DETAILED ACTION
This action is in response to the application filed on November 21st, 2023. Claims 1-20 are pending and have been examined.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statements (IDS) submitted on November 21st, 2023 and April 23rd, 2025 are being considered by the examiner.
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 1-5, 7-10, 12-13, 15, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over “Improving best-phase image quality in cardiac CT by motion correction with MAM optimization” (herein after referred to by its primary author, Rohkohl) in view of US11379994 (herein after referred to by its primary author, Lauritsch).
In regards to claim 1, Rohkohl teaches a method for performing cardiac motion compensation in a computed tomography(CT) imaging system (Rohkohl Figure 1; Abstract “Motion estimation is based on the definition of motion artifact metrics (MAM) to quantify motion artifacts in a 3-D reconstructed image volume”), the method comprising: receiving projection data acquired from an imaging object by the CT imaging system (Rohkohl Figure 1 “Parametric motion model with parameters s”); until a predefined termination criterion is met, iteratively reconstructing, based on estimated cardiac motion, the received projection data to generate a motion-compensated image of the imaging object (Rohkohl Figure 1 “Optimization” and “Motion compensated reconstruction”), determining a vessel region of interest (ROI) Rohkohl Figure 1 “Computer region of interest [OMEGA] with motion (M-ROI) by coronary segmentation”), and updating the estimated cardiac motion, based on an optimization cost function associated with the determined vessel ROI (Rohkohl Figure 1 “Gradient descent parameter update” and “MAM”); and outputting, as a final reconstructed image of the imaging object, the generated motion-compensated image (Rohkohl Figure 1 “Final image reconstruction”).
Rohkohl fails to teach determining a vessel region of interest (ROI) within the generated motion compensated image.
However, Lauritsch teaches determining a vessel region of interest (ROI) within the generated motion compensated image. (Lauritsch Figure 2 S3; Column 14, lines 57-65 “A further predetermined parameter is an update interval K, which specifies after how many iterative acts k the reference image 13 is updated. To update the reference image 13, the most current iterative image 17 in each case is described as the provisional motion-compensated image, as for process act S3, and segmented as indicated here by a program path 18 in order to obtain a new or updated reference image 13, the respective existing reference image 13 being replaced.”; Column 13 Lines 26-39 “In a process act S3, the initial reconstructed image 11 is segmented, in particular automatically, for example by using an intensity-based thresholding method. The result is a reference image 13, which may be thinly or sparsely populated—even compared with the initial reconstructed image 11… The reference image 13 shows at least one part of the vascular tree 12 but may be restricted to the maximum-intensity regions thereof.” Examiner note: This first portion of this reference teaches that a motion compensated image can be segmented. The second portion of this reference teaches that the segmentation would result in a vascular tree, which is analogous to a vessel region)
Lauritsch is considered to be analogous to the claimed invention because they are both in the same field of cardiac motion compensation. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have modified the system of Rohkohl to include the teachings of Lauritsch, to provide the advantage of a system which can estimate cardiac motion with low amounts of data, allowing for faster processing (Lauritsch Column 6 Line 8-12 “The present disclosure is therefore suited in particular to thinly or sparsely populated target objects or corresponding projection images with a relatively high contrast, because even when the target object is moving, a tomographic reconstruction is possible in a particularly reliable manner.”).
In regards to claim 2, Rohkohl in view of Lauritsch teaches the method of claim 1, wherein for a first iteration, the estimated cardiac motion is set to a predefined value (Lauritsch Column 14 Lines 12-14 “The motion field, that is, the vectors thereof s, may initially be determined on a predetermined grid, for example with a width, that is, a point spacing, of 25 mm for instance.”).
In regards to claim 3, Rohkohl in view of Lauritsch teaches the method of claim 1, wherein the predefined termination criterion is: that a predefined number of iterations are completed, or that the optimization cost function reaches a predefined threshold (Lauritsch Column 14 Line 30-31 “As a termination condition, a predetermined number of iterative acts or a similarity criterion or a quality criterion may be specified for the iterative image 17, for example.”).
In regards to claim 4, Rohkohl in view of Lauritsch teaches the method of claim 1, further comprising: reconstructing the received projection data to generate an image without motion compensation of the imaging object (Rohkohl Figure 2 “Initial reconstruction”; Section II.A. “In a first step the coronary arteries are segmented from a standard partial scan image with potential motion artifacts, using an in-house segmentation algorithm”); and performing, based on the generated image without motion compensation, vessel segmentation to develop a vessel region mask (Rohkohl Figure 2 “Compute region of interest [OMEGA] with motion (M-ROI) by coronary segmentation”; Section II.E “We confine motion estimation to specific regions of interest [OMEGA] with motion (M-ROI), located around the coronary arteries.”), wherein the determining step further comprises identifying, based on the developed vessel region mask, a region within the generated motion-compensated image, as the determined vessel ROI (Rohkohl Figure 2 “Motion compensated reconstruction f(x, sk), x ε [OMEGA]” Examiner note: This step shows that a reconstruction f(x, sk) is computed, where only values of x contained within the set of [OMEGA] are used. This is analogous to using a region mask, as they are both ensuring that only the proper region of interest is used within the reconstruction), and the updating step further comprises: calculating cardiac motion to minimize a loss function of the determined vessel ROI (Rohkohl Figure 2; Section II.F. “The MAM should be able to assess the relative amount of motion artifacts in an image or an image region. As the true anatomy of the organs in a motion-corrupted clinical dataset is unknown, a quality metric is required which does not rely on such reference information. The metrics are described by a function L(s) which computes the MAM value for the motion compensated reconstruction corresponding to the motion model parameters s in a region of interest. In the following we propose two different metrics to assess the relative amount of motion artifacts: entropy and positivity.”; Section II.G “Motion estimation corresponds to finding a set of motion parameters s that minimizes a MAM.” Examiner note: In this reference, MAM stands for motion artifact metrics. Section II.F shows that one of the motion artifact metrics used is the entropy of the vessel ROI. Section II.G shows that this motion estimation is meant to find a set of motion parameters which minimizes this MAM.), and updating the estimated cardiac motion to the calculated cardiac motion (Rohkohl Figure 2 “Gradient descent parameter update” Examiner note: This step performs an update of the sk, which is the local motion vectors (See section II.B. lines 4-5)).
In regards to claim 5, Rohkohl in view of Lauritsch teaches the method of claim 4, wherein the step of performing vessel segmentation further comprises: extracting a cardiac vessel skeleton, based on the generated image without motion compensation (Rohkohl Section II.E “An automatic segmentation algorithm presented in Ref. 23 was used to extract the coronary artery centerlines.”), and forming the developed vessel region mask by generating a region for each branch of the extracted cardiac vessel skeleton, the region covering a tubular area and an extent of motion of the tubular area, the tubular area representing a vessel corresponding to the branch of the extracted cardiac vessel skeleton (Rohkohl Section II.E “In order to obtain the M-ROI, the segmented region was dilated by several millimeters to cover the whole range of motion related artifacts originating from the contrast filled vessels”).
In regards to claim 7, Rohkohl in view of Lauritsch teaches the method of claim 5, wherein the extracting step further comprises: executing, on the generated image without motion compensation, vesselness-filtering- based, dynamic-growing-based, or deep-learning-based vessel segmentation to extract the cardiac vessel skeleton (Rohkohl Section II.E. “An automatic segmentation algorithm presented in Ref. 23 was used to extract the coronary artery centerlines. This algorithm is partly model driven and learning-based and works reasonably well even in the presence of motion artifacts in some parts of the coronary artery tree. Details of the segmentation algorithm are beyond the scope of our manuscript and not relevant for the proposed motion compensation approach.” Examiner note: The disclosure of Gulsun is included in the disclosure of Rohkohl by reference.) (Gulsun “Some of the previous work on vessel centerline modeling methods include vesselness-based methods”).
In regards to claim 8, Rohkohl in view of Lauritsch teaches the method of claim 4, wherein the loss function is based on an entropy of the determined vessel ROI, an edge function of the determined vessel ROI, or a combination thereof (Rohkohl Section II.F. “The MAM should be able to assess the relative amount of motion artifacts in an image or an image region. As the true anatomy of the organs in a motion-corrupted clinical dataset is unknown, a quality metric is required which does not rely on such reference information. The metrics are described by a function L(s) which computes the MAM value for the motion compensated reconstruction corresponding to the motion model parameters s in a region of interest. In the following we propose two different metrics to assess the relative amount of motion artifacts: entropy and positivity.”; Section II.G “Motion estimation corresponds to finding a set of motion parameters s that minimizes a MAM.”).
In regards to claim 9, Rohkohl in view of Lauritsch teaches the method of claim 1, wherein the determining step further comprises: performing, based on the generated motion-compensated image, vessel segmentation to develop a vessel region mask (Lauritsch Figure 2 S3; Column 14, lines 57-65 “A further predetermined parameter is an update interval K, which specifies after how many iterative acts k the reference image 13 is updated. To update the reference image 13, the most current iterative image 17 in each case is described as the provisional motion-compensated image, as for process act S3, and segmented as indicated here by a program path 18 in order to obtain a new or updated reference image 13, the respective existing reference image 13 being replaced.”; Column 13 Lines 26-39 “In a process act S3, the initial reconstructed image 11 is segmented, in particular automatically, for example by using an intensity-based thresholding method. The result is a reference image 13, which may be thinly or sparsely populated—even compared with the initial reconstructed image 11… The reference image 13 shows at least one part of the vascular tree 12 but may be restricted to the maximum-intensity regions thereof.” Examiner note: This first portion of this reference teaches that a motion compensated image can be segmented. The second portion of this reference teaches that the segmentation would result in a vascular tree, which is analogous to a vessel region), and identifying, based on the developed vessel region mask, a region within the generated motion-compensated image, as the determined vessel ROI (Rohkohl Figure 2 “Motion compensated reconstruction f(x, sk), x ε [OMEGA]” Examiner note: This step shows that a reconstruction f(x, sk) is computed, where only values of x contained within the set of [OMEGA] are used. This is analogous to using a region mask, as they are both ensuring that only the proper region of interest is used within the reconstruction), and the updating step further comprises: calculating cardiac motion to minimize a loss function of the determined vessel ROI (Rohkohl Figure 2; Section II.F. “The MAM should be able to assess the relative amount of motion artifacts in an image or an image region. As the true anatomy of the organs in a motion-corrupted clinical dataset is unknown, a quality metric is required which does not rely on such reference information. The metrics are described by a function L(s) which computes the MAM value for the motion compensated reconstruction corresponding to the motion model parameters s in a region of interest. In the following we propose two different metrics to assess the relative amount of motion artifacts: entropy and positivity.”; Section II.G “Motion estimation corresponds to finding a set of motion parameters s that minimizes a MAM.” Examiner note: In this reference, MAM stands for motion artifact metrics. Section II.F shows that one of the motion artifact metrics used is the entropy of the vessel ROI. Section II.G shows that this motion estimation is meant to find a set of motion parameters which minimizes this MAM.), and updating the estimated cardiac motion to the calculated cardiac motion (Rohkohl Figure 2 “Gradient descent parameter update” Examiner note: This step performs an update of the sk, which is the local motion vectors (See section II.B. lines 4-5)).
In regards to claim 10, Rohkohl in view of Lauritsch teaches the method of claim 9, wherein the step of performing vessel segmentation further comprises: extracting a cardiac vessel skeleton, based on the generated motion-compensated image (Lauritsch Figure 2 S3; Column 14, lines 57-65 “A further predetermined parameter is an update interval K, which specifies after how many iterative acts k the reference image 13 is updated. To update the reference image 13, the most current iterative image 17 in each case is described as the provisional motion-compensated image, as for process act S3, and segmented as indicated here by a program path 18 in order to obtain a new or updated reference image 13, the respective existing reference image 13 being replaced.”; Column 13 Lines 26-39 “In a process act S3, the initial reconstructed image 11 is segmented, in particular automatically, for example by using an intensity-based thresholding method. The result is a reference image 13, which may be thinly or sparsely populated—even compared with the initial reconstructed image 11… The reference image 13 shows at least one part of the vascular tree 12 but may be restricted to the maximum-intensity regions thereof.”)(Rohkohl Section II.E “An automatic segmentation algorithm presented in Ref. 23 was used to extract the coronary artery centerlines.”), and forming the developed vessel region mask by generating a region for each branch of the extracted cardiac vessel skeleton, the region covering a tubular area and an extent of motion of the tubular area, the tubular area representing a vessel corresponding to the branch of the extracted cardiac vessel skeleton (Rohkohl Section II.E “In order to obtain the M-ROI, the segmented region was dilated by several millimeters to cover the whole range of motion related artifacts originating from the contrast filled vessels”).
In regards to claim 12, Rohkohl in view of Lauritsch teaches the method of claim 1, further comprising: reconstructing the received projection data to generate an image without motion compensation of the imaging object (Rohkohl Figure 2 “Initial reconstruction”; Section II.A. “In a first step the coronary arteries are segmented from a standard partial scan image with potential motion artifacts, using an in-house segmentation algorithm”); and performing, based on the generated image without motion compensation, vessel segmentation to develop a vessel template (Lauritsch Colum 5, lines 27-35 “The target function for the iteration may be formulated to find parameters of the motion model that result in an image that has been reconstructed having reduced motion artifacts accordingly compared with the respective reference image. The basic concept here may therefore be formulated as reconstructing a template of the moving target object and maximizing a similarity between this template and a motion-compensated reconstruction.”; Column 4, lines 31-33 “The respective previous reference image is then replaced by the provisional motion-compensated image as a new current reference image.” Examiner note: The template of this disclosure is also referred to as a reference image) and a vessel region mask (Rohkohl Figure 2 “Compute region of interest [OMEGA] with motion (M-ROI) by coronary segmentation”; Section II.E “We confine motion estimation to specific regions of interest [OMEGA] with motion (M-ROI), located around the coronary arteries.”), wherein the determining step further comprises identifying, based on the developed vessel region mask, a region within the generated motion-compensated image, as the determined vessel ROI (Rohkohl Figure 2 “Motion compensated reconstruction f(x, sk), x ε [OMEGA]” Examiner note: This step shows that a reconstruction f(x, sk) is computed, where only values of x contained within the set of [OMEGA] are used. This is analogous to using a region mask, as they are both ensuring that only the proper region of interest is used within the reconstruction), and the updating step further comprises: calculating cardiac motion to maximize a similarity between the determined vessel ROI and the developed vessel template (Lauritsch Column 5 Lines 27-35 “The target function for the iteration may be formulated to find parameters of the motion model that result in an image that has been reconstructed having reduced motion artifacts accordingly compared with the respective reference image. The basic concept here may therefore be formulated as reconstructing a template of the moving target object and maximizing a similarity between this template and a motion-compensated reconstruction.”), and updating the estimated cardiac motion to the calculated cardiac motion (Rohkohl Figure 2 “Gradient descent parameter update” Examiner note: This step performs an update of the sk, which is the local motion vectors (See section II.B. lines 4-5)).
In regards to claim 13, Rohkohl in view of Lauritsch teaches the method of claim 12, wherein the step of performing vessel segmentation further comprises: extracting a cardiac vessel skeleton, based on the generated image without motion compensation (Rohkohl Section II.E “An automatic segmentation algorithm presented in Ref. 23 was used to extract the coronary artery centerlines.”), forming the developed vessel template by generating a tubular area for each branch of the extracted cardiac vessel skeleton, the tubular area representing a vessel corresponding to the branch of the extracted cardiac vessel skeleton (Lauritsch Column 4, lines 31-33 “The respective previous reference image is then replaced by the provisional motion-compensated image as a new current reference image.” Examiner note: This disclosure teaches that a vessel region and vessel template can be created. Furthermore, when considered in combination with Rohkohl, the vessel template would be created in such a way that could be compared to the vessel region mask. Therefore, the vessel template would be created using the tubular technique to obtain the ROI described in Rohkohl), and forming the developed vessel region mask by generating a region for each branch of the extracted cardiac vessel skeleton, the region covering the tubular area and an extent of motion of the tubular area (Rohkohl Section II.E “In order to obtain the M-ROI, the segmented region was dilated by several millimeters to cover the whole range of motion related artifacts originating from the contrast filled vessels”).
In regards to claim 15, Rohkohl in view of Lauritsch teaches the method of claim 1, wherein the determining step further comprises: performing, based on the generated motion-compensated image, vessel segmentation to develop a vessel region mask (Lauritsch Figure 2 S3; Column 14, lines 57-65 “A further predetermined parameter is an update interval K, which specifies after how many iterative acts k the reference image 13 is updated. To update the reference image 13, the most current iterative image 17 in each case is described as the provisional motion-compensated image, as for process act S3, and segmented as indicated here by a program path 18 in order to obtain a new or updated reference image 13, the respective existing reference image 13 being replaced.”; Column 13 Lines 26-39 “In a process act S3, the initial reconstructed image 11 is segmented, in particular automatically, for example by using an intensity-based thresholding method. The result is a reference image 13, which may be thinly or sparsely populated—even compared with the initial reconstructed image 11… The reference image 13 shows at least one part of the vascular tree 12 but may be restricted to the maximum-intensity regions thereof.” Examiner note: This first portion of this reference teaches that a motion compensated image can be segmented. The second portion of this reference teaches that the segmentation would result in a vascular tree, which is analogous to a vessel region) and a vessel template (Lauritsch Column 5, lines 27-39 “The target function for the iteration may be formulated to find parameters of the motion model that result in an image that has been reconstructed having reduced motion artifacts accordingly compared with the respective reference image. The basic concept here may therefore be formulated as reconstructing a template of the moving target object and maximizing a similarity between this template and a motion-compensated reconstruction. A problem with this is that no “correct” template is available. As a solution therefore, the respective best available reference image is used as the template, which image is then improved or refined in each case within the context of the method.”; Column 4, lines 31-33 “The respective previous reference image is then replaced by the provisional motion-compensated image as a new current reference image.” Examiner note: This portion of the reference shows that a vessel template can be constructed based on the best reference image. Furthermore, this vessel template can be created based off of a motion compensated image when the reference image has already been updated with a provisional motion compensated image at least once.), and identifying, based on the developed vessel region mask, a region within the generated motion-compensated image, as the determined vessel ROI (Rohkohl Figure 2 “Motion compensated reconstruction f(x, sk), x ε [OMEGA]” Examiner note: This step shows that a reconstruction f(x, sk) is computed, where only values of x contained within the set of [OMEGA] are used. This is analogous to using a region mask, as they are both ensuring that only the proper region of interest is used within the reconstruction), and the updating step further comprises: calculating cardiac motion to maximize a similarity between the determined vessel ROI and the developed vessel template (Lauritsch Column 5 Lines 27-35 “The target function for the iteration may be formulated to find parameters of the motion model that result in an image that has been reconstructed having reduced motion artifacts accordingly compared with the respective reference image. The basic concept here may therefore be formulated as reconstructing a template of the moving target object and maximizing a similarity between this template and a motion-compensated reconstruction.”), and updating the estimated cardiac motion to the calculated cardiac motion (Rohkohl Figure 2 “Gradient descent parameter update” Examiner note: This step performs an update of the sk, which is the local motion vectors (See section II.B. lines 4-5)).
In regards to claim 20, Rohkohl in view of Lauritsch renders obvious the claim limitations as in the consideration of claim 1.
Claims 16-17 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Rohkohl in view of Lauritsch, and further in view of “Robust Optical Flow Estimation in Cardiac Ultrasound Images Using a Sparse Representation” (herein after referred to by its primary author, Ouzir)
In regards to claim 16, Rohkohl in view of Lauritsch teaches the method of claim 1, further comprising: reconstructing the received projection data to generate an image without motion compensation of the imaging object (Rohkohl Figure 2 “Initial reconstruction”; Section II.A. “In a first step the coronary arteries are segmented from a standard partial scan image with potential motion artifacts, using an in-house segmentation algorithm”); and performing, based on the generated image without motion compensation, vessel segmentation to develop a vessel template (Lauritsch Colum 5, lines 27-35 “The target function for the iteration may be formulated to find parameters of the motion model that result in an image that has been reconstructed having reduced motion artifacts accordingly compared with the respective reference image. The basic concept here may therefore be formulated as reconstructing a template of the moving target object and maximizing a similarity between this template and a motion-compensated reconstruction.”; Column 4, lines 31-33 “The respective previous reference image is then replaced by the provisional motion-compensated image as a new current reference image.” Examiner note: The template of this disclosure is also referred to as a reference image) and a vessel region mask (Rohkohl Figure 2 “Compute region of interest [OMEGA] with motion (M-ROI) by coronary segmentation”; Section II.E “We confine motion estimation to specific regions of interest [OMEGA] with motion (M-ROI), located around the coronary arteries.”), wherein the determining step further comprises identifying, based on the developed vessel region mask, a region within the generated motion-compensated image, as the determined vessel ROI (Rohkohl Figure 2 “Motion compensated reconstruction f(x, sk), x ε [OMEGA]” Examiner note: This step shows that a reconstruction f(x, sk) is computed, where only values of x contained within the set of [OMEGA] are used. This is analogous to using a region mask, as they are both ensuring that only the proper region of interest is used within the reconstruction), and the updating step further comprises: calculating cardiac motion to minimize an optimization cost function, Rohkohl Figure 2; Section II.F. “The MAM should be able to assess the relative amount of motion artifacts in an image or an image region. As the true anatomy of the organs in a motion-corrupted clinical dataset is unknown, a quality metric is required which does not rely on such reference information. The metrics are described by a function L(s) which computes the MAM value for the motion compensated reconstruction corresponding to the motion model parameters s in a region of interest. In the following we propose two different metrics to assess the relative amount of motion artifacts: entropy and positivity.”; Section II.G “Motion estimation corresponds to finding a set of motion parameters s that minimizes a MAM.”), and a similarity between the determined vessel ROI and the developed vessel template (Lauritsch Column 5 Lines 27-35 “The target function for the iteration may be formulated to find parameters of the motion model that result in an image that has been reconstructed having reduced motion artifacts accordingly compared with the respective reference image. The basic concept here may therefore be formulated as reconstructing a template of the moving target object and maximizing a similarity between this template and a motion-compensated reconstruction.”), and updating the estimated cardiac motion to the calculated cardiac motion (Rohkohl Figure 2 “Gradient descent parameter update” Examiner note: This step performs an update of the sk, which is the local motion vectors (See section II.B. lines 4-5)).
Rohkohl in view of Lauritsch fails to teach weighted terms of the optimization cost function.
However, Ouzir teaches weighted terms of the optimization cost function (Ouzir Algorithm 1 “Weights Q and S”; Section II E “In this work, this strategy allows us to incorporate an iterative re-weighted minimization of (4), where the weights are determined in closed form and jointly with the motion estimates and the corresponding sparse coefficients at each iteration” Examiner note: This reference teaches that an optimization function can be weighted and combine multiple parameters).
Ouzir is considered to be analogous to the claimed invention because they are both in the same field of cardiac motion compensation. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have modified the system of Rohkohl in view of Lauritsch to include the teachings of Ouzir, to provide the advantage of reducing the impact of outliers (Ouzir Section II “M-estimators are robust functions that address the issue of outliers by reducing their impact on the estimates. In this work, we use weight functions associated with redescending M-estimators. The latter allow the impact of outliers to be further reduced by controlling the decrease of the M-estimator function to zero.”)
In regards to claim 17, Rohkohl in view of Lauritsch and Ouzir teaches the method of claim 16, wherein the step of performing vessel segmentation further comprises: extracting a cardiac vessel skeleton, based on the generated image without motion compensation (Rohkohl Section II.E “An automatic segmentation algorithm presented in Ref. 23 was used to extract the coronary artery centerlines.”), forming the developed vessel template by generating a tubular area for each branch of the extracted cardiac vessel skeleton, the tubular area representing a vessel corresponding to the branch of the extracted cardiac vessel skeleton (Lauritsch Column 4, lines 31-33 “The respective previous reference image is then replaced by the provisional motion-compensated image as a new current reference image.” Examiner note: This disclosure teaches that a vessel region and vessel template can be created. Furthermore, when considered in combination with Rohkohl, the vessel template would be created in such a way that could be compared to the vessel region mask. Therefore, the vessel template would be created using the tubular technique to obtain the ROI described in Rohkohl.), and forming the developed vessel region mask by generating a region for each branch of the extracted cardiac vessel skeleton, the region covering the tubular area and an extent of motion of the tubular area (Rohkohl Section II.E “In order to obtain the M-ROI, the segmented region was dilated by several millimeters to cover the whole range of motion related artifacts originating from the contrast filled vessels”).
In regards to claim 19, Rohkohl in view of Lauritsch and Ouzir teaches the method of claim 1, wherein the determining step further comprises: performing, based on the generated motion-compensated image, vessel segmentation to develop a vessel region mask (Lauritsch Figure 2 S3; Column 14, lines 57-65 “A further predetermined parameter is an update interval K, which specifies after how many iterative acts k the reference image 13 is updated. To update the reference image 13, the most current iterative image 17 in each case is described as the provisional motion-compensated image, as for process act S3, and segmented as indicated here by a program path 18 in order to obtain a new or updated reference image 13, the respective existing reference image 13 being replaced.”; Column 13 Lines 26-39 “In a process act S3, the initial reconstructed image 11 is segmented, in particular automatically, for example by using an intensity-based thresholding method. The result is a reference image 13, which may be thinly or sparsely populated—even compared with the initial reconstructed image 11… The reference image 13 shows at least one part of the vascular tree 12 but may be restricted to the maximum-intensity regions thereof.” Examiner note: This first portion of this reference teaches that a motion compensated image can be segmented. The second portion of this reference teaches that the segmentation would result in a vascular tree, which is analogous to a vessel region) and a vessel template (Lauritsch Column 5, lines 27-39 “The target function for the iteration may be formulated to find parameters of the motion model that result in an image that has been reconstructed having reduced motion artifacts accordingly compared with the respective reference image. The basic concept here may therefore be formulated as reconstructing a template of the moving target object and maximizing a similarity between this template and a motion-compensated reconstruction. A problem with this is that no “correct” template is available. As a solution therefore, the respective best available reference image is used as the template, which image is then improved or refined in each case within the context of the method.”; Column 4, lines 31-33 “The respective previous reference image is then replaced by the provisional motion-compensated image as a new current reference image.” Examiner note: This portion of the reference shows that a vessel template can be constructed based on the best reference image. Furthermore, this vessel template can be created based off of a motion compensated image when the reference image has already been updated with a provisional motion compensated image at least once.), and identifying, based on the developed vessel region mask, a region within the generated motion-compensated image, as the determined vessel ROI (Rohkohl Figure 2 “Motion compensated reconstruction f(x, sk), x ε [OMEGA]” Examiner note: This step shows that a reconstruction f(x, sk) is computed, where only values of x contained within the set of [OMEGA] are used. This is analogous to using a region mask, as they are both ensuring that only the proper region of interest is used within the reconstruction), and the updating step further comprises: calculating cardiac motion to minimize an optimization cost function, weighted (Ouzir Algorithm 1 “Weights Q and S”; Section II E “In this work, this strategy allows us to incorporate an iterative re-weighted minimization of (4), where the weights are determined in closed form and jointly with the motion estimates and the corresponding sparse coefficients at each iteration” Examiner note: This reference teaches that an optimization function can be weighted and combine multiple parameters.) terms of the optimization cost function including a loss function of the determined vessel ROI (Rohkohl Figure 2; Section II.F. “The MAM should be able to assess the relative amount of motion artifacts in an image or an image region. As the true anatomy of the organs in a motion-corrupted clinical dataset is unknown, a quality metric is required which does not rely on such reference information. The metrics are described by a function L(s) which computes the MAM value for the motion compensated reconstruction corresponding to the motion model parameters s in a region of interest. In the following we propose two different metrics to assess the relative amount of motion artifacts: entropy and positivity.”; Section II.G “Motion estimation corresponds to finding a set of motion parameters s that minimizes a MAM.”), and a similarity between the determined vessel ROI and the developed vessel template (Lauritsch Column 5 Lines 27-35 “The target function for the iteration may be formulated to find parameters of the motion model that result in an image that has been reconstructed having reduced motion artifacts accordingly compared with the respective reference image. The basic concept here may therefore be formulated as reconstructing a template of the moving target object and maximizing a similarity between this template and a motion-compensated reconstruction.”), and updating the estimated cardiac motion to the calculated cardiac motion (Rohkohl Figure 2 “Gradient descent parameter update” Examiner note: This step performs an update of the sk, which is the local motion vectors (See section II.B. lines 4-5)).
Allowable Subject Matter
Claims 6, 11, 14, and 18 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Claims 6, 11, 14, and 18 are directed towards the method of creating the tubular regions which represent the cardiac vessels. The first portion of these claims is taught by Rohkohl (Section II.E. “In order to obtain the M-ROI, the segmented region was dilated by several millimeters to cover the whole range of motion related artifacts originating from the contrast filled vessels”). The second half of these claims reads “[the tubular area] has a radius equal to a predefined value at a starting point of the branch, wherein along an axial direction of the branch, the radius of the tubular area gradually decreases from the starting point to an endpoint of the branch”. This limitation is not found in any of the prior art of record. The prior art of record instead teaches that the radius of the tubular area which represents a cardiac vessel would be based on the measured radius of the vessel from the imaging (See Gulsun Section 2 “radius R”). Furthermore, the prior art of record teaches that the radius of the blood vessel varies, and that some portions of the blood vessels gradually increase in an axial direction (See “Aspline-based hexahedral mesh generator for patient-specific coronary arteries” Figure 2). It is known that blood vessels generally decrease in radius as they get further from the heart, but this alone would not have been obvious to combine this art with any of the cited prior art, as the computer based representation of the blood vessels does not necessarily correlate one to one with the actual blood vessels. For at least these reasons, claims 6, 11, 14, and 18 would be allowable over the prior art if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
“Review on Various Approaches for Extraction of Blood Vessel and its Components from Angiogram Images” gives a broad overview of current methods for extracting blood vessels from angiogram images.
US20150339847 teaches a method of creating a representation for cardiac blood vessels, which includes a step of motion correction.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CALEB LOGAN ESQUINO whose telephone number is (703)756-1462. The examiner can normally be reached M-Fr 8:00AM-4:00PM 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 Bee can be reached at (571) 270-5183. 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.
/CALEB L ESQUINO/Examiner, Art Unit 2677
/ANDREW W BEE/Supervisory Patent Examiner, Art Unit 2677