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 .
Response to Amendment
The amendment filed on 6/4/2026 has been entered. Claims 1-20 remain pending the application.
Response to Arguments
Applicant's arguments filed on 6/4/2026 have been fully considered but they are not persuasive.
Applicant argues on pages 8-11 that the previously rejection fails to disclose the newly added limitations to the independent claims related to processing of the first and second mode images to a machine learning model. However, a new grounds of rejection necessitated by amendment relies on newly cited portions of Simpson et al. (US20190336108, hereafter Simpson) and Tek (US20250017557) discloses these limitations in the claim because Simpson discloses using both imaging modes and applying both of them to a neural network and the rejection applies the modifications from Tek to both imaging modes of Simpson as cited in the rejection below. Accordingly, this argument is not persuasive.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-6, 8-9, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Simpson et al. (US20190336108, hereafter Simpson) and Tek (US20250017557).
Regarding claims 1-2 and 20, Simpson discloses a method, a computer system, and an ultrasound imaging system (Simpson, Para 1; “The present disclosure pertains to ultrasound systems and methods which utilize a neural network for deriving imaging data, tissue information and diagnostic information from raw ultrasound echoes.”) configured for conducting a dual-mode guided ultrasound imaging procedure (Simpson, Para 5; “configured to generate an ultrasound image based on the first type of ultrasound imaging data and the second type of ultrasound imaging data and to cause a display communicatively coupled therewith to display the ultrasound image”), comprising:
an ultrasound imaging probe (Simpson, Para 22; “The ultrasound transducer 113 may include an ultrasound transducer array 114, which may be provided in a probe 112, for example a hand-held probe or a probe configured to be at least partially controlled by a computer (e.g., a machine-actuated probe).”);
a computing system; and a non-transitory computer-readable storage medium, storing instructions that, when executed by a processor of the computing system cause the ultrasound imaging system to (Simpson, Para 12; “Any of the methods described herein, or steps thereof, may be embodied in non-transitory computer-readable medium comprising executable instructions, which when executed may cause a processor of a medical imaging system to perform method or steps embodied therein.”):
obtain a first plurality of images comprising a first mode and a second mode, the first mode comprising a B-mode ultrasound imaging mode, and the second mode comprising a Doppler flow ultrasound imaging mode (Simpson, Para 6; “the ultrasound imaging system may be configured to produce B-mode imaging data as the second type of imaging data, and to produce Doppler imaging data, […] as the first type of imaging data”);
submit an unprocessed first mode image and an unprocessed second mod image of the first plurality of images to a machine learning model (Simpson, Para 53; "the coupling of samples of raw or beamformed RF signals may be selective, e.g., responsive to user input or automatically controlled by the system based on the imaging mode or clinical application. The neural network may be trained to operate in a plurality of different modes each associated with a type of input data (e.g., raw channel data […]), and thus a corresponding operational mode of the neural network may be selected (automatically or responsive to user inputs) based on the type of input data to the neural network. The imaging data and/or tissue information output by the neural network may include B-mode imaging data, Doppler imaging data") (Simpson, Para 33; "the neural network 160 may be configured specifically to produce imaging data and/or any desired tissue information other than B-mode imaging data. For example, the neural network may be trained to provide flow imaging data (e.g., beam-angle dependent or beam-angle independent velocity information) directly from the echo signals and/or beamformed signals, while the system produces an anatomy image for overlay therewith using the pre-programmed or model-based processing components in processor 150. The B-mode imaging data may then be combined (in this case, overlaid) with the flow imaging data to produce an ultrasound image similar to a conventional Doppler image showing a color-coded flow map (or in the case of VFI, showing a vector field) onto a grayscale anatomy image" ) (Simpson, Para 20; “the neural network may be trained using any of a variety of currently known or later developed machine learning techniques to obtain a neural network (e.g., a machine-trained algorithm or hardware-based system of nodes) that is able to derive or calculate the characteristics of an image for display from raw channel data (i.e., acquired radio frequency (RF) echo signals)”).
Simpson does not clearly and explicitly disclose determining one or more user metrics comprising a contemporaneous image quality score and/or a guided movement expected to improve an image quality of a subsequently acquired second plurality of images compared to an image quality of the first plurality of images, based at least in part on the unprocessed first mode image and the unprocessed second mode image of the first plurality of images; and provide the one or more user metrics to a user of the ultrasound imaging system.
In analogous machine learning for ultrasound imaging field of endeavor Tek discloses determining one or more user metrics comprising a contemporaneous image quality score and/or a guided movement expected to improve an image quality of a subsequently acquired second plurality of images compared to an image quality of the first plurality of images, based at least in part on the first plurality of images; and providing the one or more user metrics to a user of the ultrasound imaging system (Tek, Para 28; “To assist users and/or the automated solution for better images in certain regions, patches are scanned with different values for the scan settings. The areas with abnormal wall motion, whether due to actual abnormality or due to poor scanning, are scanned again with different settings to improve the data by additional acquisition and/or to improve the data by better settings for scanning those locations. In one approach, the different settings are for scanning the region of abnormality along different scan planes. The field of view is shifted not just in area (smaller) and focus (in the region) but also in the plane being scanned. This multi-plane analysis of cardiac wall motion abnormalities from 2D echo may provide data usable for more accurate tracking and corresponding strain analysis. Improved data, and even a confidence measure, may be provided for tracking and image quality. The image quality is improved specifically in low confidence regions by changing acquisition parameters, such as rotating the probe slightly if necessary. The tracking may be run again only in the low confidence regions.”) (Tek, Par 49; “the user is guided to acquire higher quality images in the vicinity of such detected region 224 by optimizing machine or acquisition parameters and/or rotating the imaging planes. The system recommends the user to rotate the probe in certain degrees and quantifies the motion only in this selected region 224”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Simpson to include determining one or more user metrics comprising a contemporaneous image quality score and/or a guided movement expected to improve an image quality of a subsequently acquired second plurality of images compared to an image quality of the first plurality of images, based at least in part on the unprocessed first mode image and the unprocessed second mode image of the first plurality of images; and provide the one or more user metrics to a user of the ultrasound imaging system in order to improve image quality, particularly in low confidence regions as taught by Tek (Tek, Para 28).
The use of the techniques of providing adjustments to a user to improve image quality taught by Tek in the invention of an ultrasound system using B-mode and Doppler mode imaging would have comprised only application of a known technique to a known device ready for improvement to yield the predictable result of improving imaging; and similar modifications have previously been held to involve only routine skill in the art. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398, 415-421, 82 USPQ2d 1385, 1395-97 (2007).
Regarding claim 3, Simpson as modified by Tek above discloses all of the limitations of claim 1 as discussed above.
Simpson further discloses wherein the first plurality of images comprises multiple, repetitive images (Simpson, Para 21; “he ultrasound system 100 may include channel memory 121 configured to store the acquired echo signals (raw RF signals), and a beamformer 122, which may be configured to perform transmit and/or receive beamforming and which may include a beamformer memory 123 configured to store beamformed signals generated responsive to the acquired echo signals. In some embodiments, the system 100 may include or be communicatively coupled to a display 138 for displaying ultrasound images generated by the ultrasound system 100.”) (Simpson, Para 24; “The channel memory 110 may be configured to store per-element or group (in the case of microbeamformed signals) echo signals (also referred to as raw RF signals or simply RF signals, or per-channel data). The pre-channel data may be accumulated in memory over multiple transmit/receive cycles.”).
Regarding claim 4, Simpson as modified by Tek above discloses all of the limitations of claim 1 as discussed above.
Simpson further discloses wherein the dual-mode guided ultrasound imaging procedure identifies a target organ (Simpson, Para 50; “he so trained neural network may then be used to segment and identify cardiac chambers directly from the raw or beamformed data without having to first reconstruct an image of the anatomy and without reliance on image processing techniques. This segmentation information could be used to suppress imaging artifacts, or it could be fed directly into algorithms to quantify ejection fraction or other clinical parameters. The system may be similarly trained to identify other types of tissue or anatomical structures (e.g., walls of vessels, lung/pleura interface) and quantify relevant clinical parameters associated therewith (e.g., obtain a nuchal translucency measurement)”).
Regarding claim 5, Simpson as modified by Tek above discloses all of the limitations of claim 1 as discussed above.
Simpson further discloses wherein the B-mode depicts an anatomical structure (Simpson, Para 28; “The color data, also referred to as Doppler image data, may then be coupled the scan converter 130 where the Doppler image data is converted to the desired image format and overlaid on the B-mode image of the tissue structure containing the blood flow to form a color Doppler image.”) (Simpson, Para 27; “The processed signals may be coupled to a B-mode processor 128 for producing B-mode imaging data. The B-mode processor 128 can employ amplitude detection for the imaging of structures in the body.”).
Regarding claim 6, Simpson as modified by Tek above discloses all of the limitations of claim 1 as discussed above.
Simpson further discloses wherein the Doppler flow ultrasound imaging mode comprises providing a color map of blood flow together with a user readable structural image of the first mode (Simpson, Para 28; “The velocity and power estimates may then be mapped to a desired range of display colors in accordance with a color map. The color data, also referred to as Doppler image data, may then be coupled the scan converter 130 where the Doppler image data is converted to the desired image format and overlaid on the B-mode image of the tissue structure containing the blood flow to form a color Doppler image.”).
Regarding claim 8, Simpson as modified by Tek above discloses all of the limitations of claim 1 as discussed above.
Simpson does not clearly and explicitly disclose wherein the improvement in image quality improves the raw image quality.
However, Tek further discloses wherein the improvement in image quality improves the raw image quality (Tek, Para 28; “The areas with abnormal wall motion, whether due to actual abnormality or due to poor scanning, are scanned again with different settings to improve the data by additional acquisition and/or to improve the data by better settings for scanning those locations.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Simpson wherein the improvement in image quality improves the raw image quality in order to improve image quality, particularly in low confidence regions as taught by Tek (Tek, Para 28).
Regarding claim 9, Simpson as modified by Tek above discloses all of the limitations of claim 8 as discussed above.
Simpson does not clearly and explicitly disclose wherein the improvement in image quality comprises an improvement in visualization of a target structural feature of the target organ of a subject.
However, Tek further disclose wherein the improvement in image quality comprises an improvement in visualization of a target structural feature of the target organ of a subject (Tek, Para 49; “the user is guided to acquire higher quality images in the vicinity of such detected region 224 by optimizing machine or acquisition parameters and/or rotating the imaging planes. The system recommends the user to rotate the probe in certain degrees and quantifies the motion only in this selected region 224. The probe or array is rotated by a specified degree suggested by the system, which analyzes the motion patterns and then estimates the next best possible location. The optimal orientation plane may be automatically determined by minimizing out of plane motion (e.g., find plane showing the largest amount of motion) and/or improving the quality of speckle patterns, which leads to improved tracking and motion field estimation.”) (Tek, Para 28; “The areas with abnormal wall motion, whether due to actual abnormality or due to poor scanning, are scanned again with different settings to improve the data by additional acquisition and/or to improve the data by better settings for scanning those locations.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Simpson wherein the improvement in image quality comprises an improvement in visualization of a target structural feature of the target organ of a subject in order to improve image quality, particularly in low confidence regions as taught by Tek (Tek, Para 28).
Regarding claim 18, Simpson as modified by Tek above discloses all of the limitations of claim 1 as discussed above.
Simpson further discloses wherein the first mode is used to determine one or more aspects including current, threshold quality, or target view; and wherein the second mode is used to determine one or more aspects including current, threshold quality, or target view (Simpson, Para 28; “The velocity and power estimates may then be mapped to a desired range of display colors in accordance with a color map. The color data, also referred to as Doppler image data, may then be coupled the scan converter 130 where the Doppler image data is converted to the desired image format and overlaid on the B-mode image of the tissue structure containing the blood flow to form a color Doppler image.”).
Regarding claim 19, Simpson as modified by Tek above discloses all of the limitations of claim 1 as discussed above.
Simpson further discloses wherein the unprocessed first mode image comprises a plurality of raw images that have not been enhanced for human-readability and are not in a displayable format; and wherein the unprocessed second mode image comprises a plurality of raw images that have not been enhanced for human-readability and are not in a displayable format (Simpson, Para 4; “The present disclosure pertains to ultrasound systems and methods which utilize a neural network (e.g., a machine-trained algorithm or hardware implemented network of artificial neurons or nodes) for deriving imaging data and/or a variety of other tissue information, such as tissue type characterization information, qualitative or quantitative diagnostic information, and other types of clinically relevant information) from raw ultrasound echo signals or from fully or partially beam-formed RF signals”) (Simpson, Para 31; “The neural network 160 may be trained to propagate the input (e.g., samples of raw echo signals and/or samples of beamformed signals) through the network of nodes to obtain predicted or estimated imaging data, which may subsequently be further processed for display. In some cases the network may be trained to operate in any one of a plurality of operational modes and may produce, responsive to the same input, a different type of imaging data or output other tissue information depending on the operational mode of the network. The mode may be selective (e.g., responsive to user input, or automatically selected by the system).”).
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Simpson and Tek as applied to claim 1 above, and further in view of Asami et al. (US20200200900, hereafter Asami).
Regarding claim 7, Simpson as modified by Tek above discloses all of the limitations of claim 1 as discussed above.
Simpson does not clearly and explicitly disclose wherein the Doppler flow ultrasound imaging mode comprises providing a spectral histogram of blood flow together with the user readable structural image of the first mode.
In an analogous ultrasound imaging field of endeavor Asami discloses providing a spectral histogram of blood flow together with a user readable structural image (Asami, Para 62; “When the data storage for the predetermined period ends, the histogram generation unit 87 generates a blood flow distribution (histogram) of the blood flow velocities acquired during the predetermined period (for example, 1 second). In the histogram of the blood flow distribution, as in an example shown in FIG. 7, velocities at a target cursor and at the vicinity thereof are plotted according to the frequency. At this time, threshold processing (for example, processing of removing a lower limit of the minimum blood flow velocity as a threshold) is performed (S345), and a value that is obviously not contained in the blood flow velocities is removed from the blood flow velocity data. Meanwhile, when a position of the cursor 401 is changed within one frame as shown in FIG. 4(b) during the predetermined period, the position after change is taken as a target in the next frame and the above steps S341 to S344 are repeated. In the example shown in FIG. 4(b), since the cursor is changed from the scan line x to a scan line y and the sample window is changed from the samples e-f to samples g-h, the transmission and reception for estimating the velocity causing no aliasing is performed and the velocity causing no aliasing is estimated with this position as a target. The cursor is transmitted and received for the speed estimation without folding, and the aliasing velocity is estimated. If the position of the cursor 401 is not changed during the predetermined period (S346), information about the blood flow velocity during the predetermined time, for example, a time corresponding to one cardiac cycle, is finally obtained.”) (Asami, Para 38; “During a measurement being performed under the control of the color Doppler control unit 71, the measurement condition calculation unit 85 estimates a velocity causing no aliasing (blood flow velocity in which aliasing is corrected) automatically or based on an instruction input via the input unit 30, and calculates a velocity range and a baseline position using the estimated velocity causing no aliasing. For this reason, as shown in FIG. 2, the measurement condition calculation unit 85 may include a blood flow velocity estimation unit 86, and may further include a histogram generation unit 87 for calculation of minimum and maximum blood flow velocities in a predetermined period. A function of the blood flow velocity estimation unit 86 may be performed by the color Doppler calculation unit 83.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Simpson wherein the Doppler flow ultrasound imaging mode comprises providing a spectral histogram of blood flow together with the user readable structural image of the first mode as taught by Asami in order to help with diagnosis by offering a detailed look at blood flow heterogeneity.
Claims 10-16 are rejected under 35 U.S.C. 103 as being unpatentable over Simpson and Tek as applied to claim 1 above, and further in view of Xie et al. (US20210177373, here after Xie).
Regarding claim 10, Simpson as modified by Tek above discloses all of the limitations of claim 1 as discussed above.
Simpson does not clearly and explicitly disclose (d) wherein the processor is further configured to obtain another unprocessed first mode image of the second plurality of images;(e) the unprocessed first mode image of (d) is submitted to the machine learning model to obtain one or more updated user metrics; and (f) the updated user metrics are provided to the user.
In an analogous ultrasound imaging field of endeavor Xie discloses submitting an image to a machine learning model to obtain one or more updated user metrics; and wherein updated user metrics are provided (Xie, Para 4; “In accordance with some examples of the present disclosure, an ultrasound system may include a probe configured to transmit ultrasound toward a subject for generating a real-time (or live) image of biological tissue of the subject, and a processor which is configured to receive the real-time image and to output a confidence metric for the real-time image, the confidence metric being indicative of a probability of the real-time ultrasound image visualizing the biological tissue in accordance with a target image view. In at least some embodiments, the processor may employ at least one artificial neural network to generate the confidence metric. Upon determination that the confidence metric exceeds a threshold value, the processor may be further configured to automatically capture (i.e. store in local memory) the real-time ultrasound image, to determine locations of first and second regions of interest (ROIs), and to compute a ratio of the echo-intensity values of the first and second ROIs. The processor may be further configured, if the confidence metric does not exceed the threshold value, to automatically receive one or more successive real-time image frames and output a confidence metric for each of the one or more successive real-time image frames so as to continue the process of identifying a suitable image frame for echo-intensity ration quantification. In one embodiment, the system is specifically configured for ultrasonically inspecting liver tissue, thus the biological tissue in the image frames may include at least one of hepatic tissue, renal tissue, or a combination thereof, and wherein the neural network may be specifically trained to produce a confidence metric that exceeds the threshold value if the input image corresponds to a sagittal liver and right kidney view suitable for computing the hepatic-renal echo-intensity ratio.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Simpson (d) wherein the processor is further configured to obtain another unprocessed first mode image of the second plurality of images;(e) the unprocessed first mode image of (d) is submitted to the machine learning model to obtain one or more updated user metrics; and (f) the updated user metrics are provided to the user in order to provide suitable images for diagnosis as taught by Xie (Xie, Para 4) which improves quality and reliability.
Regarding claim 11, Simpson as modified by Tek and Xie above discloses all of the limitations of claim 10 as discussed above.
Simpson does not clearly and explicitly disclose wherein the ultrasound imaging system is configured to repeat (d) and (e) in real-time.
In an analogous ultrasound imaging field of endeavor Xie discloses repeating (d) and (e) in real- time (Xie, Para 4; “In accordance with some examples of the present disclosure, an ultrasound system may include a probe configured to transmit ultrasound toward a subject for generating a real-time (or live) image of biological tissue of the subject, and a processor which is configured to receive the real-time image and to output a confidence metric for the real-time image, the confidence metric being indicative of a probability of the real-time ultrasound image visualizing the biological tissue in accordance with a target image view. In at least some embodiments, the processor may employ at least one artificial neural network to generate the confidence metric. Upon determination that the confidence metric exceeds a threshold value, the processor may be further configured to automatically capture (i.e. store in local memory) the real-time ultrasound image, to determine locations of first and second regions of interest (ROIs), and to compute a ratio of the echo-intensity values of the first and second ROIs. The processor may be further configured, if the confidence metric does not exceed the threshold value, to automatically receive one or more successive real-time image frames and output a confidence metric for each of the one or more successive real-time image frames so as to continue the process of identifying a suitable image frame for echo-intensity ration quantification. In one embodiment, the system is specifically configured for ultrasonically inspecting liver tissue, thus the biological tissue in the image frames may include at least one of hepatic tissue, renal tissue, or a combination thereof, and wherein the neural network may be specifically trained to produce a confidence metric that exceeds the threshold value if the input image corresponds to a sagittal liver and right kidney view suitable for computing the hepatic-renal echo-intensity ratio.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Simpson wherein the ultrasound imaging system is configured to repeat (d) and (e) in real-time in order to provide suitable images for diagnosis as taught by Xie (Xie, Para 4) which improves quality and reliability.
Regarding claim 12, Simpson as modified by Tek and Xie above discloses all of the limitations of claim 11 as discussed above.
Simpson does not clearly and explicitly disclose wherein the user metrics are provided until a target view is reached.
In an analogous ultrasound imaging field of endeavor Xie wherein the user metrics are provided until a target view is reached (Xie, Para 4; “In accordance with some examples of the present disclosure, an ultrasound system may include a probe configured to transmit ultrasound toward a subject for generating a real-time (or live) image of biological tissue of the subject, and a processor which is configured to receive the real-time image and to output a confidence metric for the real-time image, the confidence metric being indicative of a probability of the real-time ultrasound image visualizing the biological tissue in accordance with a target image view. In at least some embodiments, the processor may employ at least one artificial neural network to generate the confidence metric. Upon determination that the confidence metric exceeds a threshold value, the processor may be further configured to automatically capture (i.e. store in local memory) the real-time ultrasound image, to determine locations of first and second regions of interest (ROIs), and to compute a ratio of the echo-intensity values of the first and second ROIs. The processor may be further configured, if the confidence metric does not exceed the threshold value, to automatically receive one or more successive real-time image frames and output a confidence metric for each of the one or more successive real-time image frames so as to continue the process of identifying a suitable image frame for echo-intensity ration quantification. In one embodiment, the system is specifically configured for ultrasonically inspecting liver tissue, thus the biological tissue in the image frames may include at least one of hepatic tissue, renal tissue, or a combination thereof, and wherein the neural network may be specifically trained to produce a confidence metric that exceeds the threshold value if the input image corresponds to a sagittal liver and right kidney view suitable for computing the hepatic-renal echo-intensity ratio.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Simpson wherein the user metrics are provided until a target view is reached in order to provide suitable images for diagnosis as taught by Xie (Xie, Para 4) which improves quality and reliability.
Regarding claim 13, Simpson as modified by Tek and Xie above discloses all of the limitations of claim 12 as discussed above.
Simpson does not clearly and explicitly disclose wherein the target view is determined based at least in part on the diagnostic procedure.
In an analogous ultrasound imaging field of endeavor Xie wherein the target view is determined based at least in part on the diagnostic procedure (Xie, Para 4; “In accordance with some examples of the present disclosure, an ultrasound system may include a probe configured to transmit ultrasound toward a subject for generating a real-time (or live) image of biological tissue of the subject, and a processor which is configured to receive the real-time image and to output a confidence metric for the real-time image, the confidence metric being indicative of a probability of the real-time ultrasound image visualizing the biological tissue in accordance with a target image view. In at least some embodiments, the processor may employ at least one artificial neural network to generate the confidence metric. Upon determination that the confidence metric exceeds a threshold value, the processor may be further configured to automatically capture (i.e. store in local memory) the real-time ultrasound image, to determine locations of first and second regions of interest (ROIs), and to compute a ratio of the echo-intensity values of the first and second ROIs. The processor may be further configured, if the confidence metric does not exceed the threshold value, to automatically receive one or more successive real-time image frames and output a confidence metric for each of the one or more successive real-time image frames so as to continue the process of identifying a suitable image frame for echo-intensity ration quantification. In one embodiment, the system is specifically configured for ultrasonically inspecting liver tissue, thus the biological tissue in the image frames may include at least one of hepatic tissue, renal tissue, or a combination thereof, and wherein the neural network may be specifically trained to produce a confidence metric that exceeds the threshold value if the input image corresponds to a sagittal liver and right kidney view suitable for computing the hepatic-renal echo-intensity ratio.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Simpson wherein the target view is determined based at least in part on the diagnostic procedure in order to provide suitable images for diagnosis as taught by Xie (Xie, Para 4) which improves quality and reliability.
Regarding claim 14, Simpson as modified by Tek and Xie above discloses all of the limitations of claim 13 as discussed above.
Simpson does not clearly and explicitly disclose wherein the user metrics are provided until a threshold quality is reached.
In an analogous ultrasound imaging field of endeavor Xie wherein the user metrics are provided until a threshold quality is reached (Xie, Para 4; “In accordance with some examples of the present disclosure, an ultrasound system may include a probe configured to transmit ultrasound toward a subject for generating a real-time (or live) image of biological tissue of the subject, and a processor which is configured to receive the real-time image and to output a confidence metric for the real-time image, the confidence metric being indicative of a probability of the real-time ultrasound image visualizing the biological tissue in accordance with a target image view. In at least some embodiments, the processor may employ at least one artificial neural network to generate the confidence metric. Upon determination that the confidence metric exceeds a threshold value, the processor may be further configured to automatically capture (i.e. store in local memory) the real-time ultrasound image, to determine locations of first and second regions of interest (ROIs), and to compute a ratio of the echo-intensity values of the first and second ROIs. The processor may be further configured, if the confidence metric does not exceed the threshold value, to automatically receive one or more successive real-time image frames and output a confidence metric for each of the one or more successive real-time image frames so as to continue the process of identifying a suitable image frame for echo-intensity ration quantification. In one embodiment, the system is specifically configured for ultrasonically inspecting liver tissue, thus the biological tissue in the image frames may include at least one of hepatic tissue, renal tissue, or a combination thereof, and wherein the neural network may be specifically trained to produce a confidence metric that exceeds the threshold value if the input image corresponds to a sagittal liver and right kidney view suitable for computing the hepatic-renal echo-intensity ratio.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Simpson wherein the user metrics are provided until a threshold quality is reached in order to provide suitable images for diagnosis as taught by Xie (Xie, Para 4) which improves quality and reliability.
Regarding claim 15, Simpson as modified by Tek and Xie above discloses all of the limitations of claim 14 as discussed above.
Simpson does not clearly and explicitly disclose wherein the threshold quality depends upon a presence of a target structural feature of an organ, a clarity of structural image quality, Doppler image quality, or a combination thereof.
In an analogous ultrasound imaging field of endeavor Xie wherein the threshold quality depends upon a presence of a target structural feature of an organ, a clarity of structural image quality, Doppler image quality, or a combination thereof (Xie, Para 5; “the artificial neural network may include a deep convolutional neural network trained to segment the input image to generate a segmentation map, and the confidence metric may be based, at least in part, on the segmentation map of the real-time image. In some examples, a processor (implementing e.g., another neural network or a non machine-learning algorithm) may compare the segmentation map output by the segmentation neural network to a segmentation map or image corresponding to the target image view. The comparison may be done by a neural network or other image processing technique, for example by overlaying the two maps and quantifying the differences. In yet other examples, the confidence metric may be computed by quantitatively analyzing the content of the segmentation map, e.g., to determine whether the map, and thus the source image, contains a sufficient amount of a particular type of tissue (e.g., kidney tissue) and/or the image visualizes the particular type of tissue in the appropriate location within the image”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Simpson wherein the threshold quality depends upon a presence of a target structural feature of an organ, a clarity of structural image quality, Doppler image quality, or a combination thereof in order to provide suitable images for diagnosis as taught by Xie (Xie, Para 4) which improves quality and reliability.
Regarding claim 16, Simpson as modified by Tek and Xie above discloses all of the limitations of claim 15 as discussed above.
Simpson further discloses wherein blood flow takes place in the target organ (Simpson, Para 46; “For example, in ultrasonic liver imaging, ultrasonic attenuation and back-scattering (i.e., tissue echogenicity) increases in proportion to fat content while speed of ultrasound correspondingly reduces. By quantifying the ultrasound attenuation, echogenicity and/or speed from the beamformed RF echoes and correlating this attenuation with fat content, estimates of the fat content of the liver (or other tissue or organs, in other applications) may be performed with ultrasound. The customer-facing output of such a system may be quantitative (e.g., a single value representing the fat fraction within the imaged tissue), which may be displayed onto an image of the anatomy (e.g., for a specific point or region of interest) or it may be graphically represented, with each quantitative value being color-coded and overlaid on a 2D image or a 3D volume rendering of the liver (or other organ or tissue) similar to conventional overlays of blood flow or elastography information. As described, a neural network”).
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Simpson and Tek as applied to claim 1 above, and further in view of Li et al. (US20240173007, hereafter Li).
Regarding claim 17, Simpson as modified by Tek above discloses all of the limitations of claim 1 as discussed above.
Simpson does not clearly and explicitly disclose wherein an unprocessed second mode data is used to determine the user metrics.
In an analogous ultrasound imaging field of endeavor Li discloses wherein an unprocessed second mode data is used to determine the user metrics (Li, Para 50; “A predictive model such as a deep learning, classification model (e.g., a convolutional neural network (CNN) or other suitable neural network) can be trained to determine whether the MR jet represented in each of the color Doppler images is anterior, posterior, central, or a mix, and based on this classification, the system may output the quality metric associated with each dynamically changing position of the probe (as the user adjusts—translate and/or angulates the probe within the PLAX window). Additionally and optionally, the system may guide the user to rotate around the MR jet's direction for a certain range of angles to search (with dynamic visual feedback) for the best angle that visualizes the MR jet, and/or to translate the probe along the MR jet direction (e.g., towards LA) to identify (with visual dynamic visual feedback) the optimal position”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Simpson wherein an unprocessed second mode data is used to determine the user metrics in order to improve visualization and achieve optimal positioning as taught by Li (Li, Para 50).
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 John Li whose telephone number is (313)446-4916. The examiner can normally be reached Monday to Thursday; 5:30 AM to 3:30 PM Eastern.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Pascal Bui-Pho can be reached at (571) 272-2714. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/JOHN D LI/Primary Examiner, Art Unit 3798
Prosecution Insights