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 Arguments
Applicant's arguments below filed 7/30/2026 have been fully considered but they are not persuasive | moot in view of the new grounds of rejection.
The Applicant asserts on pages 13-14 of the Remarks:
“Re: Namkug Kim
Namkug Kim merely discloses a system and method that utilizes a FLAIR image (first image) and a DWI image (second image) of a patient with an unknown acute cerebral infarction onset time. Namkug Kim defines an infarcted region-extracted from the DWI image-onto the FLAIR image, extracts feature information, and compares this to an SVM-based machine learning model to calculate the elapsed time of the cerebral infarction.
However, Namkug Kim is fundamentally different from the present invention. Namkug Kim utilizes an SVM-based model to calculate the elapsed time as a single numerical value. Namkug Kim entirely fails to disclose labeling information on an area of a transition state for each location of the infarcted region, nor does it teach combining this labeled information into four- dimensional data to be used as input for a CNN. Furthermore, Namkug Kim does not perform MNI coordinate system-based alignment, and its output is merely a single elapsed time value rather than the claimed probability prediction values for a plurality of time intervals.
Re: Dong Eog Kim
Dong Eog Kim discloses aligning a plurality of MRI images (DWI, FLAIR, GE, T2) to an MNI standard brain coordinate system, storing the lesion region in a 3D data space, and utilizing a 3D CNN to classify the cause and severity of a stroke, as well as to predict patient status and risk within three weeks.
However, the explicit purpose of Dong Eog Kim is to classify the cause and severity of a stroke, not to predict the occurrence time of a cerebral infarction. Dong Eog Kim lacks any operation for estimating onset time utilizing a FLAIR-DWI mismatch. Most importantly, Dong Eog Kim completely fails to disclose labeling the area of a transition state for each location of the infarcted region and combining this specific data with FLAIR and DWI images into four- dimensional data to output probability prediction values for specific time intervals.”
In response the examiner respectfully asserts that the arguments directed to the amended subject matter have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
In response to applicants arguments regarding the Namkug Kim reference, the claim does not require probability prediction values for a plurality of time intervals. In response to applicants arguments regarding the Dong Eog Kim reference, the Dong Eog Kim reference was not used to teach the prediction of the occurrence time of a cerebral infarction. Dong Eog Kim aligning a plurality of MRI images (DWI, FLAIR, GE, T2) to an MNI standard brain coordinate system and is in the same field of using a machine learning model to evaluate images of stroke patients. Therefore the arguments are found to be not persuasive.
Claim Objections
Claims 2 and 7 are objected to because of the following informalities: claims 2 and 7 recite “output the probability prediction value for the occurrence time of acute cerebra I infarction”. However, this should be read as “output the probability prediction value for the occurrence time of acute cerebral infarction”. Appropriate correction is required.
Claims 4, 9, and 14 are objected to because of the following informalities: claims 4, 9, and 14 recite “output the probability prediction value for the time of acute cerebral infarction occurrence analyzed by the machine learning”. However, this should be read as “output the probability prediction value for the occurrence time of acute cerebral infarction analyzed by the machine learning”. Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-15 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claims 1, 6, and 11, line 18 of claim 1, line 16 of claim 6 and line 18 of claim 11 recite “label information on an area of a transition state for each location of the infarcted region”. However, an infarcted region has not been previously defined. It is unclear if this is the same or different from the infarction region. For examination purposes the limitation will be interpreted as “label information on an area of a transition state for each location of the infarction region”.
Regarding claims 1, 6, and 11, lines 22-23 of claim 1, lines 20-21 of claim 6 and lines 22-23 of claim 11 recite “output a probability prediction value for an occurrence time of acute cerebral infarction, which is learned and analyzed based on the machine learning”. However, a probability prediction value and an occurrence time of acute cerebral infarction have already been defined. Therefore, it is unclear if the probability prediction value and the occurrence time of acute cerebral infarction in the cited limitation are the same or different from the probability prediction value and the occurrence time of acute cerebral infarction that have been previously defined in the claims. For examination purposes the limitation will be interpreted as “output the probability prediction value for the occurrence time of acute cerebral infarction, which is learned and analyzed based on the machine learning”.
Regarding claims 2-4, 7-9, and 12-14, each of claims 2-4, 7-9, and 12-14 recite “perform machine learning-based training”. Independent claims 1, 6, and 11 claim the step of performing machine learning-based training. Therefore, it is unclear if the machine learning-based training of claims 2-4, 7-9, and 12-14 is the same or different from the machine learning-based training recited in the independent claims. For examination purposes the claims will be interpreted as “perform the machine learning-based training”.
Regarding claims 4, 9, and 14, each of claims 4, 9, and 14 recite “wherein the processor is configured to: label an area of the infarction region”. Independent claims 1, 6, and 11 recite “wherein the processor is further configured to: label information on an area of a transition state for each location of the infarcted region”. Therefore, it is unclear if an area of the infarction region of claims 4, 9, and 14 is the same or different from the area of a transition state for each location of the infarcted region recited in the independent claims. For examination purposes the claims will be interpreted as being the same region.
Regarding claims 5, 10, and 15, each of claims 5, 10, and 15 recite “generate data within a machine learning model”. Independent claims 1, 6, and 11 recite “input data for a Convolutional Neural Network (CNN) to perform machine learning-based training”. Therefore, it is unclear if the machine learning model of claims 5, 10, and 15 is the same or different from the Convolutional Neural Network (CNN) recited in the independent claims. For examination purposes the claims will be interpreted as “generate data within the CNN”.
Regarding claims 5, 10, and 15, each of claims 5, 10, and 15 recite “using machine learning based on the first image and the second image”. Independent claims 1, 6, and 11 recite “which is learned and analyzed based on the machine learning”. Therefore, it is unclear if the machine learning of claims 5, 10, and 15 is the same or different from the machine learning recited in the independent claims. For examination purposes the claims will be interpreted as “using the machine learning based on the first image and the second image”.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, 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 factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-15 are rejected under 35 U.S.C. 103 as being unpatentable over Namkug Kim (US 20190269359) and further in view of Dong Eog Kim (US 20190246904) and Ho NPL 2019 (“A Machine Learning Approach for Classifying Ischemic Stroke Onset Time from Imaging”).
Regarding claims 1, 6, and 11, Namkug Kim discloses a device for predicting an occurrence time of acute cerebral infarction (Abstract – “The present disclosure relates to a system and a method for estimating an acute cerebral infarction onset time”, [0039] – “a computer device including a processor to execute the method for estimating an onset time of acute cerebral infarction”), comprising: [claim 1]
a method for predicting an occurrence time of acute cerebral infarction performed by a prediction device (Abstract – “The present disclosure relates to a system and a method for estimating an acute cerebral infarction onset time”, [0039] – “a computer device including a processor to execute the method for estimating an onset time of acute cerebral infarction”), comprising: [claim 6]
a system for predicting an occurrence time of acute cerebral infarction (Abstract – “The present disclosure relates to a system and a method for estimating an acute cerebral infarction onset time”), comprising: [claim 11]
a communication module configured to perform communication with an imaging device that captures an image of an acute cerebral infarction patient ([0082] – “using a communication module of the computer, and what information or media as transmitted or received therebetween during communication”, [0053] – “the first image 10 and the second image 20 for a first patient whose acute cerebral infarction onset time is not identified. In some embodiments, the processor directly receives medical image data taken from a magnetic resonance imaging (MRI) device”); and
a processor configured to control an operation related to prediction of the occurrence time of acute cerebral infarction ([0039] – “a processor to execute the method for estimating an onset time of acute cerebral infarction”), wherein the processor is configured to:
receive the image of the acute cerebral infarction patient from the imaging device through the communication module ([0082] – “when the computer's processor needs to communicate with any other computer or server at a remote location to execute the functions…using a communication module of the computer, and what information or media as transmitted or received therebetween during communication”, [0053] – “the first image 10 and the second image 20 for a first patient whose acute cerebral infarction onset time is not identified. In some embodiments, the processor directly receives medical image data taken from a magnetic resonance imaging (MRI) device”), classify the image into a first image corresponding to a liquid attenuation inversion recovery image and a second image corresponding to a diffusion-weighted image, acquire the first image and the second image ([0024] – “receiving a first image and a second image of a first patient…the first image is a fluid-attenuated inversion recovery image, and the second image is a diffusion-weighted image”, [0050] – “a step S400 of extracting an infarction region image from the second image 20…a step S800 of defining an infarction region in the first image”, therefore the images are classified as first image and second image),
align the first image and the second image […], detect an infarction region in the second image ([0024] – “extracting an infarction region image from the second image; aligning the second image with the first image”), and
output a probability prediction value for the occurrence time of acute cerebral infarction based on the first image, the second image, and the infarction region (Fig. 1, [0024] describes the steps listed in Fig. 1 including “extracting an infarction region image from the second image; aligning the second image with the first image; defining an infarction region in the first image, based on a result of the alignment of the second image with the first image; extracting feature information of the first patient, from the infarction region in the first image; comparing the extracted feature information with reference data; and calculating an amount of time that has elapsed since the acute cerebral infarction onset time, based on a result of the comparison”, therefore the amount of time is based on the first image, the second image, and the infarction region, [0033] – “generating the reference data as a support vector machine”, the elapsed time is calculated based on a machine learning model therefore it is a prediction, [0062] – “outputting a signal for notifying the determination result”).
Conversely Namkug Kim does not teach align the first image and the second image with respect to a Montreal Neurological Institute (MNI) region corresponding to an infarction region of a brain,
wherein the processor is further configured to: label information on an area of a transition state for each location of the infarcted region;
combine the first image, the second image, and the labeled information into four- dimensional data to use as input data for a Convolutional Neural Network (CNN) to perform machine learning-based training; and
output a probability prediction value for an occurrence time of acute cerebral infarction, which is learned and analyzed based on the machine learning.
However Dong Eog Kim discloses align the first image and the second image with respect to a Montreal Neurological Institute (MNI) region corresponding to an infarction region of a brain ([0057] – “the stroke diagnosis and prognosis prediction system standardizes the plurality of images based on the coordinates of a Montreal neurological institute (MNI) standard brain image”, [0041] – “the lesion area detection and mapping unit 130 detects a lesion area so that information of the lesion area is output to an MNI space”).
Dong Eog Kim is an analogous art considering it is in the field of a machine learning model to evaluate images of stroke patients.
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the device, method, and system of Namkug Kim to incorporate the alignment to a Montreal neurological institute (MNI) coordinate space of Dong Eog Kim to achieve the same results. One would have motivation to combine because by standardizing all images to the same coordinate space provides consistent input which improves the accuracy of the output of the machine learning model.
Conversely Namkug Kim and Dong Eog Kim do not teach wherein the processor is further configured to: label information on an area of a transition state for each location of the infarcted region;
combine the first image, the second image, and the labeled information into four- dimensional data to use as input data for a Convolutional Neural Network (CNN) to perform machine learning-based training; and
output a probability prediction value for an occurrence time of acute cerebral infarction, which is learned and analyzed based on the machine learning.
However Ho discloses wherein the processor (pg. 4 – “Image Preprocessing”) is further configured to: label information on an area of a transition state for each location of the infarcted region (See pg. 19 Fig. 2 the ROI is labeled, pg. 6 – “the ROIs were defined by Tmax>6s, which captures both the dead tissue core and the salvageable tissue that can possibly be saved by intervention aimed at restoring blood flow”, pg. 2 – “infarction (i.e., tissue death)”, the dead tissue core is interpreted as the infarcted region the salvageable tissue included in the ROI is interpreted as the area of a transition state);
combine the first image, the second image, and the labeled information into four- dimensional data to use as input data for a Convolutional Neural Network (CNN) to perform machine learning-based training (pg. 4 – “Intra-patient registration of pre-treatment PWIs, DWI, ADC and FLAIR images was performed”, pg. 3 – “four-dimension (4-D) PWIs that can be used in TSS classification”, pg. 10 – “the ROI masks were applied to generate the deep AE features”, pg. 8 – “we also trained four popular end-to-end convolutional neural networks (CNNs) to classify TSS. The input to the CNNs were the stacked images (the MR images + the perfusion parameter maps) and the output was the TSS classification.”); and
output a probability prediction value for an occurrence time of acute cerebral infarction, which is learned and analyzed based on the machine learning (pg. 8 – “we also trained four popular end-to-end convolutional neural networks (CNNs) to classify TSS. The input to the CNNs were the stacked images (the MR images + the perfusion parameter maps) and the output was the TSS classification”, pg. 1 – “time since stroke onset (TSS)”), a machine learning model makes predications based on a likelihood or probability).
Ho is an analogous art considering it is in the field of a machine learning model to evaluate images of stroke patients.
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the device, method, and system of Namkug Kim to incorporate the Convolutional Neural Network (CNN) with labeling of an area of a transition state of Ho to achieve the same results. One would have motivation to combine because “Generating imaging features based on entire brain MR images may be less descriptive to the stroke pathophysiology and less predictive of TSS because often stroke occurs in only one cerebral hemisphere.” (Ho – pg. 6)
Regarding claims 2, 7, and 12, Namkug Kim, Dong Eog Kim, and Ho disclose all of the elements of the claimed invention as citied above in claims 1, 6, and 11.
Namkug Kim further discloses wherein the processor is configured to ([0039] – “a processor to execute the method for estimating an onset time of acute cerebral infarction”): perform machine learning-based training based on the first image, the second image, and the infarction region ([0063] – “the method comprises a step S100 of generating the reference data in a form of a support vector machine (SVM), based on first and second images 10 and 20 of a plurality of second patients. That is, in some embodiments, the processor generates a SVM for performing machine learning based on feature information…an infarction region identified in the second image 20 to the first image 10, and extracts feature information from the defined infarction region”), and
output the probability prediction value for the occurrence time of acute cerebral infarction analyzed by the machine learning (Fig. 4, reference data is generated in form of a support vector machine for performing machine learning and the extracted feature information is compared to the reference data to calculate an amount of time that has elapsed since the acute cerebral infarction onset time, [0062] – “outputting a signal for notifying the determination result”).
Regarding claims 3, 8, and 13, Namkug Kim, Dong Eog Kim, and Ho disclose all of the elements of the claimed invention as citied above in claims 1, 2, 6, 7, 11, and 12.
Namkug Kim further discloses wherein the processor is configured to: standardize an intensity of the second image ([0055] – “normalizing an intensity of an apparent diffusion coefficient map of the second image 20”), perform machine learning-based training based on the standardized second image ([0055] discloses that the step of normalizing an intensity is part of step S400 shown in Figs. 1, 4, 6, and 7 which are methods of using the extracted infarction region from the second image to extract feature information in the first image to be compared to reference data of a SVM model), and
detect the infarction region in the second image analyzed by the machine learning ([0055] – “the step S400 of infarction region image extracting operation comprises a step S410 of normalizing an intensity of an apparent diffusion coefficient map of the second image 20; and a step S420 of extracting an infarction region via an absolute reference search”).
Regarding claims 4, 9, and 14, Namkug Kim, Dong Eog Kim, and Ho disclose all of the elements of the claimed invention as citied above in claims 1, 2, 3, 6, 7, 8, 11, 12, and 13.
Namkug Kim further discloses wherein the processor is configured to: label an area of the infarction region ([0050] – “step S800 of defining an infarction region”),
perform machine learning-based training based on the first image, the second image, and the area of the infarction region (See Fig. 4), and
output the probability prediction value for the time of acute cerebral infarction occurrence analyzed by the machine learning (Fig. 4, reference data is generated in form of a support vector machine for performing machine learning and the extracted feature information is compared to the reference data to calculate an amount of time that has elapsed since the acute cerebral infarction onset time, [0062] – “outputting a signal for notifying the determination result”).
Regarding claims 5, 10, and 15, Namkug Kim, Dong Eog Kim, and Ho disclose all of the elements of the claimed invention as citied above in claims 1, 2, 6, 7, 11, and 12.
Namkug Kim further discloses wherein the processor is configured to: further generate data within a machine learning model using machine learning based on the first image and the second image ([0064] – “the step S100 (the reference data generation operation) comprises…performing an alignment of the first image of the each of the second patients classified into the training group with a second image of the each of the second patients classified into the training group”).
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 RENEE C LANGHALS whose telephone number is (571)272-6258. The examiner can normally be reached Mon.-Thurs. alternate Fridays 8:30-6.
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, Christopher Koharski can be reached at 571-272-7230. 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.
/R.C.L./ Examiner, Art Unit 3797
/CHRISTOPHER KOHARSKI/ Supervisory Patent Examiner, Art Unit 3797
