DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
Claims 1, 4, 7, 9 10, 17, and 20 have been amended.
Claims 21-23 has been newly added.
Claims 12-14 has been cancelled.
Claims 1-11, and 15-23 are still pending for consideration.
Response to Arguments
Applicant on page 2 of the “Remarks” asserts “Cornell's predictive approach is based on molecular assay data derived from tumor biopsies and plasma samples, not on quantitative vascular radiology feature extraction from imaging. Cornell does not disclose extracting vascular radiology features from radiological images, nor does Cornell disclose providing such features to a machine learning model configured to determine CDK inhibitor treatment response”.
Response: Examiner respectfully rejects Applicant’s argument because the rejection does not rely on Cornell to teach extracting vascular radiology features or ML imaging pipeline. Madabhushi teaches extracting imaging model to predict treatment response or prognosis. Cornell is relied upon for the known clinical objective of predicting response/resistance or benefit toCDK4/6 inhibitory therapy.
Madabhushi teaches the claimed imaging pipeline; segmenting tumor-associated vasculature (TAV), reduction in the tortuosity of the TAV, extracting features from the TAV, and use of those features in a predictive model. Madabhushi on para [0070] disclose “Computer vision and image processing tools were employed for the segmentation of tumors and tumor-associated vasculature on MRI and CT scans” and that the resulting quantitative vessel network metrics were used to evaluate treatment response and prognosis see para [0070] “For each treatment group, TAV response and risk scores were derived from these metrics, then their ability to predict response and time to recurrence or progression was evaluated”. Madabhushi further on para [0071] disclose “Segmented vessels were then divided into constituent branches and reduced to centerline skeletons by a fast-marching algorithm” and that features such as torsion, vessel volume, vessel length, and curvature, number of vessels entering the tumor, and percentage of vessels feeding the tumor are computed.
Cornell is not being used to replace Madabhushi imaging-drived feature inputs with molecular assay data. Rather Cornell stablished that determining whether CDK4/6 inhibition will produce clinical benefit was a known treatment response prediction problem. Cornell’s Abstract characterizes the invention as relating to “detecting CDK4/6 response and resistance”, and the disclosure teaches determining whether CDK4/6 inhibition will result in clinical benefit.
Thus, the proposed combination does not require modifying Madabhushi’s machine learning model to operate on Cornell’s molecular biomarkers. The combination merely applies Madabhushi’s known imaging-feature ML prediction framework to the know CDK4/6 response-prediction problem identified by Cornell. This is a predictable use of a known radiomic ML predictor for a known treatment-response endpoint.
For the amended claim limitation, a new reference Kunte et al. NPL “Radiomics risk score (RRS) on CT to predict survival and response to CDK 4/6 inhibitors in hormone receptor (HR) positive metastatic breast cancer (MBC)” provides the radiomic imaging features and CDK4/6 treatment response, while Madabhushi supplies the specific vascular radiology feature set.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claims 1-3, 5-6 are rejected under 35 U.S.C. 103 as being unpatentable over Madabhushi et al. (US 20210169349 A1) in view of Kunte et al. NPL “Radiomics risk score (RRS) on CT to predict survival and response to CDK 4/6 inhibitors in hormone receptor (HR) positive metastatic breast cancer (MBC).”
Regarding claim 1, Madabhushi et al. teaches a method, comprising: accessing data including one or more segmented images identifying one or more lesions and/or a plurality of blood vessels associated with the one or more lesions (see Fig. 1 step 110, para [0070]; “Computer vision and image processing tools were employed for the segmentation of tumors and tumor-associated vasculature on MRI and CT scans, from which quantitative metrics of vessel network morphology and organization were computed”, see also para [0032]; “at 110, accessing medical imaging (e.g., MRI, CT) scan(s) of a tumor (e.g., segmented on the scan,… The set of operations 100 can further comprise, at 120, segmenting tumor-associated vasculature (TAV) associated with the tumor based on the medical imaging scan(s)”), respective ones of the plurality of blood vessels corresponding to one or more centerlines, and one or more constituent branches associated with the one or more lesions (see para [0071]; “Segmented vessels were then divided into constituent branches and reduced to centerline skeletons by a fast marching algorithm. From vessel centerlines, a set of 91 QuanTAV measurements were computed”, see also para [0125]; “Finally, a fast marching algorithm was applied to the 3D segmented vasculature to identify the center lines of vessels and divide the vessel network into discrete branches”) wherein the one or more segmented images are derived from one or more radiological images of a patient having cancer (see para [0070]; “Patients received standard imaging for their cancer setting: dynamic contrast-enhanced (DCE) MRI in breast cancer and standard dose chest computed tomography (CT) in NSCLC. Computer vision and image processing tools were employed for the segmentation of tumors and tumor-associated vasculature on MRI and CT scans”); extracting one or more vascular radiology features using the centerlines, the constituent branches, and the one or more lesions, wherein the one or more vascular radiology features relate to a quantification of the plurality of blood vessels or a shape of the plurality of blood vessels (see para [0034]; “extracting one or more features from the TAV (e.g., morphological features, spatial organization features, functional features, etc.)”, see also para [0070]; “segmentation of tumors and tumor-associated vasculature on MRI and CT scans, from which quantitative metrics of vessel network morphology and organization were computed”, see also para [0066]; “an association was observed between vascular morphology on CT and MRI—as indicated by elevated vessel curvature, torsion, and heterogeneity of orientation”, and para [0057]; “these measures comprised features of the shape and architecture of the tumor-associated vessels, for example vessel orientation feature(s) (which can measure heterogeneity of directional alignment of vessels), vessel tortuosity feature(s) (which can measure 3D twisting through metrics such as curvature and torsion), etc” Note: quantification and tortuosity features extracted from segmented vasculature in relation to the tumor). Additionally, Madabhushi et al. uses those features to predict treatment response/prognosis (see para [0013]; “predictive of outcome following treatment including chemotherapy”) but does not specifically teach providing the one or more vascular radiology features to a machine learning model configured to determine a medical prediction associated with a treatment response of the patient to cyclin-dependent kinase (CDK) inhibitor therapy using the one or more vascular radiology features.
In the same field of endeavor Kunte et al. teaches providing the one or more vascular radiology features to a machine learning model configured to determine a medical prediction associated with a treatment response of the patient to cyclin-dependent kinase (CDK) inhibitor therapy using the one or more vascular radiology features (Abstract; “We hypothesized that baseline imaging features on pre-treatment CT scans using machine learning could correctly identify responders to CDK… 46 pts with HR+ MBC who received palbociclib (palbo) plus ET and had liver metastases were identified, and divided at random into equally sized training and testing cohorts… 503 radiomic texture features …. were extracted on pre-treatment CT within the first lesion measured for RECIST assessment. An elastic net Cox proportional hazards model was constructed within the training set to derive a Radiomics Risk Score (RRS), which was evaluated for association with prognosis and response”). Accordingly, it would have been obvious to one of ordinary skill in the art before the effecting filling date of the invention to modify a method of determination of a response to treatment and/or a prognosis for a tumor based on features of tumor-associated vasculature (TAV) of Madabhushi in view of the use of a radiomics risk score (RRS) on CT to predict survival and response to CDK 4/6 inhibitors in hormone receptor (HR) positive metastatic breast cancer (MBC) of Kunte et al. in order to generate a reasonable expectation of success in identifying biomarkers of resistance of CDK4/6 inhibitor treatment (Abstract).
Regarding claim 2, the rejection of claim 1 is incorporated herein.
Madabhushi et al. in the combination further teaches wherein the one or more vascular radiology features comprise one or more statistical measurements of a tortuosity of the plurality of blood vessels (see para [0156]; “wherein the at least one feature comprises one or more of the at least one TAV morphology feature or the statistic of the at least one TAV morphology feature, wherein the at least one TAV morphology feature comprises one or more of a torsion per branch of a plurality of branches of the TAV, a curvature standard deviation per branch of the plurality of branches, a mean curvature per branch, a maximum curvature per branch per branch of the plurality of branches, a curvature skewness per branch of the plurality of branches, a curvature kurtosis per branch of the plurality of branches, a global vascular curvature, the torsion across the plurality of branches, a vessel volume”).
Regarding claim 3, the rejection of claim 1 is incorporated herein.
Madabhushi et al. in the combination further teach wherein the one or more vascular radiology features comprise a percentage of the plurality of blood vessels feeding the one or more lesions (see para [0072]; “Tumor feeding branches Number (f60) and percentage (f61) of vessel (f60, f61) branches that enter the tumor volume from the surrounding tumor environment”, see also para [0127]; “Additional vessel metrics—including vessel volume, length, number of vessels entering the tumor, and percentage of vessels in the vessel network feeding the tumor—were also computed”).
Regarding claim 5, the rejection of claim 1 is incorporated herein.
Madabhushi et al. in the combination further teach further comprising: operating upon the one or more lesions and a vasculature of the plurality of blood vessels with a fast marching algorithm to reduce the plurality of blood vessels to the centerlines and to divide the vasculature of the plurality of blood vessels into the constituent branches (see para [0071]; “Segmented vessels were then divided into constituent branches and reduced to centerline skeletons by a fast marching algorithm”, see also para [0125]; “Finally, a fast marching algorithm was applied to the 3D segmented vasculature to identify the center lines of vessels and divide the vessel network into discrete branches”).
Regarding claim 6, the rejection of claim 1 is incorporated herein.
Kunte et al. in the combination further teach wherein the patient has received and/or is receiving the CDK inhibitor therapy for metastatic breast cancer (see Topic; “Radiomics risk score (RRS) on CT to predict survival and response to CDK 4/6 inhibitors in hormone receptor (HR) positive metastatic breast cancer (MBC)”).
Claims 4, 7-9 are rejected under 35 U.S.C. 103 as being unpatentable over Madabhushi et al. in view of Cornell et al. as applied in claim 1 above, and further in view of Yankeelov et al. (US 20250302394 A1)
Regarding claim 4, the rejection of claim 1 is incorporated herein.
Madabhushi et al. in the combination further teach further comprising: individually assessing the one or more vascular radiology features using pre-treatment (see para [0071]; “From pre-treatment imaging, the TAV was extracted and its morphology and organization were characterized in order to predict therapeutic outcome”). However, the combination of Madabhushi et al. and Kunte et al. as a whole does not teach and on-treatment images for association with the medical prediction associated with the outcome of the patient.
In the same field of endeavor teach Yankeelov et al. teaches and on-treatment images for association with the medical prediction associated with the treatment response of the patient (see para [0008]; “MRI data is collected prior to therapy, after one cycle of therapy, and at the completion of the first therapeutic regimen”). Accordingly, it would have been obvious to one of ordinary skill in the art before the effecting filling date of the invention to modify a method of determination of a response to treatment and/or a prognosis for a tumor based on features of tumor-associated vasculature (TAV) of Madabhushi in view of the use of a radiomics risk score (RRS) on CT to predict survival and response to CDK 4/6 inhibitors in hormone receptor (HR) positive metastatic breast cancer (MBC) of Kunte et al. and method employs quantitative MRI data to predict the response of cancer to therapy of Yankeelov et al. in order to enable a spatially resolved prediction of how a particular patient's tumor will respond to therapy (para [0008]).
Regarding claim 7, the rejection of claim 1 is incorporated herein.
Kunte et al. in the combination further teach wherein the machine learning model having been trained using a plurality of radiological images of one or more other patients treated with the CDK inhibitor therapy, the plurality of radiological images of the one or more other patients comprising pre-treatment radiological images acquired before initiation of the CDK inhibitor therapy (Abstract; “We hypothesized that baseline imaging features on pre-treatment CT scans using machine learning could correctly identify responders to CDK… 46 pts with HR+ MBC who received palbociclib (palbo) plus ET and had liver metastases were identified, and divided at random into equally sized training and testing cohorts… 503 radiomic texture features …. were extracted on pre-treatment CT within the first lesion measured for RECIST assessment. An elastic net Cox proportional hazards model was constructed within the training set to derive a Radiomics Risk Score (RRS), which was evaluated for association with prognosis and response… Radiomics analysis was able to predict response and survival in HR+ MBC pts prior to initiation of treatment with CDK”).
Yankeelov et al in the combination further teach and on-treatment radiological images acquired after initiation of the CDK inhibitor therapy (see para [0008]; “MRI data is collected prior to therapy, after one cycle of therapy, and at the completion of the first therapeutic regimen”). Accordingly, it would have been obvious to one of ordinary skill in the art before the effecting filling date of the invention to modify a method of determination of a response to treatment and/or a prognosis for a tumor based on features of tumor-associated vasculature (TAV) of Madabhushi in view of the use of a method discover a biomarker for CDK4/6 inhibitor response and resistance in cancer of Kunte et al. and a method employs quantitative MRI data to predict the response of cancer to therapy of Yankeelov et al. in order to enable a spatially resolved prediction of how a particular patient's tumor will respond to therapy (para [0008]).
Regarding claim 8, the rejection of claim 1 is incorporated herein.
Kunte et a. in the combination further teach with the CDK inhibitor therapy (We hypothesized that baseline imaging features on pre-treatment CT scans using machine learning could correctly identify responders to CDK… 46 pts with HR+ MBC who received palbociclib (palbo) plus ET and had liver metastases were identified, and divided at random into equally sized training and testing cohorts… 503 radiomic texture features …. were extracted on pre-treatment CT within the first lesion measured for RECIST assessment. An elastic net Cox proportional hazards model was constructed within the training set to derive a Radiomics Risk Score (RRS), which was evaluated for association with prognosis and response”).
Yankeelov et al. in the combination further teach wherein the one or more radiological images are taken of the patient after initiation of treatment (see para [0008]; “MRI data is collected prior to therapy, after one cycle of therapy, and at the completion of the first therapeutic regimen”). Accordingly, it would have been obvious to one of ordinary skill in the art before the effecting filling date of the invention to modify a method of determination of a response to treatment and/or a prognosis for a tumor based on features of tumor-associated vasculature (TAV) of Madabhushi in view of the use of a method discover a biomarker for CDK4/6 inhibitor response and resistance in cancer of Kunte et al. and a method employs quantitative MRI data to predict the response of cancer to therapy of Yankeelov et al. in order to enable a spatially resolved prediction of how a particular patient's tumor will respond to therapy (para [0008]).
Regarding claim 9, the rejection of claim 1 is incorporated herein.
Madabhushi et al. in the combination further and wherein the machine learning model is configured to determine the medical prediction associated with the treatment response of the patient based on the one or more vascular radiology features that correspond to both the pre-treatment radiological image and the on-treatment radiological image (see para [0148]; “a machine learning classifier configured to generate a prediction of response to NAC based on the set of shape-based vascular features and the set of functional semi-quantitative PK measurement”, see also para [0098]; “a model was trained to estimate progression-free survival (PFS), defined as the period of time following initiation of chemotherapy until progression on imaging, metastasis, or death …a multivariable Cox proportional hazards (See Table 12, below) including pre-treatment clinical variable….and post-treatment outcome information (response on imaging)”, and para [0138]; “Referring to FIG. 19, illustrated are six graphs showing Kaplan Meier curves comparing association of risk groups corresponding to pre-treatment QuanTAV risk score and post-treatment clinical model among testing set patients with available survival dat”).
Konte et al. in the combination further teach wherein the one or more radiological images include a pre-treatment radiological image taken of the patient before initiation of treatment with the CDK inhibitor therapy Abstract; “We hypothesized that baseline imaging features on pre-treatment CT scans using machine learning could correctly identify responders to CDK… 46 pts with HR+ MBC who received palbociclib (palbo) plus ET and had liver metastases were identified, and divided at random into equally sized training and testing cohorts… 503 radiomic texture features …. were extracted on pre-treatment CT within the first lesion measured for RECIST assessment. An elastic net Cox proportional hazards model was constructed within the training set to derive a Radiomics Risk Score (RRS), which was evaluated for association with prognosis and response… Radiomics analysis was able to predict response and survival in HR+ MBC pts prior to initiation of treatment with CDK”).
Yankeelov et al in the combination further teach and an on-treatment radiological image taken of the patient after the initiation of treatment with the CDK inhibitor therapy (see para [0008]; “MRI data is collected prior to therapy, after one cycle of therapy, and at the completion of the first therapeutic regimen”). Accordingly, it would have been obvious to one of ordinary skill in the art before the effecting filling date of the invention to modify a method of determination of a response to treatment and/or a prognosis for a tumor based on features of tumor-associated vasculature (TAV) of Madabhushi in view of the use of a method discover a biomarker for CDK4/6 inhibitor response and resistance in cancer of Kunte et al. and a method employs quantitative MRI data to predict the response of cancer to therapy of Yankeelov et al. in order to enable a spatially resolved prediction of how a particular patient's tumor will respond to therapy (para [0008]).
Claims 10-11, 15-16, 21, and 23 are rejected under 35 U.S.C. 103 as being unpatentable over Madabhushi et al. in view of Konte et al. and further in view of Yankeelov et al.
Regarding claim 10, Madabhushi et al. teaches a non-transitory computer-readable medium storing computer-executable instructions that, when executed, cause a processor to perform operations (see para [0147]; “non-transitory computer-readable storage device storing computer-executable instructions that when executed control a processor to perform operations”), accessing one or more segmented images of one or more computerized tomography (CT) scan images (see para [0032]; “accessing medical imaging (e.g., MRI, CT) scan(s) of a tumor (e.g., segmented on the scan”), wherein the one or more segmented images identify one or more lesions and a vasculature of a plurality of hepatic blood vessels associated with the one or more lesions (see Abstract; “wherein the tumor is segmented on the medical imaging scan; segmenting tumor-associated vasculature (TAV) associated with the tumor based on the medical imaging scan”, see also para [0008]; “FIG. 4 illustrates example images of a scan (left images), segmented tumor and vasculature (center images), and vessels (right images)” (see para [0070]; “Computer vision and image processing tools were employed for the segmentation of tumors and tumor-associated vasculature on MRI and CT scans, from which quantitative metrics of vessel network morphology and organization were computed”, see also para [0071]; “From pre-treatment imaging, the TAV was extracted and its morphology and organization were characterized in order to predict therapeutic outcome”); extracting one or more vascular radiology features associated with the one or more lesions and the vasculature of the plurality of hepatic blood vessels (see para [0076]; “For each vessel network, centerlines were derived and two categories of QuanTAV features were computed: Morphology and Organization. QuanTAV morphology features quantified the shape of tumor vessels. Statistics describing the distribution of metrics such as curvature (inversely proportional to the radius of a circle fitting three adjacent vessel points) and torsion (detecting differences in vessel length relative to the distance between its start and end points) comprised the bulk of QuanTAV morphology features”, see also para [0127]; “Additional vessel metrics—including vessel volume, length, number of vessels entering the tumor, and percentage of vessels in the vessel network feeding the tumor—were also computed”), and using the one or more vascular radiology features to determine a medical prediction associated with an outcome of the patient (see para [0030]; “that can predict neoadjuvant therapy response and/or disease prognosis using a computational approach based on quantitative imaging features describing the morphology, spatial organization, and function of tumor associated vasculature”, see also para [0066]; “quantitative tumor-associated vasculature (QuanTAV) features, and demonstrates its ability to predict response and survival across multiple cancer types, imaging modalities, and treatment regimens”), wherein the one or more vascular radiology features relate to a quantification of the plurality of hepatic blood vessels and a tortuosity of the plurality of hepatic blood vessels, (see para [0127]; “Additional vessel metrics—including vessel volume, length, number of vessels entering the tumor, and percentage of vessels in the vessel network feeding the tumor—were also computed”), wherein extracting the one or more vascular radiology features comprises: extracting a first group of the one or more vascular radiology features from a first segmented image derived from an individual pre-treatment radiological image in the one or more pre-treatment images (see para [0013]; “morphology measures detect differences in vessel shape on pre-treatment breast MRI and lung CT predictive of outcome”, see also para [0078]; “Images 920 show vessel torsion on pre-treatment dynamic MRI distinguishes non-responders and complete responders (pCR)”, see also para [0109]; “where QuanTAV measures extracted from pre-treatment CT volumes were associated with both response and survival”). However, Madabhushi et al. does not teach comprising: for a patient that has received or is receiving a cyclin-dependent kinase 4 and 6 (CDK 4/6) inhibitor treatment for cancer, wherein the one or more CT scan images comprise one or more pre-treatment images of the patient taken before initiation of the CDK 4/6 inhibitor treatment, one or more on-treatment images of the patient taken after the initiation of the CDK 4/6 inhibitor treatment, and extracting a second group of the one or more vascular radiology features from a second segmented image derived from an individual on-treatment image radiological image in the one or more on-treatment images; and using providing the first group and the second group of the one or more vascular radiology features to a machine learning model configured to determine a medical prediction associated with an outcome of the patient using both the first group and the second group of the one or more vascular radiology features.
In the same field of endeavor Kunte et al. teaches comprising: for a patient that has received or is receiving a cyclin-dependent kinase 4 and 6 (CDK 4/6) inhibitor treatment for cancer (see Topic; “Radiomics risk score (RRS) on CT to predict survival and response to CDK 4/6 inhibitors in hormone receptor (HR) positive metastatic breast cancer (MBC)”), wherein the one or more CT scan images comprise one or more pre-treatment images of the patient taken before initiation of the CDK 4/6 inhibitor treatment (see Abstract; “46 pts with HR+ MBC who received palbociclib (palbo) plus ET and had liver metastases were identified,… 503 radiomic texture features measuring subtle differences in lesion heterogeneity on a pixel level were extracted on pre-treatment CT”). Accordingly, it would have been obvious to one of ordinary skill in the art before the effecting filling date of the invention to modify a method of determination of a response to treatment and/or a prognosis for a tumor based on features of tumor-associated vasculature (TAV) of Madabhushi in view of the use of a radiomics risk score (RRS) on CT to predict survival and response to CDK 4/6 inhibitors in hormone receptor (HR) positive metastatic breast cancer (MBC) of Kunte et al. in order to generate a reasonable expectation of success in identifying biomarkers of resistance of CDK4/6 inhibitor treatment (Abstract).
However, the combination of Madabhushi et al. and Kunte et al. does not teach one or more on-treatment images of the patient taken after the initiation of the CDK 4/6 inhibitor treatment, and extracting a second group of the one or more vascular radiology features from a second segmented image derived from an individual on-treatment image radiological image in the one or more on-treatment images; and using providing the first group and the second group of the one or more vascular radiology features to a machine learning model configured to determine a medical prediction associated with an outcome of the patient using both the first group and the second group of the one or more vascular radiology features.
In the same field of endeavor Yankeelov et al. teach and one or more on-treatment images of the patient taken after the initiation of the CDK 4/6 inhibitor treatment (see para [0008]; “MRI data is collected prior to therapy, after one cycle of therapy, and at the completion of the first therapeutic regimen”), and extracting a second group of the one or more vascular radiology features from a second segmented image derived from an individual on-treatment image radiological image in the one or more on-treatment images (see para [0277]; “a first set of images obtained through a first scan performed prior to an administration of a therapy to the patient”, see also para [0065]; “data can then be analyzed to segment different tissues with differing contrast enhancement and also to extract measures characterizing contrast agent pharmacokinetics”); and using providing the first group and the second group of the one or more vascular radiology features to a machine learning model configured to determine a medical prediction associated with an outcome of the patient using both the first group and the second group of the one or more vascular radiology features (see para [0277]; “a first set of images obtained through a first scan performed prior to an administration of a therapy to the patient and a second set of images obtained through a second scan performed following the administration of the therapy to the patient, the therapy including administration of a plurality of drugs…. registering, by the computing system, image-related data generated from the second set of images with image-related data generated from the first set of images….. and the determined effect of each drug on cells included in each voxel, a score indicating a predicted response of the tumor to the therapy”, see also para [0245]; “A more recent CNN-based study using both pre-and post-treatment DCE-MRI achieved an AUC of 0.91 in a cohort of 42 breast cancer patients”). Accordingly, it would have been obvious to one of ordinary skill in the art before the effecting filling date of the invention to modify a method of determination of a response to treatment and/or a prognosis for a tumor based on features of tumor-associated vasculature (TAV) of Madabhushi in view of the use of a radiomics risk score (RRS) on CT to predict survival and response to CDK 4/6 inhibitors in hormone receptor (HR) positive metastatic breast cancer (MBC) of Kunte et al. and a method employs quantitative MRI data to predict the response of cancer to therapy of Yankeelov et al. in order to enable a spatially resolved prediction of how a particular patient's tumor will respond to therapy (para [0008]).
Regarding claim 11, the rejection of claim 10 is incorporated herein.
Madabhushi et al. in the combination further teach further comprising: reducing the plurality of hepatic blood vessels to a plurality of centerlines and dividing the vasculature of the plurality of hepatic blood vessels into a plurality of constituent branches; and extracting the one or more vascular radiology features using the centerlines, the constituent branches, and the one or more lesions (see para [0071]; “Segmented vessels were then divided into constituent branches and reduced to centerline skeletons by a fast marching algorithm. From vessel centerlines, a set of 91 QuanTAV measurements were computed”, see also para [0076]; “The tumor and associated-vasculature were extracted from pre-treatment breast DCE-MRI and chest CT. For each vessel network, centerlines were derived and two categories of QuanTAV features were computed”).
Regarding claim 15, the rejection of claim 10 is incorporated herein.
Madabhushi in the combination further teach wherein the operations further include: measuring a tortuosity separately for respective ones of the plurality of hepatic blood vessels (see para [0127]; “For each branch, torsion was computed”, see also para [0078]; “For each discrete vascular branch, all corresponding voxels within the branch are shaded according to the torsion value of the branch”, and para [0076]; “For each vessel network, centerlines were derived …. Statistics describing the distribution of metrics such as curvature.. and torsion (detecting differences in vessel length relative to the distance between its start and end points) comprised the bulk of QuanTAV morphology features”); and performing a statistical measurement of the tortuosity measured separately for the respective ones of the plurality of hepatic blood vessels to generate the one or more vascular radiology features (see para [0127]; “first order statistics (mean, standard deviation, max, skewness, and kurtosis), and branch-level statistics were summarized at the patient level with the same statistics…summarized at the patient level via first order statistics. The distributions of curvature and torsion across the full vasculature were further summarized via 10-bin histograms”).
Regarding claim 16, the rejection of claim 10 is incorporated herein.
Madabhushi in the combination further teach wherein the one or more vascular radiology features comprise a percentage of the plurality of hepatic blood vessels feeding the one or more lesions (see para [0072]; “Tumor feeding branches Number (f60) and percentage (f61) of vessel (f60, f61) branches that enter the tumor volume from the surrounding tumor environment”), a maximum of a tortuosity of the plurality of hepatic blood vessels, and a skewness of a tortuosity of the plurality of hepatic blood vessels (see para [0072]; “Statistics of torsion Mean, standard deviation (std), maximum per branch (f1-f5) (max), skewness (skew), and kurtosis (kurt) of torsion across all branches Statistics of curvature Mean, std, max, skew, kurt of the standard standard deviation per deviation of curvature measured along each branch (f6-f10) branch Statistics of mean Mean, std, max, skew, kurt of the average curvature per branch curvature measured along each branch (f11-f15) Statistics of maximum Mean, std, max, skew, kurt of the maximum curvature per branch curvature measured along each branch (f16-f20)”).
Regarding claim 21, the rejection of claim 10 is incorporated herein.
Kunte et al. in the combination further teach wherein the medical prediction associated with the outcome of the patient comprises a response or resistance to the CDK 4/6 inhibitor treatment (see Topic; “Radiomics risk score (RRS) on CT to predict survival and response to CDK 4/6 inhibitors in hormone receptor (HR) positive metastatic breast cancer (MBC)”).
Regarding claim 23, the rejection of claim 10 is incorporated herein.
Kunte et al. in the combination further teach wherein the first group and the second group of the one or more vascular radiology features relate to angiogenic characteristics associated with response to the CDK 4/6 inhibitor treatment and associated with the one or more lesions (see para [0277]; “the therapy including administration of a plurality of drugs ….tissue properties of tissue surrounding the tumor; registering, by the computing system, image-related data generated from the second set of images with image-related data generated from the first set of images”, see also para [0247]; “tumor angiogenesis models could estimate drug distribution more accurately”, and para [0043]; “analyzed with an appropriate pharmacokinetic model to estimate different tissue vascular features on a voxel-specific basis”).
Claims 17-19 are rejected under 35 U.S.C. 103 as being unpatentable over Madabhushi et al. in view of Kunte et al.
Regarding claim 17, Madabhushi et al. teaches an apparatus, comprising: a memory configured to store (see para [0031]; “The one or more processors can be coupled with and/or can include memory or storage and can be configured to execute instructions stored in the memory or storage to enable various apparatus, applications, or operating systems to perform the operations”), wherein the segmented image identifies one or more lesions and a vasculature of a plurality of blood vessels associated with the one or more lesions within a radiological image of the patient (see Fig. 1 step 110, para [0070]; “Computer vision and image processing tools were employed for the segmentation of tumors and tumor-associated vasculature on MRI and CT scans, from which quantitative metrics of vessel network morphology and organization were computed”, see also para [0008]; “FIG. 4 illustrates example images of a scan (left images), segmented tumor and vasculature (center images), and vessels (right images)”); a vessel transformation tool configured to reduce the plurality of blood vessels to centerlines and dividing the vasculature of the plurality of blood vessels into a plurality of constituent branches (see para [0071]; “The TAV was then segmented through a specialized filtering approach to emphasize vessel-like objects, and then refined through morphological processing and manual adjustment. Segmented vessels were then divided into constituent branches and reduced to centerline skeletons by a fast marching algorithm. From vessel centerlines, a set of 91 QuanTAV measurements were computed”); a feature extraction tool configured to extract one or more vascular radiology features using the centerlines, the constituent branches, and the one or more lesions, wherein the one or more vascular radiology features relate to a quantification of the plurality of blood vessels and a tortuosity of the plurality of blood vessels (see para [0070]; “Computer vision and image processing tools were employed for the segmentation of tumors and tumor-associated vasculature on MRI and CT scans, from which quantitative metrics of vessel network morphology and organization were computed”, see also para [0066]; “an association was observed between vascular morphology on CT and MRI—as indicated by elevated vessel curvature, torsion, and heterogeneity of orientation”, and para [0057]; “these measures comprised features of the shape and architecture of the tumor-associated vessels, for example vessel orientation feature(s) (which can measure heterogeneity of directional alignment of vessels), vessel tortuosity feature(s) (which can measure 3D twisting through metrics such as curvature and torsion), etc” Note: quantification and tortuosity features extracted from segmented vasculature in relation to the tumor); and a machine learning model configured to operate upon the one or more vascular radiology features to determine a medical prediction associated with a treatment response an outcome of the patient to the CDK inhibitor treatment. (see para [0147]; “a machine learning classifier configured to generate a prediction of response to NAC based on the set of shape-based vascular features and the set of functional semi-quantitative PK measurements”, see also para [0048]; “multi-region PK features and tumor shape features were combined and applied to the 120-patient independent testing set, the random forest classifier achieved an AUC of 0.70 and identified 81% of patients who would achieve pCR”). However, Madabhushi et al. does not teach one or more segmented images derived from one or more radiological images of a patient that has received or may receive a cyclin-dependent kinase (CDK) inhibitor treatment for cancer, and a machine learning model configured to operate upon the one or more vascular radiology features to determine a medical prediction associated with a treatment response an outcome of the patient to the CDK inhibitor treatment.
In the same field of endeavor Kunte et al. teach one or more segmented images derived from one or more radiological images of a patient that has received or may receive a cyclin-dependent kinase (CDK) inhibitor treatment for cancer (Abstract; “Radiomics risk score (RRS) on CT to predict survival and response to CDK 4/6 inhibitors in hormone receptor (HR) positive metastatic breast cancer (MBC)”), and a machine learning model configured to operate upon the one or more vascular radiology features to determine a medical prediction associated with a treatment response an outcome of the patient to the CDK inhibitor treatment (Abstract; “We hypothesized that baseline imaging features on pre-treatment CT scans using machine learning could correctly identify responders to CDK… 46 pts with HR+ MBC who received palbociclib (palbo) plus ET and had liver metastases were identified, and divided at random into equally sized training and testing cohorts… 503 radiomic texture features …. were extracted on pre-treatment CT within the first lesion measured for RECIST assessment. An elastic net Cox proportional hazards model was constructed within the training set to derive a Radiomics Risk Score (RRS), which was evaluated for association with prognosis and response”). Accordingly, it would have been obvious to one of ordinary skill in the art before the effecting filling date of the invention to modify a method of determination of a response to treatment and/or a prognosis for a tumor based on features of tumor-associated vasculature (TAV) of Madabhushi in view of the use of a radiomics risk score (RRS) on CT to predict survival and response to CDK 4/6 inhibitors in hormone receptor (HR) positive metastatic breast cancer (MBC) of Kunte et al. in order to generate a reasonable expectation of success in identifying biomarkers of resistance of CDK4/6 inhibitor treatment (Abstract).
Regarding claim 18, the rejection of claim 17 is incorporated herein.
Madabhushi et al. in the combination further teach wherein a vessel tortuosity is measured separately for respective ones of the plurality of constituent branches (see para [0071]; “Segmented vessels were then divided into constituent branches and reduced to centerline skeletons by a fast marching algorithm. From vessel centerlines, a set of 91 QuanTAV measurements were computed”, see also para [0127]; “For each branch, torsion was computed … a branch to the branch's length and summarized at the patient level via first order statistics. The distributions of curvature and torsion across the full vasculature were further summarized via 10-bin histograms. Additional vessel metrics—including vessel volume, length, number of vessels entering the tumor, and percentage of vessels in the vessel network feeding the tumor—were also computed”, Note: features list shows per-branch statistics), wherein the vessel tortuosity is used to generate the one or more vascular radiology features (see para [0071]; “From vessel centerlines, a set of 91 QuanTAV measurements were computed,….Features describing the 3D shape of tumor vessels. Metrics measuring the twistedness of vessels across different length scales were computed: torsion, measuring twistedness across a full vessel branch, and curvature, measuring local twistedness among adjacent points along a branch. First order statistics describing the distribution of these measures between vessel branches and the entire vasculature are computed”).
Regarding claim 19, the rejection of claim 17 is incorporated herein.
Madabhushi et al. in the combination further teach wherein a statistical assessment of the vessel tortuosity is separately performed for respective ones of the plurality of constituent branches (see para [0072]; “Features Description Statistics of torsion Mean, standard deviation (std), maximum per branch (f1-f5) (max), skewness (skew), and kurtosis (kurt) of torsion across all branches…. Statistics of global Mean, std, max, skew, kurt of the curvature vascular curvature measured across all branches combined (f31-f35) Histogram of global 10-bin histogram of the curvature measured vascular curvature across all points of the vessel volume”).
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Madabhushi et al. in view of Kunte et al. as applied in claim 17 above, and further in view of Denys et al. (US 20130324548 A1).
Regarding claim 20, the rejection of claim 17 is incorporated herein.
Kunte et al. in the combination further teach wherein the one or more lesions comprise a liver metastasis (see Abstract; “46 pts with HR+ MBC who received palbociclib (palbo) plus ET and had liver metastases were identified”). However, the combination of Madabhushi et al. and Kunte et al. as a whole does not teach the plurality of blood vessels comprise hepatic blood vessels supplying the liver metastasis.
In the same field of endeavor, Denys et al. teach the plurality of blood vessels comprise hepatic blood vessels supplying the liver metastasis (see para [0043]; “Solid tumours can develop in virtually any tissue or organ, such as lungs, breast, prostate, skin, liver and colon…. solid tumour cancers are malignant hypervascularised tumours, such as hepatoma or hepatocellular carcinoma (primary liver cancer) and metastasis (spread) to the liver from: colon cancer, breast cancer, carcinoid tumours and other neuroendocrine tumours”, see also para [0044]; “anti-cancer drugs are injected directly into the blood vessel feeding a cancerous tumour”). Accordingly, it would have been obvious to one of ordinary skill in the art before the effecting filling date of the invention to modify a method of determination of a response to treatment and/or a prognosis for a tumor based on features of tumor-associated vasculature (TAV) of Madabhushi in view of the use of a radiomics risk score (RRS) on CT to predict survival and response to CDK 4/6 inhibitors in hormone receptor (HR) positive metastatic breast cancer (MBC) of Kunte et al. and a method of preparing chemoembolization composition and to the use of chemoembolization composition of Denys et al. in order to treating solid tumour cancers (para [0043]).
Claim 22 is rejected under 35 U.S.C. 103 as being unpatentable over Madabhushi et and Kunte et al. al. in view of Yankeelov et al. as applied in claim 10 above, and further in view of Denys et al.
Regarding claim 22, the rejection of claim 10 is incorporated herein.
Kunte et al. in the combination further teach wherein the patient has received and/or is receiving the CDK 4/6 inhibitor treatment for metastatic breast cancer (see Topic; “Radiomics risk score (RRS) on CT to predict survival and response to CDK 4/6 inhibitors in hormone receptor (HR) positive metastatic breast cancer (MBC)”), the one or more lesions comprise a liver metastasis (see Abstract; “46 pts with HR+ MBC who received palbociclib (palbo) plus ET and had liver metastases were identified”). However, the combination of Madabhushi et al. and Kunte et al. as a whole does not teach and the plurality of hepatic blood vessels supply the liver metastasis.
In the same field of endeavor Denys et al. teach and the plurality of hepatic blood vessels supply the liver metastasis (see para [0043]; “Solid tumours can develop in virtually any tissue or organ, such as lungs, breast, prostate, skin, liver and colon…. solid tumour cancers are malignant hypervascularised tumours, such as hepatoma or hepatocellular carcinoma (primary liver cancer) and metastasis (spread) to the liver from: colon cancer, breast cancer, carcinoid tumours and other neuroendocrine tumours”, see also para [0044]; “anti-cancer drugs are injected directly into the blood vessel feeding a cancerous tumour”). Accordingly, it would have been obvious to one of ordinary skill in the art before the effecting filling date of the invention to modify a method of determination of a response to treatment and/or a prognosis for a tumor based on features of tumor-associated vasculature (TAV) of Madabhushi in view of the use of a radiomics risk score (RRS) on CT to predict survival and response to CDK 4/6 inhibitors in hormone receptor (HR) positive metastatic breast cancer (MBC) of Kunte et al. and a method employs quantitative MRI data to predict the response of cancer to therapy of Yankeelov et al. and a method of preparing chemoembolization composition and to the use of chemoembolization composition of Denys et al. in order to treating solid tumour cancers (para [0043]).
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 WINTA GEBRESLASSIE whose telephone number is (571)272-3475. The examiner can normally be reached Monday-Friday9:00-5:00.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Bee can be reached at 571-270-5180. 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.
/WINTA GEBRESLASSIE/Examiner, Art Unit 2677
Prosecution Insights