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 .
Specification
The amendment filed 11/21/2025 is objected to under 35 U.S.C. 132(a) because it introduces new matter into the disclosure. 35 U.S.C. 132(a) states that no amendment shall introduce new matter into the disclosure of the invention. The added material which is not supported by the original disclosure is as follows:
Paragraph 0022: the regularization function, and the amended details of the regularization function;
All of Paragraph 0026;
All of Paragraphs 0027-0028;
Paragraph 0032: the process of calculating a mean spatial gradient magnitude and variance, and comparing the magnitude to a threshold to quantify clear and distinct tissue boundaries;
Paragraphs 0035-0037: the steps and details of the preliminary annotation such as employing spectral signature decomposition and probabilistic isocontouring, using a probablisitic classifier, such as a Bayesian classifier (Paragraph 0036), and training of spectral CT images to generate models used for the preliminary annotation (Paragraph 0037);
Paragraph 0038: the steps of the automated computational cross validation
0046-0049: all the steps and examples of measuring statistical overlap (similarity metrics, distance metrics, and hypothesis testing);
0053: threshold attenuation values for generating a plaque differentiating digital filter parameter set;
0054-0058: generating a set of ranked contrast-to-noise ratio (CNR) values, identifying one or more spectral energy levels corresponding to the top-ranked CNR values, resolving spectral overlap by calculating a Mahalanobis distance or establishing a final threshold attenuation value, cross-validation of the threshold attenuation values, and generating and storing a digital filter parameter set;
0062-0063: details and examples of the watershed segmentation algorithm and level set segmentation algorithm; and
0065-0067: details of the fusion of the weighted fusion of multi-energy plaque tissue characterization (previously, the specification only provided a general description of the “weighted fusion approach”).
Applicant is required to cancel the new matter in the reply to this Office Action.
[Examiner Note: Please see MPEP section 608.04(a). All the cited paragraphs above, contains subject matter that was not present in the specification at the time of filing. No amendment may introduce new matter into the disclosure of the application. Therefore the amendment needs to be canceled.].
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claim 1 recites “estimating a single trajectory motion field of the calcified plaque lesion across a plurality of projection angles” and
“compensating for the trajectory by performing registration to align the spectral CT images by applying said single trajectory motion field derived from a high- energy spectral bin capable of resolving the calcified plaque lesion and applying said derived field identically to a lows-energy spectral bin where the vessel landmark is spectrally indistinct, thereby preserving per-voxel spectral signatures and stabilizing spectral signatures of plaque tissue in vivo.
Claim 2 recites “wherein applying the vessel landmark-based motion correction comprises deriving the single trajectory motion field from the high-energy bin and applying said field to the low- energy bin prior to image reconstruction to mitigate spectral skewing, thereby using the high- energy bin as a motion proxy to stabilize soft plaque boundaries in the low-energy bin where landmarks are spectrally indistinct”.
Claim 3 recites “utilizing a regularization function configured to enforce spatial grayscale similarity within each spectral energy level for voxels sharing a common spectral signature, thereby simultaneously preserving spectral vector fidelity across the multiple energy levels and maintaining material differentiation”.
Claim 4 recites “wherein the vessel landmark is an anatomical feature selected from the group consisting of a carotid bifurcation and a calcified plaque lesion, and wherein identifying said landmark comprises verifying a spectral slope consistency across the plurality of discrete energy levels to differentiate said lesion from iodine contrast flux or high-density bone artifacts prior to motion estimation”.
Claim 5 recites “applying principal component analysis (PCA) to the plurality of motion-corrected static spectral CT images to preserve spectral fidelity while reducing noise, wherein the PCA is applied across an energy dimension of the spectral CT images by decomposing a per-voxel spectral signature vector composed of attenuation values from the plurality of discrete energy levels into a set of principal components, selectively filtering one or more high-order principal components identified as being statistically associated with uncorrelated quantum noise, and reconstructing the spectral CT images from remaining low- order principal components that retain material-specific spectral attenuation characteristics to increase a contrast-to-noise ratio (CNR) between plaque tissue and surrounding perivascular tissue, thereby facilitating plaque tissue differentiation in said static images without temporal data”.
Claim 6 recites “applying one or more pre-defined quantitative inclusion criteria”, said criteria comprising: calculating a mean spatial gradient magnitude at a plaque tissue boundary independently for each of the plurality of discrete energy levels and computing a variance of said gradient magnitude across said levels; and determining that said mean spatial gradient magnitude exceeds a threshold value defined as being at least two standard deviations above a mean gradient calculated from a homogenous background tissue region and that said variance is below a predefined spectral consistency threshold, thereby indicating that the single trajectory motion field derived from the high-energy bin has aligned the plurality of discrete energy levels to a sub-pixel accuracy relative to the low-energy bin suitable for spectral tissue differentiation”.
Claim 7 recites “generating, for each voxel in a region of interest of an image acquired from a photon counting CT system, a spectral signature vector comprising attenuation values at a plurality of discrete spectral energy levels; performing a material basis decomposition on each spectral signature vector using a pre- calibrated library of plaque-specific basis vectors, wherein said basis vectors are defined by spectral attenuation curves derived from histologically confirmed pure tissue reference samples of carotid plaque tissue, wherein said library comprises at least a spectrally distinct hemorrhagic component vector and a lipid core component vector established via least-squares fitting of spectral data extracted from regions of spectral homogeneity within said reference samples to serve as material standards independent of spatial registration; generating a probabilistic tissue map by utilizing a Bayesian classifier to assign each voxel a posterior probability of belonging to a specific plaque tissue type, wherein the Bayesian classifier is constrained by prior probabilities derived from histological prevalence data and dynamically adjusted by applying patient-specific demographic scaling factors to the histological prevalence data before classification; defining the preliminary annotation as a confidence isocontour, said isocontour being a boundary line connecting voxels that exceed a predetermined posterior probability threshold; and outputting the defined preliminary annotation for use as an initialization boundary for an automatic spectral CT segmentation module.”
Claim 8 recites “a computer-implemented method for generating a set of plaque-differentiating digital filter parameters for use in plaque segmentation in spectral CT, the method comprising: receiving one or more spectral CT images of carotid plaque, wherein the images have been computationally processed using vessel landmark-based algorithms to correct motion artifacts; receiving expert-delineated annotations on the motion-corrected spectral CT images that define boundaries of specific plaque constituents; executing, by one or more processors, a computational analysis module to determine, from a baseline set of expert-annotated carotid plaque spectral CT images, one or more threshold attenuation values, wherein said determining comprises: computing, for each annotated plaque constituent, a spectral signature vector comprising an energy-dependent attenuation value distribution at each of a plurality of discrete spectral energy levels; generating a set of ranked CNR values by differentiating the spectral signature vector of the annotated plaque constituent against a background spectral signature vector of surrounding tissues across the plurality of discrete spectral energy levels; identifying a selected subset of spectral energy levels corresponding to one or more top-ranked CNR values to enhance spectral separation between the plaque constituent and the surrounding tissues; and establishing one or more final threshold attenuation values based on distributions derived from the selected subset; and generating and storing, in a non-transitory computer-readable medium, a digital filter parameter set comprising the one or more determined threshold attenuation values and the identified selected subset of spectral energy levels, wherein the digital filter parameter set is structured as a machine-readable initialization file configured to constrain a search space of an automatic spectral CT image segmentation module.”
Claim 9 recites “wherein said annotation process comprises: presenting a simultaneous, side-by-side display of the same anatomical cross-section at a plurality of different spectral energy levels; and automatically propagating a user-delineated boundary drawn on a high-contrast spectral energy level to all other displayed spectral energy levels to generate a spatially consistent volumetric mask, thereby facilitating multi-energy annotation of plaque tissue across spectral energy levels where the tissue boundary is indistinct.”
Claim 10 recites “calculating a Mahalanobis distance between a spectral signature vector of the IPH and a spectral signature vector of the LRNC within the identified selected subset of spectral energy levels, and assigning a voxel to a tissue type when said distance exceeds a statistical separability threshold derived from the energy-dependent attenuation value distribution.”
Claim 11 recites “establishing one or more threshold attenuation values comprises applying a statistical function to the attenuation value distributions of the annotated plaque constituent and a distribution of an overlapping adjacent tissue to define a statistical threshold, wherein the statistical threshold comprises a percentile value dynamically selected to reduce a spectral overlap coefficient between the distributions, wherein said value is constrained to be greater than or equal to a 95th percentile of said distribution to constitute a statistically significant separation from a spectral noise floor inherent to low-photon energy bins caused by photon starvation while enhancing specificity for the annotated plaque constituent.”
Claim 12 recites “wherein establishing one or more threshold attenuation values comprises: calculating a localized spectral noise floor for the surrounding tissues within the selected subset of spectral energy levels; and dynamically establishing a delineation threshold to constitute a value that is at least two standard deviations above a mean of said localized spectral noise floor, thereby facilitating distinction of the plaque tissue signal from quantum noise inherent to the specific spectral energy levels utilized.”
Claim 13 recites “computing an expert-specific spectral attenuation curve for the same annotated plaque tissue region across the plurality of discrete spectral energy levels; applying a Kolmogorov-Smirnov hypothesis test to compare a shape and magnitude of the expert-specific spectral attenuation curves against one another; and validating the digital filter parameter set upon determining that the test produces a p- value greater than a predetermined significance level, thereby statistically verifying that the expert annotations preserve the physical spectral signature of the plaque tissue independent of observer variability.”
Claim 14 recites “a cross-validation step to verify a functional fidelity of the determined one or more threshold attenuation values, the validation comprising: applying said one or more determined threshold attenuation values as a filter to the motion-corrected spectral CT images to generate computationally derived segmentation masks; computationally determining a Dice coefficient as a measure of spatial overlap between said computationally derived segmentation masks and the received expert- delineated annotations; and determining that said Dice coefficient exceeds a predetermined threshold, thereby verifying that the statistically derived threshold attenuation values are functionally representative of the expert-delineated boundaries.“
Claim 15 recites “accessing, from a non-transitory computer-readable medium, a digital filter parameter set comprising one or more threshold attenuation values and an identified selected subset of spectral energy levels; extracting said one or more threshold attenuation values and the identified selected subset of spectral energy levels from the accessed digital filter parameter set; applying filtering to unannotated target spectral CT images based on said one or more extracted threshold attenuation values to generate candidate plaque boundaries that exclude background regions; computationally constructing a multi-energy topographical gradient map by calculating a weighted combination of local gradients from the extracted selected subset of spectral energy levels to enhance edge detection sensitivity for plaque tissue interfaces; applying an automatic watershed or level-set segmentation algorithm to the unannotated target spectral CT images, wherein the segmentation is constrained within the candidate plaque boundaries and said algorithm is guided by the multi-energy topographical gradient map; and spatially fusing a plurality of multi-energy plaque characterizations resulting from the automatic segmentation via a pixel-wise weighted averaging algorithm that utilizes a normalized CNR to generate a consolidated plaque map, wherein the weighted averaging applies distinct weights to the same spatial voxel across different spectral energy levels to enhance local tissue contrast.“
Claim 16 recites “wherein the weighted averaging fusion algorithm comprises: calculating a new set of voxel-specific local CNR values for each of the plurality of multi- energy plaque characterizations derived from the selected subset of spectral energy levels; generating a spectral weighting vector proportional to the local CNR values such that spectral energy levels with higher photon starvation noise are computationally down- weighted relative to spectral energy levels with higher contrast fidelity; and applying the spectral weighting vector to the plurality of multi-energy plaque characterizations to generate a single, weighted plaque characterization map, thereby facilitating that the consolidated map prioritizes spectral data fidelity over density magnitude.”
Claim 17 recites “computationally segmenting an arterial wall boundary from a virtual monochromatic energy bin or broad-spectrum integration of the unannotated target spectral CT images to generate an anatomical mask thereof; computationally comparing the fused consolidated plaque map derived from the selected subset of spectral energy levels to said generated anatomical mask; and verifying that a predetermined percentage of voxels in the fused consolidated plaque map are spatially located within said generated anatomical mask, thereby indicating that the plaque boundaries align with anatomical constraints.”
Claim 18 recites “computationally extracting a stenosis percentage metric from the fused consolidated plaque map derived from the multi-energy spectral fusion; generating a geometric reference stenosis metric by applying an automated Hounsfield Unit thresholding algorithm to a contrast-enhanced lumen within a synthesized virtual monochromatic image reconstruction of the same spectral CT images at an energy level of70keV;andaccepting the fused consolidated plaque map when a calculated difference between the extracted stenosis percentage metric and the geometric reference stenosis metric is less than a predetermined threshold value, thereby validating that the spectral characterization preserves luminal geometry relative to standard angiographic density.”
Claim 19 recites “a spectrally-weighted marker-controlled watershed algorithm, wherein the extracted threshold attenuation values are used as hard threshold limits to generate internal markers defining designated plaque regions having attenuation values within the threshold range and external markers defining designated background regions, which serve as seed points for said watershed algorithm, and wherein the algorithm is applied to a topographical gradient map computed specifically from the selected subset of spectral energy levels identified in the digital filter parameter set, such that the topographical gradient map represents a local contrast gradient derived from a weighted combination of said selected subset to reduce leakage of the watershed algorithm across spectral boundaries that are indistinct in single-energy images.”
Claim 20 recites “a level set algorithm configured to evolve a zero-level set contour, wherein the candidate plaque boundaries derived from the extracted threshold attenuation values are used to define an initial contour that geometrically constrains an evolution of the level set algorithm, and wherein the algorithm evolves said contour based on an underlying energy function minimized with respect to a topographical gradient map derived from multi-energy plaque characterizations.”
The cited limitations of claims 1-20 contain subject matter which was not described or found in the specification at the time the application was filed. Thus the cited limitations are considered as “new matter”, and are required to be canceled the new matter. (See MPEP 2163)
Response to Arguments
Applicant’s arguments with respect to claim(s) 1-20 have been considered but are moot because the arguments are based on the new amended claims. However, as stated in the 35 U.S.C. 112(a) rejections above, the newly amended claim limitations which the arguments are based upon, are considered as “new matter” since no support can be found in the originally filed specification or the specification that was filed before the first non-final rejection office action was issued. As such, the new matter found in claims 1-20 must be canceled, and would render applicant’s arguments to be moot. The examiner suggests that if applicant desires to keep the “new matter” in claims 1-20, then applicant must file a new application as a “continuation-in-part” (See MPEP 201.08), which would also allow applicant to file the newly amended specification, which was objected to, above, in the “Specification” section. Otherwise, applicant must cancel all the “new matter” cited in claims 1-20, and base any claims in a “request for continued examination” (RCE) from the claims filed on 03/20/2024, and ensure that any “new” amendments made is/are found/supported in the specification filed on 03/20/2024, or in the drawings filed on 10/17/2024.
Additionally, the examiner notes that as a Pro Se applicant (applicants that file patent applications without the assistance of a registered patent attorney or agent), the Pro Se Assistance Center (https://www.uspto.gov/patents/patents-ombuds/pro-se-assistance-center) is available to assist pro se applicants with making informed decisions regarding their patent applications (but please note that they cannot give legal advice), including one-on-one assistance via video conference or telephone.
Conclusion
THIS ACTION IS MADE FINAL. 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 Milton Truong whose telephone number is (571)272-2158. The examiner can normally be reached 9AM - 5PM, MON-FRI.
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, Keith Raymond can be reached at (571) 270-1790. 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.
/MT/ Examiner, Art Unit 3798
/KEITH M RAYMOND/ Supervisory Patent Examiner, Art Unit 3798