least one light irradiation unit 400, a plurality of light detection units 401, and a light guiding unit 402 to improve light detection efficiency” [0041]; “FIG. 4 is a graph obtained by irradiating the inside of the abdomen of the body from the surface with lights of two wavelengths 855 nm and 765 nm while pressing the interface unit P thereon […] As evident from FIG. 4, the measured light intensity rises when the interface unit P is pressed and the light intensity attenuates when pressing of the interface unit P is released. This is because blood is pressed out by the surface being pressed by the interface unit P and the amount of light absorbed by blood is decreased with decreased blood as a result, the amount of received light is considered to increase” [0058]; “Also according to the present ultrasonic diagnosis apparatus, an operation to press the probe P against the body surface and releasing the probe in the reference position using the reference wavelength light intensity calibration function to calculate a reference wavelength calibrating straight line corresponding to each incident/detection position specific to individual subjects and light intensity is measured by horizontally scanning the ultrasonic probe and then calibrated and normalized, which can then be formed as a signal. Accordingly, variation noise caused by the operation to press the probe P against the body surface and releasing the probe can dramatically be reduced” [0118].
As shown in FIG. 2, the ultrasonic probe 12 and the light probe 40 and located within the probe P. Since the light probe 40 includes at least one light irradiation unit 400 and a plurality of light detection units 401, the light probe 40 represents a light sensor which is configured to receive an amount of light (see [0058]). In this case, the reference wavelength light intensity calibration function can be used to calculate a reference wavelength calibrating straight line corresponding to each incident/detection position specific to individual subjects such that the probe P (i.e. containing the ultrasonic probe 12 and the light probe 40) is pressed to a reference position, in order to dramatically reduce the variation noise cause by pressing the probe against the body surface. Therefore, the light probe 40 (i.e. used to calculate the light intensity) can be used to determine the reference position the probe P should be positioned to such that the ultrasound probe obtains an image with less noise.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to modify the ultrasound machine of Ziv-Ari in view of Lundberg so as to include a light sensor as disclosed in Urano in order to determine the reference position the ultrasound probe (i.e. scanner) should be placed in order to dramatically reduce the variation noise caused by the operation of pressing the probe against the body surface (see Urano: [0118]). Utilizing a light sensor which detects an amount of light reflected by tissue (i.e. specifically the region of interest, such as a blood vessel) is one of a finite number of techniques which can be used to determine the position/pressing force that should be used to perform ultrasound imaging with a reasonable expectation of success. Therefore, it would be obvious to modify the ultrasound machine of Ziv-Ari in view of Lundberg so as to include the light probe of Urano in order to determine a reference position (i.e. based on reference wavelength light intensity) at which to position the ultrasonic probe such that variation noise is dramatically reduced.
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ziv-Ari et al. US 2012/0065509 A1 “Ziv-Ari” and Lundberg et al. US 2020/0088862 A1 “Lundberg” as applied to claim 1 above, and further in view of Nimomiya et al. US 2015/0025386 A1 “Nimomiya”.
Regarding claim 10, Ziv-Ari in view of Lundberg discloses all features of the claimed invention as discussed with respect to claim 1 above, however, the combination does not teach “wherein the sensor data include a number of open/close cycles of a display of the ultrasound machine”.
Ninomiya is within a related field of endeavor to the claimed invention because it involves a technology for limiting the deterioration of hardware in a portable diagnostic ultrasound apparatus (see [Abstract]).
Ninomiya teaches “wherein the sensor data include a number of open/close cycles of a display of the ultrasound machine” (“Any one of the lid housing 120, the main body housing 110, the monitor 121, and the operation portion 111 is provided with a sensor (not shown) for detecting that the lid housing 120 is closed, and the monitor 121 is accommodated in the main body 110. When the sensor detects that the lid body is closed, the sensor outputs a closed signal to the control unit 200, whereas when the sensor detects that the lid body is opened, it outputs an open signal to the control unit 200. The sensor may be constituted so as to output a signal indicating whether the lid housing 120 is closed or opened at present to the control unit 200 every predetermined period of time” [0041]; “If the lid housing 120 is opened during the end delay time T, supply of power to the ultrasonic transmission/receipt unit 113 is not resumed” [0069]; “Moreover, the automatic end portion 220 may be so configured that supply of power to the ultrasonic transmission/receipt unit 113 and the display device (monitor 121) is shut off, when the lid housing 120 is closed” [0087]. As shown in FIG. 1a, the monitor 121 (i.e. display) of the portable diagnostic ultrasound apparatus 100 (i.e. ultrasound machine) is included within the lid housing 120. The act of shutting off the supply of power when the lid housing is either open for too long (i.e. during the end delay time T) or closed serves to conserve power and therefore, limit the deterioration of hardware. Therefore, since a sensor for detecting when the lid housing 120 is open or closed outputs a signal every predetermined period of time, the sensor data includes a number of open/close cycles of a display of the ultrasound machine.).
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 ultrasound machine of Ziv-Ari in view of Lundberg such that it is configured to obtain sensor data that includes a number of open/close cycles of a display of the ultrasound machine as disclosed in Ninomiya in order to limit deterioration of the hardware included therein (see Ninomiya: [Abstract]). When an apparatus is continuously “left in a powered state”, “deterioration of the hardware can progress faster” (See Ninomiya: [0006]). Utilizing a sensor to detect a number of open/close cycles of a display of the ultrasound machine, therefore serves to conserve power and thus limit the progression of the deterioration of the hardware included therein. Thus, modifying the ultrasound machine of Ziv-Ari in view of Lundberg such that it is configured to obtain sensor data that includes a number of open/close cycles of a display of the ultrasound machine as disclosed in Ninomiya would yield the predictable result of limiting the deterioration of the hardware components contained therein.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KAITLYN E SEBASTIAN whose telephone number is (571)272-6190. The examiner can normally be reached Mon.- Fri. 7:30-4:30 (Alternate Fridays Off).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Anne M Kozak can be reached at (571) 270-0552. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/KAITLYN E SEBASTIAN/Examiner, Art Unit 3797