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 .
Claim Objections
Claim 1 is objected to because of the following informalities: “the radiomic features” should read “the plurality of radiomic features”. Appropriate correction is required.
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 1-15 are rejected under 35 U.S.C. 103 as being unpatentable over
CHOI HEUNG KOOK et al., (KR 20240012736 A) hereafter CHOI in view of NPL1 (Identifying lesions in pediatric epilepsy using morphometric and textural analysis of magnetic resonance images, Sancgeetha Kulaseharan et al., ELSEVIER, 2019, Pages 1-8) hereafter NPL1.
1. Regarding claim 1, CHOI discloses a prediction (figs 1-8 shows a prediction computing system) computing system, comprising: a storage device configured to store at least one instruction (a storage device configured to store at least one instruction; and a processor coupled to the storage device, and the processor configured to access and execute the at least one instruction would be implied/obvious in view of a device for classifying brain tumors using artificial intelligence technology and algorithm as shown in figs 1-9 and pages 6-7) ; and a processor coupled to the storage device, and the processor configured to access and execute the at least one instruction (a processor coupled to the storage device, and the processor configured to access and execute the at least one instruction would be implied/obvious in view of a device for classifying brain tumors using artificial intelligence technology and algorithm as shown in figs 1-9 and pages 6-7) for:
performing a pre-process on a magnetic resonance imaging (MRI scans are divided into training and test data sets in a 9:1 ratio. Brain tumors were extracted from 2D MRI scans using ground truth/mask images using MATLAB R2020b (MathWorks, Natick, MA,USA) and AI classification was performed using Anaconda (Jupyter notebook) meeting the limitations of performing a pre-process on a MRI imaging to obtain a pre-processed MRI, Abstract discloses “overlaying an annotated binary mask (i.e mask images) on an original MRI image” would meet the limitations of performing a pre-process on a MRI imaging to obtain a pre-processed MRI, Examiner notes that the specifics of “a pre-process” are not required by the current claim);
finding a region of interest from the pre-processed MRI (Abstract and pages 7, 7 discloses a step in which a region of interest (ROI) extraction unit extracts an ROI image of a brain tumor by overlaying an annotated binary mask on an original MRI image (i.e from the pre-processed MRI) meeting the above claim limitations),
obtaining a plurality of radiomic features based on the region of interest (page 7 discloses “A feature calculation unit extracting 2D features by performing feature extraction on the ROI image”, Pages 3-4 discloses “Figure 4 shows extracted MRI patches used to calculate radiomic features (i.e plurality of radiomic features) for classification. Referring to Figure 4, it shows regions of interest (ROI) extracted for three different classes of brain tumors. In Figure 3, (A) to (C) are ROIs classified as gliomas, (D) to (F) are ROIs classified as meningiomas, and (G) to (I) are ROIs classified as pituitary tumors. Next, the feature calculation unit 130 performs feature extraction from each ROI using Pyradiomics, an opensource Python package for feature calculation (feature extraction) from ROI images. As shown in (c) of Figure 2, features are calculated or extracted from each ROI image. Feature calculation(extraction) is one of the prominent methods in pattern recognition and image processing for pattern analysis of images. Pyradiomics, an opensource Python package, is used to extract a number of radiomic features based on heterogeneity (i.e. image gray level) and shape (i.e. segmented regions in the image meeting the claim limitations); and
performing a machine learning based on the radiomic features to obtain classes of brain tumor ROI (pages 5-6 discloses “The tumor classification unit 150 classifies the tumor based on the characteristics of the brain tumor image. As shown in (e) of FIG. 2, the tumor classification unit 150 uses long short-term memory (LSTM), support vector machine (SVM), k-nearest neighbor (KNN), logistic regression (LR), and RF (Random forest) and AI-based multiclass and binary classification using LDA (linear discriminant analysis) are performed to predict the class of brain tumor (glioma, meningioma, pituitary). In the present invention, DL and ML techniques are used to classify features extracted (i.e plurality of radiomic features) from three different classes of brain tumor ROI.). As seen in the disclosure, CHOI discloses MRI images and predicting tumor in brain (i.e brain’s disorder). CHOI however is silent and fails to disclose MRI of a child's brain and an epilepsy prediction model.
NPL1 discloses MRI of a child's brain and an epilepsy prediction model (pages 1- 2 discloses “In this study, we explored the development of a unified mathematical model that considers segmentation, morphometric analysis, and textural analysis in a joint formulation for the purpose of identifying FCD in children with focal intractable epilepsy and sections 2.1 and 2.2 discloses the subjects (i.e children’s) and MRI meeting the above claim limitations). Before the effective filing date of the invention was made CHOI and NPL1 are combinable because they are from the same field of endeavor and are analogous art of image processing. The suggestion/motivation would be (“The algorithm allows us to predict a class, given a set of features using probabilities. By the class conditional independence assumption, all predictor variables contribute independently to class labels and any dependence between input variables is disregarded; this process has the advantage of being less computationally expensive. We applied the2-StepNaiveBayes Classifier trained on morphometric and textural features, not only on volumetricT1-w, but also onT2-w and FLAIR sequences. See page 2 col 1 2nd paragraph). Therefore, it would be obvious and within one of ordinary skill in the art to have recognized the advantages of NPL1 in the system/method of CHOPI to obtain the invention as specified in claim 1.
2. Regarding claim 2, CHOI and NPL1 disclose the prediction computing system of claim 1. CHOI discloses MRI on page 3 and in figs 2-5. NPL1 also discloses wherein the MRI is a T2-fluid attenuated inversion recovery (T2-FLAIR) image (page 2 section 2.2 discloses T2w and FLAIR sequences meeting the limitations of T2-FLAIR), and the pre-process comprises an image normalization process (page 4 section 2.5 discloses “The gradient magnitude was computed for each case using the original volume following intensity normalization (i.e image normalization process) from FreeSurfer). CHOI and NPL1 in combination would therefore meet the limitations as claimed in claim 2.
3. Regarding claim 3, CHOI and NPL1 discloses the prediction computing system of claim 1. CHOI discloses further wherein the region of interest is a supratentorial glioma region (page 3, Fig 3 discloses ROI as glioma meeting the above claim limitations).
4. Regarding claim 4, CHOI and NPL1 discloses the prediction computing system of claim 1. CHOI discloses further wherein the radiomic features comprises a brain tumor shape feature, a brain tumor image grayscale intensity feature, a brain tumor texture feature, and a brain tumor location feature (pages 2 and 4 discloses wherein the radiomic features comprises a brain tumor shape feature, a brain tumor image grayscale intensity feature, a brain tumor texture feature, and a brain tumor location feature).
5. Regarding claim 5, CHOI and NPL1 discloses the prediction computing system of claim 1. CHOI discloses further wherein the processor accesses and executes the at least one instruction for: selecting one radiomic feature from the plurality of radiomic features, and then using the one radiomic feature to perform the machine learning (page 4 discloses “The feature selection unit 140 receives features extracted from the ROI of the brain tumor image from the feature calculation unit 130. Then, as shown in (d) of FIG. 2, the feature selection unit 140 uses a filter method (redundant feature removal and Pearson correlation coefficient) and a wrapper method (Perform three-step feature selection using recursive feature removal. As shown in (d) of Figure 2, three-step feature selection is performed using a filter method (removing redundant features and Pearson correlation coefficients) and a wrapper method (removing recursive features). perform feature selection. Feature selection is an important step before DL and ML classification. The feature selection unit 140 may use three techniques: feature deduplication, Pearson correlation coefficient, and RFE to perform the feature reduction process. Many feature selection methods have been proposed over the past decades. In general, feature selection methods can be divided into three groups: filter methods, wrapper methods, and embedded methods. Filter methods select the relevance of features based on univariate statistics rather than cross-validation (CV) performance. Common filter methods include information gain, chi-square test, Fisherscore, Pearson correlation coefficient, and variance threshold. Additionally, the wrapper method considers the efficiency of features based on the performance of the classifier. Some common wrapper methods include recursive feature elimination (RFE), sequential feature selection algorithms, and genetic algorithms. Embedded methods work similarly to wrapper methods, two common methods include L1 (LASSO) regularization and decision trees. In the first step, the feature selection unit 140 searches for similar values in columns of the dataset and removes duplicate features. Another reason to remove redundant features is because it does not change the training algorithm. Instead, unnecessary delays are added to the training time. In the second step, the feature selection unit 140 removes highly correlated features (features with a correlation of 85% or more) from the dataset using the Pearson correlation coefficient. Finally, in the third step, the feature selection unit 140 removes the weakest and poorest performing features using RFE”).
6. Claim 6 is a corresponding method claim of claim 1. See the corresponding explanation of claim 1.
7. Claim 7 is a corresponding method claim of claim 2. See the corresponding explanation of claim 2.
8. Claim 8 is a corresponding method claim of claim 3. See the corresponding explanation of claim 3.
9. Claim 9 is a corresponding method claim of claim 4. See the corresponding explanation of claim 4.
10. Claim 10 is a corresponding method claim of claim 5. See the corresponding explanation of claim 5.
11. Claim 11 is a corresponding non-transitory computer readable medium claim of claim 1. See the explanation of claim 1. A storage device (i.e non-transitory computer readable medium) configured to store at least one instruction; and a processor coupled to the storage device, and the processor configured to access and execute the at least one instruction would be implied/obvious in view of a device for classifying brain tumors using artificial intelligence technology and algorithm as shown in figs 1-9 and pages 6-7 of CHOI).
12. Claim 12 is a corresponding non-transitory computer readable medium claim of claim 2. See the explanation of claim 2.
13. Claim 13 is a corresponding non-transitory computer readable medium claim of claim 3. See the explanation of claim 3.
14. Claim 14 is a corresponding non-transitory computer readable medium claim of claim 4. See the explanation of claim 4.
15. Claim 15 is a corresponding non-transitory computer readable medium claim of claim 5. See the explanation of claim 5.
Examiner's Note: Examiner has cited figures, and paragraphs in the references as applied to the claims above for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested for the applicant, in preparing the responses, to fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner. Examiner has also cited references in PTO892 but not relied on, which are relevant and pertinent to the applicant’s disclosure, and may also be reading (anticipatory/obvious) on the claims and claimed limitations. Applicant is advised to consider the references in preparing the response/amendments in-order to expedite the prosecution.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JAYESH PATEL whose telephone number is (571)270-1227. The examiner can normally be reached IFW Mon-FRI.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Bee can be reached at 571-270-5183. 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.
/JAYESH A PATEL/Primary Examiner, Art Unit 2677
/JAYESH PATEL/
Primary Examiner
Art Unit 2677
Prosecution Insights