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 .
Priority
Receipt is acknowledged of certified copies of papers submitted under 35 U.S.C. 119(a)-(d), which papers have been placed of record in the file.
Terminal Disclaimer
The terminal disclaimer filed on 08/06/2026 disclaiming the terminal portion of any patent granted on this application which would extend beyond the expiration date of Patent of co-pending application #18817161 has been reviewed and is accepted. The terminal disclaimer has been recorded.
Response to Amendment
Applicant’s remarks, filed 08/06/2026, regarding the objections made to the claims and the 112(b) rejections submitted in the non-final office action dated 05/21/2026 are withdrawn due to the amendments made to the claims. It is also noted that additional claim objections have been made to the claims and some claim objections have not been obviated, as noted in the claim objections section of this office action.
Response to Arguments
Applicant’s arguments see remarks, filed 08/06/2026, with respect to the claims 1-12 have been fully considered but are moot because the arguments do not apply to the current combinations of references being used in the current rejection.
Claim Objections
Claims 1 and 7-12 are objected to because of the following informalities:
In claim 1, line 9, the term “the second region is the other of” should be changed to “the second region is in order to provide clarity to the claims and avoid an insufficient antecedent issue and prevent a rejection under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph issues.
In claim 7, line 9, the term “the second region is the other of” should be changed to “the second region is in order to provide clarity to the claims and avoid an insufficient antecedent issue and prevent a rejection under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph issues.
In claim 8, line 6, the term “the second region is the other of” should be changed to “the second region is in order to provide clarity to the claims and avoid an insufficient antecedent issue and prevent a rejection under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph issues.
In claim 9, line 7, the term “the second region is the other of” should be changed to “the second region is in order to provide clarity to the claims and avoid an insufficient antecedent issue and prevent a rejection under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph issues.
In claim 10, line 7, the term “the second region is the other of” should be changed to “the second region is in order to provide clarity to the claims and avoid an insufficient antecedent issue and prevent a rejection under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph issues.
In claim 11, line 1-3, the term “a non-transitory computer-readable storage medium that stores a learning program executable by a computer to perform a process comprising:” should be changed to “a non-transitory computer-readable storage medium that stores a learning program executable by a computer configured to perform a process comprising:” in order to ensure the computer is carrying out the function of the program and avoid a grammatical issue.
In claim 11, line 9, the term “the second region is the other of” should be changed to “the second region is in order to provide clarity to the claims and avoid an insufficient antecedent issue and prevent a rejection under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph issues.
In claim 12, line 1-3, the term “a non-transitory computer-readable storage medium that stores a learning program executable by a computer to perform a process comprising:” should be changed to “a non-transitory computer-readable storage medium that stores a learning program executable by a computer configured to perform a process comprising:” in order to ensure the computer is carrying out the function of the program and avoid a grammatical issue.
In claim 12, line 9, the term “the second region is the other of” should be changed to “the second region is in order to provide clarity to the claims and avoid an insufficient antecedent issue and prevent a rejection under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph issues.
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, 4-5, and 7-12, are rejected under 35 U.S.C. 103 as being unpatentable over AKAHORI (US 20200104996 A1), hereinafter referenced as AKAHORI, in view of KIM et al. (US 10898152 B1), hereinafter referenced as KIM.
Regarding claim 1, AKAHORI explicitly teaches an information processing apparatus comprising (Fig. 2, #1 called disease region discrimination apparatus. Paragraph [0047]):
at least one processor (Fig. 1. Paragraph [0095]-AKAHORI discloses the various processors include a CPU which is a general-purpose processor executing software (program) to function as various processing units as described above, a programmable logic device (PLD), such as a field programmable gate array (FPGA), which is a processor whose circuit configuration can be changed after manufacture, and a dedicated electric circuit, such as an application specific integrated circuit (ASIC), which is a processor having a dedicated circuit configuration designed to perform a specific process.),
wherein the at least one processor is configured to (Fig. 1. Paragraph [0095]-AKAHORI discloses the various processors include a CPU which is a general-purpose processor executing software (program) to function as various processing units as described above, a programmable logic device (PLD), such as a field programmable gate array (FPGA), which is a processor whose circuit configuration can be changed after manufacture, and a dedicated electric circuit, such as an application specific integrated circuit (ASIC), which is a processor having a dedicated circuit configuration designed to perform a specific process.):
acquire a non-contrast Computed Tomography (CT) image of a head of a patient (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below. Further in paragraph [0094]-AKAHORI discloses the non-contrast-enhanced CT images are used as the CT images B0, Bt1, and Bi1.) and first information representing a first region (Figs. 4 and 12, illustrate first information (i.e. a CT image). Paragraph [0052]),
wherein the first region is any one of an infarction region (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below.) or a large vessel occlusion region in the non-contrast CT image (Fig. 3 and 12. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires the CT image B0, from which disease regions are to be extracted, from the image storage server 3 in order to extract the disease regions such as a thrombus region and an infarction region (wherein a thrombus region is a large vessel occlusion region). Further in paragraph [0071]- AKAHORI discloses in the CT image Bt1 illustrated in FIG. 12, a region represented by an arrow indicates middle cerebral artery trunk occlusion. Further in paragraph [0094]-AKAHORI discloses the non-contrast-enhanced CT images are used as the CT images B0, Bt1, and Bi1.) and derive second information representing a second region (Fig. 5. Paragraph [0060]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the second information is result R2).),
the first information (Figs. 4 and 12, illustrate first information (i.e. a CT image). Paragraph [0052]) by using a discriminative model (Fig. 2, #23 called discriminator. Paragraph [0054]-AKAHORI discloses the discriminator 23 discriminates a disease region in the CT image B0 of the brain. In this embodiment, the thrombus region and the infarction region are used as the disease regions. In this embodiment, it is assumed that the discriminator 23 includes a plurality of convolutional neural networks (hereinafter, referred to as CNNs) which are one of multi-layer neural networks that have a plurality of processing layers hierarchically connected to each other and are subjected to deep learning.) that has been trained to output the second information (Fig. 5. Paragraph [0060]-AKAHORI discloses the discrimination result R2 of the infarction region for each pixel of the CT image B0 is output from the output layer 33b of the third CNN 33.) in response to receiving the non-contrast CT image and the first information as inputs (Fig. 5. Paragraph [0050]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the training data is input into the model).).
AKAHORI fails to explicitly teach wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image based on the non-contrast CT image and.
However, KIM explicitly teach wherein the second region is the other of the infarction region (Fig. 4. Col. 12, Line [13-17]-KIM discloses the ischemia classifier 41 according to the present disclosure may independently perform determining whether there is an affected part in each divided region and classifying the shape in relation to Old infarct (0I)/Recent infarct (RI)/Frank hypodensity (FH)/Early ischemic sign (EIS) (wherein the classification of a region is the first information).) or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image based on the non-contrast CT image (Fig. 4. Col. 14, Line [42-49]-KIM discloses when it is determined that a non-hemorrhage patient has ischemia (S70), the large vessel occlusion determiner 43 determines whether the patient has large vessel occlusion (S90). Whether the large vessel occlusion has been generated in the step (S90) may be determined on the basis of whether a dense MCA sign has been detected at an infra-ganglionic level (wherein the second region is the large vessel occlusion generated, which is not the first information.).) and.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of AKAHORI of an information processing apparatus comprising: at least one processor, wherein the at least one processor is configured to: acquire a non-contrast Computed Tomography (CT) image of a head of a patient and first information representing a first region, with the teachings of KIM of wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image based on the non-contrast CT image and.
Wherein having AKAHORI’s infarction region identification apparatus having wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image based on the non-contrast CT image and.
The motivation behind the modification would have been to obtain an infarction region identification apparatus that enhances the accuracy of identifying and detecting infarction regions in CT images. Since both AKAHORI and KIM relate to analyzing brain CT scans to identify infarction and large vessel occlusion, wherein AKAHORI is to provide a technique that discriminates a disease region with high accuracy, using a limited amount of data, even in an image in which it is difficult to prepare a large amount of data indicating a correct disease region, while KIM may reduce scoring variability when estimating an ASPECT score on the basis of an image processing and deep learning technology. Please see AKAHORI (US 20200104996 A1), Paragraph [0006], and KIM et al. (US 10898152 B1), Col. 3, Line [34-37].
Regarding claim 4, AKAHORI in view of KIM explicitly teach the information processing apparatus according to claim 1,
AKAHORI further explicitly teaches wherein the at least one processor is configured to derive the second information (Fig. 5. Paragraph [0060]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the second information is result R2).) further based on at least one of information representing an anatomical region of a brain (Fig. 12. Paragraph [0071]-AKAHORI discloses the learning unit 22-2 trains a discriminator 23-2 which discriminates an anatomic part of thrombus in the input CT image B0, using the correct information of an anatomic part of thrombus specified in the CT image Bt1 as training data (wherein the anatomic part is the anatomical region of the brain).) or clinical information (Fig. 5. Paragraph [0060]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the CT image is clinical information).).
Regarding claim 5, AKAHORI in view of KIM explicitly teach the information processing apparatus according to claim 1,
AKAHORI further explicitly teaches wherein the at least one processor is configured to acquire the first information by extracting any one of the infarction region or the large vessel occlusion region from the non-contrast CT image (Fig. 2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires the CT image B0, from which disease regions are to be extracted, from the image storage server 3 in order to extract the disease regions such as a thrombus region and an infarction region (wherein the thrombus region is the large vessel occlusion region).).
Regarding claim 7, AKAHORI explicitly teaches a learning device comprising (Fig. 2, #1 called disease region discrimination apparatus. Paragraph [0047]):
at least one processor (Fig. 1. Paragraph [0095]-AKAHORI discloses the various processors include a CPU which is a general-purpose processor executing software (program) to function as various processing units as described above, a programmable logic device (PLD), such as a field programmable gate array (FPGA), which is a processor whose circuit configuration can be changed after manufacture, and a dedicated electric circuit, such as an application specific integrated circuit (ASIC), which is a processor having a dedicated circuit configuration designed to perform a specific process.),
wherein the at least one processor is configured to (Fig. 1. Paragraph [0095]-AKAHORI discloses the various processors include a CPU which is a general-purpose processor executing software (program) to function as various processing units as described above, a programmable logic device (PLD), such as a field programmable gate array (FPGA), which is a processor whose circuit configuration can be changed after manufacture, and a dedicated electric circuit, such as an application specific integrated circuit (ASIC), which is a processor having a dedicated circuit configuration designed to perform a specific process.):
acquire training data including input data consisting of a non-contrast Computed Tomography (CT) image of a head of a patient with cerebral infarction (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below.) and first information (Figs. 4 and 12, illustrate first information (i.e. a CT image). Paragraph [0052]) representing a first region (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below.),
wherein the first region is any one of an infarction region (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below.) or a large vessel occlusion region in the non-contrast CT image (Fig. 3 and 12. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires the CT image B0, from which disease regions are to be extracted, from the image storage server 3 in order to extract the disease regions such as a thrombus region and an infarction region (wherein a thrombus region is a large vessel occlusion region). Further in paragraph [0071]- AKAHORI discloses in the CT image Bt1 illustrated in FIG. 12, a region represented by an arrow indicates middle cerebral artery trunk occlusion. Further in paragraph [0094]-AKAHORI discloses the non-contrast-enhanced CT images are used as the CT images B0, Bt1, and Bi1.), and correct answer data consisting of second information representing a second region (Fig. 5 and 8. Paragraph [0079]-AKAHORI discloses the first CNN 31 is trained using not only data indicating a correct thrombus region and data indicating a correct infarction region but also data indicating the correct information of an anatomic part of thrombus and data of information indicating whether or not an infarction region is present (wherein a thrombus region is a large vessel occlusion region).),
train a neural network through machine learning using the training data to construct a discriminative model (Fig. 2, #23 called discriminator. Paragraph [0053]-AKAHORI discloses the learning unit 22 trains the discriminator 23 that discriminate the infarction region in the input CT image B0, using the data set of the CT image Bi1 and the infarction region A2 specified in the CT image Bi1 as training data, as illustrated in FIG. 4. Further in paragraph [0054]-AKAHORI discloses the discriminator 23 discriminates a disease region in the CT image B0 of the brain. In this embodiment, the thrombus region and the infarction region are used as the disease regions. In this embodiment, it is assumed that the discriminator 23 includes a plurality of convolutional neural networks (hereinafter, referred to as CNNs) which are one of multi-layer neural networks that have a plurality of processing layers hierarchically connected to each other and are subjected to deep learning.) that outputs the second information (Fig. 5. Paragraph [0060]-AKAHORI discloses the discrimination result R2 of the infarction region for each pixel of the CT image B0 is output from the output layer 33b of the third CNN 33 (wherein the infarction region is second information).) in response to receiving the non-contrast CT image (Fig. 5. Paragraph [0050]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the training data is input into the model).) and the first information as inputs (Fig. 5. Paragraph [0050]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the training data is input into the model).).
AKAHORI fails to explicitly teach wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image; and.
However, KIM explicitly teaches wherein the second region is the other of the infarction region (Fig. 4. Col. 12, Line [13-17]-KIM discloses the ischemia classifier 41 according to the present disclosure may independently perform determining whether there is an affected part in each divided region and classifying the shape in relation to Old infarct (0I)/Recent infarct (RI)/Frank hypodensity (FH)/Early ischemic sign (EIS) (wherein the classification of a region is the first information).) or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image (Fig. 4. Col. 14, Line [42-49]-KIM discloses when it is determined that a non-hemorrhage patient has ischemia (S70), the large vessel occlusion determiner 43 determines whether the patient has large vessel occlusion (S90). Whether the large vessel occlusion has been generated in the step (S90) may be determined on the basis of whether a dense MCA sign has been detected at an infra-ganglionic level (wherein the second region is the large vessel occlusion generated, which is not the first information.).); and
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of AKAHORI of a learning device comprising: at least one processor, wherein the at least one processor is configured to: acquire training data including input data consisting of a non- contrast Computed Tomography (CT) image of a head of a patient with cerebral infarction and first information representing a first region, with the teachings of KIM of wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image; and.
Wherein having AKAHORI’s infarction region identification apparatus having wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image; and.
The motivation behind the modification would have been to obtain an infarction region identification apparatus that enhances the accuracy of identifying and detecting infarction regions in CT images. Since both AKAHORI and KIM relate to analyzing brain CT scans to identify infarction and large vessel occlusion, wherein AKAHORI is to provide a technique that discriminates a disease region with high accuracy, using a limited amount of data, even in an image in which it is difficult to prepare a large amount of data indicating a correct disease region, while KIM may reduce scoring variability when estimating an ASPECT score on the basis of an image processing and deep learning technology. Please see AKAHORI (US 20200104996 A1), Paragraph [0006], and KIM et al. (US 10898152 B1), Col. 3, Line [34-37].
Regarding claim 8, AKAHORI explicitly teaches a discriminative model that, in response to receiving a non-contrast Computed Tomography (CT) image of a head of a patient (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below. Further in paragraph [0094]-AKAHORI discloses the non-contrast-enhanced CT images are used as the CT images B0, Bt1, and Bi1.) and first information representing a first region (Figs. 4 and 12, illustrate first information (i.e. a CT image). Paragraph [0052]),
wherein the first region is any one of an infarction region (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below.) or a large vessel occlusion region in the non-contrast CT image as inputs (Fig. 3 and 12. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires the CT image B0, from which disease regions are to be extracted, from the image storage server 3 in order to extract the disease regions such as a thrombus region and an infarction region (wherein a thrombus region is a large vessel occlusion region). Further in paragraph [0071]- AKAHORI discloses in the CT image Bt1 illustrated in FIG. 12, a region represented by an arrow indicates middle cerebral artery trunk occlusion. Further in paragraph [0094]-AKAHORI discloses the non-contrast-enhanced CT images are used as the CT images B0, Bt1, and Bi1.), outputs second information representing a second region (Fig. 5. Paragraph [0060]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the second information is a discrimination result).),
AKAHORI fails to explicitly teach wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image.
However, KIM explicitly teaches wherein the second region is the other of the infarction region (Fig. 4. Col. 12, Line [13-17]-KIM discloses the ischemia classifier 41 according to the present disclosure may independently perform determining whether there is an affected part in each divided region and classifying the shape in relation to Old infarct (0I)/Recent infarct (RI)/Frank hypodensity (FH)/Early ischemic sign (EIS) (wherein the classification of a region is the first information).) or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image (Fig. 4. Col. 14, Line [42-49]-KIM discloses when it is determined that a non-hemorrhage patient has ischemia (S70), the large vessel occlusion determiner 43 determines whether the patient has large vessel occlusion (S90). Whether the large vessel occlusion has been generated in the step (S90) may be determined on the basis of whether a dense MCA sign has been detected at an infra-ganglionic level (wherein the second region is the large vessel occlusion generated, which is not the first information.).).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of AKAHORI of a discriminative model that, in response to receiving a non-contrast Computed Tomography (CT) image of a head of a patient and first information representing a first region with the teachings of KIM of wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image.
Wherein having AKAHORI’s infarction region identification apparatus having wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image.
The motivation behind the modification would have been to obtain an infarction region identification apparatus that enhances the accuracy of identifying and detecting infarction regions in CT images. Since both AKAHORI and KIM relate to analyzing brain CT scans to identify infarction and large vessel occlusion, wherein AKAHORI is to provide a technique that discriminates a disease region with high accuracy, using a limited amount of data, even in an image in which it is difficult to prepare a large amount of data indicating a correct disease region, while KIM may reduce scoring variability when estimating an ASPECT score on the basis of an image processing and deep learning technology. Please see AKAHORI (US 20200104996 A1), Paragraph [0006], and KIM et al. (US 10898152 B1), Col. 3, Line [34-37].
Regarding claim 9, AKAHORI explicitly teaches an information processing method comprising (Fig. 2, #1 called disease region discrimination apparatus. Paragraph [0047]):
acquiring a non-contrast Computed Tomography (CT) image of a head of a patient (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below. Further in paragraph [0094]-AKAHORI discloses the non-contrast-enhanced CT images are used as the CT images B0, Bt1, and Bi1.) and first information (Figs. 4 and 12, illustrate first information (i.e. a CT image). Paragraph [0052]) representing a first region,
wherein the first region is any one of an infarction region (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below.) or a large vessel occlusion region in the non-contrast CT image (Fig. 3 and 12. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires the CT image B0, from which disease regions are to be extracted, from the image storage server 3 in order to extract the disease regions such as a thrombus region and an infarction region (wherein a thrombus region is a large vessel occlusion region). Further in paragraph [0071]- AKAHORI discloses in the CT image Bt1 illustrated in FIG. 12, a region represented by an arrow indicates middle cerebral artery trunk occlusion. Further in paragraph [0094]-AKAHORI discloses the non-contrast-enhanced CT images are used as the CT images B0, Bt1, and Bi1.); and
deriving second information representing a second region (Fig. 5. Paragraph [0060]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the second information is result R2).),
the first information (Figs. 4 and 12, illustrate first information (i.e. a CT image). Paragraph [0052]) by using a discriminative model (Fig. 2, #23 called discriminator. Paragraph [0054]-AKAHORI discloses the discriminator 23 discriminates a disease region in the CT image B0 of the brain. In this embodiment, the thrombus region and the infarction region are used as the disease regions. In this embodiment, it is assumed that the discriminator 23 includes a plurality of convolutional neural networks (hereinafter, referred to as CNNs) which are one of multi-layer neural networks that have a plurality of processing layers hierarchically connected to each other and are subjected to deep learning.) that has been trained to output the second information (Fig. 5. Paragraph [0060]-AKAHORI discloses the discrimination result R2 of the infarction region for each pixel of the CT image B0 is output from the output layer 33b of the third CNN 33.) in response to receiving the non-contrast CT image and the first information as inputs (Fig. 5. Paragraph [0050]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the training data is input into the model).).
AKAHORI fails to explicitly teach wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image based on the non- contrast CT image and.
However, KIM explicitly teaches wherein the second region is the other of the infarction region (Fig. 4. Col. 12, Line [13-17]-KIM discloses the ischemia classifier 41 according to the present disclosure may independently perform determining whether there is an affected part in each divided region and classifying the shape in relation to Old infarct (0I)/Recent infarct (RI)/Frank hypodensity (FH)/Early ischemic sign (EIS) (wherein the classification of a region is the first information).) or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image based on the non- contrast CT image (Fig. 4. Col. 14, Line [42-49]-KIM discloses when it is determined that a non-hemorrhage patient has ischemia (S70), the large vessel occlusion determiner 43 determines whether the patient has large vessel occlusion (S90). Whether the large vessel occlusion has been generated in the step (S90) may be determined on the basis of whether a dense MCA sign has been detected at an infra-ganglionic level (wherein the second region is the large vessel occlusion generated, which is not the first information.).) and.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of AKAHORI of an information processing method comprising: acquiring a non-contrast Computed Tomography (CT) image of a head of a patient and first information representing a first region with the teachings of KIM of wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image based on the non- contrast CT image and.
Wherein having AKAHORI’s infarction region identification apparatus having wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image based on the non- contrast CT image and.
The motivation behind the modification would have been to obtain an infarction region identification apparatus that enhances the accuracy of identifying and detecting infarction regions in CT images. Since both AKAHORI and KIM relate to analyzing brain CT scans to identify infarction and large vessel occlusion, wherein AKAHORI is to provide a technique that discriminates a disease region with high accuracy, using a limited amount of data, even in an image in which it is difficult to prepare a large amount of data indicating a correct disease region, while KIM may reduce scoring variability when estimating an ASPECT score on the basis of an image processing and deep learning technology. Please see AKAHORI (US 20200104996 A1), Paragraph [0006], and KIM et al. (US 10898152 B1), Col. 3, Line [34-37].
Regarding claim 10, AKAHORI explicitly teaches a learning method comprising (Fig. 2, #1 called disease region discrimination apparatus. Paragraph [0047]):
acquiring training data including input data consisting of a non-contrast Computed Tomography (CT) image of a head of a patient with cerebral infarction (Fig. 5. Paragraph [0050]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the training data consisting of CT images is input into the mode).) and first information (Figs. 4 and 12, illustrate first information (i.e. a CT image). Paragraph [0052]) representing a first region (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below.),
wherein the first region is any one of an infarction region (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below.) or a large vessel occlusion region in the non-contrast CT image (Fig. 5. Paragraph [0059]-AKAHORI discloses the first CNN 31 and the second CNN 32 are trained, using a data set of a plurality of CT images of the brain including a thrombus region and the thrombus region specified in the CT images as training data, so as to output a discrimination result R1 of the thrombus region for each pixel included in the input CT image (wherein a thrombus region is a large vessel occlusion region).), and
correct answer data consisting of second information representing a second region (Fig. 5 and 8. Paragraph [0079]-AKAHORI discloses the first CNN 31 is trained using not only data indicating a correct thrombus region and data indicating a correct infarction region but also data indicating the correct information of an anatomic part of thrombus and data of information indicating whether or not an infarction region is present (wherein a thrombus region is a large vessel occlusion region and is a second region).),
training a neural network through machine learning using the training data to construct a discriminative model (Fig. 2, #23 called discriminator. Paragraph [0053]-AKAHORI discloses the learning unit 22 trains the discriminator 23 that discriminate the infarction region in the input CT image B0, using the data set of the CT image Bi1 and the infarction region A2 specified in the CT image Bi1 as training data, as illustrated in FIG. 4. Further in paragraph [0054]-AKAHORI discloses the discriminator 23 discriminates a disease region in the CT image B0 of the brain. In this embodiment, the thrombus region and the infarction region are used as the disease regions. In this embodiment, it is assumed that the discriminator 23 includes a plurality of convolutional neural networks (hereinafter, referred to as CNNs) which are one of multi-layer neural networks that have a plurality of processing layers hierarchically connected to each other and are subjected to deep learning.) that outputs the second information (Fig. 5. Paragraph [0060]-AKAHORI discloses the discrimination result R2 of the infarction region for each pixel of the CT image B0 is output from the output layer 33b of the third CNN 33 (wherein the infarction region is second information).) in response to receiving the non-contrast CT image (Fig. 5. Paragraph [0050]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the training CT images are input into the model).) and the first information as inputs (Fig. 5. Paragraph [0050]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the CT images are first information and wherein training data is input into the model).).
AKAHORI fails to explicitly teach wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image; and.
However, KIM explicitly teaches wherein the second region is the other of the infarction region (Fig. 4. Col. 12, Line [13-17]-KIM discloses the ischemia classifier 41 according to the present disclosure may independently perform determining whether there is an affected part in each divided region and classifying the shape in relation to Old infarct (0I)/Recent infarct (RI)/Frank hypodensity (FH)/Early ischemic sign (EIS) (wherein the classification of a region is the first information).) or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image based on the non-contrast CT image (Fig. 4. Col. 14, Line [42-49]-KIM discloses when it is determined that a non-hemorrhage patient has ischemia (S70), the large vessel occlusion determiner 43 determines whether the patient has large vessel occlusion (S90). Whether the large vessel occlusion has been generated in the step (S90) may be determined on the basis of whether a dense MCA sign has been detected at an infra-ganglionic level (wherein the second region is the large vessel occlusion generated, which is not the first information.).); and.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of AKAHORI of a learning method comprising: acquiring training data including input data consisting of a non-contrast Computed Tomography (CT) image of a head of a patient with cerebral infarction and first information representing a first region, with the teachings of KIM of wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image; and.
Wherein having AKAHORI’s infarction region identification apparatus having wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image; and.
The motivation behind the modification would have been to obtain an infarction region identification apparatus that enhances the accuracy of identifying and detecting infarction regions in CT images. Since both AKAHORI and KIM relate to analyzing brain CT scans to identify infarction and large vessel occlusion, wherein AKAHORI is to provide a technique that discriminates a disease region with high accuracy, using a limited amount of data, even in an image in which it is difficult to prepare a large amount of data indicating a correct disease region, while KIM may reduce scoring variability when estimating an ASPECT score on the basis of an image processing and deep learning technology. Please see AKAHORI (US 20200104996 A1), Paragraph [0006], and KIM et al. (US 10898152 B1), Col. 3, Line [34-37].
Regarding claim 11, AKAHORI explicitly teaches a non-transitory computer-readable storage medium that stores an information processing program executable by a computer to perform a process comprising (Fig. 1, #3 called image storage server. Paragraph [0045]-AKAHORI discloses the image storage server 3 is a computer that stores and manages various types of data and comprises a high-capacity external storage device and database management software. The image storage server 3 performs communication with other apparatuses through the wired or wireless network 4 to transmit and receive, for example, image data. Specifically, the image storage server 3 acquires various types of data including image data of the CT image generated by the three-dimensional imaging apparatus 2 through the network, stores the acquired data in a recording medium, such as a high-capacity external storage device, and manages the data. Further in paragraph [0013]-AKAHORI discloses a non-transitory computer readable medium for storing a program that causes a computer to perform the learning method.):
a procedure of acquiring a non-contrast Computed Tomography (CT) image of a head of a patient (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below. Further in paragraph [0094]-AKAHORI discloses the non-contrast-enhanced CT images are used as the CT images B0, Bt1, and Bi1.) and first information (Figs. 4 and 12, illustrate first information (i.e. a CT image). Paragraph [0052]) representing a first region (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below.),
wherein the first region is any one of an infarction region (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below.) or a large vessel occlusion region in the non- contrast CT image (Fig. 3 and 12. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires the CT image B0, from which disease regions are to be extracted, from the image storage server 3 in order to extract the disease regions such as a thrombus region and an infarction region (wherein a thrombus region is a large vessel occlusion region). Further in paragraph [0071]- AKAHORI discloses in the CT image Bt1 illustrated in FIG. 12, a region represented by an arrow indicates middle cerebral artery trunk occlusion. Further in paragraph [0094]-AKAHORI discloses the non-contrast-enhanced CT images are used as the CT images B0, Bt1, and Bi1.); and
a procedure of deriving second information representing a second region (Fig. 5. Paragraph [0060]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the third information is result R2).),
the first information (Fig. 5. Paragraph [0050]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the CT images are first information and wherein training data is input into the model).) by using a discriminative model (Fig. 2, #23 called discriminator. Paragraph [0053]-AKAHORI discloses the learning unit 22 trains the discriminator 23 that discriminate the infarction region in the input CT image B0, using the data set of the CT image Bi1 and the infarction region A2 specified in the CT image Bi1 as training data, as illustrated in FIG. 4. Further in paragraph [0054]-AKAHORI discloses the discriminator 23 discriminates a disease region in the CT image B0 of the brain. In this embodiment, the thrombus region and the infarction region are used as the disease regions. In this embodiment, it is assumed that the discriminator 23 includes a plurality of convolutional neural networks (hereinafter, referred to as CNNs) which are one of multi-layer neural networks that have a plurality of processing layers hierarchically connected to each other and are subjected to deep learning.) that has been trained to output the second information (Fig. 5. Paragraph [0060]-AKAHORI discloses the discrimination result R2 of the infarction region for each pixel of the CT image B0 is output from the output layer 33b of the third CNN 33 (wherein the infarction region is second information).) in response to receiving the non-contrast CT image (Fig. 5. Paragraph [0050]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the training data is input into the model).) and the first information as inputs (Fig. 5. Paragraph [0050]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the CT images are first information and wherein training data is input into the model).).
AKAHORI fails to explicitly teach wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image based on the non-contrast CT image and.
However, KIM explicitly teaches wherein the second region is the other of the infarction region (Fig. 4. Col. 12, Line [13-17]-KIM discloses the ischemia classifier 41 according to the present disclosure may independently perform determining whether there is an affected part in each divided region and classifying the shape in relation to Old infarct (0I)/Recent infarct (RI)/Frank hypodensity (FH)/Early ischemic sign (EIS) (wherein the classification of a region is the first information).) or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image based on the non-contrast CT image (Fig. 4. Col. 14, Line [42-49]-KIM discloses when it is determined that a non-hemorrhage patient has ischemia (S70), the large vessel occlusion determiner 43 determines whether the patient has large vessel occlusion (S90). Whether the large vessel occlusion has been generated in the step (S90) may be determined on the basis of whether a dense MCA sign has been detected at an infra-ganglionic level (wherein the second region is the large vessel occlusion generated, which is not the first information.).) and.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of AKAHORI of a non-transitory computer-readable storage medium that stores an information processing program executable by a computer to perform a process comprising: a procedure of acquiring a non-contrast Computed Tomography (CT) image of a head of a patient and first information representing a first region with the teachings of KIM of wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image based on the non-contrast CT image and.
Wherein having AKAHORI’s infarction region identification apparatus having wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image based on the non-contrast CT image and.
The motivation behind the modification would have been to obtain an infarction region identification apparatus that enhances the accuracy of identifying and detecting infarction regions in CT images. Since both AKAHORI and KIM relate to analyzing brain CT scans to identify infarction and large vessel occlusion, wherein AKAHORI is to provide a technique that discriminates a disease region with high accuracy, using a limited amount of data, even in an image in which it is difficult to prepare a large amount of data indicating a correct disease region, while KIM may reduce scoring variability when estimating an ASPECT score on the basis of an image processing and deep learning technology. Please see AKAHORI (US 20200104996 A1), Paragraph [0006], and KIM et al. (US 10898152 B1), Col. 3, Line [34-37].
Regarding claim 12, AKAHORI explicitly teaches a non-transitory computer-readable storage medium that stores an information processing program executable by a computer to perform a process comprising (Fig. 1, #3 called image storage server. Paragraph [0045]-AKAHORI discloses the image storage server 3 is a computer that stores and manages various types of data and comprises a high-capacity external storage device and database management software. The image storage server 3 performs communication with other apparatuses through the wired or wireless network 4 to transmit and receive, for example, image data. Specifically, the image storage server 3 acquires various types of data including image data of the CT image generated by the three-dimensional imaging apparatus 2 through the network, stores the acquired data in a recording medium, such as a high-capacity external storage device, and manages the data. Further in paragraph [0013]-AKAHORI discloses a non-transitory computer readable medium for storing a program that causes a computer to perform the learning method.):
a procedure of acquiring training data including input data consisting of a non- contrast Computed Tomography (CT) image of a head of a patient with cerebral infarction (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below.) and first information (Figs. 4 and 12, illustrate first information (i.e. a CT image). Paragraph [0052]) representing a first region (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below.),
wherein the first region is any one of an infarction region (Fig. 4, illustrates an infarction region #A2. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires a CT image Bt1 of the brain of the subject that has developed cerebral thrombosis and a CT image Bi1 of the brain of the subject that has developed cerebral infarction from the image storage server 3 in order to train the discriminator 23 which will be described below.) or a large vessel occlusion region in the non-contrast CT image (Fig. 3 and 12. Paragraph [0052]-AKAHORI discloses the image acquisition unit 21 acquires the CT image B0, from which disease regions are to be extracted, from the image storage server 3 in order to extract the disease regions such as a thrombus region and an infarction region (wherein a thrombus region is a large vessel occlusion region). Further in paragraph [0071]- AKAHORI discloses in the CT image Bt1 illustrated in FIG. 12, a region represented by an arrow indicates middle cerebral artery trunk occlusion. Further in paragraph [0094]-AKAHORI discloses the non-contrast-enhanced CT images are used as the CT images B0, Bt1, and Bi1.), and correct answer data consisting of second information representing a second region (Fig. 5 and 8. Paragraph [0079]-AKAHORI discloses the first CNN 31 is trained using not only data indicating a correct thrombus region and data indicating a correct infarction region but also data indicating the correct information of an anatomic part of thrombus and data of information indicating whether or not an infarction region is present (wherein a thrombus region is a large vessel occlusion region).),
a procedure of training a neural network through machine learning using the training data to construct a discriminative model (Fig. 2, #23 called discriminator. Paragraph [0053]-AKAHORI discloses the learning unit 22 trains the discriminator 23 that discriminate the infarction region in the input CT image B0, using the data set of the CT image Bi1 and the infarction region A2 specified in the CT image Bi1 as training data, as illustrated in FIG. 4. Further in paragraph [0054]-AKAHORI discloses the discriminator 23 discriminates a disease region in the CT image B0 of the brain. In this embodiment, the thrombus region and the infarction region are used as the disease regions. In this embodiment, it is assumed that the discriminator 23 includes a plurality of convolutional neural networks (hereinafter, referred to as CNNs) which are one of multi-layer neural networks that have a plurality of processing layers hierarchically connected to each other and are subjected to deep learning.) that outputs the second information (Fig. 5. Paragraph [0060]-AKAHORI discloses the discrimination result R2 of the infarction region for each pixel of the CT image B0 is output from the output layer 33b of the third CNN 33 (wherein the infarction region is second information).) in response to receiving the non-contrast CT image (Fig. 5. Paragraph [0050]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the training CT images are input into the model).) and the first information as inputs (Fig. 5. Paragraph [0050]-AKAHORI discloses the first CNN 31 and the third CNN 33 are trained, using a data set of a plurality of CT images of the brain including an infarction region and the infarction region specified in the CT images as training data, so as to output a discrimination result R2 of the infarction region for each pixel included in the input CT image (wherein the CT images are first information and wherein training data is input into the model).).
AKAHORI fails to explicitly teach wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image; and.
However, KIM explicitly teaches wherein the second region is the other of the infarction region (Fig. 4. Col. 12, Line [13-17]-KIM discloses the ischemia classifier 41 according to the present disclosure may independently perform determining whether there is an affected part in each divided region and classifying the shape in relation to Old infarct (0I)/Recent infarct (RI)/Frank hypodensity (FH)/Early ischemic sign (EIS) (wherein the classification of a region is the first information).) or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image based on the non-contrast CT image (Fig. 4. Col. 14, Line [42-49]-KIM discloses when it is determined that a non-hemorrhage patient has ischemia (S70), the large vessel occlusion determiner 43 determines whether the patient has large vessel occlusion (S90). Whether the large vessel occlusion has been generated in the step (S90) may be determined on the basis of whether a dense MCA sign has been detected at an infra-ganglionic level (wherein the second region is the large vessel occlusion generated, which is not the first information.).); and.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of AKAHORI of a non-transitory computer-readable storage medium that stores a learning program executable by a computer to perform a process comprising: a procedure of acquiring training data including input data consisting of a non- contrast Computed Tomography (CT) image of a head of a patient with cerebral infarction and first information representing a first region with the teachings of KIM of wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image; and.
Wherein having AKAHORI’s infarction region identification apparatus having wherein the second region is the other of the infarction region or the large vessel occlusion region that is not represented by the first information in the non-contrast CT image; and.
The motivation behind the modification would have been to obtain an infarction region identification apparatus that enhances the accuracy of identifying and detecting infarction regions in CT images. Since both AKAHORI and KIM relate to analyzing brain CT scans to identify infarction and large vessel occlusion, wherein AKAHORI is to provide a technique that discriminates a disease region with high accuracy, using a limited amount of data, even in an image in which it is difficult to prepare a large amount of data indicating a correct disease region, while KIM may reduce scoring variability when estimating an ASPECT score on the basis of an image processing and deep learning technology. Please see AKAHORI (US 20200104996 A1), Paragraph [0006], and KIM et al. (US 10898152 B1), Col. 3, Line [34-37].
Claims 2 and 6 are rejected under 35 U.S.C. 103 as being unpatentable over AKAHORI (US 20200104996 A1), hereinafter referenced as AKAHORI, in view of KIM et al. (US 10898152 B1), hereinafter referenced as KIM, and further in view of STRAKA et al. (US 20200359981 A1), hereinafter referenced as STRAKA.
Regarding claim 2, AKAHORI in view of KIM explicitly teach the information processing apparatus according to claim 1,
AKAHORI in view of KIM fail to explicitly teach wherein the at least one processor is configured to derive the second information further based on information on symmetrical regions with respect to a midline of a brain in at least the non-contrast CT image out of the non-contrast CT image and the first information.
However, STRAKA explicitly teaches wherein the at least one processor is configured to derive the second information further based on information on symmetrical regions with respect to a midline of a brain in at least the non-contrast CT image (Fig. 3, illustrates symmetrical regions with respect to the midline of the brain. Paragraph [0073]-STRAKA discloses the brain 304 can be divided into a number of regions with the regions of the first hemisphere 306 having a counterpart region in the second hemisphere 308. For example, the first hemisphere 306 can include a first region 314 and the second hemisphere 308 can have a first counterpart region 316 that corresponds to and is substantially symmetrically located with respect to the first region 314. In addition, the first hemisphere 306 can include a second region 318 and the second hemisphere 308 can include a second counterpart region 320 that corresponds to and is substantially symmetrically located with respect to the second region 318. Further, the first hemisphere 306 can include a third region 322 and the second hemisphere 308 can include a third counterpart region 324 that corresponds to and is substantially symmetrically locate with respect to the third region 322. Further in paragraph [0088]-STRAKA discloses at operation 502, the process 500 can include obtaining image data corresponding to one or more images indicating blood vessels located in a brain of an individual. The image data can be generated by an imaging device, such as a computed tomography (CT) imaging device.) out of the non-contrast CT image (Fig. 5. Paragraph [0088]-STRAKA discloses at operation 502, the process 500 can include obtaining image data corresponding to one or more images indicating blood vessels located in a brain of an individual. The image data can be generated by an imaging device, such as a computed tomography (CT) imaging device.) and the first information (Fig. 4. Paragraph [0085]-STRAKA discloses the possible LVO can be indicated on an image of the brain of the patient (wherein the LVO is first information).).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of AKAHORI in view of KIM of an information processing apparatus comprising: at least one processor, wherein the at least one processor is configured to: acquire a non-contrast Computed Tomography (CT) image of a head of a patient and first information representing a first region, with the teachings of STRAKA of wherein the at least one processor is configured to derive the second information further based on information on symmetrical regions with respect to a midline of a brain in at least the non-contrast CT image out of the non-contrast CT image and the first information.
Wherein having AKAHORI’s infarction region identification apparatus having wherein the at least one processor is configured to derive the second information further based on information on symmetrical regions with respect to a midline of a brain in at least the non-contrast CT image out of the non-contrast CT image and the first information.
The motivation behind the modification would have been to obtain an infarction region identification apparatus that enhances the accuracy of identifying and detecting infarction regions in CT images. Since both AKAHORI and STRAKA relate to analyzing brain CT scans to identify information in blood vessels, wherein AKAHORI is to provide a technique that discriminates a disease region with high accuracy, using a limited amount of data, even in an image in which it is difficult to prepare a large amount of data indicating a correct disease region, while STRAKA the treatment of individuals can be prioritized based on conditions indicated by the images. Please see AKAHORI (US 20200104996 A1), Paragraph [0006], and STRAKA et al. (US 20200359981 A1), Paragraph [0029].
Regarding claim 6, AKAHORI in view of KIM explicitly teach the information processing apparatus according to claim 1,
AKAHORI further explicitly teaches wherein the at least one processor is configured to (Fig. 1. Paragraph [0095]-AKAHORI discloses the various processors include a CPU which is a general-purpose processor executing software (program) to function as various processing units as described above, a programmable logic device (PLD), such as a field programmable gate array (FPGA), which is a processor whose circuit configuration can be changed after manufacture, and a dedicated electric circuit, such as an application specific integrated circuit (ASIC), which is a processor having a dedicated circuit configuration designed to perform a specific process.):
AKAHORI in view of KIM fail to explicitly teach derive quantitative information for at least one of the first information or the second information; and cause display of the quantitative information.
However, STRAKA explicitly teaches derive quantitative information for at least one of the first information or the second information (Fig. 6. Paragraph [0109]-STRAKA discloses the probabilities and/or severities related to abnormalities of blood vessels located in the brain of an individual can be displayed using different colors in the one or more images. For example, a first range of probabilities of an abnormality and/or levels of severity of an abnormality with respect to blood vessels included in a brain of an individual can be shown as a first color in the one or more images and a second range of probabilities of an abnormality and/or levels of severity of an abnormality with respect to blood vessels included in a brain of an individual can be shown as a second color in the one or more images (wherein the quantitative information is a range of probabilities of an abnormality and/or levels of severity of an abnormality). Further in paragraph [0109]-STRAKA discloses the one or more images can highlight locations within the brain of the individual where an occlusion may be located by displaying an arrow, circle, box, or other arbitrarily shaped outline (wherein the first information and second information are the highlighted locations where an occlusion may be located).); and
cause display of the quantitative information (Fig. 6. Paragraph [0109]-STRAKA discloses the probabilities and/or severities related to abnormalities of blood vessels located in the brain of an individual can be displayed using different colors in the one or more images. For example, a first range of probabilities of an abnormality and/or levels of severity of an abnormality with respect to blood vessels included in a brain of an individual can be shown as a first color in the one or more images and a second range of probabilities of an abnormality and/or levels of severity of an abnormality with respect to blood vessels included in a brain of an individual can be shown as a second color in the one or more images (wherein displays the quantitative information is displaying the probabilities/severities with different colors).).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of AKAHORI in view of KIM of an information processing apparatus comprising: at least one processor, wherein the at least one processor is configured to: acquire a non-contrast Computed Tomography (CT) image of a head of a patient and first information representing a first region, with the teachings of STRAKA of derive quantitative information for at least one of the first information or the second information; and cause display of the quantitative information.
Wherein having AKAHORI’s infarction region identification apparatus having derive quantitative information for at least one of the first information or the second information; and cause display of the quantitative information.
The motivation behind the modification would have been to obtain an infarction region identification apparatus that enhances the accuracy of identifying and detecting infarction regions in CT images. Since both AKAHORI and STRAKA relate to analyzing brain CT scans to identify information in blood vessels, wherein AKAHORI is to provide a technique that discriminates a disease region with high accuracy, using a limited amount of data, even in an image in which it is difficult to prepare a large amount of data indicating a correct disease region, while STRAKA the treatment of individuals can be prioritized based on conditions indicated by the images. Please see AKAHORI (US 20200104996 A1), Paragraph [0006], and STRAKA et al. (US 20200359981 A1), Paragraph [0029].
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over AKAHORI (US 20200104996 A1), hereinafter referenced as AKAHORI, in view of KIM et al. (US 10898152 B1), hereinafter referenced as KIM, and further in view of STRAKA et al. (US 20200359981 A1), hereinafter referenced as STRAKA, and further in view of SHIN et al. (US 20210098115 A1), hereinafter referenced as SHIN.
Regarding claim 3, AKAHORI in view of KIM and further in view of STRAKA explicitly teach the information processing apparatus according to claim 2,
AKAHORI in view of KIM and further in view of STRAKA fail to explicitly teach wherein the information on the symmetrical regions is inversion information obtained by inverting at least the non-contrast CT image out of the non-contrast CT image and the first information with respect to the midline of the brain.
However, SHIN explicitly teaches wherein the information on the symmetrical regions is inversion information obtained by inverting at least the non-contrast CT image (Fig. 1. Paragraph [0053]-SHIN discloses in the pre-processing step, the pre-processing unit 20 may perform a step of detecting a position of a skull in the brain CT image based on the image processing, an alignment step of aligning the image with respect to a rotation degree and a center point, and a horizontal inverting step in accordance with a lesion-side (wherein inversion information/information on the symmetrical regions is horizontal inversion in accordance with a lesion-side and wherein the brain CT is the non-contrast CT image).) out of the non-contrast CT image (Fig. 1. Paragraph [0053]-SHIN discloses in the pre-processing step, the pre-processing unit 20 may perform a step of detecting a position of a skull in the brain CT image based on the image processing, an alignment step of aligning the image with respect to a rotation degree and a center point, and a horizontal inverting step in accordance with a lesion-side (wherein the brain CT is the non-contrast CT image).) and the first information with respect to the midline of the brain (Fig. 1. Paragraph [0054]-SHIN discloses the pre-processed image is standardized as an image centered such that a left brain is a lesion and a center vertical line of the image is a symmetry line of the brain (wherein first information is the image).).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of AKAHORI in view KIM and further in view of STRAKA of an information processing apparatus comprising: at least one processor, wherein the at least one processor is configured to: acquire a non-contrast Computed Tomography (CT) image of a head of a patient and first information representing a first region, with the teachings of SHIN of wherein the information on the symmetrical regions is inversion information obtained by inverting at least the non-contrast CT image out of the non-contrast CT image and the first information with respect to the midline of the brain.
Wherein having AKAHORI’s infarction region identification apparatus wherein the information on the symmetrical regions is inversion information obtained by inverting at least the non-contrast CT image out of the non-contrast CT image and the first information with respect to the midline of the brain.
The motivation behind the modification would have been to obtain an infarction region identification apparatus that enhances the accuracy of identifying and detecting infarction regions in CT images. Since both AKAHORI and SHIN relate to analyzing brain CT scans of stroke patients, wherein AKAHORI is to provide a technique that discriminates a disease region with high accuracy, using a limited amount of data, even in an image in which it is difficult to prepare a large amount of data indicating a correct disease region, while SHIN the test method based on the CT has an advantage of being able to test quickly, so that it is considered as a test method suitable for a characteristic of the stroke disease for which prompt response is essential. Please see AKAHORI (US 20200104996 A1), Paragraph [0006], and SHIN et al. (US 20210098115 A1), Paragraph [0007].
Conclusion
Listed below are the prior arts made of record and not relied upon but are considered pertinent to applicant’s disclosure.
TAUBMANN et al. (US 20220395244 A1) – At least one example embodiment relates to a computer-implemented method for providing stroke information, the method comprising receiving computed tomography imaging data of an examination area of a patient, the examination area of the patient comprising a plurality of brain regions, at least one brain region of the plurality of brain regions being affected by a stroke, receiving brain atlas data, generating registered imaging data based on the computed tomography imaging data and the brain atlas data, the registered imaging data being registered to the brain atlas data, generating the stroke information regarding the stroke based on a set of algorithms and the registered imaging data, and providing the stroke information…Abstract, Fig. 4.
YANG (US 20190298291 A1) – A brain imaging system includes a first imaging device, a second imaging device, a third imaging device and a central processor. The first imaging device captures a first brain image, and calculates a cerebral blood flow, a cerebral blood volume, a cerebral blood mean transit time and a first contrast agent time to peak. The second imaging device captures a second brain image, and calculates the cerebral blood flow, the cerebral blood volume, the cerebral blood mean transit time and a second contrast agent time to peak. The central processor generates an image of a vessel occlusion, infarction or ischemia region respectively according to the vessel occlusion, infarction or ischemia regions in the first brain image and in the second brain image. The third imaging device obtains a brain atrophy region according to the cerebral cortex volume calculated by the third imaging device…Abstract, Fig. 2.
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 ETHAN N WOLFSON whose telephone number is (571)272-1898. The examiner can normally be reached Monday - Friday 8:00 am - 5:00 pm.
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, Chineyere Wills-Burns can be reached at (571) 272-9752. 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.
/ETHAN N WOLFSON/Examiner, Art Unit 2673
/CHINEYERE WILLS-BURNS/Supervisory Patent Examiner, Art Unit 2673
