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 .
DETAILED ACTION
Claims 1 – 20 are pending in this application. Claims 1, 15 and 18 are independent.
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 pre-AIA 35 U.S.C. 112, second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1 – 20 are rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, 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.
The terms "…partially filtered data…", "…partially filtered image…", "…partially processed image…", "…potential secondary/second filters…" are relative terms which renders the claim indefinite. The terms are not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. Appropriate action 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 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 of this title, 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.
Claim(s) 1 – 17 are rejected under 35 U.S.C. 103 as being unpatentable over DE MAN; Bruno Kristiaan Bernard (US-20190328348-A1, hereinafter simply referred to as Bruno) in view of ZABIC, Stanislav (US-20210225046-A1, hereinafter simply referred to as Zabic).
Regarding independent claim(s) 1 and 15, Bruno teaches:
A method (e.g., method of Bruno) for processing images comprising: retrieving measured data for a first image (See at least Bruno, ¶ [0003]; FIGS. 2 – 11; "…various imaging modalities, such as X-ray-based computed tomography (CT) measure projection data of an object or patient from various angles or views about the object or patient…Using tomographic reconstruction techniques, cross-sectional images or volumetric images can be estimated or “reconstructed” from the projection data…"), the measured data being in a frequency domain or in a domain other than the frequency domain (See at least Bruno, ¶ [0040]; FIGS. 2 – 11; "…The input data and/or the target data may also undergo a pre-processing step such that one or both are converted to a domain where the missing data is easier to estimate…"); generating partially filtered data by applying a first filter to the measured data, the first filter being a generic filter (See at least Bruno, ¶ [0045]; FIGS. 2 – 11; "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data, where some aspects of the reconstruction process (e.g., multi-scale filtering, ramp-filtering, etc.) may already be performed by the processing…"); reconstructing the partially filtered data to generate a partially filtered image (See at least Bruno, ¶ [0003, 0045]; FIGS. 2 – 11; "…various imaging modalities, such as X-ray-based computed tomography (CT) measure projection data of an object or patient from various angles or views about the object or patient…Using tomographic reconstruction techniques, cross-sectional images or volumetric images can be estimated or “reconstructed” from the projection data…", "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data, where some aspects of the reconstruction process (e.g., multi-scale filtering, ramp-filtering, etc.) may already be performed by the processing…"); outputting the filtered image (See at least Bruno, ¶ [0003, 0045]; FIGS. 2 – 11; "…various imaging modalities, such as X-ray-based computed tomography (CT) measure projection data of an object or patient from various angles or views about the object or patient…Using tomographic reconstruction techniques, cross-sectional images or volumetric images can be estimated or “reconstructed” from the projection data…", "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data, where some aspects of the reconstruction process (e.g., multi-scale filtering, ramp-filtering, etc.) may already be performed by the processing…").
Bruno teaches the subject matter of the claimed inventive concept as expressed in the rejections above.
But, Bruno does not expressly disclose the concept of generating a partially processed image by applying a first processing routine to the partially filtered image; generating a filtered image by applying a second filter to the partially processed image, the second filter being a filter selected from a plurality of potential secondary filters.
Nevertheless, Zabic teaches the concept of generating a partially processed image by applying a first processing routine to the partially filtered image (See at least Zabic, ¶ [0118]; FIGS. 1, 5, 7; "…the first air mask may be used for image processing, image segmentation, image denoising, or the like…"); generating a filtered image by applying a second filter to the partially processed image, the second filter being a filter selected from a plurality of potential secondary filters (See at least Zabic, ¶ [0155]; FIGS. 1, 5, 7; "…The processing device 140 may perform a 2D low-pass filtering on the first seed image to reduce streak artifacts…").
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use and apply the known technique of generating a partially processed image by applying a first processing routine to the partially filtered image; generating a filtered image by applying a second filter to the partially processed image, the second filter being a filter selected from a plurality of potential secondary filters as disclosed in the device of Zabic to modify and improve the known and similar device of Bruno for the desirable and advantageous purpose of accelerating the iterative reconstruction, as discussed in Zabic (See ¶ [0003]); thereby, achieving the predictable result of improving the overall efficiency and speed of the system with a reasonable expectation of success while enabling others skilled in the art to best utilize the invention along with various implementations and modifications as are suited to the particular use contemplated.
Regarding dependent claim 2, Bruno modified by Zabic above teaches:
wherein the method further comprises initially converting any measured data provided to the frequency domain if in the domain other than the frequency domain (See at least Bruno, ¶ [0040, 0063]; FIGS. 2 – 11; "…The input data and/or the target data may also undergo a pre-processing step such that one or both are converted to a domain where the missing data is easier to estimate…", "…the presence, extent, and boundaries of missing data regions may be determined using one or more of: (1) thresholding or segmentation directly in the projection domain; (2) an initial image reconstruction, followed by thresholding or segmentation in the image domain, followed by re-projection, followed by thresholding or masking…"), wherein the generating of partially filtered data is by applying the first filter to the measured data in the frequency domain (See at least Bruno, ¶ [0043]; FIGS. 2 – 11; "…the knowledge about the periodicity of the data (such as within traces corresponding to input data as well as in traces corresponding to data to be estimated, as discussed below) the Fourier transform of the data may be used for input and/or output. Additional or subsequent layers may optionally be used to implement/approximate a Fourier or inverse Fourier transform…"), and wherein reconstruction comprises converting the partially filtered data to an image domain (See at least Bruno, ¶ [0040, 0063]; FIGS. 2 – 11; "…The input data and/or the target data may also undergo a pre-processing step such that one or both are converted to a domain where the missing data is easier to estimate…", "…the presence, extent, and boundaries of missing data regions may be determined using one or more of: (1) thresholding or segmentation directly in the projection domain; (2) an initial image reconstruction, followed by thresholding or segmentation in the image domain, followed by re-projection, followed by thresholding or masking…").
Regarding dependent claim 3, Bruno modified by Zabic above teaches:
wherein generating the filtered image comprises: extracting partially processed data from the partially processed image and converting the partially processed data to the frequency domain (See at least Bruno, ¶ [0040, 0063]; FIGS. 2 – 11; "…The input data and/or the target data may also undergo a pre-processing step such that one or both are converted to a domain where the missing data is easier to estimate…", "…the presence, extent, and boundaries of missing data regions may be determined using one or more of: (1) thresholding or segmentation directly in the projection domain; (2) an initial image reconstruction, followed by thresholding or segmentation in the image domain, followed by re-projection, followed by thresholding or masking…"); generating filtered partially processed data by applying the second filter in the frequency domain (See at least Zabic, ¶ [0155]; FIGS. 1, 5, 7; "…The processing device 140 may perform a 2D low-pass filtering on the first seed image to reduce streak artifacts…"); converting the filtered partially processed data to the image domain to generate the filtered image (See at least Bruno, ¶ [0040, 0063]; FIGS. 2 – 11; "…The input data and/or the target data may also undergo a pre-processing step such that one or both are converted to a domain where the missing data is easier to estimate…", "…the presence, extent, and boundaries of missing data regions may be determined using one or more of: (1) thresholding or segmentation directly in the projection domain; (2) an initial image reconstruction, followed by thresholding or segmentation in the image domain, followed by re-projection, followed by thresholding or masking…").
Regarding dependent claim 4, Bruno modified by Zabic above teaches:
wherein the measured data comprises projection data for a CT image (See at least Bruno, ¶ [0003]; FIGS. 2 – 11; "…various imaging modalities, such as X-ray-based computed tomography (CT) measure projection data of an object or patient from various angles or views about the object or patient…Using tomographic reconstruction techniques, cross-sectional images or volumetric images can be estimated or “reconstructed” from the projection data…" Also, see at least Zabic, ¶ [Abstract, 0098, 0155]; FIGS. 1, 5, 7).
Regarding dependent claim 5, Bruno modified by Zabic above teaches:
wherein the reconstruction of the partially filtered data is by back-projecting the partially filtered data (See at least Bruno, ¶ [0003, 0039]; FIGS. 2 – 11; "…various imaging modalities, such as X-ray-based computed tomography (CT) measure projection data of an object or patient from various angles or views about the object or patient…Using tomographic reconstruction techniques, cross-sectional images or volumetric images can be estimated or “reconstructed” from the projection data…", "…the ramp-filter in a filtered backprojection reconstruction algorithm is sensitive to the derivative of the data (within each projection image)…" Also, see at least Zabic, ¶ [Abstract, 0098, 0155]; FIGS. 1, 5, 7).
Regarding dependent claim 6, Bruno modified by Zabic above teaches:
wherein the first processing routine is a first machine-learning algorithm (e.g., ¶[0034] of Bruno) trained on measured data filtered by applying the first filter but not the second filter (See at least Bruno, ¶ [0003, 0039]; FIGS. 2 – 11; "…various imaging modalities, such as X-ray-based computed tomography (CT) measure projection data of an object or patient from various angles or views about the object or patient…Using tomographic reconstruction techniques, cross-sectional images or volumetric images can be estimated or “reconstructed” from the projection data…", "…the ramp-filter in a filtered backprojection reconstruction algorithm is sensitive to the derivative of the data (within each projection image)…" Also, see at least Zabic, ¶ [Abstract, 0098, 0118, 0155]; FIGS. 1, 5, 7).
Regarding dependent claim 7, Bruno modified by Zabic above teaches:
wherein the first processing routine is a denoising routine, an image segmentation routine, or a diagnosis prediction routine (See at least Bruno, ¶ [0003, 0039]; FIGS. 2 – 11; "…various imaging modalities, such as X-ray-based computed tomography (CT) measure projection data of an object or patient from various angles or views about the object or patient…Using tomographic reconstruction techniques, cross-sectional images or volumetric images can be estimated or “reconstructed” from the projection data…", "…the ramp-filter in a filtered backprojection reconstruction algorithm is sensitive to the derivative of the data (within each projection image)…" Also, see at least Zabic, ¶ [Abstract, 0098, 0118, 0155]; FIGS. 1, 5, 7).
Regarding dependent claim 8, Bruno modified by Zabic above teaches:
wherein the first filter is a ramp filter (See at least Bruno, ¶ [0003, 0039]; FIGS. 2 – 11; "…various imaging modalities, such as X-ray-based computed tomography (CT) measure projection data of an object or patient from various angles or views about the object or patient…Using tomographic reconstruction techniques, cross-sectional images or volumetric images can be estimated or “reconstructed” from the projection data…", "…the ramp-filter in a filtered backprojection reconstruction algorithm is sensitive to the derivative of the data (within each projection image)…" Also, see at least Zabic, ¶ [Abstract, 0098, 0118, 0155]; FIGS. 1, 5, 7).
Regarding dependent claim 9, Bruno modified by Zabic above teaches:
wherein each of the plurality of potential secondary filters, if applied to the partially processed image, would generate different image and noise characteristics in a resulting filtered image (See at least Bruno, ¶ [0003, 0039]; FIGS. 2 – 11; "…various imaging modalities, such as X-ray-based computed tomography (CT) measure projection data of an object or patient from various angles or views about the object or patient…Using tomographic reconstruction techniques, cross-sectional images or volumetric images can be estimated or “reconstructed” from the projection data…", "…the ramp-filter in a filtered backprojection reconstruction algorithm is sensitive to the derivative of the data (within each projection image)…" Also, see at least Zabic, ¶ [Abstract, 0098, 0109, 0118, 0155]; FIGS. 1, 5, 7), and wherein the filtered image resulting from the application of the second filter to the partially processed image is different than a hypothetical filtered image resulting from the application of a different filter of the plurality of potential secondary filters (See at least Bruno, ¶ [0003, 0039]; FIGS. 2 – 11; "…various imaging modalities, such as X-ray-based computed tomography (CT) measure projection data of an object or patient from various angles or views about the object or patient…Using tomographic reconstruction techniques, cross-sectional images or volumetric images can be estimated or “reconstructed” from the projection data…", "…the ramp-filter in a filtered backprojection reconstruction algorithm is sensitive to the derivative of the data (within each projection image)…" Also, see at least Zabic, ¶ [Abstract, 0098, 0102, 0109, 0118, 0155]; FIGS. 1, 5, 7).
Regarding dependent claim 10, Bruno modified by Zabic above teaches:
wherein a first of the potential second filters is a soft reconstruction filter and a second of the potential second filters is a sharp reconstruction filter (See at least Bruno, ¶ [0040]; FIGS. 2 – 11; "…After deep learning estimation of the missing data, a one-dimensional or multi-dimensional low-pass filter may be applied to compensate for the effect of the high-pass filter…" Also, see at least Zabic, ¶ [Abstract, 0098, 0102, 0109, 0118, 0155]; FIGS. 1, 5, 7).
Regarding dependent claim 11, Bruno modified by Zabic above teaches:
wherein the second filter is selected from the plurality of potential secondary filters based on the body part or type of tissue represented in the first image (See at least Bruno, ¶ [0040]; FIGS. 2 – 11; "…After deep learning estimation of the missing data, a one-dimensional or multi-dimensional low-pass filter may be applied to compensate for the effect of the high-pass filter…" Also, see at least Zabic, ¶ [Abstract, 0098, 0102, 0109, 0118, 0155]; FIGS. 1, 5, 7).
Regarding dependent claim 12, Bruno modified by Zabic above teaches:
evaluating the partially processed image and outputting a result of the evaluation of the partially processed image prior to or with the filtered image (See at least Bruno, ¶ [0040, 0045]; FIGS. 2 – 11; "…After deep learning estimation of the missing data, a one-dimensional or multi-dimensional low-pass filter may be applied to compensate for the effect of the high-pass filter…", "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data…" Also, see at least Zabic, ¶ [Abstract, 0098, 0102, 0109, 0118, 0155]; FIGS. 1, 5, 7).
Regarding dependent claim 13, Bruno modified by Zabic above teaches:
evaluating the partially processed image prior to generating the filtered image, and selecting the second filter for application based at least partially on the evaluation of the partially processed image (See at least Bruno, ¶ [0063]; FIGS. 2 – 11; "…regions of corrupted data may be identified or estimated by an evaluation of the local projection image quality, which itself may use a deep learning approach (or other approach known in the art) to estimate the local “quality” of the acquired projection data…" Also, see at least Zabic, ¶ [Abstract, 0098, 0102, 0109, 0118, 0155]; FIGS. 1, 5, 7, 9).
Regarding dependent claim 14, Bruno modified by Zabic above teaches:
wherein the first processing routine is an image segmentation routine and wherein the partially processed image is segmented into a plurality of segments (See at least Bruno, ¶ [0063]; FIGS. 2 – 11; "…a missing data region 162 may be determined using segmentation directly in the projection domain; (2) an initial image reconstruction, followed by segmentation in the image domain... regions of corrupted data may be identified or estimated by an evaluation of the local projection image quality, which itself may use a deep learning approach (or other approach known in the art) to estimate the local “quality” of the acquired projection data…" Also, see at least Zabic, ¶ [Abstract, 0098, 0102, 0109, 0118, 0155]; FIGS. 1, 5, 7, 9), and wherein different second filters selected from the plurality of potential secondary filters are applied to different segments of the plurality of segments (See at least Bruno, ¶ [0063]; FIGS. 2 – 11; "…a missing data region 162 may be determined using segmentation directly in the projection domain; (2) an initial image reconstruction, followed by segmentation in the image domain... regions of corrupted data may be identified or estimated by an evaluation of the local projection image quality, which itself may use a deep learning approach (or other approach known in the art) to estimate the local “quality” of the acquired projection data…" Also, see at least Zabic, ¶ [Abstract, 0098, 0102, 0109, 0118, 0155]; FIGS. 1, 5, 7, 9).
Regarding dependent claim 16, Bruno modified by Zabic above teaches:
wherein the processing circuitry initially converts any measured data obtained in the domain other than the frequency domain to the frequency domain and converts the partially filtered data to an image domain during reconstruction (See at least Bruno, ¶ [0040, 0045]; FIGS. 2 – 11; "…The input data and/or the target data may also undergo a pre-processing step such that one or both are converted to a domain where the missing data is easier to estimate…After deep learning estimation of the missing data, a one-dimensional or multi-dimensional low-pass filter may be applied to compensate for the effect of the high-pass filter…", "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data…" Also, see at least Zabic, ¶ [Abstract, 0098, 0102, 0109, 0118, 0155]; FIGS. 1, 5, 7), wherein the generating of partially filtered image data is by applying the first filter to the image data in the frequency domain (See at least Bruno, ¶ [0040, 0045]; FIGS. 2 – 11; "…The input data and/or the target data may also undergo a pre-processing step such that one or both are converted to a domain where the missing data is easier to estimate…After deep learning estimation of the missing data, a one-dimensional or multi-dimensional low-pass filter may be applied to compensate for the effect of the high-pass filter…", "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data…" Also, see at least Zabic, ¶ [Abstract, 0098, 0102, 0109, 0118, 0155]; FIGS. 1, 5, 7), and wherein the reconstruction of the partially filtered image data is by back-projecting the partially filtered data (See at least Bruno, ¶ [0040, 0045]; FIGS. 2 – 11; "…The input data and/or the target data may also undergo a pre-processing step such that one or both are converted to a domain where the missing data is easier to estimate…After deep learning estimation of the missing data, a one-dimensional or multi-dimensional low-pass filter may be applied to compensate for the effect of the high-pass filter…", "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data…" Also, see at least Zabic, ¶ [Abstract, 0098, 0102, 0109, 0118, 0155]; FIGS. 1, 5, 7).
Regarding dependent claim 17, Bruno modified by Zabic above teaches:
wherein the first processing routine is a first machine-learning algorithm trained on measured data filtered by applying the first filter but not the second filter(See at least Bruno, ¶ [0040, 0045]; FIGS. 2 – 11; "…The input data and/or the target data may also undergo a pre-processing step such that one or both are converted to a domain where the missing data is easier to estimate…After deep learning estimation of the missing data, a one-dimensional or multi-dimensional low-pass filter may be applied to compensate for the effect of the high-pass filter…", "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data…" Also, see at least Zabic, ¶ [Abstract, 0098, 0102, 0109, 0118, 0155]; FIGS. 1, 5, 7).
Claim(s) 18 – 20 are rejected under 35 U.S.C. 103 as being unpatentable over DE MAN; Bruno Kristiaan Bernard (US-20190328348-A1, hereinafter simply referred to as Bruno).
Regarding independent claim 18, Bruno teaches:
A method for training a neural network model (e.g., FIG. 10 of Bruno) comprising: retrieving sample measured data for an image of an object (See at least Bruno, ¶ [0003]; FIGS. 2 – 11; "…various imaging modalities, such as X-ray-based computed tomography (CT) measure projection data of an object or patient from various angles or views about the object or patient…Using tomographic reconstruction techniques, cross-sectional images or volumetric images can be estimated or “reconstructed” from the projection data…"); retrieving a first target image associated with the sample image data for use as ground truth (See at least Bruno, ¶ [0037]; FIGS. 2 – 11; "…The loss or error function 62 measures the difference between the network output (i.e., predicted projection data values) and the corresponding training target (i.e., actual or ground truth projection data values)…"); generating partially filtered sample measured data by applying a first filter to the sample measured data, the first filter being a generic filter (See at least Bruno, ¶ [0045]; FIGS. 2 – 11; "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data, where some aspects of the reconstruction process (e.g., multi-scale filtering, ramp-filtering, etc.) may already be performed by the processing…"); reconstructing the partially filtered data to generate a partially filtered image (See at least Bruno, ¶ [0003, 0045]; FIGS. 2 – 11; "…various imaging modalities, such as X-ray-based computed tomography (CT) measure projection data of an object or patient from various angles or views about the object or patient…Using tomographic reconstruction techniques, cross-sectional images or volumetric images can be estimated or “reconstructed” from the projection data…", "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data, where some aspects of the reconstruction process (e.g., multi-scale filtering, ramp-filtering, etc.) may already be performed by the processing…"); applying a first processing routine based on the neural network model being trained to the partially filtered image to generate a partially processed image (See at least Bruno, ¶ [0040, 0045]; FIGS. 2 – 11; "…After deep learning estimation of the missing data, a one-dimensional or multi-dimensional low-pass filter may be applied to compensate for the effect of the high-pass filter…", "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data, where some aspects of the reconstruction process (e.g., multi-scale filtering, ramp-filtering, etc.) may already be performed by the processing…"); generating a first filtered image by applying a second filter to the partially processed image (See at least Bruno, ¶ [0040, 0045]; FIGS. 2 – 11; "…After deep learning estimation of the missing data, a one-dimensional or multi-dimensional low-pass filter may be applied to compensate for the effect of the high-pass filter…", "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data, where some aspects of the reconstruction process (e.g., multi-scale filtering, ramp-filtering, etc.) may already be performed by the processing…"), the second filter being a filter selected from a plurality of potential secondary filters (See at least Bruno, ¶ [0040, 0045]; FIGS. 2 – 11; "…After deep learning estimation of the missing data, a one-dimensional or multi-dimensional low-pass filter may be applied to compensate for the effect of the high-pass filter…", "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data, where some aspects of the reconstruction process (e.g., multi-scale filtering, ramp-filtering, etc.) may already be performed by the processing…"); and evaluating the output of the processing routine by comparing the first filtered image to the first target image, the target image being associated with the second filter (See at least Bruno, ¶ [0063]; FIGS. 2 – 11; "…regions of corrupted data may be identified or estimated by an evaluation of the local projection image quality, which itself may use a deep learning approach (or other approach known in the art) to estimate the local “quality” of the acquired projection data…").
Bruno teaches the subject matter of the claimed inventive concept as expressed in the rejections above. However, the teachings are taught in separate embodiments.
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Bruno taught in separate embodiments for the desirable and advantageous purpose combining multi-scale processing with non-linear processing (e.g., using soft-thresholding to minimize streak artifacts), leading to a significant improvement in achieved image quality, as discussed in Bruno (See ¶ [0045]); thereby, achieving the predictable result of improving the overall efficiency and speed of the system with a reasonable expectation of success while enabling others skilled in the art to best utilize the invention along with various implementations and modifications as are suited to the particular use contemplated.
Regarding dependent claim 19, Bruno teaches:
wherein the first target image is one of a plurality of target images associated with the sample image data (See at least Bruno, ¶ [0037]; FIGS. 2 – 11; "…The loss or error function 62 measures the difference between the network output (i.e., predicted projection data values) and the corresponding training target (i.e., actual or ground truth projection data values)…"), and where each of the plurality of target images are associated with different second filters of the plurality of potential secondary filters (See at least Bruno, ¶ [0040, 0045]; FIGS. 2 – 11; "…After deep learning estimation of the missing data, a one-dimensional or multi-dimensional low-pass filter may be applied to compensate for the effect of the high-pass filter…", "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data, where some aspects of the reconstruction process (e.g., multi-scale filtering, ramp-filtering, etc.) may already be performed by the processing…"), and wherein the method further comprises: generating a second filtered image by applying an alternative second filter to the partially processed image (See at least Bruno, ¶ [0040, 0045]; FIGS. 2 – 11; "…After deep learning estimation of the missing data, a one-dimensional or multi-dimensional low-pass filter may be applied to compensate for the effect of the high-pass filter…", "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data, where some aspects of the reconstruction process (e.g., multi-scale filtering, ramp-filtering, etc.) may already be performed by the processing…"), the alternative second filter selected from the plurality of potential secondary filters (See at least Bruno, ¶ [0040, 0045]; FIGS. 2 – 11; "…After deep learning estimation of the missing data, a one-dimensional or multi-dimensional low-pass filter may be applied to compensate for the effect of the high-pass filter…", "…the missing data estimation step as performed by the neural network may be tightly integrated with the specific reconstruction process that is utilized to generate a 3D volumetric image from the processed projection data, where some aspects of the reconstruction process (e.g., multi-scale filtering, ramp-filtering, etc.) may already be performed by the processing…"), and evaluating the output of the processing routine further by comparing the second filtered image to an alternative target image associated with the alternative second filter (See at least Bruno, ¶ [0063]; FIGS. 2 – 11; "…regions of corrupted data may be identified or estimated by an evaluation of the local projection image quality, which itself may use a deep learning approach (or other approach known in the art) to estimate the local “quality” of the acquired projection data…").
Regarding dependent claim 20, Bruno modified by Zabic above teaches:
wherein the method is repeated for sample measured data for a plurality of images (See at least Bruno, ¶ [0032]; FIGS. 2 – 11; "…a portion of the reconstructed volume is not measured or is insufficiently sampled due to the finite number of detector rows…") and wherein for each repetition of the method, the neural network model is modified based on the evaluation of the output of the processing routine (See at least Bruno, ¶ [0047]; FIGS. 2 – 11; "…Note that in any of these scenarios, later stages of the training process may still be configured to update/modify parts of the network 50 that were previously pre-trained or explicitly modeled or selected, thereby further improving performance of the overall network…").
Conclusion
The prior art made of record and not relied upon is considered pertinent to Applicant's disclosure: See the Notice of References Cited (PTO–892)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to IDOWU O OSIFADE whose telephone number is (571)272-0864. The Examiner can normally be reached on Monday-Friday 8:00am-5:00pm EST.
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, ANDREW MOYER can be reached on (571) 272 – 9523. The fax phone number for the organization where this application or proceeding is assigned is (571) 273 – 8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov.
Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at (866) 217 – 9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call (800) 786 – 9199 (IN USA OR CANADA) or (571) 272 – 1000.
/IDOWU O OSIFADE/Primary Examiner, Art Unit 2675
Prosecution Insights