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 Preliminary Amendment
Preliminary amendments filed 12/03/2024 have been acknowledged.
Claims 2-6, 8-13, 16, and 18 are amended.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 03/04/2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Objections
Claim 17 is objected to because of the following informalities: “SARS-CoV-2 “ is not a pathology, it is the physical pathogen itself that causes the pathology seen in COVID-19 not the pathology itself. For examination purposes, Examiner will assume the pathology in claim 17 is “COVID-19”, the actual pathological disease caused by the SARS-CoV-2 pathogen and or the structural/functional changes in the body associated with the disease. Appropriate correction is required.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-5 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Madabhushi et al (Madabhushi hereinafter US 20200000396 A1)
As per claim 1
Madabhushi teaches computer-implemented method (Figure 11) for producing a bank of radiomics features from the radiological imaging data of a patient pathology having multiple lesion sites (Figure 4, Paragraph [0019] “…extract radiomic features that are predictive of DECIPHER risk score from pre-operative (e.g., pre-radical prostatectomy) MRI imagery, and generate a prognostic prediction of outcome for the patient of whom the MRI imagery is associated, based on the radiomic features.”) the method comprising the steps of: a) receiving radiological imaging data of the patient from a database of medical data; (Figure 4, ) segmenting the radiological imaging data to produce at least two connected components (Paragraph [0026] “The set of operations 100 also includes, at 120, segmenting a tumoral region represented in the image. Segmenting the tumoral region includes defining a tumoral boundary” the “two components” are the boundary and the tumor. Furthermore figure 4 shows tumors/ROI connected either by their boundary to one another or connected through the mass of the organ tissue itself. Note If “connecting components” is a means of illustrating broken contours of segmentation, Madabhushi states “tumoral region includes defining a tumoral boundary. In one embodiment, the tumoral region is segmented using a watershed segmentation technique, a region growing or active contour technique” in paragraph [0026]. A region growing segmentation algorithm connects segmentations by expanding from seed points to connect neighboring pixels seamlessly merging regions into a ROI such as the images seen in figure 4. ) each connected component characterizing a lesion site (Figure 4, Figure 9, Paragraph [0026] “The set of operations 100 also includes, at 120, segmenting a tumoral region represented in the image. Segmenting the tumoral region includes defining a tumoral boundary” A “lesion” is a broad term that illustrates abnormal tissue growth. This of course includes tumors and their boundaries.) the connected components forming an object of interest to characterize a pathology of the patient (Paragraph [0025] “The method or set of operations 100 includes, at 110, accessing a radiological image associated with a patient. The radiological image includes a region of interest (ROI) demonstrating prostate cancer (PCa) pathology.” Paragraph [0041] “These radiomic features are extracted on a voxel-wise basis within the tumor regions of interest (ROIs) obtained via co-registration”) extracting a bank of radiomics features from the at least two connected components (Figure 4, Paragraph [0026] “The set of operations 100 also includes, at 120, segmenting a tumoral region represented in the image. Segmenting the tumoral region includes defining a tumoral boundary.” Paragraph [0027] “The set of operations 100 also includes, at 130, extracting a set of radiomic features from the image. The set of radiomic features may be extracted from the tumoral region.” Paragraph [0100] “segment a tumoral region represented in the bpMRI image, where segmenting the tumoral region includes defining a tumoral boundary; a radiomic feature circuit configured to: extract a set of radiomic features from the tumoral region represented in the bpMRI image”) storing the bank of radiomics features in a database of digital health features (Paragraph [0065] “memory 1020 can store a training set of images (e.g., comprising bpMRI images showing radiomic features, along with a known DECIPHER risk group, or outcome) for training a classifier (e.g., logistic regression model classifier, etc.) to determine a probability of PCa DECIPHER risk group, while in the same or other embodiments, memory 1020 can store a radiological image of a patient for whom a prediction of PCa DECIPHER risk group or outcome is to be determined. Memory 1020 can be further configured to store one or more clinical features or other data associated with the patient of the bpMRI image. “) characterized in that: extracting a bank of radiomics features comprises a step of producing at least two values selected from: a total value, an average value and/or a maximum value of at least one radiomics feature calculated from all the connected components. (Paragraph [0056] “ Gland morphology features, including lumen shape, orientation, arrangement, and graph-based entropy were then extracted at 430 to characterize the PCa gland morphology. Fifteen distribution statistics including mean, standard deviation, range, minimum, maximum, mode, median, variance, kurtosis, harmonic mean, skewness, absolute deviation, inter-quartile range, disorder, min/max, were calculated for morphology features of each lesion on the digitized pathology images.”)
As per claim 2
Madabhushi teaches all claim limitations previously rejected in claim 1’s 102 rejection. See claim 1’s 102 rejection.
Madabhushi teaches The computer-implemented method of claim 1, further comprising the step of_ localizing, from the radiological imaging data, at least one anatomical area of interest to produce an anatomical area label (Figures 1-4)
As per claim 3
Madabhushi teaches all claim limitations previously rejected in claim 2’s 102 rejection. See claim 2’s 102 rejection.
Madabhushi teaches The computer-implemented method of claim 2, further comprising the steps of: acquiring a localization model trained to extract an anatomical area label from radiological imaging data (Paragraph [0025] “Embodiments described herein can employ techniques discussed herein for distinguishing different DECIPHER risk groups (e.g., DECIPHER low risk score, intermediate risk score, high risk score) via a machine learning classifier trained on radiological imagery (e.g., MRI, mpMRI, bpMRI) and radiomic features extracted from said imagery that have been identified as distinguishing between different low risk, intermediate risk, or high risk lesions (e.g., tumors) according to DECIPHER risk groups’ Paragraph [0032] “generating the classification includes classifying the patient associated with the ROI” Paragraph [0033] classify an ROI or a patient associated with the ROI into a DECIPHER risk group, classify PCa, or stratify PCa metastasis risk, thus improving on existing approaches to predicting PCa risk of metastasis, or of classifying a patient or ROI ““Paragraph [0035] “that facilitates training of a machine learning classifier to generate a probability that a patient associated with an ROI demonstrating PCa has a low-risk of metastasis, intermediate-risk of metastasis, or high-risk of metastasis, as defined by the DECIPHER risk score, based on radiomic features extracted from radiographic “ Paragraph [0042] Paragraph [0046] “ classifier can also include determining which radiomic features are most discriminative in distinguishing DECIPHER risk group in PCa. Training the machine learning classifier can also include determining the optimal combination of parameters used in the computation of the probability that can best separate a positive class from a negative class “)
As per claim 4
Madabhushi teaches all claim limitations previously rejected in claim 3’s 102 rejection. See claim 3’s 102 rejection.
Madabhushi teaches The computer-implemented method of claim 3 further comprising the step of identifying from the radiological imaging data, a set of imaging signal properties. (Paragraph [0028] “, the set of radiomic features includes at least one ADC co-occurrence of local anisotropic gradient orientations (CoLIAGe) feature, at least one ADC Laws features, at least one ADC Gabor feature, and at least one T2WI CoLIAGe feature. ADC CoLIAGe features quantify ADC gradient heterogeneity within cancer lesion regions. ADC Laws features capture the spot and ripple texture pattern of cancer lesion ADC signals. “ Paragraph [0054] “In this example, at 420, radiomic features are extracted from the mpMRI imagery, including the T2WI and ADC maps. In this example, T2WI signal intensity for each patient was standardized prior to feature extraction to the template intensity distribution to keep the T2WI intensity range consistent. 75 Radiomic features, including first-order statistics (n=10), Gabor (n=14), Haralick (n=13), Laws (n=25) and Co-occurrence of Local Anisotropic Gradient Orientations (CoLIAGe) (n=13), were derived from both T2WI and ADC maps. These features facilitate detecting the presence and stratifying the risk of PCa. These radiomic features are extracted on a voxel-wise basis within the tumor ROIs obtained via co-registration.”)
As per claim 5
Madabhushi teaches all claim limitations previously rejected in claim 4’s 102 rejection. See claim 4’s 102 rejection.
Madabhushi teaches The computer-implemented method of claim 4, further comprising the steps of: acquiring a signal identification model trained to extract a set of imaging signal properties from radiological imaging data (Paragraph [0047] “Training the machine learning classifier may also include determining the optimal combination of parameters used in the computation of a probability of PCa metastasis risk (e.g., which radiomic features to extract, number of radiomic features to extract) to best separate a positive and negative class. “ “Paragraph [0054] “In this example, at 420, radiomic features are extracted from the mpMRI imagery, including the T2WI and ADC maps…75 Radiomic features, including first-order statistics (n=10), Gabor (n=14), Haralick (n=13), Laws (n=25) and Co-occurrence of Local Anisotropic Gradient Orientations (CoLIAGe) (n=13), were derived from both T2WI and ADC maps. These features facilitate detecting the presence and stratifying the risk of PCa.” Paragraph [0061] “The ability to identify or stratify patients into PCa DECIPHER risk categories based on radiomic features extracted from bpMRI images using a machine learning classifier trained according to embodiments described herein” Paragraph [0067] “The set of circuits 1050 includes image acquisition circuit 1051, tumor segmentation circuit 1053, radiomic feature circuit 1055, DECIPHER risk group prediction circuit 1057, and display circuit 1059.” )
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.
Claims 6-15 are rejected under 35 U.S.C. 103 as being unpatentable over Madabhushi et al (Madabhushi hereinafter US 20200000396 A1) in view of Zhou et al (Zhou hereinafter US 20190205606 A1)
As per claim 6
Madabhushi teaches all claim limitations previously rejected in claim 5’s 102 rejection. See claim 5’s 102 rejection.
Madabhushi does not teach the step of selecting for each anatomical area label, a segmentation method for segmenting the radiological imaging data according to the imaging signal properties.
Zhou the step of selecting for each anatomical area label, a segmentation method for segmenting the radiological imaging data according to the imaging signal properties (Figure 4, Figure 2 Paragraph [0040] “The segmentation algorithm database 108 stores multiple versions of each segmentation algorithm corresponding to different target anatomical structures and different medical imaging modalities. For deep learning based segmentation algorithms, each version corresponding to a specific target anatomical structure and a specific medical imaging modality includes a respective trained deep network architecture with parameters (weights) learned for segmentation of that target anatomical structure in that imaging modality” Differing imaging modalities controlling segmentation type is the same as “segmenting the radiological imaging data according to the imaging signal properties”)
Accordingly, a person of ordinary skill in the art, at the time this invention was effectively filed would have found it obvious to modify Madabhushi’s methodology with Zhou’s concept of selecting for each anatomical area label, a segmentation method for segmenting the radiological imaging data according to the imaging signal properties. A person of ordinary skill in the art would have recognized that bpMRI in Madabhushi’s methodology includes imaging sequences which have different signal properties. Because those signal properties will affect tissue contrast and lesion boundary definition it would have been highly advantageous to select the segmentation technique based on signal properties as taught Zhou, before extracting radiomic features. This enables reliable regions of interest for later feature extraction and downstream machine learning analysis.
As per claim 7
Madabhushi’s and Zhou teach all claim limitations previously rejected in claim 6’s 103 rejection. See claim 6’s 103 rejection.
Madabhushi’s teaches wherein the segmentation method is a manual method, a semi-automated method, or an automated method (Paragraph [0038] “ In one embodiment, an automated segmentation technique is employed. In another embodiment, the prostate capsule is manually segmented. In another embodiment, the prostate capsule has already been segmented.”)
As per claim 8
Madabhushi’s and Zhou teach all claim limitations previously rejected in claim 7’s 103 rejection. See claim 7’s 103 rejection.
Madabhushi’s teaches wherein the segmentation method is an automated method, (Paragraph [0038] “ In one embodiment, an automated segmentation technique is employed.”) comprising the steps of acquiring a segmentation model trained to extract from radiological imaging data, at least two connected components (Figure 4, Figure 11 label 1050, Paragraph [0056] “gland segmentation within the lesion ROIs on digitized surgical specimens was first obtained using the Unet segmentation network at 10× resolution.” Paragraph [0067] “The set of circuits 1050 includes image acquisition circuit 1051, tumor segmentation circuit 1053, radiomic feature circuit 1055, DECIPHER risk group prediction circuit 1057, and display circuit 1059.” Paragraph [0069] “Tumor segmentation circuit 1053 is configured to segment a tumoral region represented in the bpMRI image. Segmenting the tumoral region includes defining a tumoral boundary. “) applying the segmentation model to the radiological imaging data to produce at least two connected components. (Paragraph [0069] “tumor segmentation circuit 1053 is configured to segment a tumoral region represented in the bpMRI image. Segmenting the tumoral region includes defining a tumoral boundary.” The tumor and its boundary are the two components.)
As per claim 9
Madabhushi’s and Zhou teach all claim limitations previously rejected in claim 7’s 103 rejection. See claim 7’s 103 rejection.
Madabhushi’s teaches wherein the segmentation method produces a set of at least two connected components( Paragraph [0069] “tumor segmentation circuit 1053 is configured to segment a tumoral region represented in the bpMRI image. Segmenting the tumoral region includes defining a tumoral boundary”) and wherein extracting a bank of radiomics features from the connected components comprises aggregating the at least two connected components (Figure 4, Figure 9 Paragraph [0100] “where segmenting the tumoral region includes defining a tumoral boundary; a radiomic feature circuit configured to: extract a set of radiomic features from the tumoral region represented in the bpMRI image” The tumor and its boundary are viewed together therefore the two connected components are aggregated) calculating a radiomics feature value from the aggregated connected components to produce a summarized radiomics feature value (Paragraph [0042] “radiomic features are extracted from lesion ROIs and distribution statistics are calculated for each ROI.” A distribution is a comprehensive summary of data Paragraph [0055] “The remainder of the radiomic features (R<=0.6) were employed to train a logistic regression model with elastic-net regularization via a 5-fold cross validation approach. This method allows for intelligent selection of features that discriminate D1 and D2 and train the predictive model simultaneously. A receiver operating characteristic curve (ROC) was generated and area under the ROC (AUC) was calculated. “)
As per claim 10
Madabhushi and Zhou teach all claim limitations previously rejected in claim 9’s 103 rejection. See claim 9’s 103 rejection.
Zhou teaches wherein the segmentation method produces a set of at least two connected components and wherein extracting a bank of radiomics features from the connected components comprises: calculating a component-specific radiomics feature value from each component in the at least two connected components; (Paragraph [0118] “First, the largest connected component is selected as the final myocardium segmentation result. The centroid of the segmentation mask is then calculated to determine a point within the left ventricle blood pool. Boundary points surrounding the mask are then computed, and two turning points at the left ventricle base are detected based on the point determined to be within the left ventricle blood pool.)
Madabhushi teaches averaging the component-specific radiomics feature values to produce an average feature value (Paragraph [0056] “In this example, radiomics and tissue morphology may be correlated at 440. In this example, gland segmentation within the lesion ROIs…Gland morphology features, including lumen shape, orientation, arrangement, and graph-based entropy were then extracted at 430 to characterize the PCa gland morphology. Fifteen distribution statistics including mean…were calculated for morphology features of each lesion on the digitized pathology images”) storing the average radiomics feature value into the bank of radiomics features. (Madabhushi’s states “Memory 1020 can be further configured to store one or more clinical features or other data associated with the patient of the bpMRI image” in paragraph [0065]. Madabhushi’s also shows in figure 11 Tumor segmentation circuit and radiomic feature circuit being in direct communication with memory. Furthermore, it is without question that a person of ordinary skill in the art knows to store their obtained objective values and calculations into memory. The “bank of radiomics features” can be any storage file or dataset within the storage file the person of ordinary skill in the art chooses it to be.)
As per claim 11
Madabhushi and Zhou teach all claim limitations previously rejected in clam 10’s 103 rejection. See claim 10’s 103 rejection.
Zhou teaches wherein the segmentation method produces a set of at least two connected components (Paragraph [0069] “tumor segmentation circuit 1053 is configured to segment a tumoral region represented in the bpMRI image. Segmenting the tumoral region includes defining a tumoral boundary”) wherein extracting a bank of radiomics features from the connected components comprises :calculating a component-specific radiomics feature value from the largest connected component (Paragraph [0118] “the largest connected component is selected as the final myocardium segmentation result…The centroid of the segmentation mask is then calculated to determine a point within the left ventricle blood pool” Calculation of a centroid of a segmented region is classified as a shape based radiomic feature. Furthermore, Zhou describes their segmenting as “a target anatomical structure” limitations of what is targeted is up to the practitioner. ) storing the component-specific radiomics feature value into the bank of radiomics features (Zhou states paragraph [0037] “. Medical images of a patient can be acquired using the image acquisition device 104, and the medical images can be sent to the computer system 100 running the master segmentation artificial agent 102 and/or stored in the PACS 106…The PACS 106 stores medical images of various modalities for various patients in a digital format…Segmentation results extracted from the medical images can also be stored in the PACS 106.” Refer to figures 1 and 25 for supplement. Furthermore, it is without question that a person of ordinary skill in the art knows to store their obtained objective values and calculations into memory. The “bank of radiomics features” can be any storage file or dataset within the storage file the person of ordinary skill in the art chooses it to be.)
As per claim 12
Madabhushi and Zhou teach all claim limitations previously rejected in clam 7’s 103 rejection. See claim 7’s 103 rejection.
Madabhushi’s teaches wherein at least one of the radiomics features is a morphological feature (Paragraph [0070] e set of radiomic features includes at least one ADC co-occurrence of local anisotropic gradient (CoLIAGe) feature, at least one ADC Laws features, at least one ADC Gabor feature, …”) wherein the segmentation method produces at least two connected components
(Figure 4 ,Paragraph [0069] “tumor segmentation circuit 1053 is configured to segment a tumoral region represented in the bpMRI image. Segmenting the tumoral region includes defining a tumoral boundary”) and wherein extracting a bank of radiomics features from the connected components comprises aggregating all the connected components in the at least two connected components (Figure 4, Figure 9 Paragraph [0100] “where segmenting the tumoral region includes defining a tumoral boundary; a radiomic feature circuit configured to: extract a set of radiomic features from the tumoral region represented in the bpMRI image” The tumor and its boundary are viewed together therefore the two connected components are aggregated) and calculating a summarized morphological feature from the aggregated connected components to produce a first morphological radiomics feature value (Paragraph [0042] “radiomic features are extracted from lesion ROIs and distribution statistics are calculated for each ROI.” A distribution is a comprehensive summary of data Paragraph [0055] The remainder of the radiomic features (R<=0.6) were employed to train a logistic regression model with elastic-net regularization via a 5-fold cross validation approach. This method allows for intelligent selection of features that discriminate D1 and D2 and train the predictive model simultaneously. A receiver operating characteristic curve (ROC) was generated and area under the ROC (AUC) was calculated. ) calculating a component-specific morphological feature value from each component in the at least two connected components (Paragraph [0042] (“, radiomic features are extracted from lesion ROIs and distribution statistics are calculated for each ROI” boundary and tumor are each their own ROI. Paragraph [0056] “ In this example, radiomics and tissue morphology may be correlated at 440. In this example, gland segmentation within the lesion ROIs on digitized surgical specimens was first obtained using the Unet segmentation network at 10× resolution. Gland morphology features, including lumen shape, orientation, arrangement, and graph-based entropy were then extracted at 430 to characterize the PCa gland morphology.” Feature values of the plurality of lesions/tumors components connected in origin within the ROI’s ) averaging the component-specific radiomics feature values to produce a second morphological radiomics feature value; (Paragraph [0056] “In this example, radiomics and tissue morphology may be correlated at 440. In this example, gland segmentation within the lesion ROIs…Gland morphology features, including lumen shape, orientation, arrangement, and graph-based entropy were then extracted at 430 to characterize the PCa gland morphology. Fifteen distribution statistics including mean…were calculated for morphology features of each lesion on the digitized pathology images”)
Zhou teaches measuring a size of each connected component in the at least two connected components to identify the largest connected component (Paragraph [0118] “the largest connected component is selected as the final myocardium segmentation result.” Zhou describes their segmenting as “a target anatomical structure” limitations of what is targeted is up to the practitioner. )
In regards to “storing the first, second and third morphological radiomics feature values into the bank of radiomics features” Zhou states paragraph [0037] “. Medical images of a patient can be acquired using the image acquisition device 104, and the medical images can be sent to the computer system 100 running the master segmentation artificial agent 102 and/or stored in the PACS 106…The PACS 106 stores medical images of various modalities for various patients in a digital format… Segmentation results extracted from the medical images can also be stored in the PACS 106.” Refer to figures 1 and 25 for supplement.
Madabhushi’s states “Memory 1020 can be further configured to store one or more clinical features or other data associated with the patient of the bpMRI image” in paragraph [0065]. Madabhushi’s also shows in figure 11 Tumor segmentation circuit and radiomic feature circuit being in direct communication with memory.
Furthermore, it is without question that a person of ordinary skill in the art knows to store their obtained objective values and calculations into memory. The “bank of radiomics features” can be any storage file or dataset within the storage file the person of ordinary skill in the art chooses it to be.
As per claim 13
Madabhushi and Zhou teach all claim limitations previously rejected in clam 12’s 103 rejection. See claim 12’s 103 rejection.
Madabhushi teaches The computer-implemented method of any of the claim 12,wherein the patient pathology is a cancer (Paragraph [0019] “Radiomic features extracted from pre-operative medical imagery, including magnetic resonance imaging (MRI) imagery may be employed for prostate cancer (PCa) characterization or risk-stratification in vivo”) and each connected component corresponds to a different tumor or metastasis site. (Figure 4 shows multiple region of interests that correspond to tumors that are connected in origin, phenotype (tumors of prostate cancer) region (prostate) . Paragraph [0042] “…radiomic features are extracted from lesion ROIs “
As per claim 14
Madabhushi and Zhou teach all claim limitations previously rejected in clam 13’s 103 rejection. See claim 13’s 103 rejection.
Zhou teaches wherein the pathology is a non- small cell lung cancer (NSCLC) at stage IV, the anatomical area of interest is lung, and at least one of the connected components corresponds to a lung tumor or metastasis. (Paragraph [0045] “In another advantageous embodiment, the master segmentation artificial agent 102 can be applied to select an optimal segmentation strategy across multiple different target anatomies and imaging modalities. Typically, medical image segmentation algorithms are designed and optimized with a specific context of use. For example, algorithms designed for segmenting tubular structures generally perform well in arteries and veins, while algorithms designed for “blob” like structures are well suited for organs such as the heart, brain, liver, etc. The master segmentation artificial agent 102 can automatically identify the context of use (e.g., the target anatomical structure to be segmented) and automatically switch between different segmentation algorithms for different target anatomical structures.”)
Within the Madabhushi/Zhou workflow, a person of ordinary skill in the art would find it obvious to see that the same methodology can be used for various organs, tumor phenotypes, pathologies and stages of organ cancer.
As per claim 15
Madabhushi and Zhou teach all claim limitations previously rejected in clam 13’s 103 rejection. See claim 13’s 103 rejection.
Zhou teaches wherein the pathology is a non- small cell lung cancer (NSCLC) at stage IV, the anatomical area of interest is lung, and at least one of the connected components corresponds to a lung tumor or metastasis. (Paragraph [0045] “In another advantageous embodiment, the master segmentation artificial agent 102 can be applied to select an optimal segmentation strategy across multiple different target anatomies and imaging modalities Typically, medical image segmentation algorithms are designed and optimized with a specific context of use. For example, algorithms designed for segmenting tubular structures generally perform well in arteries and veins, while algorithms designed for “blob” like structures are well suited for organs such as the heart, brain, liver, etc. The master segmentation artificial agent 102 can automatically identify the context of use (e.g., the target anatomical structure to be segmented) and automatically switch between different segmentation algorithms for different target anatomical structures.”)
Within the Madabhushi/Zhou workflow, a person of ordinary skill in the art would find it obvious to see that the same methodology can be used for various organs, tumor phenotypes, pathologies and stages of organ cancer.
Claims 16-18 are rejected under 35 U.S.C. 103 as being unpatentable over Madabhushi et al (Madabhushi hereinafter US 20200000396 A1) in view of Zhou et al (Zhou hereinafter US 20190205606 A1) in further view of Jacobs et al (Jacobs hereinafter US 20240370997 A1)
As per claim 16
Madabhushi and Zhou teach all claim limitations previously rejected in clam 12’s 103 rejection. See claim 12’s 103 rejection.
Jacobs teaches wherein the patient pathology is an infectious disease (Paragraph [0004] “A computing system for detecting and characterizing COVID-19 tissue in a lung region of a patient is disclosed”) the anatomical area of interest is lung (Figure 3 Figure, 11) at least one of the connected components corresponds to a different ground glass opacity site. (Figure 1, Figure 3, Figure 10 Paragraph [0036] “Running the artificial intelligence model also includes classifying one or more segments of the COVID-19 tissue in the lung region as ground glass opacity, crazy paving pattern, consolidation, or a combination thereof based at least partially upon the one or more radiological images and the textures” paragraph [0062] “For example, a lung slice may have consolidation, ground glass opacities, neither, or both.” Paragraph [0066] “the left column of FIG. 10 shows axial CT lung volume and CV-19 abnormality segmentation across multiple slices from a patient with CV-19 characteristics of nodular and peripheral ground glass opacities (as shown by the arrows).”)
Accordingly, a person of ordinary skill in the art would have found it obvious to modify the Madabhushi/Zhou workflow with Jacob’s concept of having the patient pathology being infectious disease and having the connected components correspond to a different ground glass opacity site. A person of ordinary skill in the art would see this modification as useful because it allows for a variety of lesion segmentation and radiomic feature extraction not just limited to the lesions caused by cancer but also the abnormality caused by an infectious disease. A person of ordinary skill in the art would see this as an obvious advantage in flexibility within the methodology.
As per claim 17
Madabhushi and Zhou teach all claim limitations previously rejected in clam 13’s 103 rejection. See claim 13’s 103 rejection.
Jacobs teaches wherein the patient pathology is SARS-Cov2 (Figure 1, Figure 2, Paragraph [0004] “ A computing system for detecting and characterizing COVID-19 tissue in a lung region of a patient is disclosed” Paragraph [0041] “The COVID-19 classification model may be generated or updated based at least partially upon the one or more radiological images (e.g., images 102, 104, 106), the pathology results, “)
As per claim 18
Madabhushi, Zhou and Jacobs teach all claim limitations previously rejected in clam 17’s 103 rejection. See claim 17’s 103 rejection.
Madabhushi teaches wherein the radiomics feature is a morphological radiomics feature selected among an IBSI feature (Paragraph [0028] “ the set of radiomic features may include other, different radiomic features or first order statistics associated with the members of the set of radiomic features. “ Paragraph [0030] “Providing the set of radiomic features may, in this embodiment, include providing the first order statistics to the machine learning classifier” Paragraph [0056] “Gland morphology features, including lumen shape, orientation, arrangement, and graph-based entropy were then extracted at 430 to characterize the PCa gland morphology. Fifteen distribution statistics including mean, standard deviation, range, minimum, maximum, mode, median, variance, kurtosis, harmonic mean, skewness, absolute deviation, inter-quartile range, disorder, min/max, were calculated for morphology features of each lesion on the digitized pathology images” )
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHANE WRENSFORD CODRINGTON whose telephone number is (571)272-8130. The examiner can normally be reached 8:00am-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, Matthew Bella can be reached at (571) 272-7778. 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.
/SHANE WRENSFORD CODRINGTON/Examiner, Art Unit 2667 /MATTHEW C BELLA/Supervisory Patent Examiner, Art Unit 2667
Prosecution Insights