zDETAILED 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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Response to Amendment
Claims 118-119, 121-122, 124-125, 130-135, and 137-139 were previously pending and subject to the non-final action filed on 01/13/2026. In the response filed on 05/13/2026, claims 118 were amended, claim 141-143 newly added claim. Claims 1-117; 120-129, 131, 132, 134, 136, 137, and 139 were canceled. Therefore, claims 118-119, 130, 133, 135, 138, and 140-143 are currently pending and subject to the final action below.
Response to Arguments
Applicant's arguments see pages 6-13, filed on 05/13/2026 regarding claims 118-119, 121-122, 124-125, 130-135, and 137-139 under 35 U.S.C. 101 have been fully considered but they are not persuasive.
Applicant’s argument: A. Step 2A, Prong One - The amended claims are not directed to a mental process or a mathematical concept. The Office Action contends that the claims recite a mental process because they cover "concepts performed in the human mind, including observation, evaluation, judgment, and opinion," and that the measure of central tendency limitation encompasses a mathematical concept. Applicant respectfully disagrees. Amended claim 118 expressly recites "operating a processor to automatically segment the images to provide digital image data corresponding to ROIs in each of the image regions, and determining the image metrics by operating the processor to perform, on the digital data, image processing steps configured to provide said image metrics. "The claim then requires computation of (i) a GLCM correlation from the right rostral middle frontal, (ii) a GLCM correlation from the right supramarginal, and (iii) a measure of central tendency of pixel intensity from the right temporal pole, with each computation expressly tied to providing "a quantitative indication of tissue characteristics" in the corresponding anatomical region.
The Federal Circuit has repeatedly recognized that claims requiring this kind of large-scale, structured computational processing of physical-measurement data are not properly characterized as mental processes. See, e.g., SRI Int'l, Inc. v. Cisco Sys., Inc., 930 F.3d 1295, 1303 (Fed. Cir. 2019). Moreover, even if one of the recited metrics could in isolation be characterized as a mathematical computation, the Supreme Court has held that "an invention is not rendered ineligible for patent simply because it involves [a mathematical computation]." Alice Corp. v. CLS Bank Int', 573 U.S. 208, 217 (2014). The proper inquiry is whether the claim as a whole is directed to the alleged exception. As discussed below, it is not.
B. Step 2A, Prong Two - The claim integrates any alleged exception into a practical application that improves a medical diagnostic technology. Even assuming arguendo that any portion of claim 118 recites an abstract idea, the claim as a whole integrates that idea into a practical application that is directly analogous to the claims held patent-eligible in CardioNet, LLC v. InfoBionic, Inc., 955 F.3d 1358 (Fed. Cir. 2020). In CardioNet, the Federal Circuit reversed a § 101 dismissal and held patent- eligible claims directed to a cardiac monitoring device that distinguished atrial fibrillation/atrial flutter from ventricular arrhythmias using specific criteria. This is not "apply it" using a generic computer. The "thereby providing a quantitative indication of tissue characteristics" language ties each pixel-level computation to the underlying physical properties of the brain tissue from which it is computed. The weighted-sum language ties those tissue indications to a unitary diagnostic indicator.
This overlay limitation is closely analogous to the CardioNet claims' specific arrangement of detection logic. Just as the CardioNet claims achieved a particular technological improvement in cardiac monitoring (more accurate AF/AFL discrimination), claim 118 achieves a particular technological improvement in neuroimaging-based cognitive impairment diagnosis. Second, the specification confirms the improvement. Paragraphs [0244]-[0245] describe the overlay-display means as a specific component of the inventive system The improvement is described, demonstrated, and quantified in the specification, satisfying the second CardioNet factor.
Third, the claim is not directed to the abstract idea of diagnosing cognitive impairment. It is directed to a specific improved technique for doing so, built around a particular combination of region-metric pairings (selected from an enormous feature space, as discussed in Section C below) and a particular display modality (anatomically- registered overlay).
C. Step 2B - The specific combination is unconventional and amounts to significantly more. The Office Action contends that the additional limitations amount to no more than insignificant extra-solution activity similar to "receiving or transmitting data over the network." Applicant respectfully disagrees. The recited operations are not generic data transmission. They are domain-specific medical image processing operations performed in a specific ordered combination: " atlas-based parcellation of the human cortex into anatomically labeled regions;" computation of GLCM correlation from two specifically identified cortical regions;" computation of a measure of central tendency of pixel intensity in a third specifically identified cortical region; " weighted-sum combination of those region-specific tissue indications; and " anatomically-registered overlay display of the resulting indicator on the contributing image regions.
Considered as an ordered combination, these limitations amount to significantly more than any alleged judicial exception. The claim does not preempt diagnosis of cognitive impairment from brain images. It is restricted to a specific technical implementation built around specifically-recited region-metric pairings and a specifically- recited overlay display.
Examiner Response: After careful consideration and review of applicant’s argument. The examiner respectfully disagrees for the following reason below.
Claims 118-119, 130, 133, 135, 138, and 140-143 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1 Analysis: Claims 118 is directed to a method, which is directed to a process, one of the statutory categories.
Step 2A prong 1: Does the claim recite a judicial exception? Yes, claim 118 recites limitations of “determining the image metrics by operating the processor…”, determining… an indicator based on said image metrics according to a predetermined method..” and displaying the indicator as an overlay on an image of the human subject’s brain to assist a clinician in predicting or diagnosing cognitive impairment state...” Under the broadest reasonable interpretation, these limitation encompass evaluating image information, applying mathematical relationships to derive image metrics and an indicator, and presenting the resulting information to assist a clinician in making a diagnostic decision. Accordingly, these limitations fall within the “Mental Processes” grouping of abstract idea because they recite observations, evaluations, and judgements directed to analyzing information and assisting a clinician in making a diagnostic determination.
Furthermore, the limitation directed to determining a measure of central tendency using pixel intensity recites a mathematical concept because it requires performing a mathematical calculation on image data.
Step 2A prong 2: Does the claim recite additional elements? Do those additional elements, individually and in combination, integrate the judicial exception into a practical application? No.
Claim 118 further recites the additional limitations of “operating a processor to automatically segment the images to provide digital image data corresponding to ROIs in each of the image regions,” “determining the image metrics by operating the processor to perform, on the digital image, image processing steps configured to provide said image metrics,” and “displaying the indicator as an overlay on an image of the human subject’s brain… where the overlay comprises one or more portions overlaid on one or more of the image regions used to determine the indicator…”
Applicant contends that the additional elements integrate the judicial exception into a practical application by providing a technological improvement in medical image processing. The examiner respectfully disagrees.
The additional elements merely use a processor to obtain and process image data, determine image metrics, determine an indicator based on mathematical relationships, and present the resulting information as an overlay to assist a clinician in predicting or diagnosing cognitive impairment. Although the claimed overlay identified the image regions used to determine the indicator and provides a visual marker, the overlay merely presents the results generated by the recited mathematical analysis and diagnostic evaluation. The claims does not recite an improvement to the functioning of a computer, image processing technology, or another technology or technical field. Rather, the claimed processor preforms its ordinary computer functions to analyze information and display the resulting information to a user.
Likewise, the recited image segmentation and image processing steps do not improve the underlying image processing technology itself. Rather, the segmentation and image processing steps are used in carrying out the claimed mathematical analysis and determining the claimed indicator, rather than improving the manner in which image segmentation or image processing is performed.
Accordingly, the additional elements merely implement the judicial exception by using generic computer components preforming their ordinary functions (MPEP 2106.05(f)). Furthermore, displaying the indicator as an overlay merely presents the results of the recited mathematical analysis and diagnostic evaluation to a clinician and therefore amounts to insignificant extra-solution activity (MPEP 2106.05(g)). When considered individually and as an ordered combination, the additional elements do not integrate the judicial exception into a practical application. Therefore, the additional elements do not integrate the judicial exception into a practical application, and claim 118 is directed to an abstract idea.
Step 2B: Do the additional elements, considered individually and in combination, amount to significantly more than the judicial exception? No.
As discussed above, the additional elements consist of a processor configured to perform image segmentation, image processing, determining image metrics, determining an indicator, and displaying the indicator as an overlay. These additional elements merely implement the judicial exception using generic computer components performing their ordinary functions (MPEP 2106.05(f)). Furthermore, displaying the indicator as an overlay merely presents the results of the recited mathematical analysis and diagnostic evaluation and therefore amounts to insignificant extra-solution activity (MPEP 2106.05(g)). The claim does not recite any additional element or ordered combination that improves the functioning of a computer or another technology or technical field, nor does it recite any other inventive concept sufficient to amount to significantly more than the abstract idea (judicial exception). Thus, the claim is not patent eligible.
The dependent claims (claims 130, 133, 135 138 and 140-143) further recite limitations including “using an HLH filter, a measure of correlation, determining parameters of age related effects in the voxel, based on the vector of age values and the vector of intensity values and a model of said effects; and determining the image metrics is in response to age normalizing the images, wherein the tissue characteristics comprise at least one of: tissue morphology, tissue texture, and/or tissue structure,” these limitations likewise fall within the “Mental Processes and Mathematical Concept” groupings of abstract ideas.
These additional limitations do not integrate the judicial exception into a practical application because they merely add further mathematical concepts together with insignificant extra-solution activity to the abstract idea already identified above. The additional limitations do not improve the functioning of a computer, image processing technology, or another technology or technical field. Rather, they merely provide additional calculations and image processing performed as part of implementing the abstract idea and do not impose any meaningful limit on practicing the judicial exception. Accordingly, for the reason discussed above with respect to claim 118, the dependent claims likewise do not include additional elements sufficient to amount to significantly more than the judicial exception.
Applicant's arguments see pages 14-19, filed on 05/13/2026 regarding claims 118-119, 121-122, 124-125, 130-135, and 137-139 under 35 U.S.C. 103 have been fully considered but they are not persuasive.
Applicant’s argument: Claims 118, 119, 121, 122, 131, 132, 134, 135, 137, and 138 stand rejected under 35 U.S.C. § 103 over Desikan in view of Oliveira, Raj, and Nicastro. Claim 130 stands further rejected over the same combination in view of Antoniades. Claims 124 and 133 stand further rejected over the same combination in view of Murray. Claims 125 and 139 stand rejected over Desikan, Oliveira, Raj, and Murray. Applicant respectfully traverses.
A. Desikan does not teach prediction or diagnosis of cognitive impairment. The Office Action contends that Desikan teaches "A computer implemented method of predicting or diagnosing cognitive impairment" because Desikan refers to "tracking the evolution of disease from the degenerative changes associated with dementing illnesses such as Alzheimer's disease." Applicant respectfully disagrees. Desikan does not compute any image metric from any region for diagnostic purposes, does not produce any diagnostic indicator, and does not display any diagnostic result as an overlay on a brain image. Accordingly, Desikan cannot supply the diagnostic chain required by amended claim 118.
B. Oliveira does not teach a GLCM correlation in the right rostral middle frontal or in the right supramarginal. The Office Action contends that Oliveira teaches the recited image texture metrics in the recited cortical regions, citing Figure 3 of Oliveira and the GLCM-based texture parameters disclosed there. Applicant respectfully disagrees. Oliveira does not analyze, much less teach the diagnostic use of, the right rostral middle frontal or the right supramarginal regions recited in amended claim 118.
C. Nicastro does not teach the right-hemisphere cortical findings, and the claims no longer require fractal dimension in the independent claim.
D. Murray teaches normalization, not a diagnostic central tendency metric of an anatomical region. Murray teaches computing a mean and standard deviation for Z-score normalization, as a preprocessing step performed across voxel populations of healthy controls. See Murray at [0051]. The amended claim 118 requires a measure of central tendency of pixel intensity in the image region corresponding to the right temporal pole as one of the image metrics from which the diagnostic indicator is determined, thereby providing a quantitative indication of tissue characteristics in that region. These are fundamentally different operations performed for fundamentally different purposes. Murray does not cure the deficiencies of Desikan and Oliveira.
Examiner Response: After careful consideration and review of applicant’s argument. The examiner respectfully disagrees for the following reason below.
During examination, the claims must be interpreted as broadly as their terms reasonably allow. In re American Academy of Science Tech Center, 367 F.3d 1359, 1369, 70 U.S.P.Q.2d 1827, 1834 (Fed. Cir. 2004).
Desikan teaches: A computer implemented method of predicting or diagnosing cognitive impairment in a human subject based on images of the subject's brain, the method comprising: (Desikan − [pdf page 1] Structural magnetic resonance imaging (MRI) of cerebral cortex (brain); tracking the evolution of disease from the degenerative changes associated with dementing illnesses such as Alzheimer’s disease (AD))
PNG
media_image1.png
572
1188
media_image1.png
Greyscale
operating a processor to automatically segment the images to provide digital image data corresponding to ROls in each of the image regions, (Desikan – [pdf page 3], segmenting and identifying skull ROI using a skull-stripping algorithm)
PNG
media_image2.png
394
903
media_image2.png
Greyscale
PNG
media_image3.png
901
524
media_image3.png
Greyscale
and determining the image metrics by operating the processor to perform, on the digital data, image processing steps configured to provide said image metrics; (Desikan − [pdf page 6] Construction of cortical atlas; minimizing the metric distortion between the cortical and the spherical representations through automatic segmenting regions of interest in the brain;)
determining, based on processing by the computer of digital image data obtained from the images, image metrics comprising: an image texture metric, (Desikan − [pdf page 6] Construction of cortical atlas; minimizing the metric distortion between the cortical and the spherical representations through automatic segmenting regions of interest in the brain;)
Oliveira teaches: determining, based on processing by the computer, an indicator based on said image metrics according to a predetermined method, the predetermined method comprising computing a weighted sum of the image metrics; (Oliveira − [pdf page 3-4] sum averages of GLCMs; a weighted average of the 176 texture parameters )
an image texture metric, comprising a GLCM correlation, of an image region corresponding to [the right rostral middle frontal], thereby providing a quantitative indication of tissue characteristics in [the right rostral middle frontal]; an image texture metric, comprising a GLCM correlation, in the image region corresponding to [the right supramarginal], thereby providing a quantitative indication of tissue characteristics in the right supramarginal; (Oliveira − [pdf page 3] The statistical approach adopted here to extract texture parameters from the MR images was padded on the GLCM (gray level co-occurrence matrices); Fig. 3 MR imaging of the temporal structure, Maps of textural parameters to compute the GLCM with distance of pixels 0 degrees, 45 degrees, 90 degrees or 135 degrees, totaling 16 GLCMs and totaling 176 texture parameters for each region of interest. Region of interest of the temporal structure that includes the temporal pole.) Examiner notes: limitation recites “at least one of (i.e., A, B, or C)” therefore teaching one of the limitation meets the limitation of at least one of
PNG
media_image4.png
289
585
media_image4.png
Greyscale
determining, based on processing by the computer, an indicator based on said image metrics according to a predetermined method, the predetermined method comprising computing a weighted sum of the image metrics; (Oliveira − [pdf page 3-4] sum averages of GLCMs; a weighted average of the 176 texture parameters )
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Desikan with the weighted-sum image metric processing taught by Oliveira as both references are directed to analyzing MRI-derived brain image data to quantitatively characterize brain tissue for the prediction or diagnosis of cognitive impairment. Incorporating Oliveira’s weighted-sum processing would have improved Desikan’s quantitative evaluation of image metrics by combining multiple texture parameters into a single diagnostic indicator, thereby improving the robustness and reliability of the resulting diagnostic indicator.
Raj teaches: and displaying the indicator as an overlay on an image of the human subject's brain to assist a clinician in predicting or diagnosing cognitive impairment state in the subject based on the indicator, (Raj – [0066] The predicted future disease patterns may be output in a representation selected from the group of a) a ball and stick model overlaid on a connectivity map of the human brain; b) a table; c) a graph; and d) a color-coded surface map of the brain.)
wherein the overlay comprises one or more portions overlayed on one or more of the image regions used to determine the indicator, (Raj – Fig. 13, Parkinson's Disease, Fig. 22 and 2 show the predicted disease locations displayed on the brain itself. [0066] The predicted future disease patterns may be output in a representation selected from the group of a) a ball and stick model overlaid on a connectivity map of the human brain; b) a table; c) a graph; and d) a color-coded surface map of the brain.)
thereby providing a visual marker of the extent and location of structural changes associated with cognitive impairment to assist a clinician in predicting or diagnosing a cognitive impairment state. (Raj – [0067] In some embodiments, a method for analyzing the brain of a subject may be applied in the context of testing a medical intervention in a clinical trial conducted under a protocol. Such a method may include taking a medical image of a patient's brain and applying the method described above to predict future changes to the brain of the subject. In this context, administering a medical intervention to the patient may be followed by taking a second medical image of said patient's brain after the time period indicated in the clinical trial protocol, again applying the method described above to obtain new predicted future changes to the brain of the subject, and comparing the results of steps to determine the efficacy of the intervention.)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Desikan and Oliveira to present the computed diagnostic indicator as an overlay on an anatomical brain image using the visualization technique taught by Raj because Raj teaches displaying predicted disease patterns as overlays on anatomical brain images to facilitate clinical interpretation. Thereby improving a clinician’s ability to identify the location and extent of predicted structural changes when evaluating cognitive impairment.
Murray teaches and a measure of central tendency of pixel intensity in an image region corresponding to [the right temporal pole], thereby providing a quantitative indication of tissue characteristics in [the right temporal pole]; the method further comprising: (Murray – [0051] The process then proceeds to act 316, where the individual data types (e.g., data for each of the metrics/features of interest) are normalized. Normalization establishes a mean and standard deviation (measure of central tendency and defined distribution) for the values in the data and applies a Z-score (or other statistical measure of difference) to determine how far an individual data point falls from the mean. The mean and standard deviation for a particular voxel is determined from a group (e.g., 20 or more) of comparable, healthy individuals. )
thereby providing a visual marker of the extent and location of structural changes associated with cognitive impairment (Murray – [0051] [0073] FIG. 9 shows yet another visualization generated based on the techniques described herein. The visualization shown in FIG. 9 is similar to the visualization in FIG. 8B and provides additional detail about the relative impact of each of the imaging data types that contributed to the injury mask for each of the nodes in the right executive control network. [0074] The function can be determined by measuring small changes in oxygen consumption throughout the grey matter. A local increase of oxygen consumption indicates activation of that group of neurons. By comparing the patterns of fluctuation over time between two regions, how well those regions are working together or share a functional connection can be measured.)
to assist a clinician in predicting or diagnosing a cognitive impairment state. (Murray – [0085] In some implementations, the eloquence map can be used as a tool for neurosurgical guidance. For example, the eloquence map can be used to develop and modify a surgical plan with predictions of how likely a patient is to have lasting cognitive impairment by following one plan or another during an intervention. The eloquence map may be used in conjunction with an existing platform to surgical and radiosurgical planning and or guidance.)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Desikan, Oliveira, and Raj to perform the statistical processing taught by Murray because Murray teaches normalizing image metric value using measures of central tendency and statistical distribution to account for subject-to-subject variability before generating diagnostic indicators. Incorporating Murray’s normalization techniques would have improved the consistency and comparability of the computed image metrics, thereby providing more consistent and comparable image metrics from which the diagnostic indicator may be generated and subsequently visualized for clinical interpretation.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 118-119, 130, 133, 135, 138, and 140-143 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1 Analysis: Claims 118 is directed to a method, which is directed to a process, one of the statutory categories.
Step 2A prong 1: Does the claim recite a judicial exception? Yes, claim 118 recites limitations of “determining the image metrics by operating the processor…”, determining… an indicator based on said image metrics according to a predetermined method..” and displaying the indicator as an overlay on an image of the human subject’s brain to assist a clinician in predicting or diagnosing cognitive impairment state...” Under the broadest reasonable interpretation, these limitation encompass evaluating image information, applying mathematical relationships to derive image metrics and an indicator, and presenting the resulting information to assist a clinician in making a diagnostic decision. Accordingly, these limitations fall within the “Mental Processes” grouping of abstract idea because they recite observations, evaluations, and 0judgements directed to analyzing information and assisting a clinician in making a diagnostic determination.
Furthermore, the limitation directed to determining a measure of central tendency using pixel intensity recites a mathematical concept because it requires performing a mathematical calculation on image data.
Step 2A prong 2: Does the claim recite additional elements? Do those additional elements, individually and in combination, integrate the judicial exception into a practical application? No.
Claim 118 further recites the additional limitations of “operating a processor to automatically segment the images to provide digital image data corresponding to ROIs in each of the image regions,” “determining the image metrics by operating the processor to perform, on the digital image, image processing steps configured to provide said image metrics,” and “displaying the indicator as an overlay on an image of the human subject’s brain… where the overlay comprises one or more portions overlaid on one or more of the image regions used to determine the indicator…”
Applicant contends that the additional elements integrate the judicial exception into a practical application by providing a technological improvement in medical image processing. The examiner respectfully disagrees.
The additional elements merely use a processor to obtain and process image data, determine image metrics, determine an indicator based on mathematical relationships, and present the resulting information as an overlay to assist a clinician in predicting or diagnosing cognitive impairment. Although the claimed overlay identified the image regions used to determine the indicator and provides a visual marker, the overlay merely presents the results generated by the recited mathematical analysis and diagnostic evaluation. The claims does not recite an improvement to the functioning of a computer, image processing technology, or another technology or technical field. Rather, the claimed processor preforms its ordinary computer functions to analyze information and display the resulting information to a user.
Likewise, the recited image segmentation and image processing steps do not improve the underlying image processing technology itself. Rather, the segmentation and image processing steps are used in carrying out the claimed mathematical analysis and determining the claimed indicator, rather than improving the manner in which image segmentation or image processing is performed.
Accordingly, the additional elements merely implement the judicial exception by using generic computer components preforming their ordinary functions (MPEP 2106.05(f)). Furthermore, displaying the indicator as an overlay merely presents the results of the recited mathematical analysis and diagnostic evaluation to a clinician and therefore amounts to insignificant extra-solution activity (MPEP 2106.05(g)). When considered individually and as an ordered combination, the additional elements do not integrate the judicial exception into a practical application. Therefore, the additional elements do not integrate the judicial exception into a practical application, and claim 118 is directed to an abstract idea.
Step 2B: Do the additional elements, considered individually and in combination, amount to significantly more than the judicial exception? No.
As discussed above, the additional elements consist of a processor configured to perform image segmentation, image processing, determining image metrics, determining an indicator, and displaying the indicator as an overlay. These additional elements merely implement the judicial exception using generic computer components performing their ordinary functions (MPEP 2106.05(f)). Furthermore, displaying the indicator as an overlay merely presents the results of the recited mathematical analysis and diagnostic evaluation and therefore amounts to insignificant extra-solution activity (MPEP 2106.05(g)). The claim does not recite any additional element or ordered combination that improves the functioning of a computer or another technology or technical field, nor does it recite any other inventive concept sufficient to amount to significantly more than the abstract idea (judicial exception). Thus, the claim is not patent eligible.
The dependent claims (claims 130, 133, and 140-143) further recite limitations including “using an HLH filter, a measure of correlation, determining parameters of age related effects in the voxel, based on the vector of age values and the vector of intensity values and a model of said effects; and determining the image metrics is in response to age normalizing the images, wherein the tissue characteristics comprise at least one of: tissue morphology, tissue texture, and/or tissue structure,” these limitations likewise fall within the “Mental Processes and Mathematical Concept” groupings of abstract ideas.
These additional limitations do not integrate the judicial exception into a practical application because they merely add further mathematical concepts together with insignificant extra-solution activity to the abstract idea already identified above. The additional limitations do not improve the functioning of a computer, image processing technology, or another technology or technical field. Rather, they merely provide additional calculations and image processing performed as part of implementing the abstract idea and do not impose any meaningful limit on practicing the judicial exception. Accordingly, for the reason discussed above with respect to claim 118, the dependent claims likewise do not include additional elements sufficient to amount to significantly more than the judicial exception.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 140-141 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 140 recites the limitation “determining the image metrics is in response to age normalizing the images”. However, the metes and bounds of the claim are not clear. Specifically the scope of the claim is uncertain because it is unclear what relationship is intended between the age normalizing step and the determining of the image metrics. For example, it is unclear whether the image metrics are determined after age normalizing the images, using the age normalized images, or whether the determining is merely triggered by the age normalizing. Accordingly, one of ordinary skill in the art would not be reasonably able to determine the scope of the claimed invention.
Dependent claim 141 is rejected for fully incorporating the dependencies of their bases.
Claims 118-119, 133, 135, 138, 140-141, and 143 are rejected under 35 U.S.C. 103 as being unpatentable over Desikan (An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest, Pub Date: Mar. 2006) in view of M.S. de Oliveira (MR Imaging Texture Analysis of the Corpus Callosum and Thalamus in Amnestic Mild Cognitive Impairment and Mild Alzheimer Disease, Pub Date: AJNR 32 Jan. 2011, hereinafter “Oliveira”) in view of Raj (US PGPUB: 20160300352 A1, Filed Date: 3/20/2014) in view of Murray (US 20220148181 A1, Filed Date: Apr. 17, 2019).
Regarding independent claim 118, Desikan teaches: A computer implemented method of predicting or diagnosing cognitive impairment in a human subject based on images of the subject's brain, the method comprising: (Desikan − [pdf page 1] Structural magnetic resonance imaging (MRI) of cerebral cortex (brain); tracking the evolution of disease from the degenerative changes associated with dementing illnesses such as Alzheimer’s disease (AD))
PNG
media_image1.png
572
1188
media_image1.png
Greyscale
operating a processor to automatically segment the images to provide digital image data corresponding to ROls in each of the image regions, (Desikan – [pdf page 3], segmenting and identifying skull ROI using a skull-stripping algorithm)
PNG
media_image2.png
394
903
media_image2.png
Greyscale
PNG
media_image3.png
901
524
media_image3.png
Greyscale
and determining the image metrics by operating the processor to perform, on the digital data, image processing steps configured to provide said image metrics; (Desikan − [pdf page 6] Construction of cortical atlas; minimizing the metric distortion between the cortical and the spherical representations through automatic segmenting regions of interest in the brain;)
determining, based on processing by the computer of digital image data obtained from the images, image metrics comprising: an image texture metric, (Desikan − [pdf page 6] Construction of cortical atlas; minimizing the metric distortion between the cortical and the spherical representations through automatic segmenting regions of interest in the brain;)
Desikan does not explicitly teach: a weighted sum of the image metrics
However, Oliveira teaches: determining, based on processing by the computer, an indicator based on said image metrics according to a predetermined method, the predetermined method comprising computing a weighted sum of the image metrics; (Oliveira − [pdf page 3-4] sum averages of GLCMs; a weighted average of the 176 texture parameters )
an image texture metric, comprising a GLCM correlation, of an image region corresponding to [the right rostral middle frontal], thereby providing a quantitative indication of tissue characteristics in [the right rostral middle frontal]; an image texture metric, comprising a GLCM correlation, in the image region corresponding to [the right supramarginal], thereby providing a quantitative indication of tissue characteristics in the right supramarginal; (Oliveira − [pdf page 3] The statistical approach adopted here to extract texture parameters from the MR images was padded on the GLCM (gray level co-occurrence matrices); Fig. 3 MR imaging of the temporal structure, Maps of textural parameters to compute the GLCM with distance of pixels 0 degrees, 45 degrees, 90 degrees or 135 degrees, totaling 16 GLCMs and totaling 176 texture parameters for each region of interest. Region of interest of the temporal structure that includes the temporal pole.) Examiner notes: limitation recites “at least one of (i.e., A, B, or C)” therefore teaching one of the limitation meets the limitation of at least one of
PNG
media_image4.png
289
585
media_image4.png
Greyscale
determining, based on processing by the computer, an indicator based on said image metrics according to a predetermined method, the predetermined method comprising computing a weighted sum of the image metrics; (Oliveira − [pdf page 3-4] sum averages of GLCMs; a weighted average of the 176 texture parameters )
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Desikan with the weighted-sum image metric processing taught by Oliveira as both references are directed to analyzing MRI-derived brain image data to quantitatively characterize brain tissue for the prediction or diagnosis of cognitive impairment. Incorporating Oliveira’s weighted-sum processing would have improved Desikan’s quantitative evaluation of image metrics by combining multiple texture parameters into a single diagnostic indicator, thereby improving the robustness and reliability of the resulting diagnostic indicator.
Desikan does not explicitly teach: and displaying the indicator as an overlay on an image of the human subject's brain to assist a clinician in predicting or diagnosing cognitive impairment state in the subject based on the indicator
However, Raj teaches: and displaying the indicator as an overlay on an image of the human subject's brain to assist a clinician in predicting or diagnosing cognitive impairment state in the subject based on the indicator, (Raj – [0066] The predicted future disease patterns may be output in a representation selected from the group of a) a ball and stick model overlaid on a connectivity map of the human brain; b) a table; c) a graph; and d) a color-coded surface map of the brain.)
wherein the overlay comprises one or more portions overlayed on one or more of the image regions used to determine the indicator, (Raj – Fig. 13, Parkinson's Disease, Fig. 22 and 2 show the predicted disease locations displayed on the brain itself. [0066] The predicted future disease patterns may be output in a representation selected from the group of a) a ball and stick model overlaid on a connectivity map of the human brain; b) a table; c) a graph; and d) a color-coded surface map of the brain.)
thereby providing a visual marker of the extent and location of structural changes associated with cognitive impairment to assist a clinician in predicting or diagnosing a cognitive impairment state. (Raj – [0067] In some embodiments, a method for analyzing the brain of a subject may be applied in the context of testing a medical intervention in a clinical trial conducted under a protocol. Such a method may include taking a medical image of a patient's brain and applying the method described above to predict future changes to the brain of the subject. In this context, administering a medical intervention to the patient may be followed by taking a second medical image of said patient's brain after the time period indicated in the clinical trial protocol, again applying the method described above to obtain new predicted future changes to the brain of the subject, and comparing the results of steps to determine the efficacy of the intervention.)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Desikan and Oliveira to present the computed diagnostic indicator as an overlay on an anatomical brain image using the visualization technique taught by Raj because Raj teaches displaying predicted disease patterns as overlays on anatomical brain images to facilitate clinical interpretation. Thereby improving a clinician’s ability to identify the location and extent of predicted structural changes when evaluating cognitive impairment.
Desikan does not explicitly teach: and a measure of central tendency of pixel intensity in an image region
However, Murray teaches and a measure of central tendency of pixel intensity in an image region corresponding to [the right temporal pole], thereby providing a quantitative indication of tissue characteristics in [the right temporal pole]; the method further comprising: (Murray – [0051] The process then proceeds to act 316, where the individual data types (e.g., data for each of the metrics/features of interest) are normalized. Normalization establishes a mean and standard deviation (measure of central tendency and defined distribution) for the values in the data and applies a Z-score (or other statistical measure of difference) to determine how far an individual data point falls from the mean. The mean and standard deviation for a particular voxel is determined from a group (e.g., 20 or more) of comparable, healthy individuals. )
thereby providing a visual marker of the extent and location of structural changes associated with cognitive impairment (Murray – [0051] [0073] FIG. 9 shows yet another visualization generated based on the techniques described herein. The visualization shown in FIG. 9 is similar to the visualization in FIG. 8B and provides additional detail about the relative impact of each of the imaging data types that contributed to the injury mask for each of the nodes in the right executive control network. [0074] The function can be determined by measuring small changes in oxygen consumption throughout the grey matter. A local increase of oxygen consumption indicates activation of that group of neurons. By comparing the patterns of fluctuation over time between two regions, how well those regions are working together or share a functional connection can be measured.)
to assist a clinician in predicting or diagnosing a cognitive impairment state. (Murray – [0085] In some implementations, the eloquence map can be used as a tool for neurosurgical guidance. For example, the eloquence map can be used to develop and modify a surgical plan with predictions of how likely a patient is to have lasting cognitive impairment by following one plan or another during an intervention. The eloquence map may be used in conjunction with an existing platform to surgical and radiosurgical planning and or guidance.)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Desikan, Oliveira, and Raj to perform the statistical processing taught by Murray because Murray teaches normalizing image metric value using measures of central tendency and statistical distribution to account for subject-to-subject variability before generating diagnostic indicators. Incorporating Murray’s normalization techniques would have improved the consistency and comparability of the computed image metrics, thereby providing more consistent and comparable image metrics from which the diagnostic indicator may be generated and subsequently visualized for clinical interpretation.
Regarding dependent claim 119, depends on claim 118, Desikan teaches: Alzheimer’s disease, but does not explicitly teach: wherein predicting or diagnosing cognitive impairment state comprises distinguishing between: (a) Alzheimer's disease; and (b) non-Alzheimer's disease.
However, Oliveira teaches: wherein predicting or diagnosing cognitive impairment state comprises distinguishing between:(a) Alzheimer's disease; and (b) non-Alzheimer's disease. (Oliveira − [pdf page 2-6] how many times gray level co-occurs with gray level determine the level or severity of AMCI, mild AD and normal control patient)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Desikan, Oliveira, and Raj to perform the statistical processing taught by Murray because Murray teaches normalizing image metric value using measures of central tendency and statistical distribution to account for subject-to-subject variability before generating diagnostic indicators. Incorporating Murray’s normalization techniques would have improved the consistency and comparability of the computed image metrics, thereby providing more consistent and comparable image metrics from which the diagnostic indicator may be generated and subsequently visualized for clinical interpretation.
Regarding dependent claim 133, depends on claim 118, Desikan doesn’t teach: central tendency is the mean.
However, Murray teaches: central tendency is the mean. (Murray − 0051] The process then proceeds to act 316, where the individual data types (e.g., data for each of the metrics/features of interest) are normalized. Normalization establishes a mean and standard deviation (measure of central tendency and defined distribution) for the values in the data and applies a Z-score (or other statistical measure of difference) to determine how far an individual data point falls from the mean. The mean and standard deviation for a particular voxel is determined from a group (e.g., 20 or more) of comparable, healthy individuals. )
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Desikan, Oliveira, and Raj to perform the statistical processing taught by Murray because Murray teaches normalizing image metric value using measures of central tendency and statistical distribution to account for subject-to-subject variability before generating diagnostic indicators. Incorporating Murray’s normalization techniques would have improved the consistency and comparability of the computed image metrics, thereby providing more consistent and comparable image metrics from which the diagnostic indicator may be generated and subsequently visualized for clinical interpretation.
Regarding dependent claim 135, depends on claim 118, Desikan does not explicitly teach: comprising obtaining reference data configured to indicate a cognitive impairment state using reference indicators determined according to the predetermined method, and comparing the indicators for the subject to the reference indicators to perform said predicting or diagnosing of the cognitive impairment state in the subject.
However, Oliveira teaches: comprising obtaining reference data configured to indicate a cognitive impairment state using reference indicators determined according to the predetermined method, and comparing the indicators for the subject to the reference indicators to perform said predicting or diagnosing of the cognitive impairment state in the subject. (Oliveira − [pdf page 2, 6] find differences among patients with aMCI (mild cognitive impairment) and mild AD (Alzheimer Disease) and normal-aging subjects (non-Alzheimer disease), by using TA (texture analysis) applied to the MR images of the CC and the thalami of these groups of subjects. The application of TA techniques seeks mathematic parameters that can differentiate normal and lesioned tissues, by using texture parameters extracted from GLCMs. [pdf page 2-6] how many times gray level co-occurs with gray level determine the level or severity of AMCI, mild AD and normal control patient)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Desikan, Oliveira, and Raj to perform the statistical processing taught by Murray because Murray teaches normalizing image metric value using measures of central tendency and statistical distribution to account for subject-to-subject variability before generating diagnostic indicators. Incorporating Murray’s normalization techniques would have improved the consistency and comparability of the computed image metrics, thereby providing more consistent and comparable image metrics from which the diagnostic indicator may be generated and subsequently visualized for clinical interpretation.
Regarding dependent claim 138, depends on claim 118, Desikan and Oliveira teaches all the limitation of claim 118, Oliveira teaches: A computer program product or computer apparatus configured to perform the method of claim 118 and to provide an output indicating said prediction or diagnosis. (Oliveira – [pdf page 4] weighted average of the 176 texture parameters over the different sections, by using the region-of-interest size as weight, was computed, by using Matlab (MathWorks, Natick, Massachusetts). [Official notice] Matlab is a software that is run on a computer apparatus.)
Regarding dependent claim 140, depends on claim 118, Desikan teaches: age normalizing the images by: obtaining, for each voxel in the images of the subject's brain, a vector of intensity values wherein each intensity value comprises the intensity of the voxel in one of a corresponding plurality of images each obtained from a control subject (CN); (Desikan − [pdf page 2] The MRI scans of 40 subjects from this cohort were used in the present analyses. As noted above, for the development of a cortical atlas, we wanted to include subjects with a range of atrophy. We therefore selected MRI scans from subjects that varied widely in age and clinical status to incorporate the types of variance we find in our typical studies of aging and dementia. The 40 subjects were therefore divided into four groups: Group 1—young adults (n = 10; mean age = 21.5, age range 19–24; 6 females, 4 males); Group 2—middle-aged adults (n = 10; mean age = 49.8, age range 41–57; 7 females, 3 males); Group 3—elderly adults (n = 10; mean age = 74.3, age range 66–87; 8 females, 2 males); and Group 4—patients with AD (n = 10; mean age = 78.2, age range 71–86; 5 females, 5 males).)
Desikan does not explicitly teach: obtaining a vector of age values, each age value identifying the age of a corresponding one of the control subjects so that each element of the vector of age values corresponds to an element of the vector of intensity values;
However, Murray teaches: obtaining a vector of age values, each age value identifying the age of a corresponding one of the control subjects so that each element of the vector of age values corresponds to an element of the vector of intensity values; determining parameters of age related effects in the voxel, based on the vector of age values and the vector of intensity values and a model of said effects; and using said model and said parameters to normalize intensity values in the voxel in images of test subjects based on the age of said test subject; and determining the image metrics is in response to age normalizing the images. (Murray − [0051] The process then proceeds to act 316, where the individual data types (e.g., data for each of the metrics/features of interest) are normalized. Normalization establishes a mean and standard deviation (measure of central tendency and defined distribution) for the values in the data and applies a Z-score (or other statistical measure of difference) to determine how far an individual data point falls from the mean. Normalization may be performed in any suitable way, examples of which are described in more detail below. [0052] Normalize against a reference population (e.g., healthy, age and sex-matched subjects). The mean and standard deviation for a particular voxel is determined from a group (e.g., 20 or more) of comparable, healthy individuals.)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Desikan, Oliveira, and Raj to perform the statistical processing taught by Murray because Murray teaches normalizing image metric value using measures of central tendency and statistical distribution to account for subject-to-subject variability before generating diagnostic indicators. Incorporating Murray’s normalization techniques would have improved the consistency and comparability of the computed image metrics, thereby providing more consistent and comparable image metrics from which the diagnostic indicator may be generated and subsequently visualized for clinical interpretation.
Regarding dependent claim 141, depends on claim 118, Desikan does not explicitly teach: wherein the model of age related effects comprises a linear model and determining parameters of age comprises fitting said model to the vector of intensity values.
However, Murray teaches: wherein the model of age related effects comprises a linear model and determining parameters of age comprises fitting said model to the vector of intensity values.
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Desikan, Oliveira, and Raj to perform the statistical processing taught by Murray because Murray teaches normalizing image metric value using measures of central tendency and statistical distribution to account for subject-to-subject variability before generating diagnostic indicators. Incorporating Murray’s normalization techniques would have improved the consistency and comparability of the computed image metrics, thereby providing more consistent and comparable image metrics from which the diagnostic indicator may be generated and subsequently visualized for clinical interpretation.
Regarding dependent claim 143, depends on claim 118, Desikan teaches: wherein the tissue characteristics comprise at least one of: tissue morphology, tissue texture, and/or tissue structure. (Desikan − [pdf page 2] anatomic curvature is visually represented well on inflated images as they provide a view of the brain in which the entire cortical surface is exposed, including the tissue)
Claim(s) 130 is rejected under 35 U.S.C. 103 as being unpatentable over Desikan, Oliveira, Raj, Murray as applied to claim 118 above, and further in view of ANTONIADES (US PGPUB: 20210374951 A1).
Regarding dependent claim 130, depends on claim 118, Desikan teaches:
wherein the image data in the region corresponding to the right inferior lateral ventricle (Desikan − [pdf page 3-5, 8] MRI image acquisition; the cerebral hemispheres were subdivided into 34 regions; Subdivided Temporal lobe, Middle temporal gyrus; the lateral fissure (and when present, the supramarginal gyrus; Parietal lobe, the supramarginal gyrus; Frontal Pole, the middle frontal gyrus; Table 1 (manual) and Table 2 (automatic))
Regarding dependent claim 142, depends on claim 118, Desikan does not explicitly teach: using a HLH filter
However, ANTONIADES teaches: using an HLH filter. ([0163] a three level filter bank is used, eight wavelet decompositions result, corresponding to HHH, HHL, HLH, HLL, LHH, LHL, LLH and LLL, where H refers to “high-pass”, and L refers to “low-pass”)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Desikan, Oliveira, Raj, Murray and ANTONIADES as each of the image processing of imagery data of the anatomy. Adding the teaching of ANTONIADES provides Desikan with a filter bank of high and low pass filter. Therefore, providing the benefit of filter out signal to noise from imagery data.
Claim(s) 142 is rejected under 35 U.S.C. 103 as being unpatentable over Desikan, Oliveira, Raj, Murray as applied to claim 118 above, and further in view of Nicolas Nicastro (Cortical complexity analyses and their cognitive correlate in Alzheimer’s disease and frontotemporal dementia, Pub Date: Dec. 04, 2019, hereinafter “Nicastro”).
Desikan doesn’t teach: a minimum fractal dimension
However, Nicastro teaches: wherein the image metrics further comprise a minimum fractal dimension of an image region corresponding to the right middle temporal gyrus, thereby providing a quantitative indication of tissue characteristics in the right middle temporal gyrus. (Nicastro − [page 7, Fig. 1] AD showed reduced fractal dimension in the bilateral insula and supramarginal gyrus, left middle frontal, superior temporal, inferior temporal, and right parahippocampal gyri Fig. 2 fractal dimension group comparison between Controls, Ad, and FTD. [page 9, Fig. 4 associate with reduced fractal dimension in left middle temporal,… for AD.) Nicastro would apply the similar fractal measure to right middle temporal of the right side of the brain
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Desikan, Oliveira, Raj and Nicastro as each of the inventions relates to providing identifying changes over time regarding brain disease using image processing of imagery data. Adding the teaching of Nicastro provides Desikan with fractal metric for determining fractal measure of the brain. Therefore, providing the benefit of distinguishing brain disease from normal aging brain.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CARL E BARNES JR whose telephone number is (571)270-3395. The examiner can normally be reached Monday-Friday 9am-6pm.
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, Stephen Hong can be reached at (571) 272-4124. 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.
/CARL E BARNES JR/Examiner, Art Unit 2178
/STEPHEN S HONG/Supervisory Patent Examiner, Art Unit 2178
Prosecution Insights