DETAILED ACTION
Summary
Claims 1-20 are pending in the application. Claims 18-20 are rejected under 35 USC 112(b). Claims 1-20 are rejected under 35 USC 103.
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 § 112
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.
Claim 18-20 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.
Claim 18 recites “the classes comprising a first class for flow or moving tissue, a second class for clutter or flash, and a third class for background noise”. This is an improper Markush grouping as it is an open list of alternatives (i.e. uses comprising) (MPEP 2173.05(h)). For the purposes of examination, the claim will be interpreted as stating “the classes selected from the group consisting of”.
All claims dependent from the above claims rejected under 35 USC 112(b) are also rejected, as the limitations of the dependent claims fail to cure the deficiencies identified above.
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.
Claims 1, 2, 4, 11, 13-15, and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Koh et al. (U.S PGPub 2014/0316274 A1) in view of Freiburger et al. (U.S PGPub 2019/0261952 A1) and Yang (U.S PGPub 2021/0088639 A1).
Regarding Claim 1, Koh teaches a method for adaptive clutter filtering in color imaging by an ultrasound scanner (Abstract), the method comprising:
scanning, by the ultrasound scanner (Fig. 1, 110) [0033], a patient (Fig. 6, S605-S610) [0085];
discriminating a first region from a second region (Fig. 6, S615-S620) [0085] by first and second types of signals represented in scan data from the scanning [0043]+[0045] (the different doppler signals are the first and second types of signals);
applying a first wall filter for the first region of the first type of signal (Fig. 6, S630) [0086]-[0087] and a second wall filter for the second region of the second type of signal (Fig. 6, S630) [0086]-[0087], the first wall filter different than the second wall filter [0064]-[0065]+[0068] (one of ordinary skill would recognize the clutter filter of Koh is a wall filter, as it removes clutter generated by reflections from the vessel wall [0051]); and
color imaging, by the ultrasound scanner, using estimates resulting from the applying of the first and second wall filters [0074].
Koh fails to explicitly teach the discriminating occurs using a machine-learned model.
Freiburger teaches a system for color flow imaging optimization (Abstract). This system uses machine learning to segment the target [0031].
It would have been obvious to one of ordinary skill in the art before the effective filing date to substitute the method of segmenting the image of Koh with a machine learning method, as taught by Freiburger, as the substitution for one known method for segmenting an image with another yields predictable results to one of ordinary skill in the art. One of ordinary skill would have been able to carry out such a substitution, and the results of using machine learning to discriminate regions in the image are reasonably predictable.
The combination fails to explicitly teach the first type of signal being from moving tissue or fluid, the second type of signal being from flash, clutter, or background noise such that the discriminating discriminates the moving tissue or the fluid from the flash, the clutter, or the background noise. The first wall filter for the first region being for the moving tissue or fluid, and the second wall filter for the second region being for the flash, the clutter, or the background noise.
Yang teaches a system for color flow imaging (Abstract). This system uses a neural network [0032] to discriminate the flow data and flash artifacts (Fig. 5, 515) [0041]-[0042]. This system then uses different clutter (i.e. wall) filters based on the flash strength (including whether the flash is not present, which would result in only a flow signal) [0044]-[0045].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the combined system to discriminate the flow signal from the flash signal using a machine learning system, and then adjust the filter based on the signal, as taught by Yang, because this allows for strong flash artifacts to be dynamically suppressed, thereby increasing the quality of the image, as recognized by Yang [0003].
Regarding Claim 2, Koh teaches the invention substantially as claimed. Koh further teaches wherein applying comprises applying to the scan data [0066], and wherein color imaging comprises color imaging from estimates of the scan data for the first region as filtered by the first wall filter [0071]+[0074].
Koh fails to explicitly teach wherein color imaging comprises color imaging from estimates of the scan data for the second region as filtered by the second wall filter.
Freiburger teaches a system for color flow imaging (Abstract). This system uses wall filtered data [0018] from the tissue region [0029]+[0034] in the color flow imaging [0070]-[0071].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the combined system to use the estimate of the scan data from the second region in the color imaging, as taught by Freiburger, because this allows the used to see the entire image while minimizing the influence of the tissue, thereby allowing the user to see imaging data from regions other than the flow regions and increasing the user’s field of view, a recognized by Freiburger [0084]+[0086].
Regarding Claim 4, the combination of references teaches the invention substantially as claimed. Koh further teaches wherein discriminating comprises segmenting the first region from the second region sample location-by-sample location [0085] (the plurality of regions are locations, and as such the system is segmenting the image location by location).
Regarding Claim 11, the combination of references teaches the invention substantially as claimed. Koh fails to explicitly teach wherein discriminating comprises estimating velocity, variance, and/or power from the scan data and segmenting, by the machine-learned model, in response to input of the velocity, variance, and/or power to the machine-learned model.
Freiburger further teaches wherein discriminating comprises estimating velocity, variance, and/or power from the scan data [0026]+[0031] and segmenting, by the machine-learned model, in response to input of the velocity, variance, and/or power to the machine-learned model [0026]+[0031].
It would have been obvious to one of ordinary skill in the art before the effective filing date to substitute the method of segmenting the image of Koh with a machine learning method, as taught by Freiburger, as the substitution for one known method for segmenting an image with another yields predictable results to one of ordinary skill in the art. One of ordinary skill would have been able to carry out such a substitution, and the results of using machine learning to discriminate regions in the image are reasonably predictable.
Regarding Claim 13, the combination of references teaches the invention substantially as claimed. Koh further teaches wherein color imaging comprises color imaging for one of various imaging applications [0074], wherein discriminating comprises discriminating for any of the various imaging applications [0006]+[0051] (imaging the heart is a different application then imaging the blood vessel wall).
Koh fails to explicitly teach the discriminating occurs using a machine-learned model.
Freiburger teaches a system for color flow imaging optimization (Abstract). This system uses machine learning to segment the target [0031].
It would have been obvious to one of ordinary skill in the art before the effective filing date to substitute the method of segmenting the image of Koh with a machine learning method, as taught by Freiburger, as the substitution for one known method for segmenting an image with another yields predictable results to one of ordinary skill in the art. One of ordinary skill would have been able to carry out such a substitution, and the results of using machine learning to discriminate regions in the image are reasonably predictable.
Regarding Claim 14, Koh teaches a method for adaptive clutter filtering in color imaging by an ultrasound scanner (Abstract), the method comprising:
generating a discrimination map discriminating sample locations into multiple categories (Fig. 6, S615-S620) [0085];
adapting clutter filtering based on the discrimination map (Fig. 6, S630) [0086]-[0087]; and
color flow imaging using the clutter filtering as adapted [0074].
Koh fails to explicitly teach the discrimination map generated by an artificial intelligence.
Freiburger teaches a system for color flow imaging optimization (Abstract). This system uses machine learning (an artificial intelligence) to segment the target (and there generate a discrimination map) [0031].
It would have been obvious to one of ordinary skill in the art before the effective filing date to substitute the method of segmenting the image of Koh with a machine learning method, as taught by Freiburger, as the substitution for one known method for segmenting an image with another yields predictable results to one of ordinary skill in the art. One of ordinary skill would have been able to carry out such a substitution, and the results of using machine learning to discriminate regions in the image are reasonably predictable.
The combination fails to explicitly teach the categories distinguishing the sample locations for flow from the sample locations for flash, clutter, and/or background noise, or such that the sample locations for the flow are clutter filtered differently than the sample locations for the flash, the clutter, and/or the background noise.
Yang teaches a system for color flow imaging (Abstract). This system uses a neural network [0032] to discriminate the flow data and flash artifacts (Fig. 5, 515) [0041]-[0042]. This system then uses different clutter (i.e. wall) filters based on the flash strength (including whether the flash is not present, which would result in only a flow signal) [0044]-[0045].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the combined system to discriminate the flow signal from the flash signal using a machine learning system, and then adjust the filter based on the signal, as taught by Yang, because this allows for strong flash artifacts to be dynamically suppressed, thereby increasing the quality of the image, as recognized by Yang [0003].
Regarding Claim 15, the combination of references teaches the invention substantially as claimed. Koh fails to explicitly teach wherein generating comprises generating by the artificial intelligence in response to input of estimates of velocity, variance, and/or power to the artificial intelligence.
Freiburger further teaches generating, by the artificial intelligence, in response to input of the velocity, variance, and/or power to the artificial intelligence [0026]+[0031].
It would have been obvious to one of ordinary skill in the art before the effective filing date to substitute the method of segmenting the image of Koh with a machine learning method, as taught by Freiburger, as the substitution for one known method for segmenting an image with another yields predictable results to one of ordinary skill in the art. One of ordinary skill would have been able to carry out such a substitution, and the results of using machine learning to discriminate regions in the image are reasonably predictable.
Regarding Claim 18, Koh teaches an ultrasound system for color imaging (Abstract), the ultrasound system comprising:
a transducer and beamformer (Fig. 1, 110) [0035] for scanning a scan region (Fig. 6, S605-S610) [0085];
a programmable wall filter (Fig. 3, 415) [0042]+[0054] (choosing different clutter filters is programming the wall filter to be a certain one)
an image processor (Fig. 1, 130) configured to segment, by application of a machine-learned segmentation model, the scan region into at least two classes (Fig. 6, S615-S620) [0085] and adapt settings of the programmable wall filter based on the at least two classes such that different locations of the scan region use different ones of the settings [0042]+[0086]-[0087]
a Doppler estimator (Fig. 1, 130) [0072] configured to estimate, from data filtered by the programmable wall filter based on the settings, color values in the scan region [0074]
a display configured to display an image using the color values [0074].
Koh fails to explicitly teach the application of a machine-learned segmentation model.
Freiburger teaches a system for color flow imaging optimization (Abstract). This system uses machine learning to segment the target [0031].
It would have been obvious to one of ordinary skill in the art before the effective filing date to substitute the method of segmenting the image of Koh with a machine learning method, as taught by Freiburger, as the substitution for one known method for segmenting an image with another yields predictable results to one of ordinary skill in the art. One of ordinary skill would have been able to carry out such a substitution, and the results of using machine learning to discriminate regions in the image are reasonably predictable.
The combination fails to explicitly teach the classes comprising a first class for flow or moving tissue, a second class for clutter or flash, and a third class for background noise.
Yang teaches a system for color flow imaging (Abstract). This system uses a neural network [0032] to discriminate the flow data and flash artifacts (Fig. 5, 515) [0041]-[0042]. This system then uses different clutter (i.e. wall) filters based on the flash strength (including whether the flash is not present, which would result in only a flow signal) [0044]-[0045].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the combined system to discriminate the flow signal from the flash signal using a machine learning system, and then adjust the filter based on the signal, as taught by Yang, because this allows for strong flash artifacts to be dynamically suppressed, thereby increasing the quality of the image, as recognized by Yang [0003].
Regarding Claim 19, the combination of references teaches the invention substantially as claimed. Koh fails to explicitly teach wherein the image processor is configured to input estimates of velocity, variance, and/or power to the machine-learned segmentation model, the machine-learned segmentation model outputting a segmentation map in response to the input.
Freiburger further teaches wherein the image processor is configured to input estimates of velocity, variance, and/or power to the machine-learned segmentation model, the machine-learned segmentation model outputting a segmentation map in response to the input [0026]+[0031].
It would have been obvious to one of ordinary skill in the art before the effective filing date to substitute the method of segmenting the image of Koh with a machine learning method, as taught by Freiburger, as the substitution for one known method for segmenting an image with another yields predictable results to one of ordinary skill in the art. One of ordinary skill would have been able to carry out such a substitution, and the results of using machine learning to discriminate regions in the image are reasonably predictable.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Koh in view of Freiburger and Yang as applied to claim 1 above, and further in view of Kim (U.S PGPub 2022/0211352 A1).
Regarding Claim 3, the combination of references teaches the invention substantially as claimed. Koh further teaches wherein color imaging comprises color flow imaging [0074] where the first and second wall filter with different frequency responses [0065]+[0068].
Koh fails to explicitly teach the filter is a high pass filter.
Kim teaches a system for color imaging system (Abstract). This system uses a high pass filter as the wall filter [0024].
It would have been obvious to one of ordinary skill in the art before the effective filing date to substitute the filter of the combined system to be a high pass filter, as the substitution for one known clutter filter with another yields predictable results to one of ordinary skill in the art. One of ordinary skill would have been able to carry out such a substitution, and the results of using a high pass filter as a wall filter are reasonably predictable. One of ordinary skill would recognize that, in the combination, the different high pass filters of Kim would have different cutoff frequencies, as taught by Koh.
Claims 5 and 7 are rejected under 35 U.S.C. 103 as being unpatentable over Koh in view of Freiburger and Yang as applied to claim 1 above, and further in view of Mo et al. (U.S PGPub 2002/0169378 A1).
Regarding Claim 5, the combination of references teaches the invent substantially as claimed. Koh further teaches wherein discriminating comprises discriminating by the first type of signal, the second type of signal [0043]+[0045].
The combination fails to explicitly teach a third type of signal, the third type of signal being at a third region, wherein applying comprises applying a third wall filter for the third region, the third wall filter different than the first and second wall filters, and wherein color imaging comprises color imaging using estimates resulting from applying of the third wall filter.
Mo teachers a system for adaptive clutter filtering (Abstract). This system looks at each pixel, which would be a signal type representing a third region (i.e. the pixel) [0012]+[0016]. This system applies a different wall filter to each of the pixels (acoustic point) (i.e. regions including a third region) [0081]+[0099]. The filters for each of the pixels can be different from one another (which would make the third wall filter different from the first and second wall filters) [0032]. This filtered data is then used to generate a color image [0078].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the combined system to have a third type of signal with a third wall filter, as taught by Mo, because this better suppresses artifacts in the image without eliminating low velocity signals, as recognized by Mo [0032].
Regarding Claim 7, the combination of references teaches the invention substantially as claimed. Koh further teaches wherein the first wall filter has a lowest cutoff frequency relative to the first, second, and third wall filters, the second wall filter has a highest cutoff frequency relative to the first, second, and third wall filters, and the third wall filter has a cutoff frequency between the highest and lowest cutoff frequencies relative to the first, second, and third wall filters (Fig. 6, S625) [0086].
Once of ordinary skill would recognize that as each region has a different cutoff frequency, and the combination contains at least three regions, one region must have a highest cutoff frequency, one region must have a lowest cutoff frequency, and one region would have a cutoff frequency between the two.
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Koh in view of Freiburger, Yang, and Mo as applied to claim 5 above, and further in view of Lee et al. (U.S Patent 9,261,485 B2).
Regarding Claim 6, the combination of references fails to explicitly teach wherein the first type of signal comprises flow signal from the fluid or the moving tissue, the second type of signal comprises the flash and/or the clutter, and the third type of signal comprises the background noise, and wherein color imaging comprises color imaging of the fluid or moving tissue.
Lee teaches a method for color Doppler imaging (Abstract). This system separates the Doppler signal into flow signal from fluid or moving tissue signal from tissue (Fig. 4, 410), the second type of signal comprises flash and/or clutter (Fig. 4, 420), and the third type of signal comprises background noise (Fig. 4, 430) (Col 4, lines 54-65), and wherein color imaging comprises color imaging of the fluid or moving tissue (Col 5, lines 39-44).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the combined system so the signals are flow, clutter, and noise signals, as taught by Lee, because this allows the system to more accurately obtain an remove noise, thereby resulting in higher quality images, as recognized by Lee (Col 1, lines 51-62).
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Koh in view of Freiburger and Yang as applied to claim 1 above, and further in view of Bakircioglu et al. (U.S PGPub 2005/0131300 A1)
Regarding Claim 8, the combination of references teaches the invention substantially as claimed. The combination fails to explicitly teach setting a threshold for the estimates for the first region differently than a threshold for the estimates for the second region, wherein the estimates for color imaging result from thresholding using the thresholds for the first and second regions.
Bakircioglu teaches a method for optimizing ultrasonic imaging (Abstract). This system setting a threshold for the estimates for the first region differently than a threshold for the estimates for the second region [0046] (the system sets the threshold as a function of spatial location, which suggests the different regions would have different thresholds), wherein the estimates for color imaging result from thresholding using the thresholds for the first and second regions [0038].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the combined system to use different thresholds for the different regions, as taught by Bakircioglu, because this optimizes the flow imaging, thereby reducing artifacts in the image, as recognized by Bakircioglu [0002].
Claims 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Koh in view of Freiburger and Yang as applied to claim 1 above, and further in view of Yoo (U.S PGPub 2021/0224991 A1).
Regarding Claim 9, the combination of references teaches the invention substantially as claimed. The combination fails to explicitly teach wherein the machine-learned model comprises a semantic segmentation deep network.
Yoo teaches an ultrasound system for semantic segmentation in ultrasound images (Abstract). This system uses a semantic segmentation deep network to segment the images [0007]+[0012].
It would have been obvious to one of ordinary skill in the art before the effective filing date to substitute the machine learning model of the combination with a semantic segmentation, as taught by Yoo, as the substitution for one known machine learning segmentation method with another yields predictable results to one of ordinary skill in the art. One of ordinary skill would have been able to carry out such a substitution, and the results of using a semantic segmentation model are reasonably predictable.
Regarding Claim 10, the combination of references teaches the invention substantially as claimed. Koh fails to explicitly teach wherein the semantic segmentation deep network comprises an image-to-image neural network.
Yoo further teaches w the semantic segmentation deep network comprises an image-to-image neural network [0016] (as the neural network is performed on images and was taught using other images, it is considered an image to image neural network.
It would have been obvious to one of ordinary skill in the art before the effective filing date to substitute the machine learning model of the combination with an image to image neural network, as taught by Yoo, as the substitution for one known machine learning segmentation method with another yields predictable results to one of ordinary skill in the art. One of ordinary skill would have been able to carry out such a substitution, and the results of using an image to image neural network are reasonably predictable.
Claims 12, 16, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Koh in view of Freiburger and Yang as applied to claims 11, 15, and 19, respectively, above, and further in view of Guracar et al. (U.S Patent 6,309,357 B1)
Regarding Claim 12, the combination of references teaches the invention substantially as claimed. Koh fails to explicitly teach wherein estimating comprises estimating two or more versions of the velocity, the variance, and/or the power, and wherein the two or more versions are input to the machine-learned model.
Freiburger teaches a system for color flow imaging optimization (Abstract). This system inputs velocity, variance and/or power to the machine learned model to segment the target [0031].
It would have been obvious to one of ordinary skill in the art before the effective filing date to substitute the method of segmenting the image of Koh with a machine learning method, as taught by Freiburger, as the substitution for one known method for segmenting an image with another yields predictable results to one of ordinary skill in the art. One of ordinary skill would have been able to carry out such a substitution, and the results of using machine learning to discriminate regions in the image are reasonably predictable.
The combination fails to explicitly teach estimating two or more versions, and inputting the two or more versions to the machine-learned model.
Guracar teaches a system for flow imaging (Abstract). This system uses multiple clutter filters (Fig. 1, 110+120) (Col 3, lines 18-35) which are used to determine different versions of the velocity, variance, and/or power (Col 4, lines 32-46).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the combined system to use multiple versions, as taught by Guracar, because using multiple versions of the parameters allows for an improved sensitivity and calculation of the flow rate, as well as allowing the benefits of multiple filters to be obtained in the calculation, as recognized by Guracar (Col 7, lines 58-67)+(Col 8, lines 1-6). One of ordinary skill would recognize that, in the combination, the multiple versions of the parameters generated by Guracar would be input to the machine-learned model as taught by Freiburger.
Regarding Claim 16, the combination of references teaches the invention substantially as claimed. Koh fails to explicitly teach wherein generating comprises generating by the artificial intelligence in response to input of the estimates for each of the sample locations.
Freiburger teaches a system for color flow imaging optimization (Abstract). This system inputs velocity, variance and/or power to the machine learned model to segment the target [0031].
It would have been obvious to one of ordinary skill in the art before the effective filing date to substitute the method of segmenting the image of Koh with a machine learning method, as taught by Freiburger, as the substitution for one known method for segmenting an image with another yields predictable results to one of ordinary skill in the art. One of ordinary skill would have been able to carry out such a substitution, and the results of using machine learning to discriminate regions in the image are reasonably predictable.
The combination fails to explicitly teach multiple versions of the estimates for each of the sample locations, the multiple versions for each of the sample locations having different wall filtering.
Guracar teaches a system for flow imaging (Abstract). This system uses multiple clutter (wall) filters (Fig. 1, 110+120) (Col 3, lines 18-35) which are used to determine different versions of the velocity, variance, and/or power (Col 4, lines 32-46).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the combined system to use multiple versions, as taught by Guracar, because using multiple versions of the parameters allows for an improved sensitivity and calculation of the flow rate, as well as allowing the benefits of multiple filters to be obtained in the calculation, as recognized by Guracar (Col 7, lines 58-67)+(Col 8, lines 1-6). One of ordinary skill would recognize that, in the combination, the multiple versions of the parameters generated by Guracar would be input to the machine-learned model as taught by Freiburger.
Regarding Claim 20, the combination of references teaches the invention substantially as claimed. Koh fails to explicitly teach wherein the image processor is configured to input the estimates.
Freiburger teaches a system for color flow imaging optimization (Abstract). This system inputs velocity, variance and/or power to the machine learned model to segment the target [0031].
It would have been obvious to one of ordinary skill in the art before the effective filing date to substitute the method of segmenting the image of Koh with a machine learning method, as taught by Freiburger, as the substitution for one known method for segmenting an image with another yields predictable results to one of ordinary skill in the art. One of ordinary skill would have been able to carry out such a substitution, and the results of using machine learning to discriminate regions in the image are reasonably predictable.
The combination fails to explicitly teach multiple versions corresponding to different frequency responses.
Guracar teaches a system for flow imaging (Abstract). This system uses multiple clutter filters (Fig. 1, 110+120) (Col 3, lines 18-35) which are used to determine different versions of the velocity, variance, and/or power (Col 4, lines 32-46). These filters have different frequency responses (Col 2, lines 32-44)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the combined system to use multiple versions, as taught by Guracar, because using multiple versions of the parameters allows for an improved sensitivity and calculation of the flow rate, as well as allowing the benefits of multiple filters to be obtained in the calculation, as recognized by Guracar (Col 7, lines 58-67)+(Col 8, lines 1-6). One of ordinary skill would recognize that, in the combination, the multiple versions of the parameters generated by Guracar would be input to the machine-learned model as taught by Freiburger.
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Koh in view of Freiburger and Yang as applied to claim 14 above, and further in view of Lee and Kim.
Regarding Claim 17, the combination of references teaches the invention substantially as claimed. Koh further teaches selecting different frequency responses [0042].
The combination fails to explicitly teach generating the discrimination map comprises distinguishing between the sample locations with of the flow, the sample locations with the clutter and/or the flash and the sample locations with the background noise
Lee teaches a method for color Doppler imaging (Abstract). This system separates the Doppler signal into flow signal from fluid or moving tissue signal from tissue (Fig. 4, 410), the second type of signal comprises flash and/or clutter (Fig. 4, 420), and the third type of signal comprises background noise (Fig. 4, 430) (Col 4, lines 54-65), and wherein color imaging comprises color imaging of the fluid or moving tissue (Col 5, lines 39-44).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the combined system so the signals are flow, clutter, and noise signals, as taught by Lee, because this allows the system to more accurately obtain an remove noise, thereby resulting in higher quality images, as recognized by Lee (Col 1, lines 51-62).
The combination fails to explicitly teach high pass frequency response.
Kim teaches a system for color imaging system (Abstract). This system uses a high pass filter as the wall filter [0024].
It would have been obvious to one of ordinary skill in the art before the effective filing date to substitute the filter of the combined system to be a high pass filter, as the substitution for one known clutter filter with another yields predictable results to one of ordinary skill in the art. One of ordinary skill would have been able to carry out such a substitution, and the results of using a high pass filter as a wall filter are reasonably predictable. One of ordinary skill would recognize that, in the combination, the different high pass filters of Kim would have different cutoff frequencies, as taught by Koh. One of ordinary skill would recognize that, as Koh changes the filter for the different spatial areas, in the combined system the high pass filters of Kim would be changed for the different areas (and therefore have different frequency responses).
Response to Arguments
Applicant's arguments filed 12/2/2025 have been fully considered but they are not persuasive.
Applicant’s arguments, see page 8, filed 12/2/2025, with respect to the rejection under 35 USC 101 have been fully considered and are persuasive. The claims are integrated into a practical application as they reflect an improvement in the art. The rejection of claims 1-20 under 35 USC 101 has been withdrawn.
Applicant’s arguments with respect to claim(s) 1 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Yang is relied upon to teach the machine learning model for differentiating flow and flash, as well as using different filters for the different flow or flash regions.
Applicant argues that Lee does not teach different wall filtering for different regions. The Examiner disagrees. In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). Lee is relied on to teach that the different regions can be flow, flash/clutter, and background noise. Mo is relied on to teach that every pixel/region would have a different clutter (wall) filter applied. When viewed together, this suggests to one of ordinary skill in the art that regions discriminated by Lee having different cutoff frequency.
Applicant argues that Mo does not teach discriminating a third type of signal. The Examiner disagrees. In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). Both Koh and Yang teach discriminating different signals. Mo teaches discriminating, pixel by pixel/region by region, based on the clutter signal [0032]. This is a different signal that either Koh or Yang use for discrimination, and therefore would be considered a third signal.
Applicant argues that Yoo does not render using a semantic segmentation model obvious. The Examiner disagrees. In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). Koh teaches discriminating based on different signals. Yoo teaches that a semantic segmentation model is a well-known model for discriminating regions in ultrasound images. Furthermore, the data the model analyzes of Yoo (i.e. image data) can be considered a “signal”. "A person of ordinary skill in the art is also a person of ordinary creativity, not an automaton." KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398, 421, 82 USPQ2d 1385, 1397 (2007). "[I]n many cases a person of ordinary skill will be able to fit the teachings of multiple patents together like pieces of a puzzle." Id. at 420, 82 USPQ2d 1397. Office personnel may also take into account "the inferences and creative steps that a person of ordinary skill in the art would employ." Id. at 418, 82 USPQ2d at 1396. (MPEP 2141.02(I)), and would be capable of using a known method for segmenting an ultrasound image to segment an ultrasound image. Therefore, the claim remains rejected under 35 USC 103.
Applicant argues that an image to image neural network is a term of art, and that Yoo is not an image to image neural network. The Examiner disagrees. The Applicant’s specification details that the image-to-image network is merely a neural network, not a specific neural network [0037]. By the broadest reasonable interpretation, any neural network which uses images can be considered an image-to-image neural network. As the Yoo reference uses the neural network on images [0016], it can be considered an image to image neural network by the broadest reasonable interpretation.
Applicant argues that both versions of the velocity would not be input to the machine learning model. The Examiner disagrees. In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). The machine learning model in the claims is used for discriminating the different signals, and both versions of the velocity are output to discriminators in Guracar (Col 4-5, lines 47-5). Therefore, one of ordinary skill would recognize that in the combination, the outputs for Guracar would be output to the machine learning model of the combination which performs the discrimination.
The rejection of the other claims remains rejected for similar reasons as detailed 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 nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SEAN D MATTSON whose telephone number is (408)918-7613. The examiner can normally be reached Monday - Friday 9 AM - 5 PM PST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Pascal Bui-Pho can be reached at (571) 272-2714. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/SEAN D MATTSON/Primary Examiner, Art Unit 3798