Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
NOTICE OF PRELIMINARY AMENDMENT
The Examiner acknowledges the amended claims filed on 08/12/2022.
- Claims 1, 3-6, 8-12, 14-19 & 21-27 have been amended.
CLAIM REJECTIONS - 35 USC § 112
The following is a quotation of the second paragraph of 35 U.S.C. 112:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-27 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 pre-AIA the applicant regards as the invention.
Claim 1 recites the limitation “determining an optimal QUS biomarker for response prediction”.
The specification does give provide how this was done. The phrase “optimal QUS biomarker” is a term of degree that lacks objective boundaries. The claim does not specify the performance metric, dataset, or feature-selection process used to determine optimality, nor does it incorporate the specific 4-feature subset described in the specification. As a result, one of ordinary skill in the art cannot determine with reasonable certainty whether a given feature set falls within the scope of “optimal”, rendering the claim indefinite under 35 USC 112b.
Claims 19-20 recites the limitation “estimating a clustering quality metric comprising Bayesian information criterion (BIC), Calinski-Harabasz index, or Davies-Bouldin index; and identifying a least number of regions associated with an appropriate clustering quality metric as the optimum number of the distinct intra-tumor regions on the at least one QUS parametric map.”
The term “appropriate clustering quality metric” fails to inform those skilled in the art, with reasonable certainty, about the scope of the invention. The claim does not specify with quality metric must be used, how “appropriateness” is determined, or what threshold defines a metric as “appropriate”. Thus, limitations relying on an “appropriate clustering quality metric” are indefinite under 35 USC 112(b).
As to claims 2-18 & 21-27, these claims are rejected due to their dependence on claims 1 & 19-20 and are rejected for the same reasons.
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 1-27 are rejected under 35 U.S.C. 101 because the claimed invention is directed to as ineligible under subject eligibility test. In the Subject Matter Eligibility Test for Products and Processes (Federal Register, Vol. 79, No. 241, dated Tuesday, December 16, 2014, page 74621), The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional device elements, which are recited at a high level of generality, provide conventional computer functions that do not add meaningful limits to practicing the abstract idea.
Claim 1
Step 1
This step inquires “is the claim to a process, article of machine, manufacture or composition of matter?” Yes,
Claim 1 – “Method” is a process.
Step 2A - Prong 1
This step inquires “does the claim recite an abstract idea, law or natural phenomenon”. This claim appears to directed to an abstract idea.
The limitation of “acquiring, using an ultrasound device, ultrasound radiofrequency (RF) data comprising RF frames and B-mode images from a tumor subject prior to the NAC; generating, if not acquired at said acquiring step, said B-mode images using the acquired RF data; identifying a region of interest (ROI) in each of said B-mode images, the ROI comprising a tumor; generating at least one quantitative ultrasound (QUS) parametric map by QUS spectral analysis or analysis of RF signal envelope statistics of each RF frame associated with said B- mode images throughout the ROI to derive a corresponding QUS parameter, each said QUS parametric map based on a respective said QUS parameter; identifying distinct intra-tumor regions on the at least one QUS parametric map by applying a classification (clustering) algorithm to the at least one QUS parametric map, wherein the distinct intra-tumor regions are identified as segmented regions; extracting features from the segmented regions on each of the at least one QUS parametric map within the ROI to characterize the tumor; determining an optimal QUS biomarker for response prediction; training a classification algorithm for the response prediction using the optimal QUS biomarker; and classifying the tumor subject into a responder or a non-responder to the NAC using the optimal QUS biomarker in conjunction with the trained classification algorithm, the trained classification algorithm comprising a response prediction model.”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind (e.g. mathematical concepts, mental processes or certain methods of organizing human activity) but for the recitation of generic computer components. That is, other than reciting “ultrasound device” nothing in the claim element precludes the step from practically being performed in the mind. For example, but for the “ultrasound device” language, “acquiring, generating, identifying, extracting, determining, training, classifying” in the context of this claim encompasses covers performance of the limitation in the mind (e.g. mathematical concepts, mental processes or certain methods of organizing human activity).
STEP 2A – PRONG 1 - CONCLUSION
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A - Prong 2
This step inquires “does the claim recite additional elements that integrate the judicial exception into a practical application”. This judicial exception is not integrated into a practical application. In particular, the claim recites one additional element – using a “ultrasound device” to perform “acquiring, generating, identifying, extracting, determining, training, classifying” steps. The “ultrasound device” are recited at a high-level of generality (i.e., as a generic processor) “acquiring, using an ultrasound device, ultrasound radiofrequency (RF) data comprising RF frames and B-mode images from a tumor subject prior to the NAC; generating, if not acquired at said acquiring step, said B-mode images using the acquired RF data; identifying a region of interest (ROI) in each of said B-mode images, the ROI comprising a tumor; generating at least one quantitative ultrasound (QUS) parametric map by QUS spectral analysis or analysis of RF signal envelope statistics of each RF frame associated with said B- mode images throughout the ROI to derive a corresponding QUS parameter, each said QUS parametric map based on a respective said QUS parameter; identifying distinct intra-tumor regions on the at least one QUS parametric map by applying a classification (clustering) algorithm to the at least one QUS parametric map, wherein the distinct intra-tumor regions are identified as segmented regions; extracting features from the segmented regions on each of the at least one QUS parametric map within the ROI to characterize the tumor; determining an optimal QUS biomarker for response prediction; training a classification algorithm for the response prediction using the optimal QUS biomarker; and classifying the tumor subject into a responder or a non-responder to the NAC using the optimal QUS biomarker in conjunction with the trained classification algorithm, the trained classification algorithm comprising a response prediction model.” such that it amounts no more than mere instructions to apply the exception using a generic computer component.
STEP 2A – PRONG 2 - CONCLUSION
Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
Step 2B
The critical inquiry here is does the claim recite additional elements that amount to “significantly more” than the judicial exception? The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a “ultrasound device” to perform “acquiring, generating, identifying, extracting, determining, training, classifying” steps amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claim is not patent eligible.
Dependent Claims
As to claim 2, this claim is directed to insignificant extra-solution activity (“field of use limitation that does not add any meaningful technical application”), mental process (“Narrowing the clinical context (type of cancer) in which the same abstract data analysis and classification is performed.”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 3, this claim is directed to mental process (“restricts the patient cohort (LABC). The mental/diagnostic abstraction predicting response to NAC based on QUC features and classification”), insignificant extra-solution activity (“field of use restriction to LABC is insignificant extra solution context; it does not change how the data is processed or how the classifier operates”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 4, this claim is directed to mental process (“mathematical processing: instead of one map for all planes, you compute per plane maps”) and insignificant extra-solution activity (“core data processing”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 5, this claim is directed to mental process (“mathematical/statistical parameters derived from signal analysis”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 6, this claim is directed to mental process (“deciding ROI = core + margin is conceptual segmentation”) and insignificant extra-solution activity (“data selection/pre-processing”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 7, this claim is directed to mental process (“choosing “5mm thickness is a design parameter (e.g. mathematical/segmentation”)) and insignificant extra-solution activity (“data selection/ROI definition”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 8, this claim is directed to mental process (“deciding to compute features for regions + margin is analytic strategy (e.g. data analysis/mathematical characterization)”) and insignificant extra-solution activity (“analytic processing;”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 9, this claim is directed to mental process (“selecting particular feature sources is mathematical/analytic selection”) and insignificant extra-solution activity (“internal data analysis”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 10, this claim is directed to mental process (“classic statistical descriptors (mean, SNR) and geometric descriptors (e.g. mathematical abstractions) which are viewed as mental process/mathematical concept”) and insignificant extra-solution activity (“internal data analysis”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 11, this claim is directed to mental process (“volumetric averaging (e.g. mathematical operation”) and insignificant extra-solution activity (“internal data processing”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 12, this claim is directed to mental process (“feature selection is itself is statistical/machine learning concept and can be done mentally with pencil and paper. This a mathematical algorithm”) and insignificant extra-solution activity (“internal to abstract analysis; not pre/post solution”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 13, this claim is directed to mental process (“mathematical/statistical methods”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 14, this claim is directed to mental process (“choosing to start with 56 and reduce to 21 is a design choice”) and insignificant extra-solution activity (“internal data analysis design; not extra solution”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 15, this claim is directed to mental process (“selecting a specific four feature combination as “optimal” is mathematical/diagnostic design choice”) and insignificant extra-solution activity (“internal to abstract analysis”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 16, this claim is directed to mental process (“computing and normalizing power spectra, performing spectral analysis and computing envelope statistics are classic mathematical transformations.”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 17, this claim is directed to mental process (“deciding to segment at pixel level is abstract image processing algorithm; mental/mathematical concept”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 18, this claim is directed to mental process (“choosing an optimum number of clusters is mathematical clustering concept”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 19, this claim is directed to mental process (“statistical/mathematical measurements -> mathematical optimization”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 20, this claim is directed to mental process (“selecting the cluster number that minimizes BIC is mathematically is statistical decision making”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 21, this claim is directed to mental process (“choosing a fixed number of classes is a model design choice ”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 22, this claim is directed to mental process (“ML algorithms are mathematical models are mathematical concepts or mental processes”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 23, this claim is directed to mental process (“medical judgment is mental process”) and insignificant extra-solution activity (“using groud truth to label training data or judge performance is insignificant extra solution activity”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 24, this claim is directed to mental process (“RECIST/MR is clinical evaluation based on tumor size and pathology; these are archetypes of mental processes by physicians”) and insignificant extra-solution activity (“label definition/evaluation criteria”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 25, this claim is directed to mental process (“standard mathematical clustering is mathematical concepts”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 26, this claim is directed to mental process (“decision trees, RF, SVM, ANN, K-NN are mathematical models”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
As to claim 27, this claim is directed to mental process (“AdaBoost with decision trees is a canonical ML algorithm is purely mathematical”). Thus, this claim does not integrate the abstract idea into a practical application or constitute significantly more than the abstract.
CLAIM REJECTIONS - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-8, 10-12, 16-20, 22-23 & 25-27 are rejected under 35 U.S.C. 103 as being unpatentable over Tadayyon et al. (U.S. Publication 2018/0189947) in view of Gaskill-Shipley et al. (U.S. Publication 2022/0405932)
As to claim 1, Tadayyon discloses a computer-implemented method for predicting tumor response to neoadjuvant chemotherapy (NAC) ([0014-0015] discloses a system and methods for using quantitative ultrasound (QUS) techniques to generate imaging biomarkers that can be used to assess a prediction of tumor response to different chemotherapy treatment regimens. A quantitative ultrasound technique to classify tumors, such as locally advanced breast tumor and others, in terms of their chemo-responsiveness prior to beginning neoadjuvant chemotherapy treatment.), the method comprising: acquiring, using an ultrasound device, ultrasound radiofrequency (RF) data comprising RF frames and B-mode images from a tumor subject prior to the NAC; generating, if not acquired at said acquiring step, said B-mode images using the acquired RF data; ([0016-0018] discloses raw echo signal data (e.g. ultrasound radio frequency are acquired from the subject as indicated in step 102. The raw echo signal data can be acquired from a subject using an ultrasound system operating at a conventional ultrasound frequency.)
identifying a region of interest (ROI) in each of said B-mode images, the ROI comprising a tumor;
([0005, 0019] discloses an anatomical image of the subject is provided, and a region of interest that contains a tumor is identified in the anatomical image. One or more regions of interest are then identified in the provided images of the subject, as indicated at step 106. In general, one or more ROIs are identified for each tumor depicted in the provided images. Preferably, at least two ROIs are identified for each tumor: one ROI being associated with the core of the tumor and one ROI being associated with the tumor margin. )
generating at least one quantitative ultrasound (QUS) parametric map by QUS spectral analysis or analysis of RF signal envelope statistics of each RF frame associated with said B- mode images throughout the ROI to derive a corresponding QUS parameter, each said QUS parametric map based on a respective said QUS parameter;
([0003, 0021, 0026-0027] discloses QUS techniques examine the frequency-dependent backscatter of tissues based on data acquired using these techniques, quantitative parameters including mid-band fit (“MBF”), spectral slope (“SS”), spectral 0-Mhz intercept (“SI”), spacing among scatterers (“SAS”), attenuation coefficient estimate (“ACE”), average scatterer diameter (“ASD”), and average acoustic concentration (“AAC”) can be computed. For each RF block, a normalized power spectrum is computed from the acquired raw echo signal data to make the analysis of the raw echo signal data system independent. From the normalized power spectra, one or more parametric maps are generated for each ROI, as indicated at Step 114. For instance, the parametric maps are images whose pixel values are representative of quantitative ultrasound parameters computed from the raw echo signal data. Examples of such parameters include mid band fit (“MBF”), spectral slope (“SS”), spectral 0-Mhz intercept (“SI”), average scatterer diameter (“ASD”), and average acoustic concentration (“AAC”).
identifying distinct intra-tumor regions on the at least one QUS parametric map by applying a classification (clustering) algorithm to the at least one QUS parametric map,
([0019, 0038] discloses at least two ROIs are identified for each tumor: one ROI being associated with the core of the tumor and one ROI being associated with the tumor margin. Image quality measures can include signal to noise ratio and contrast to noise ratio. Image quality features can be defined to compare pixel intensities between two ROIs such as an ROI associated with a tumor core and an ROI associated with a tumor margin. )
extracting features from the segmented regions on each of the at least one QUS parametric map within the ROI to characterize the tumor; ([0029-0031, 0038-0039] discloses one or more features such as first order statistical measures, second order statistical measures, are next extracted from the parametric maps, as indicated at step 116. )
determining an optimal QUS biomarker for response prediction;
([0005, 0014] discloses using quantitative ultrasound (QUS) technique to generate imaging biomarkers that can be used to assess a prediction of tumor response to different chemotherapy treatment regimens. At least one of a first order statistical measure, a second order statistical measure, or an image quality measure is computed based on the at least one parametric map. The tumor is then classified by applying a classifier to the computed at least one first order, second order or image quality measure.)
training a classification algorithm for the response prediction using the optimal QUS biomarker; and classifying the tumor subject into a responder or a non-responder to the NAC using the optimal QUS biomarker in conjunction with the trained classification algorithm, the trained classification algorithm comprising a response prediction model ([0005, 0014-0015] disclose the tumor is then classified based on a prediction of the tumor’s response to a chemotherapy treatment by applying a classifier to the computed measure. Imaging biomarkers that can be used to assess a prediction of tumor response to different chemotherapy treatment regimens. Classify tumors in terms of their chemo responsiveness prior to beginning neoadjuvant chemotherapy treatment. ).
Tadayyon is silent to wherein the distinct intra-tumor regions are identified as segmented regions.
However, in the same field of endeavor seeking to solve the same problem of “using imaging derived sub regional variation within a tumor to improve patient level predictions (e.g. outcome, risk, treatment selection) Gaskill-Shipley discloses wherein the distinct intra-tumor regions are identified as segmented regions. ([0089-0093, 0104-0107] discloses image biomarkers are derived for each voxel or pixel of the region of interest. Each voxel of pixel is classified using a classifier model for example as tumor genotype or molecular subtype. Spatial information based on the distribution of genotypes/molecular subtypes is generated. Intra site heterogeneity is measured based on the spatial information. Examiner views derive image biomarkers for each voxel/pixel as computing QUS features for each pixel regions. Classify each voxel/pixel as genotype/subtype corresponds to classifying subregions in your QUS maps as different biological states. Measure intra site heterogeneity based on spatial distribution as intra tumor heterogeneity.)
It would have been obvious to one of ordinary skill in the art at the time of effective filing to modify Tadayyon’s disclosure to include the above limitations in order to improve pre-treatment prediction of chemotherapy response by incorporating spatial intra-tumor heterogeneity into the imaging biomarker.
As to claim 2, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 1. In addition, Tadayyon discloses wherein the tumor is associated with a cancer comprising breast, prostate, liver, or thyroid cancer. ([0041-0043, 0052-0054])
As to claim 3, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 1. In addition, Tadayyon discloses wherein the tumor comprises a locally advanced breast cancer.
([0051-0053, 0057-0059])
As to claim 4, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 1. In addition, Tadayyon discloses wherein the generating the at least one QUS parametric map for each of the RF frames associated with said B-mode images comprises generating at least one QUS parametric map for each image plane of each of the B-mode images. ([0017, 0054, 0056])
As to claim 5, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 1. In addition, Tadayyon discloses wherein the at least one QUS parameter comprises amid-band fit (MBF), a spectral slope (SS) ([0003, 0026]), a spectral 0-MHz intercept (SI) ([0003, 0026]), an effective scatterer diameter (ESD), an effective acoustic concentration (EAC), or a homodyned K and Nakagami distribution parameter.
As to claim 6, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 5. In addition, Tadayyon discloses wherein the ROI comprises a tumor core and a tumor margin. ([0019, 0054-0056])
As to claim 7, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 6. In addition, Tadayyon discloses wherein the tumor margin comprises a thickness of 5 mm around the tumor core. ([0055, 0058])
As to claim 8, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 6. In addition, Tadayyon discloses wherein the extracting the features from the segmented regions on each of the at least one QUS parametric map within the ROI to characterize the tumor comprises said extracting of the features to characterize the segmented regions and the tumor margin. ([Tadayyon: 0056; Gaskill-Shipley: [0104-0107, 0118-0123])
As to claim 10, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 6. In addition, Tadayyon discloses wherein the features comprise mean-value and signal to noise ratio (SNR) of each of the at least one QUS parametric map within the tumor core, mean-value and SNR of each of the at least one QUS parametric map within the tumor margin, mean-value and SNR of each of the at least one QUS parametric map within each of the segmented regions, a difference between the mean-value of each of two of the segmented regions in each of the at least one QUS parametric map, a proportion area of each of the segmented regions within the tumor core, and a relative area of the tumor margin to the core. ([0030, 0038-0039] discloses first order and image quality features: mean, contrast, correlation, energy, homogeneity, SNR/CNR via CMR and CMCR. )
Tadayyon in view of Gaskill-Shipley is silent to proportion area of each segmented region within tumor core & relative area of margin to core.
However, Gaskill-Shipley discloses creates a distribution of genotrypes or molecular subtypes in each of the plurality of sub-region [0105]. Generating spatial information of genotypes or molecular subtypes in the tumor sites based on the distribution [0106]. Characterizes intra site heterogeneity in the tumor sites based on the spatial information. [0107].
It would have been obvious to one of ordinary skill in the art at the time of effective filing to modify Tadayyon in view of Gaskill-Shipley’s disclosure to include the above limitations in order to better quantify spatial intra-tumor heterogeneity for response prediction.
As to claim 11, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 1. In addition, Tadayyon discloses wherein the features are extracted for all image planes and subsequently averaged over an entire volume of the tumor. (Tadayyon: [0037,0054] Gaskill-Shipley: [0098, 0116-0117])
As to claim 12, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 1. In addition, Tadayyon discloses wherein said determining the optimal QUS biomarker for the response prediction comprises analyzing the features using a multi-step feature selection process to eliminate features that do not contribute to the response prediction, to obtain an optimal QUS feature set for the response prediction, the optimal QUS biomarker comprising the optimal QUS feature set. ([0057-0060] discloses wrapper based sequential forward selection (SFS) to choose the best subset of features: “In each case, a wrapper based sequential forward feature selection was used to obtain the set of features that yielded the highest classification accuracy.)
Tadayyon in view of Gaskill-Shipley is silent to first restricting to stable, robust radiomic features.
However, Gaskill-Shipley discloses only stable and robust radiomic features associated with cancer biology are selected. [0111]. Feature dimensionality using absolute shrinkage and selection operator (LASSO) algorithm may be reduced. [0124]”
It would have been obvious to one of ordinary skill in the art at the time of effective filing to modify Tadayyon in view of Gaskill-Shipley’s disclosure to include the above limitations in order to eliminate non-contributory or redundant QUD features and derive a more generalizable “optimal QUS feature set” used as a biomarker.
As to claim 16, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 1. In addition, Tadayyon discloses wherein said generating the at least one QUS parametric map comprises computing a normalized power spectrum of the ultrasound RF data acquired from the ROI and deriving the at least one QUS parameter by the QUS spectral analysis of the normalized power spectrum of the ultrasound RF data or by the analysis of the RF signal envelope statistics. ([0021-0028, 0056])
As to claim 17, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 1. In addition, Gaskill-Shipley discloses wherein the distinct intra-tumor regions are identified at pixel level on the at least one QUS parametric map. ([0103-0105, 0137-0138])
As to claim 18, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 1 but is silent to wherein the identifying the distinct intra-tumor regions on the at least one QUS parametric map comprises determining an optimum number of the distinct intra-tumor regions.
However, Gaskill-Shipley discloses determining an optimum number of regions when clustering: “Performing intra-tumor segmentation for different number of regions” and using clustering quality metrics (BIC, etc.) to decide an optimum number [0119-0121]. It states that a “least number of regions associated with an appropriate clustering quality metric” is selected [0119-0121].
It would have been obvious to one of ordinary skill in the art at the time of effective filing to modify Tadayyon in view of Gaskill-Shipley’s disclosure to include the above limitations in order to obtain a parsimonious segmentation that balances detail with robustness and avoids over/under segmenting the tumor.
As to claim 19, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 18. In addition, Gaskill-Shipley discloses wherein said optimum number of the distinct intra-tumor regions is determined by: performing intra-tumor segmentation for different numbers of regions; estimating a clustering quality metric comprising Bayesian information criterion (BIC), Calinski-Harabasz index, or Davies-Bouldin index; and identifying a least number of regions associated with an appropriate clustering quality metric as the optimum number of the distinct intra-tumor regions on the at least one QUS parametric map. ([0119-0121])
As to claim 20, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 19 but is silent to wherein the clustering quality metric comprising said BIC and the appropriate clustering quality metric comprises a low BIC.
However, Gaskill-Shipley discloses clustering quality metric comprising Bayesian information criterion. Identifying a least number of regions associated with an appropriate clustering quality metric [0119-0121].
It would have been obvious to one of ordinary skill in the art at the time of effective filing to modify Tadayyon in view of Gaskill-Shipley’s disclosure to include the above limitations in order to select the simplest clustering model that adequately explains the data
As to claim 22, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 1. In addition, Tadayyon discloses supervised classifiers: Fisher’s linear discriminant (LDA/FLD), SVM, k-NN [0040-0042]
Tadayyon in view of Gaskill-Shipley is silent to supervised, unsupervised, and reinforcement learning.
However, Gaskill-Shipley discloses definition of machine learning categories, supervised vs. unsupervised vs. reinforcement learning [0068-0069]. Unsupervised clustering (hierarchical, k-means, density-based, Gaussian clustering model [0068] and deep learning variants [0069].
It would have been obvious to one of ordinary skill in the art at the time of effective filing to modify Tadayyon in view of Gaskill-Shipley’s disclosure to include the above limitations in order to explore different learning paradigms and potentially improve predictive performance with available labeled and unlabeled data.
As to claim 23, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 1. In addition, Tadayyon discloses wherein the responder and the non-responder classification are determined by clinical and/or pathological ground truth classification criteria. ([0052-0053, 0057-0063])
As to claim 25, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 1 but is silent to wherein the classification (clustering) algorithm comprises a K-means, aGaussian mixture model (GMM), ahidden Markov random field (HMRF) expectation maximization (EM) algorithm, or a clustering algorithm with spatial constraints followed by a consensus clustering algorithm.
However, Gaskill-Shipley discloses k-means and gaussian clustering as unsupervised methods: unsupervised machine learning methods include hierarchical clustering, k-means clustering, density based scan clustering, gaussian clustering model. [0068]
It would have been obvious to one of ordinary skill in the art at the time of effective filing to modify Tadayyon in view of Gaskill-Shipley’s disclosure to include the above limitations in order to implement the clustering needed for intra-tumor region identification with familiar, widely used methods.
As to claim 26, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 1. In addition, Tadayyon in view of Gaskill-Shipley discloses wherein the classification (clustering) algorithm comprises a decision tree with adaptive boosting, a random forest, a support vector machine (SVM), an artificial neural network, or aK nearest neighbours (K-NN) algorithm. (Tadayyon discloses SVM and k-NN classifiers for tumor response prediction: [0040-0042] discloses classifiers such as support vector machine (SVM) or k-nearest neighbors (k-NN) can be used. [0057-0058] and Table A shows performance of FLD, SVM, and k-NN)(Gaskill-Shipley [0029, 0068] discloses ). (Tadayyon: [0040-0042, 0057-0058]; Gaskill-Shipley: [0029, 0068] discloses ML methods – decision trees, random forests, neural networks.)
As to claim 27, Tadayyon in view of Gaskill-Shipley discloses everything as disclosed in claim 26 is silent to wherein the classification (clustering) algorithm comprises said decision tree with adaptive boosting.
However, Gaskill’s-Shipley discloses the classifier model comprises one or more of machine learning models, including a decision tree, a boosted tree, a random forest classifier, a fuzzy logic classifier, a neural network, a nearest neighbor classifier, deep learning, and a nonlinear classifier [0029, 0120].
It would have been obvious to one of ordinary skill in the art at the time of effective filing to modify Tadayyon in view of Gaskill-Shipley’s disclosure to include the above limitations in order to improve classification accuracy by leveraging ensemble boosting over simple trees.
CONCLUSION
No prior art has been found for claims 9, 13-15, 21 & 24 in their current form.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Stephen P Coleman whose telephone number is (571)270-5931. The examiner can normally be reached Monday-Thursday 8AM-5PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Moyer can be reached at (571) 272-9523. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of 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.
Stephen P. Coleman
Primary Examiner
Art Unit 2675
/STEPHEN P COLEMAN/Primary Examiner, Art Unit 2675