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 .
Information Disclosure Statement
The IDS(s) has/have been considered and placed in the application file.
CLAIM INTERPRETATION
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier.
Claim 13 recites an "analysis device," an "interface device," a "storage device," and a "calculation device." Each uses the generic placeholder "device" coupled with functional language and modified by no sufficient recited structure, invoking the presumption under Williamson v. Citrix. Each is therefore interpreted under 35 U.S.C. 112(f). The recited functions and the corresponding structures disclosed in the specification are as follows:
The "interface device that receives ... 2D MRI slices" performs the function of receiving the 2D MRI slices. The corresponding structure is the interface device 640 of FIG. 6, "a device that receives predetermined commands and data from the outside" (Specification, FIG. 6 description). Receiving data is a function achievable by a general-purpose interface without special programming, so no algorithm is required.
The "storage device configured to store" the segmentation model and the learning models performs the function of storing. The corresponding structure is the storage device 610 of FIG. 6 (a memory/data store). Storing is a function achievable by a general-purpose memory without special programming, so no algorithm is required.
The "calculation device configured to" input the slices to the segmentation model, extract ROIs, predict a volume, and output the dementia information performs those computational functions. The corresponding structure is the calculation device 630 of FIG. 6 programmed with the preprocessing, segmentation model, first learning model , and second learning model algorithms disclosed at FIGS. 1-5 and the accompanying description.
The overall "analysis device" is the computer device 600 of FIG. 6 ("a PC, a smart device, a server of a network, a data processing-only chipset, or the like") comprising the foregoing components and programmed to perform the disclosed pipeline.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
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.
Claim 2, 3, 8, 9, and 13 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.
Claims 2, 3, 8, and 9 are rejected under 35 U.S.C. 112(b) as indefinite. Each recites "the
first learning models" (plural), which lacks antecedent basis; parent claims 1 and 7 recite "a pre trained first learning model" (singular). It is unclear whether one model or a plurality of models is intended.
Claim 13 is rejected under 35 U.S.C. 112(b) as indefinite. Claim 13 recites extracting a ROI "from the 2D MRI slice" (singular), which lacks antecedent basis; the claim earlier recites "2D MRI slices" (plural).
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-18 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-6 of copending Application No. 19/398,339 (both commonly assigned to Samsung Life Public Welfare Foundation and share inventors) in view of Bin et al., WO 2016/205811 A1.
Both sets of claims are directed to deriving dementia information by (i) extracting regions of interest from a brain image using a pre-trained segmentation model, (ii) predicting a volume of at least one region by inputting pixel information of the region into a pre-trained first learning model, and (iii) calculating the dementia information by inputting the volume into a pre-trained second learning model, wherein the regions of interest include cerebrospinal fluid and lateral ventricle regions. The instant claims recite a two-dimensional MRI brain image, whereas claims 1-6 of the '339 application recite a brain CT image. Substituting one well-known brain-imaging modality (2D MRI) for another (brain CT) in the same segmentation-and-prediction pipeline is an obvious variation that yields no new or unexpected result; that brain atrophy and cerebrospinal fluid volume are assessed from brain CT images as well as from MRI is itself known in the art (see, e.g., WO 2016/205811 A1, ¶5), confirming that the choice of imaging modality is a matter of routine design. Instant claim additionally predicts a cortical thickness; predicting a cortical thickness with a learning model is a known expedient in the same art (see, e.g., Rebsamen), so instant claim 1 is an obvious variant of '339 claim 1. The instant dependent claims (multiple learning models prepared in advance for each ROI, clinical information including age/gender/APOE4 input to the second learning model, and the analysis-device apparatus) correspond to the dependent and apparatus claims of the '339 application. This is a provisional nonstatutory double patenting rejection.
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, 4-7, 10-14, and 16-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kim et al., KR 20200062589 A (Espacenet English machine translation of record; paragraph citations herein are to that translation; hereinafter "Kim") in view of Basher et al., "Volumetric Feature-Based Alzheimer 's Disease Diagnosis From sMRI Data Using a Convolutional Neural Network and a Deep Neural Network," (hereinafter "Basher") and Rebsamen et al., "Brain Morphometry Estimation: From Hours to Seconds Using Deep Learning," (hereinafter "Rebsamen").
Claim 1.
Kim discloses a dementia information calculation method using two-dimensional magnetic resonance imaging (2D MRI), comprising:
receiving, by an analysis device, inputs of 2D MRI slices of a subject (KIM: "obtaining a brain MRI image from a subject" (¶ 10), wherein "the brain MRI image is processed into 2D data using semantic segmentation and divided into pixels"(¶ 45). This teaches receiving 2D MRI slices of a subject.);
inputting, by the analysis device, the 2D MRI slices to a segmentation model to extract regions of interest (ROIs) (KIM: "the brain MRI image is processed into 2D data using semantic segmentation and divided into pixels" (¶ 45), and the measurement unit labels each region as "Right Lateral Ventricle, Left Lateral Ventricle, Right Amygdala, Left Amygdala, Right Hippocampus, and Left Hippocampus" (¶ 47). This teaches a segmentation model extracting the ROIs.);
inputting, by the analysis device, pixel information about the ROIs to a (KIM: the measurement unit "calculates the number of pixels of an object in each area to measure the brain capacity for each area" (¶ 46) and "may measure the capacity, volume, and thickness of the brain cortex for each divided brain region" (¶ 48). This teaches a cortical thickness and a volume of at least one ROI obtained from the ROI pixel information.); and
inputting, by the analysis device, the cortical thickness of the at least one region and the volume of the at least one region to a pre-trained second learning model to output dementia information about the subject ("Prediction unit 160, based on the deep learning model, predicts the likelihood of dementia and the time of dementia through the measured brain capacity" (¶ 49). This teaches a pre-trained second learning model outputting dementia information from the morphometric values.),
wherein the ROIs include at least one of frontal gray matter, temporal gray matter, parietal gray matter, occipital gray matter, lateral ventricle (LV), hippocampus, and extracerebral cerebrospinal fluid (KIM: "Right Lateral Ventricle, Left Lateral Ventricle, ... Right Hippocampus, and Left Hippocampus" (¶ 47). This teaches ROIs including at least the LV and hippocampus, satisfying the "at least one of' recitation.).
Kim obtains the cortical thickness and volume by pixel-count measurement rather than
predicting them by inputting the ROI pixel information to a pre-trained first learning model.
However, Basher teaches predicting a volume of a brain region by a learning model (BASHER:
"extract volumetric features from each slice by using a discrete volume estimation
convolutional neural network (DYE-CNN) model"; the DVE-CNN "estimates the number
of voxels (discrete volume) of the corresponding ROI" (Abstract; § I).), and Rebsamen
teaches predicting both a cortical thickness and a volume of a brain region by a learning model
(REBSAMEN: a CNN is used "to predict the volumes of anatomically delineated
subcortical regions of interest (ROI), and mean thicknesses and curvatures of cortical
parcellations directly from Tl-weighted MRI" (Abstract). This teaches a pre-trained first
learning model predicting the cortical thickness and volume from the image.).
The difference between claim 1 and Kim is that the claimed method predicts the cortical
thickness and volume with a pre-trained first learning model, whereas Kim obtains these
characteristics by pixel-count measurement without such a model. Kim, however, already
extracts the regions of interest and provides the per-region pixel information(¶ 45-47), and
Basher and Rebsamen teach that a convolutional network can predict such morphometry from
that information: Basher predicts a region volume (the volume prong) and Rebsamen predicts a
cortical thickness (the thickness prong), each of which the claim recites for "at least one region"
(and which may be different regions). It would have been obvious to one of ordinary skill in the
art before the effective filing date to substitute a pre-trained learning model, as taught by Basher and Rebsamen, for Kim's pixel-count measurement in order to obtain the cortical thickness and volume from Kim's ROI pixel information. This is the simple substitution of one known means of obtaining regional brain morphometry (a learned estimator) for another (pixel-count measurement) to yield the predictable result of quantifying per-region volume and cortical thickness, with a reasonable expectation of success because Basher and Rebsamen each demonstrate a convolutional network reliably producing such measures from brain MRI (MPEP 2143(B)). A further motivation would have been to obtain these measures rapidly from a limited set of 2D MRI slices, avoiding the time and cost of conventional volumetric tools (Rebsamen reduces morphometry "from hours to seconds", and notes that such networks are commonly applied per slice, "Input is often fed patch- or slice-wise" (§ I)).
Claim 7.
Kim discloses a dementia information calculation method using two-dimensional magnetic resonance imaging (MRI), comprising:
receiving, by an analysis device, inputs of 2D MRI slices of a subject; inputting, by the analysis device, the 2D MRI slices to a segmentation model to extract regions of interest (ROIs) (KIM: "the brain MRI image is processed into 2D data using semantic segmentation and divided into pixels"(¶ 45).);
inputting, by the analysis device, pixel information of the ROIs to a (KIM: the measurement unit "may measure the capacity, volume, and thickness of the brain cortex for each divided brain region" (¶ 48).); and
inputting, by the analysis device, the volume of the at least one region to a pre- trained second learning model to output dementia information about the subject (KIM: "Prediction unit 160,
based on the deep learning model, predicts the likelihood of dementia and the time of
dementia through the measured brain capacity" (¶ 49).), wherein the ROIs include at least one of frontal gray matter, temporal gray matter, parietal gray matter, occipital gray matter, lateral ventricle (LV), hippocampus, and extracerebral cerebrospinal fluid (KIM: "Right
Lateral Ventricle, ... Right Hippocampus, and Left Hippocampus" (¶ 47).).
Kim obtains the volume by pixel-count measurement rather than predicting it by a pre-trained first learning model. However, Basher teaches predicting the volume by a learning model (BASHER: "extract volumetric features from each slice by using a discrete volume
estimation convolutional neural network (DVE-CNN) model" (Abstract).). The combination
is made for the reasons given for claim 1, mutatis mutandis.
Claim 13.
Kim discloses an analysis device for calculating dementia information, the analysis device comprising:an interface device that receives two-dimensional magnetic resonance imaging (2D MRI) slices of a subject (KIM: "the communication unit 180 receives the brain MRI image
of the subject from the user terminal" (¶ 53).);
a storage device configured to store a segmentation model that extracts a region of interest (ROI) from the 2D MRI slice, a (KIM: the semantic-segmentation processing (¶ 45), the per-region capacity/volume measurement of measurement unit 140 (¶ 48), and the deep learning model of prediction unit 160 that predicts dementia (¶ 49).); and
a calculation device configured to input the received 2D MRI slices into the segmentation model to extract ROIs, input pixel information of at least one first region of the extracted ROIs to the (KIM: the dementia prediction apparatus 100 includes the measurement unit 140 and the prediction unit 160 (¶ 41).), wherein the ROIs include at least one of frontal gray matter, temporal gray matter, parietal gray matter, occipital gray matter, lateral ventricle (LV), hippocampus, and extracerebral cerebrospinal fluid (KIM: "Right Lateral Ventricle, ... Right Hippocampus, and Left Hippocampus" (¶ 47).).
Kim measures the volume rather than predicting it by a stored first learning model. However, Basher teaches a learning model that predicts the volume (BASHER: the "discrete volume estimation convolutional neural network (DVE-CNN)" (Abstract).). As construed under 35 U.S.C. 112(f) above, the analysis device, interface device, storage device, and calculation device correspond to the computer device 600 and its components in FIG. 6; Kim's dementia prediction apparatus 100, implemented as a computer connected to a user terminal, likewise provides this structure. The combination is made for the reasons given for claim 1, mutatis mutandis.
Claims 4, 10, and 14.
Kim as modified by Basher and Rebsamen discloses the dementia information calculation method of claim 1, wherein the first learning model includes multiple learning models prepared in advance for each ROI. Kim segments and separately measures the volume and cortical thickness for each of several distinct brain regions (KIM: the measurement unit divides the image into six regions (Right/Left Lateral Ventricle, Right/Left Amygdala, Right/Left Hippocampus) (¶ 47) and measures the volume and cortical thickness for each region (¶ 48).), and Basher shows that a per-region learning model is instantiated separately for each region (BASHER: the discrete volume estimation network "has two models named left hippocampal model (LHM) and right hippocampal model" (RHM) (§ I).).
As the several regions have different properties, it would have been obvious to provide a respective first learning model prepared in advance for each ROI; this is a mere duplication of
the taught learning model that yields the predictable result of a per-region prediction (MPEP
2144.04 (VI)).
Claim 5 and 11.
Kim as modified by Basher and Rebsamen discloses wherein the second learning model receives at least one of a cortical thickness of frontal gray matter, a cortical thickness of temporal gray matter, a cortical thickness of parietal gray matter, and a cortical thickness of occipital gray matter and receives at least one of a volume of the LV, a volume of the hippocampus, and a volume of the extracerebral cerebrospinal fluid to output the dementia information about the subject (KIM: the deep learning model predicts dementia from the per-region brain capacity (¶ 49). REBSAMEN: the CNN predicts "mean thicknesses ... of cortical parcellations" (Abstract), supplying the gray-matter cortical-thickness input.). The combination is made for the reasons given for claim 1, mutatis mutandis.
Claims 6 and 12.
Kim as modified by Basher and Rebsamen discloses wherein the second learning model further receives at least one information of the age, gender, and APOE4 genotype of the subject (KIM: the deep learning model is "a model generated by learning characteristics of capacity, volume, and thickness of brain cortex according to age" (¶ 44). This teaches age used by the dementia-output model.). Providing this clinical information to the second learning model would have been obvious to improve dementia classification accuracy.
Claim 16.
Kim as modified by Basher and Rebsamen discloses wherein the storage device further stores a third learning model that receives the ROI information to predict a cortical thickness, and the calculation device inputs pixel information of at least one second region of the extracted ROIs to the third learning model to predict a cortical thickness of the at least one second region, and further inputs the cortical thickness of the at least one second region to the second learning model to output the dementia information about the subject (REBSAMEN: the CNN predicts "mean thicknesses ... of cortical parcellations directly from Tl-weighted MRI" (Abstract). This teaches a further learning model predicting a cortical thickness of a gray-matter region.). Providing a further such model for a second (gray-matter) region is an obvious duplication of the taught thickness prediction model. The combination is made for the reasons given for claim 1, mutatis mutandis.
Claim 17.
Kim as modified by Basher and Rebsamen discloses wherein the at least one second region includes at least one of frontal gray matter, temporal gray matter, parietal gray matter, and occipital gray matter (REBSAMEN: the CNN predicts "mean thicknesses ... of cortical parcellations directly from Tl-weighted MRI" (Abstract). Where, the cortex is gray matter. DK atlas … resulting in 34 ROIs (§ 2.1.2) i.e. the cortical gray matter regions that subdivide the frontal/temporal/parietal/occipital lobes. “Age-related Cortial Gray Matter” (Abstract/§2.5)).
Claim 18.
Kim as modified by Basher and Rebsamen discloses wherein the calculation device further inputs at least one information of age, gender, and APOE4 genotype of the subject to the second learning model to output the dementia information about the subject (KIM: the deep learning model learns brain characteristics "according to age" (¶ 44).).
Claims 2, 3, 8, and 9 are rejected under 35 U.S.C. 103 as being unpatentable over Kim as modified by Basher and Rebsamen, and further in view of Seong Jun Kyeong et al., KR 20220008233 A (hereinafter "Seong").
Claims 2 and 8.
Kim as modified by Basher and Rebsamen discloses wherein the first learning models receives the summed number of pixels of the ROIs and clinical information about the subject to predict the cortical thickness and the volume (KIM: the measurement unit "calculates the number of pixels of an object in each area to measure the brain capacity for each area" (¶ 46). This teaches the summed ROI pixels that are used as the model input.), and the clinical information includes at least one of age, gender, and APOE4 genotype of the subject.
Basher and Rebsamen do not expressly teach that the first learning model further receives clinical information including at least one of age, gender, and APOE4 genotype. However, Seong teaches inputting such clinical information to the learning model (SEONG: the learning model receives biological information that "includes a gender, an age, and a cerebral size" (Claim 2). This teaches clinical information including age and gender input to the model.).
It would have been obvious to provide Seong's clinical information to the first learning model of the combination to improve the accuracy of the morphometric prediction, a predictable use of a known input.
Claims 3 and 9.
Kim as modified by Basher, Rebsamen, and Seong discloses dementia information calculation method of claim 1, wherein the first learning models further receive a brain size calculated from the 2D MRI slices to predict the cortical thickness and the volume (SEONG: the biological information input to the learning model "includes a gender, an age, and a cerebral size" (Claim 2). This teaches a brain-size input to the model.).
It would have been obvious to provide a brain size calculated from the 2D MRI slices to the first learning model of the combination, as brain size is known to influence regional volume and cortical thickness.
Allowable Subject Matter
Claim 15 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims. Addanki, US 2022/0254490 A1 (hereinafter “Addanki”) teaches that the cerebrospinal fluid volume is a per-region brain morphometric feature obtained from the brain image and processed by a learning model (ADDANKI: the extracted features include "cerebrospinal fluid (CSF) volume of the brain tissue" and "a total volume for GM, CSF, and WM for each region of interest in the brain tissue"(¶ 28), the features being processed by a machine learning model comprising "a convolutional neural network (CNN)" (¶ 21).). However, "extracerebral cerebrospinal fluid" is the cerebrospinal fluid outside the brain parenchyma and outside the ventricles (the sulcal/subarachnoid compartment), as distinct from Addanki 's computation of a total cerebrospinal fluid volume "for each region of interest" (¶ 28), which does not teach the extracerebral cerebrospinal fluid.
Conclusion
The prior art made of record but not relied, yet considered pertinent to the applicant’s disclosure, and are made or record: US 2020/0027557 A1 (Karow et al.; Human Longevity, Inc.) (extracting per-region volume, cortical thickness, and hippocampal volume from brain MRI and combining them with genetic features, including APOE genotype, using a long short-term memory neural network to predict dementia risk); WO 2020/033566 A1 (Human Longevity) (neural networks quantifying brain-region volume, surface area, and thickness); and WO 2016/205811 A1 (Zahid/Rusinek et al.) (segmenting the intracranial space in a brain CT image and separating the cerebrospinal fluid volume from the brain tissue to assess brain atrophy).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Ross Varndell whose telephone number is (571)270-1922. The examiner can normally be reached M-F, 9-5 EST.
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, O’Neal Mistry can be reached at (313)446-4912. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Ross Varndell/Primary Examiner, Art Unit 2674
Prosecution Insights