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 .
DETAILED ACTION
This action is in response to the amendments filed 07 January 2026. Claims 1, 8, and 15 are amended. Claims 1-20 are pending and have been examined.
Response to Arguments
Applicant's arguments, see pages 7-12, filed 07 January 2026, with respect to the rejections of Claims 1-20 under 35 U.S.C. 101 have been fully considered but they are not persuasive.
APPLICANT'S ARGUMENT: Applicant argues (page 7, paragraph 5) that "The claimed invention is not directed to an abstract idea, but rather to a specific, technical solution to a technical problem in the field of deep learning neural networks for three-dimensional spatial-channel image classification."
Applicant argues (page 7, paragraph 5) that "The claims recite a specific process for training a convolutional neural network using color-channel images, and then using that trained network to classify groupings of spatial-channel images, which are formed in a particular way (e.g., using a sliding window, with overlapping groupings). This process is not a mental process, nor can it be performed practically in the human mind or with pen and paper. It requires a computer system, a neural network trained on color-channel images, and specialized grouping and feeding of spatial-channel images, as recited in the claims."
EXAMINER'S RESPONSE: Examiner respectfully disagrees. As currently recited, amended Claim 1 recites the mental process step of forming a plurality of images into a plurality of groupings of the images. The claim recites the additional element of feeding the formed groupings to a trained neural network, but the step of feeding appears to recite use of a computer or computing machinery merely to perform an existing process. In the absence of an additional element that integrates the mental process step into a practical application or provides significantly more, the claim is directed to the mental process and is ineligible.
APPLICANT'S ARGUMENT: Applicant argues (page 9, paragraph 1) that "the claims are directed to a specific improvement in the operation of deep learning neural networks: enabling a neural network trained on color-channel images to classify three-dimensional spatial-channel images, overcoming the technical limitations of insufficient three-dimensional training data and enabling defect detection in components using CT scan images."
Applicant argues (page 10, paragraph 1) that "These steps are specifically designed to solve the technical problem of insufficient three-dimensional training data and enable practical defect detection in components. The process is not routine or conventional, but rather provides a concrete improvement to the functioning of neural networks and image classification systems."
EXAMINER'S RESPONSE: Examiner notes that, as currently recited, amended Claim 1 does not recite three-dimensional spatial-channel images or CT scan images. Examiner also notes that amended Claim 1 does not recite an insufficiency in three dimensional training data, nor do the claims reflect such an insufficiency, which the specification does not appear to describe.
In the absence of an additional element that integrates the mental process step into a practical application, amended Claim 1 cannot be said to provide an improvement in the functioning of a computer, or an improvement to other technology or technical field. Therefore, the claim is directed to the recited abstract idea.
APPLICANT'S ARGUMENT: Applicant argues (page 11, paragraph 1) that : "These concrete limitations ... tie the claims to a specific machine-learning configuration and data-processing pipeline that cannot be performed in the human mind, and that is integrated into a practical application of classifying spatial-channel image groupings using the trained network."
EXAMINER'S RESPONSE: Examiner respectfully disagrees. As currently recited, the additional elements of amended Claim 1 do not appear to integrate the recited mental process step into a practical application or provide significantly more for the reasons given in the 35 U.S.C. 101 rejection below.
Applicant' s arguments, see pages 12-16, filed 07 January 2026, with respect to the rejections of Claims 1-20 under 35 U.S.C. 103 have been fully considered but they are not persuasive.
APPLICANT'S ARGUMENT: Applicant argues (page 14, paragraph 1) that "The problem is that the multidimensional images in this training set are not spatial-channel images. Not all multidimensional images are spatial-channel images. Multidimensional RGB images, like those in Sharma, are not spatial-channel images. Spatial-channel images are images where the channels represent spatial features versus color features. The claims have been amended to clarify this distinction."
EXAMINER'S RESPONSE: Examiner notes that amended Claim 1 is now rejected in view of Sharma in view of Hsiao.
Examiner disagrees that Sharma does not teach the spatial-channel images recited by amended Claim 1. Sharma teaches multidimensional images that comprise color channels and depth channels. The depth channels of Sharma's RGB-D images encode spatial information such as height and angle (see Sharma, [0042]: "the depth images 204 may be encoded with three distinct channels at each image pixel. These channels include horizontal disparity (H), height above ground (H), and the angle the pixel's local surface normal makes with the inferred gravity direction (A)"). Each of Sharma's depth channels
correspond to a single channel encoding a spatial feature other than color intensity.
APPLICANT'S ARGUMENT: Applicant argues (page 15, paragraph 1) that "The problem is that the present claims are starting with the spatial-channel images that are already two-dimensional, and then further grouping those two-dimensional images into groupings. Jin, on the other hand, is starting with a three-dimensional image and then the cited portion involves splitting the three-dimensional image into multiple two-dimensional images."
EXAMINER'S RESPONSE: Examiner notes that amended Claim 1 is now rejected in view of Sharma in view of Hsiao.
APPLICANT'S ARGUMENT: Applicant argues (page 15, paragraph 2) that "the claims have been amended to further clarify that at least one of the images is contained in multiple of the groupings - in other words the grouping involves not merely splitting a large group into smaller groups, but rather creating overlapping sets of images in the groups. That is not taught by any of the cited art."
EXAMINER'S RESPONSE: Examiner notes that amended Claim 1 is now rejected in view of Sharma in view of Hsiao. Hsiao is relied on to teach the feature of forming spatial-channel images into a plurality of groupings.
APPLICANT'S ARGUMENT: Applicant argues (page 15, paragraph 3) that "the present claims require that the convolutional neural network that the groupings of spatial-channel images are fed into be the same convolutional neural network that was trained using the color-channel images from earlier in the claims."
Applicant argues (page 15, paragraph 3) that "none of them teach using a color-channel-trained neural network to evaluate spatial-channel images, or even more broadly teach the concept of using a neural network trained using one type of image being used to evaluate a different type of image."
EXAMINER'S RESPONSE: Examiner notes that amended Claim 1 is now rejected in view of Sharma in view of Hsiao. In the rejection of amended Claim 1 below, Sharma is shown to teach use of a pre-trained CNN to construct a neural network comprising two CNNs (one depth CNN and one color CNN). As currently recited, amended Claim 1 does not appear to limit the convolutional neural network in such a way as to prevent Sharma's depth and color CNN from reading on the recited limitations.
Claim Objections
Claim 15 is objected to because of the following informalities: line 17 of the claim ("feeding the plurality of groupings into the trained convolutional neural network to make a") appears to be a typographic error. For the purposes of examination, line 17 of Claim 15 has been interpreted to have been deleted by redlining. Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding Claim 1
Step 1
Claim 1 recites a system, and thus the claimed machine falls within a statutory category of invention.
Step 2A Prong 1
The claim recites forming the plurality ... into a plurality of groupings ..., wherein each grouping contains a different combination of the plurality ..., and wherein at least one ... is contained in multiple groupings, which is a mental process, such as a judgment, when forming groupings is understood as a step of organization of images that can be undertaken in the mind or with the aid of pen and paper.
Thus, the claim recites an abstract idea.
Step 2A Prong 2
The additional element a first ... data source; a second ... data source; a computer system comprising at least one hardware processor and a non-transitory computer-readable medium storing instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element image data does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element accessing a plurality ... from the first ... data source amounts to insignificant extra-solution activity (see MPEP 2106.05(g), "mere data gathering"). The additional element a plurality of images ..., the plurality of images each having n number of color channels does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element training a convolutional neural network using the plurality ... and a plurality of labels, each label corresponding to a classification, the convolutional neural network comprising a convolutional layer, a nonlinearity layer, a pooling layer, a classification layer, and a loss layer invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element accessing a plurality ... from the second ... data source amounts to insignificant extra-solution activity (see MPEP 2106.05(g), "mere data gathering"). The additional element sequentially taken spatial-channel images ..., the plurality of sequentially taken spatial-channel images having a first order based upon when they were taken, wherein the spatial-channel images each have a single channel encoding a spatial feature other than intensity of a color does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element groupings of n spatial-channel images does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element feeding the plurality of groupings into the trained convolutional neural network, passing the plurality of groupings through each of the convolutional layer, a nonlinearity layer, a pooling layer, and a classification layer, to make a prediction of a classification for each of the plurality of groupings invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it").
Step 2B
The additional element a first ... data source; a second ... data source; a computer system comprising at least one hardware processor and a non-transitory computer-readable medium storing instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element image data does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element accessing a plurality ... from the first ... data source is well-understood, routine, conventional activity (see MPEP 2106.05(d), "receiving or transmitting data over a network"). The additional element a plurality of images ..., the plurality of images each having n number of color channels does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element training a convolutional neural network using the plurality ... and a plurality of labels, each label corresponding to a classification, the convolutional neural network comprising a convolutional layer, a nonlinearity layer, a pooling layer, a classification layer, and a loss layer invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element accessing a plurality ... from the second ... data source is well-understood, routine, conventional activity (see MPEP 2106.05(d), "receiving or transmitting data over a network"). The additional element sequentially taken spatial-channel images ..., the plurality of sequentially taken spatial-channel images having a first order based upon when they were taken, wherein the spatial-channel images each have a single channel encoding a spatial feature other than intensity of a color does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element groupings of n spatial-channel images does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element feeding the plurality of groupings into the trained convolutional neural network, passing the plurality of groupings through each of the convolutional layer, a nonlinearity layer, a pooling layer, and a classification layer, to make a prediction of a classification for each of the plurality of groupings invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 2
Step 1
Regarding Claim 2, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
The claim recites forming the plurality ... into a plurality of groupings ..., wherein each grouping contains a different combination of the plurality ..., and wherein at least one ... is contained in multiple groupings (as recited by Claim 1), wherein the forming the plurality ... into a plurality of groupings includes utilizing a sliding window method, such that each grouping contains an ordered group ... in an order that matches the first order, and wherein some of the plurality ... reappear in n different positions in n different groupings, which is a mental process.
Thus, the claim recites an abstract idea.
Step 2A Prong 2, Step 2B
The additional element sequentially taken spatial-channel images does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element groupings of n spatial-channel images does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 3
Step 1
Regarding Claim 3, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
Claim 3 recites the abstract ideas recited by parent Claim 1.
Step 2A Prong 2, Step 2B
The additional element wherein the second image data source is a computerized tomography (CT) scan machine does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element image data does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 4
Step 1
Regarding Claim 4, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
Claim 4 recites the abstract ideas recited by parent Claim 1.
Step 2A Prong 2, Step 2B
The additional element a first ... data source; a second ... data source (as recited by Claim 1), wherein ... the first ... data source are two-dimensional and wherein the second ... data source is a three-dimensional ... generator invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element images from the first image data source does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element image generator does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 5
Step 1
Regarding Claim 5, the rejection of Claim 4 is incorporated.
Step 2A Prong 1
Claim 5 recites the abstract ideas recited by parent Claim 4.
Step 2A Prong 2, Step 2B
The additional element sequentially taken spatial-channel images ..., the plurality of sequentially taken spatial-channel images having a first order based upon when they were taken, wherein the spatial-channel images each have a single channel encoding a spatial feature other than intensity of a color (as recited by Claim 1), wherein each spatial-channel image is a different slice of a three-dimensional image from the three-dimensional image generator does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 6
Step 1
Regarding Claim 6, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
Claim 6 recites the abstract ideas recited by parent Claim 1.
Step 2A Prong 2, Step 2B
The additional element feeding the plurality of groupings into the trained convolutional neural network, passing the plurality of groupings through each of the convolutional layer, a nonlinearity layer, a pooling layer, and a classification layer, to make a prediction of a classification for each of the plurality of groupings (as recited by Claim 1), wherein the classification for each of the plurality of groupings is an indication of whether a defect is detected in a component in the plurality of sequentially taken spatial-channel images invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 7
Step 1
Regarding Claim 7, the rejection of Claim 2 is incorporated.
Step 2A Prong 1
Claim 7 recites the abstract ideas recited by parent Claim 2.
Step 2A Prong 2, Step 2B
The additional element wherein each grouping contains images taken immediately sequentially to one another does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 8
Step 1
Claim 8 recites a method, and thus the claimed process falls within a statutory category of invention.
Step 2A Prong 1
The claim recites forming the plurality ... into a plurality of groupings ..., wherein each grouping contains a different combination of the plurality ..., and wherein at least one ... is contained in multiple groupings, which is a mental process, such as a judgment, when forming groupings is understood as a step of organization of images that can be undertaken in the mind or with the aid of pen and paper.
Thus, the claim recites an abstract idea.
Step 2A Prong 2
The additional element a first ... data source; a second ... data source; a computer system comprising at least one hardware processor and a non-transitory computer-readable medium storing instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element image data does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element accessing a plurality ... from the first ... data source amounts to insignificant extra-solution activity (see MPEP 2106.05(g), "mere data gathering"). The additional element a plurality of images ..., the plurality of images each having n number of color channels does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element training a convolutional neural network using the plurality ... and a plurality of labels, each label corresponding to a classification, the convolutional neural network comprising a convolutional layer, a nonlinearity layer, a pooling layer, a classification layer, and a loss layer invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element accessing a plurality ... from the second ... data source amounts to insignificant extra-solution activity (see MPEP 2106.05(g), "mere data gathering"). The additional element sequentially taken spatial-channel images ..., the plurality of sequentially taken spatial-channel images having a first order based upon when they were taken, wherein the spatial-channel images each have a single channel encoding a spatial feature other than intensity of a color does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element groupings of n spatial-channel images does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element feeding the plurality of groupings into the trained convolutional neural network, passing the plurality of groupings through each of the convolutional layer, a nonlinearity layer, a pooling layer, and a classification layer, to make a prediction of a classification for each of the plurality of groupings invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it").
Step 2B
The additional element a first ... data source; a second ... data source; a computer system comprising at least one hardware processor and a non-transitory computer-readable medium storing instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element image data does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element accessing a plurality ... from the first ... data source is well-understood, routine, conventional activity (see MPEP 2106.05(d), "receiving or transmitting data over a network"). The additional element a plurality of images ..., the plurality of images each having n number of color channels does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element training a convolutional neural network using the plurality ... and a plurality of labels, each label corresponding to a classification, the convolutional neural network comprising a convolutional layer, a nonlinearity layer, a pooling layer, a classification layer, and a loss layer invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element accessing a plurality ... from the second ... data source is well-understood, routine, conventional activity (see MPEP 2106.05(d), "receiving or transmitting data over a network"). The additional element sequentially taken spatial-channel images ..., the plurality of sequentially taken spatial-channel images having a first order based upon when they were taken, wherein the spatial-channel images each have a single channel encoding a spatial feature other than intensity of a color does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element groupings of n spatial-channel images does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element feeding the plurality of groupings into the trained convolutional neural network, passing the plurality of groupings through each of the convolutional layer, a nonlinearity layer, a pooling layer, and a classification layer, to make a prediction of a classification for each of the plurality of groupings invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Claims 9-14, dependent on Claim 8, incorporate the rejection of Claim 15. Claims 9-14 incorporate substantively all the limitations of Claims 2-6, respectively, in method form and are rejected under the same rationales.
Regarding Claim 15
Step 1
Claim 15 recites a non-transitory machine-readable storage medium having embodied thereon instructions executable by one or more machines to perform operations, and thus the claimed manufacture falls within a statutory category of invention.
Step 2A Prong 1
The claim recites forming the plurality ... into a plurality of groupings ..., wherein each grouping contains a different combination of the plurality ..., and wherein at least one ... is contained in multiple groupings, which is a mental process, such as a judgment, when forming groupings is understood as a step of organization of images that can be undertaken in the mind or with the aid of pen and paper.
Thus, the claim recites an abstract idea.
Step 2A Prong 2
The additional element a first ... data source; a second ... data source; a computer system comprising at least one hardware processor and a non-transitory computer-readable medium storing instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element image data does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element accessing a plurality ... from the first ... data source amounts to insignificant extra-solution activity (see MPEP 2106.05(g), "mere data gathering"). The additional element a plurality of images ..., the plurality of images each having n number of color channels does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element training a convolutional neural network using the plurality ... and a plurality of labels, each label corresponding to a classification, the convolutional neural network comprising a convolutional layer, a nonlinearity layer, a pooling layer, a classification layer, and a loss layer invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element accessing a plurality ... from the second ... data source amounts to insignificant extra-solution activity (see MPEP 2106.05(g), "mere data gathering"). The additional element sequentially taken spatial-channel images ..., the plurality of sequentially taken spatial-channel images having a first order based upon when they were taken, wherein the spatial-channel images each have a single channel encoding a spatial feature other than intensity of a color does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element groupings of n spatial-channel images does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element feeding the plurality of groupings into the trained convolutional neural network, passing the plurality of groupings through each of the convolutional layer, a nonlinearity layer, a pooling layer, and a classification layer, to make a prediction of a classification for each of the plurality of groupings invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it").
Step 2B
The additional element a first ... data source; a second ... data source; a computer system comprising at least one hardware processor and a non-transitory computer-readable medium storing instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element image data does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element accessing a plurality ... from the first ... data source is well-understood, routine, conventional activity (see MPEP 2106.05(d), "receiving or transmitting data over a network"). The additional element a plurality of images ..., the plurality of images each having n number of color channels does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element training a convolutional neural network using the plurality ... and a plurality of labels, each label corresponding to a classification, the convolutional neural network comprising a convolutional layer, a nonlinearity layer, a pooling layer, a classification layer, and a loss layer invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it"). The additional element accessing a plurality ... from the second ... data source is well-understood, routine, conventional activity (see MPEP 2106.05(d), "receiving or transmitting data over a network"). The additional element sequentially taken spatial-channel images ..., the plurality of sequentially taken spatial-channel images having a first order based upon when they were taken, wherein the spatial-channel images each have a single channel encoding a spatial feature other than intensity of a color does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element groupings of n spatial-channel images does not amount to more than generally linking the use of a judicial exception to a particular field of use (see MPEP 2106.05(h), "limit the use of the abstract idea to a particular technological environment"). The additional element feeding the plurality of groupings into the trained convolutional neural network, passing the plurality of groupings through each of the convolutional layer, a nonlinearity layer, a pooling layer, and a classification layer, to make a prediction of a classification for each of the plurality of groupings invokes a computer or other machinery merely as a tool to perform an existing process (see MPEP 2106.05(f), "apply it").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Claims 16-20, dependent on Claim 15, incorporate the rejection of Claim 15. Claims 16-20 incorporate substantively all the limitations of Claims 2-6, respectively, in storage medium form and are rejected under the same rationales.
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.
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.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Sharma, et al. (US 2017/0032222 A1, hereinafter "Sharma") in view of Hsiao, et al. (US 2020/0219262 A1, hereinafter "Hsiao").
Regarding Claim 1, Sharma teaches:
A system comprising: a first image data source; a second image data source (Sharma, [0055]: "In one embodiment, the interface(s) 310 may assist to receive the training dataset 201 from the image database 304, a testing dataset including multidimensional images," where Sharma's training dataset and testing dataset correspond to the instant first image source and second image source, respectively);
a computer system comprising at least one hardware processor and a non-transitory computer-readable medium storing instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations (Sharma, [0052]: "The image data analysis device 302 may be implemented by way of a single device (e.g., a computing device, a processor or an electronic storage device) or a combination of multiple devices that are operatively or logically connected or networked together," where Sharma's image data analysis device, processor, and storage device correspond to the instant system, processor, and memory, respectively) comprising:
accessing a plurality of images from the first image data source, the plurality of images each having n number of color channels (Sharma, [0003]: "Such 3D images having both depth and color information are also referred to as RGB-D images being an aggregation of RGB images and depth images or depth map" and [0007]: "The input module receives a training dataset including a plurality of multidimensional images, each of the multidimensional images including a color image and a depth image" and [0018]: "A 'training dataset' is used in the present disclosure in the context of its broadest definition. The training dataset may refer to a collection of one or more multidimensional images such as RGB-D images, each having a color image such as an RGB image and a depth image," where Sharma's RGB-D images have three color channels);
training a convolutional neural network using the plurality of images and a plurality of labels, each label corresponding to a classification (Sharma, [0039]: "In one embodiment, the pre-trained CNN 202 may be trained using multimodal images such as multidimensional images having color and depth information to improve performance of tasks related to computer vision. [… ] In a non-limiting example, the training dataset may have a total of 207,920 RGB-D images that can be classified into 51 different classes of household objects with 300 instances of these classes," which teaches training a convolutional neural network with the training dataset with 51 different classifications), the convolutional neural network comprising a convolutional layer (Sharma, [0027]: "the CNN 100 has eight learning layers 102 including five convolutional layers 104- 1, 104-2, ... , 104-5 (collectively, convolutional layers 104)"), a nonlinearity layer (Sharma, [0031]: "each learning layer of the CNN 100 includes multiple feature maps that are activated using an activation function (e.g., rectified linear unit (ReLu), sigmoid, tan h, etc.) to provide filtered responses to the next learning layer," where Sharma's learning layer with a non-linear activation function corresponds to the instant non-linearity layer), a pooling layer (Sharma, [0030]: "each of the convolutional layers 104-1, 104-2, and 104-5 can be combined with a pooling layer that pools the feature maps using one of many available algorithms such as max pooling, sub-sampling, spatial pyramid pooling, and so on"), a classification layer (Sharma, [0048]: "during a testing workflow 30, depth features ... and color features ... may be concatenated at a classification layer (not shown) to produce combined feature vectors 218, which may be used to train one of a variety of classifiers, such as a classifier 220, known in the art, related art, or developed later including Softmax and SVM over the entire set of RGB-D images"), and a loss layer (Sharma, [0036]: "The classifier 112 can classify the image feature into a class label corresponding to the image dataset ... and can determine the classification error. Based on the determined error, the CNN 100 can adjust the set of initialized parameters ... by applying backpropagation based on any of the available techniques, such as gradient descent," where Sharma's classifier may be a layer, as in Fig. 1, 112, and [0036]: "the classifier 112, and in turn the CNN 100, can be trained over the entire training dataset 110.... Examples of the classifier 112 include, but are not limited to, Softmax");
accessing a plurality of sequentially taken spatial-channel images from the second image data source (Sharma, [0055]: "the interface(s) 310 may assist to receive the training dataset 201 from the image database 304, a testing dataset including multidimensional images" and [0075]: "the input module receives a testing dataset including multidimensional images, each having a color image and a depth image"), the plurality of sequentially taken spatial-channel images having a first order based upon when they were taken (Sharma, [0019]: "A 'feature' or 'feature vector' is used in the present disclosure in the context of its broadest definition. The feature may refer to aspects of an entity such as a person or an object, in an image or video frame," where Sharma's images may be video frames, and thus being sequentially taken and thus having an order by inherency, even if later extracted from the video sequence), wherein the spatial-channel images each have a single channel encoding a spatial feature other than intensity of a color (Sharma, [0040]: "These multidimensional images may be segregated into depth images 204 and color images 206" and [0042]: "the depth images 204 may be encoded with three distinct channels at each image pixel. These channels include horizontal disparity (H), height above ground (H), and the angle the pixel's local surface normal makes with the inferred gravity direction (A). Such HHA representation of depth images 204 encodes properties of geocentric pose that emphasize complementary discontinuities (e.g., depth, surface normal, and height) in the depth images 204," where Sharma's depth image comprises a single channel encoding the spatial feature of horizontal disparity);
forming the plurality of sequentially taken spatial-channel images into a plurality of groupings of n spatial-channel images (Sharma, [0042]: "the depth images 204 may be encoded with three distinct channels at each image pixel. These channels include horizontal disparity (H), height above ground (H), and the angle the pixel's local surface normal makes with the inferred gravity direction (A)," where Sharma's three distinct depth channels reasonably suggests the instant image grouping, given that Sharma has previously referred to an image decomposed according to channels as multiple images, one per channel, as in[0040]: "The RGB images include R, G, and B image channels, providing respective R, G, and B images that can be represented as 2D matrices of pixel values indicating brightness intensities," reasonably suggesting three spatial channel images corresponding to the three color-channel images), wherein each grouping contains a different combination of the plurality of sequentially taken spatial-channel images (Sharma, [0048]: "during a testing workflow 30, depth features (e.g., the depth features 210) from the depth CNN 208 and color features (e.g., the color features 216) ... may be concatenated at a classification layer ... or developed later ... over the entire set of RGB-D images," where Sharma's depth images decomposed from a set of RGB-D images reasonably suggests a unique combination of decomposed depth images, thus a different combination); and
feeding the plurality of groupings into the trained convolutional neural network ... to make a prediction of a classification for each of the plurality of groupings (Sharma, [0048]: "The generated depth CNN 208 and the depth-enhanced color CNN 214 can be used to perform various vision tasks such as object recognition. For example, during a testing workflow 30, depth features (e.g., the depth features 210) from the depth CNN 208 and color features (e.g., the color features 216), such as the RGB features from the depth-enhanced color CNN 214, may be concatenated at a classification layer") ... passing the plurality of groupings through each of (Sharma, Fig. 2, depicting the depth CNN initialized as the pre-trained CNN 202, and [0046]: "The pre-trained CNN 202 that can be fine-tuned using the depth images 204, can provide a depth CNN 208") the convolutional layer (Sharma, [0038]: "The training workflow 200 may include the use of a pre-trained CNN 202 that can include multiple learning layers, such as the convolutional layers"), a nonlinearity layer (Sharma, [0046]: "The pre-trained CNN 202 that can be fine-tuned using the depth images 204, can provide a depth CNN 208, which provides activations of the penultimate fully-connected layer" and [0031]: "each learning layer of the CNN 100 includes multiple feature maps that are activated using an activation function (e.g., rectified linear unit (ReLu), sigmoid, tan h, etc.) to provide filtered responses to the next learning layer," where Sharma's learning layer with a non-linear activation function corresponds to the instant non-linearity layer), a pooling layer (Sharma, [0030]: "each of the convolutional layers 104-1, 104-2, and 104-5 can be combined with a pooling layer that pools the feature maps using one of many available algorithms such as max pooling, sub-sampling, spatial pyramid pooling, and so on"), and a classification layer (Sharma, [0048]: "during a testing workflow 30, depth features ... and color features ... may be concatenated at a classification layer (not shown) to produce combined feature vectors 218, which may be used to train one of a variety of classifiers, such as a classifier 220, known in the art, related art, or developed later including Softmax and SVM over the entire set of RGB-D images").
Sharma teaches forming a plurality of sequentially taken spatial-channel images into a plurality of groupings of n spatial-channel images.
Sharma does not explicitly teach forming the plurality of sequentially taken spatial-channel images into a plurality of groupings ... wherein at least one spatial-channel image is contained in multiple groupings.
However, Hsiao teaches:
forming the plurality of sequentially taken (Hsiao, [0051]: "We first constructed a four channel VGG19 network, where a sliding window of four consecutive frames was used as the network input," where Hsiao's consecutive frames corresponds to the instant sequentially taken) spatial-channel images (Hsiao, [0071]: "The MVS model was trained to classify proposal slices as either 'atrial' or 'ventricular' to the ground truth labeled MVS. Spatial context was provided by adding two slices atrial and two slices ventricular to each target slice for a total of 5 channels") into a plurality of groupings ... wherein at least one spatial-channel image is contained in multiple groupings (Hsiao, Fig. 2, depicting at label 22 the second image of group W1 as the first image of group W2).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Sharma regarding forming a plurality of sequentially taken spatial-channel images into a plurality of groupings of n spatial-channel images with those of Hsiao regarding forming the plurality of sequentially taken spatial-channel images into a plurality of groupings wherein at least one spatial-channel image is contained in multiple groupings.
The motivation to do so would be to improve the reliability and repeatability of determining an optimal image from a temporal sequence of images using a trained classifier (Hsiao, [0049]: "since the temporal context of each frame could be helpful for identifying the optimal inversion time, we implemented a sliding window approach where multiple windows, each consisting of four consecutive frames, are shown simultaneously to the neural network" and [0012]: "The basic problem to which the inventive method is addressed is that of finding a single optimal image within a sequence of images.... The challenge of automating the selection process, as would be desirable for improving reliability and repeatability, arises from the fact that selection of the optimal image from within a batch of similar images is an unbalanced classification problem-a problem not well suited for machine learning. ... By defining the selection process as a two class problem, it enables application of a deep learning approach for solution of a balanced classification problem").
Regarding Claim 8, Sharma teaches:
A method (Sharma, [0006]: "The method comprises receiving, using an input module of a system memory, a training dataset including a plurality of multidimensional images, each multidimensional image including a color image and a depth image; performing, using a processor, a fine-tuning of the pretrained CNN using the depth image for each of the plurality of multidimensional images") comprising: precisely those steps recited by the system of Claim 1. Claim 8 is rejected under the same rationale as Claim 1.
Regarding Claim 15, Sharma teaches:
A non-transitory machine-readable storage medium having embodied thereon instructions executable by one or more machines to perform operations (Sharma, [0008]: "Yet another embodiment of the present disclosure includes a non-transitory computer-readable medium comprising computer-executable instructions for training a convolutional neural network (CNN)") comprising: precisely those steps recited by the system of Claim 1. Claim 15 is rejected under the same rationale as Claim 1.
Regarding Claim 2, the rejection of Claim 1 is incorporated. Hsiao further teaches:
wherein the forming the plurality of sequentially taken spatial-channel images into a plurality of groupings includes utilizing a sliding window method, such that each grouping contains an ordered group of spatial-channel images in an order that matches the first order (Hsiao, [0051]: "We first constructed a four channel VGG19 network, where a sliding window of four consecutive frames was used as the network input," where Hsiao's consecutive frames corresponds to the instant sequentially taken), and wherein some of the plurality of sequentially taken spatial-channel images reappear in n different positions in n different groupings (Hsiao, Fig. 2, depicting at label 22 the fourth image of group W1 as the third image of group W2, etc., for the four groupings).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the Sharma/Hsiao combination regarding accessing a plurality of sequentially taken spatial-channel images from the second image data source, the plurality of sequentially taken spatial-channel images having a first order based upon when they were taken, with the further teachings of Hsiao regarding wherein the forming the plurality of sequentially taken spatial-channel images into a plurality of groupings includes utilizing a sliding window method, such that each grouping contains an ordered group of spatial-channel images in an order that matches the first order, and wherein some of the plurality of sequentially taken spatial-channel images reappear in n different positions in n different groupings.
The motivation to do so would be to improve the reliability and repeatability of determining an optimal image from a temporal sequence of images using a trained classifier (Hsiao, [0049]: "since the temporal context of each frame could be helpful for identifying the optimal inversion time, we implemented a sliding window approach where multiple windows, each consisting of four consecutive frames, are shown simultaneously to the neural network" and [0012]: "The basic problem to which the inventive method is addressed is that of finding a single optimal image within a sequence of images.... The challenge of automating the selection process, as would be desirable for improving reliability and repeatability, arises from the fact that selection of the optimal image from within a batch of similar images is an unbalanced classification problem-a problem not well suited for machine learning. ... By defining the selection process as a two class problem, it enables application of a deep learning approach for solution of a balanced classification problem").
Claims 9 and 16 incorporates substantively all the limitations of Claim 2 in method and non-transitory machine-readable storage medium forms and are rejected under the same rationale.
Regarding Claim 3, the rejection of Claim 1 is incorporated. Hsiao further teaches:
wherein the second image data source is a computerized tomography (CT) scan machine (Hsiao, [0013]: "The results of this analysis may be used for the evaluation of dynamic temporal activities and/or series for object recognition within images generated by, for example, MR and CT scans," where Hsiao previously indicates use of a computed tomography radiation for CT images at [0003]: "Cardiac patients with chronic conditions such as congenital heart disease often require many imaging exams over their lifetime. These are generally performed using computed tomography (CT). However, CT exposes patients to ionizing radiation, and CT does not have the same contrast and ability to delineate soft tissues as MRI").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the Sharma/Hsiao combination regarding accessing a plurality of sequentially taken spatial-channel images from the second image data source with the further teachings of Hsiao regarding wherein the second image data source is a computerized tomography (CT) scan machine.
The motivation to do so would be to facilitate improved anatomic imaging (Hsiao, [0013]: "In application to medical images, the inventive approach may be used to localize key anatomic landmarks that define imaging planes. Deep learning based localizations of these landmarks are believed to be sufficient to accurately prescribe the desired imaging planes").
Claims 10 and 17 incorporates substantively all the limitations of Claim 3 in method and non-transitory machine-readable storage medium forms and are rejected under the same rationale.
Regarding Claim 4, the rejection of Claim 1 is incorporated. The Sharma/Hsiao combination teaches:
wherein the images from the first image data source are two-dimensional (Sharma, [0007]: "The input module receives a training dataset including a plurality of multidimensional images, each of the multidimensional images including a color image and a depth image" and [0018]: "A 'training dataset' is used in the present disclosure in the context of its broadest definition. The training dataset may refer to a collection of one or more multidimensional images such as RGB-D images, each having a color image such as an RGB image and a depth image," where Sharma's RGB color images are two dimensional).
Hsiao further teaches:
wherein the second image data source is a three-dimensional image generator (Hsiao, [0013]: "The results of this analysis may be used for the evaluation of dynamic temporal activities and/or series for object recognition within images generated by, for example, MR and CT scans" and [0017]: "the sequence of image frames is MRI time sequence and the serial features comprise time. The MRI time sequence may be Tl mapping sequence. In other embodiments, the sequence of image frames is a stack of MRI slices and the serial features comprise location within the stack," where Hsiao's MRI or CT generating a stack of image slices corresponds to the instant 3D image generator, under BRI and in light of the specification, per [0023]: "the spatial-channel image generator 112 may be any component that generates spatial-channel images").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the Sharma/Hsiao combination regarding the images from the first image data source are two-dimensional with the further teachings of Hsiao regarding wherein the second image data source is a three-dimensional image generator.
The motivation to do so would be to facilitate automation of a reliable and repeatable selection process for finding optimal anatomical images (Hsiao, [0011]: "the issues and goals of segmentation within a static MRI slice are distinct from those involved in the analysis of sequences of frames having both spatial and temporal, or other series, characteristics that are fundamental to improving the reliability of selection of a specific frame within the series, for example, the
T
I
N
P
for myocardial MRI, or selection of a slice within a stack of images for localization of anatomical features" and [0012]: "The basic problem to which the inventive method is addressed is that of finding a single optimal image within a sequence of images, where the series may be a time sequence of images or a stack or collection of images, e.g., multiple image planes. The challenge of automating the selection process, as would be desirable for improving reliability and repeatability, arises from the fact that selection of the optimal image from within a batch of similar images is an unbalanced classification problem-a problem not well suited for machine learning. ... By defining the selection process as a two class problem, it enables application of a deep learning approach for solution of a balanced classification problem").
Claims 11 and 18 incorporates substantively all the limitations of Claim 4 in method and non-transitory machine-readable storage medium forms and are rejected under the same rationale.
Regarding Claim 5, the rejection of Claim 4 is incorporated. Hsiao further teaches:
wherein each spatial-channel image is a different slice of a three-dimensional image from the three-dimensional image generator (Hsiao, [0017]: "the sequence of image frames is MRI time sequence and the serial features comprise time. The MRI time sequence may be Tl mapping sequence. In other embodiments, the sequence of image frames is a stack of MRI slices and the serial features comprise location within the stack," where Hsiao's timeseries sequence of slices teaches or reasonably suggests the instant different slice).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the Sharma/Hsiao combination regarding accessing a plurality of sequentially taken spatial-channel images from the second image data source with the further teachings of Hsiao regarding wherein each spatial-channel image is a different slice of a three-dimensional image from the three-dimensional image generator.
The motivation to do so would be to facilitate automation of a reliable and repeatable selection process for finding optimal anatomical images (Hsiao, [0011]: "the issues and goals of segmentation within a static MRI slice are distinct from those involved in the analysis of sequences of frames having both spatial and temporal, or other series, characteristics that are fundamental to improving the reliability of selection of a specific frame within the series, for example, the
T
I
N
P
for myocardial MRI, or selection of a slice within a stack of images for localization of anatomical features").
Claims 12 and 19 incorporates substantively all the limitations of Claim 5 in method and non-transitory machine-readable storage medium forms and are rejected under the same rationale.
Regarding Claim 6, the rejection of Claim 1 is incorporated. Hsiao further teaches:
wherein the classification for each of the plurality of groupings is an indication of whether a defect is detected in a component in the plurality of sequentially taken spatial-channel images (Hsiao, [0012]: "The basic problem to which the inventive method is addressed is that of finding a single optimal image within a sequence of images, where the series may be a time sequence of images or a stack or collection of images, e.g., multiple image planes. ... By defining the selection process as a two class problem, it enables application of a deep learning approach for solution of a balanced classification problem" and [0008]: "Inversion Recovery (IR) pulses are used to null the signal from a desired tissue to accentuate surrounding pathology. A common use of this technique is to null the signal from normal myocardium during DE-CMR imaging. The nulled normal myocardium will be dark in contrast to the enhanced abnormal myocardium," where Hsiao's abnormal myocardium corresponds to the instant defect).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the Sharma/Hsiao combination regarding making a prediction of a classification for each of the plurality of groupings with the further teachings of Hsiao regarding wherein the classification for each of the plurality of groupings is an indication of whether a defect is detected in a component in the plurality of sequentially taken spatial-channel images.
The motivation to do so would be to facilitate automation of image selection resulting in consistent selection (Hsiao, [0008]: "In practice, selection of TI [inversion time] is generally performed through visual inspection and selection of
'
T
I
N
P
from the inversion recovery scout acquisition. This approach is dependent on the skill of a technologist or physician to select the optimal inversion time, which may not be readily available outside of specialized centers. ... [S]uch methods still rely on visual inspection of an image series by a trained human observer to select an optimal myocardial inversion time. In addition, in certain diffuse myocardial diseases such as amyloidosis, it may be difficult to identify a single optimal null point. ... Consistent selection of the TI time tends to be a significant problem, especially when different technicians are generating the imaging planes").
Claims 13 and 20 incorporates substantively all the limitations of Claim 6 in method and non-transitory machine-readable storage medium forms and are rejected under the same rationale.
Regarding Claim 7, the rejection of Claim 1 is incorporated. Hsiao further teaches:
wherein each grouping contains images taken immediately sequentially to one another (Hsiao, [0056]: "STEMI-Net predicted the exact inversion recovery time as the ground truth for 63% of the patients (n=285). In 94% of cases (n=397), predictions ofTINP were within one frame (about 36 ms) of the ground truth," where prediction frame rate of 36 ms matches the collection frame rate, reasonably suggesting images taken immediately sequentially, where collection is described at [0067]: "Cine SSFP (steady state free precession) images were each acquired on a 1.5 T MRI scanner-the same image set that was used in Example 1. The inversion recovery (Cine IR) scout sequence captures image contrast evolution at multiple time points ... acquired with a temporal resolution of 24-36 ms").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the Sharma/Hsiao combination regarding forming the plurality of sequentially taken spatial-channel images into a plurality of groupings with the further teachings of Hsiao regarding wherein each grouping contains images taken immediately sequentially to one another.
The motivation to do so would be to improve the reliability and repeatability of determining an optimal image from a temporal sequence of images using a trained classifier (Hsiao, [0012]: "The basic problem to which the inventive method is addressed is that of finding a single optimal image within a sequence of images, where the series may be a time sequence of images or a stack or collection of images, e.g., multiple image planes").
Claim 14 incorporates substantively all the limitations of Claim 7 in method form and is rejected under the same rationale.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ROBERT N DAY whose telephone number is (703)756-1519. The examiner can normally be reached M-F 9-5.
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, Kakali Chaki can be reached at (571) 272-3719. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/R.N.D./Examiner, Art Unit 2122
/KAKALI CHAKI/Supervisory Patent Examiner, Art Unit 2122
Prosecution Insights