DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
Applicant's arguments filed June 24, 2026 have been fully considered but they are not persuasive.
Regarding the rejection of the claims under 35 U.S.C. 101 as being directed to a mental process, Applicant argues that limitations that have been added to independent claims 1 and 12 by the present amendment “recite specific processor-executed data-processing technique that includes:
1) obtaining reference data for comparison with a subject dataset;
2) partitioning at least a portion of the subject dataset into a plurality of subject windows;
3) Calculating respective comparison values between the subject windows and corresponding portions of the reference data;
4) generating a spatially indexed comparison map associating the calculated comparison values with the spatial locations of the corresponding subject windows;
5) identifying a region of interest based on satisfaction of a predetermined comparison criterion; and
6) transmitting a notification that includes the spatial location of the identified region of interest.”
Regarding limitation 1), the BRI for this limitation is that reference data and subject data, such as a reference image and a target image, respectively, are somehow obtained. The BRI is based on para. [0077] of the present disclosure. This step can be performed as a mental process by a person who, for example, looks at a reference image and a subject image that are displayed side by side on a display device.
Regarding limitation 2), the BRI for this limitation is based on the plain meaning of the term “partitioning” because the term is not explicitly defined in the present specification. The plain meaning of the term is dividing or separating something into parts. In the context of the present disclosure, the BRI is that at least a portion of the subject data is divided into multiple windows. This step is also a mental process that can be performed by a person who mentally divides the subject image into parts by focusing on sub-regions of the subject image at different times and considering them individually. Also, mental processes include processes that can be performed by a human being with the aid of a tool, such as pen and paper. MPEP 2106.04(a)(2) citing CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011). Step 2 can also be performed by a human being who uses pen and paper to, for example, subdivide a print out of the subject image into windows.
Regarding limitation 3), a human being can perform the step of mentally calculating respective comparison values between the subject windows and corresponding portions of the reference data by visually comparing the subject and target portions and making a mental note of how similar they are, or by manually labeling the windows of the subject image with numbers based on how similar the portions are. For example, on a scale of 1 to 10, a human being could label windows in the print out with lower or higher numbers in the range based on how dissimilar or similar they are, respectively.
Regarding limitation 4), this step can also be performed by a human being who labels the windows of the subject image print out with the numerical corresponding to the mentally calculated degrees of similarity. The BRI for the term “spatially indexed comparison map”, based on para. [0119] of the present specification, is that is a mapping of the similarity values obtained via the comparison process to the spatial locations of the windowed subregions of the subject image. As indicated above, a person could manually label the windows the printed out subject image based on the determined similarities with the corresponding subregions of the reference image, which would constitute a spatially indexed comparison map.
Applicant argues in part that “[a] human may generally observe that two regions appear different. A human, however, does not mentally partition a dataset into a potentially large number of windows”. Although this may be true in cases where, for example, hundreds or thousands of windowed subregions are compared or in cases where a pixel-by-pixel comparison is performed for images with small pixels and high image resolutions. However, the claims are silent as to the number of regions that are compared or as to the granularity of the comparison.
Regarding limitation 5), a human being can use a mental threshold by which that person determines whether a subject image region and a target image region are similar or dissimilar to determine whether or not a region meets criterion for classifying it as a region of interest (ROI).
Regarding limitation 6), transmitting the result of the process performed by the steps of limitations 1) - 5) is insignificant extra-solution activity. Adding insignificant extra-solution activity to the judicial exception does not integrate the abstract idea into a practical application or result in the claim reciting significantly more than the abstract idea. MPEP 2106.05(g).
For all of these reasons, the rejection of the claims under 35 U.S.C. 101 is maintained.
Regarding the rejections of independent claims 1 and 12 under 35 U.S.C. 103 over Rao in view of Haas, Applicant’s arguments are moot in view of the new grounds of rejection necessitated by Applicant’s claim amendments.
Claim Interpretation
The claims in this application are given their broadest reasonable interpretation (BRI) using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The BRI of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification.
In the following, some of the terms in the claims have been given BRIs in light of the specification. These BRIs are used for purposes of searching for prior art and examining the claims, but cannot be incorporated into the claims. Should Applicant believe that different interpretations are appropriate, Applicant should point to the portions of the specification that clearly support a different interpretation.
The present claims recite alternative language such as, for example, “the subject dataset, a reference dataset, or both”. In accordance with MPEP 2111.04, claim scope is not limited by claim language that suggests or makes optional but does not require steps to be performed. In addition, when a claim requires selection of an element from a list of alternatives, the prior art teaches the element if one of the alternatives is taught by the prior art. See, e.g., Fresenius USA, Inc. v. Baxter Int’l, Inc., 582 F.3d 1288, 1298, 92 USPQ2d 1163, 1171 (Fed. Cir. 2009). Therefore, these alternative limitations in the claims of the present application are interpreted as requiring one or the other of the elements, but not both.
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. Claims 1-11 fall into the statutory class of process. Claim 12-20 fall into the statutory class of machine. Notwithstanding that these claims fall into statutory classes, they recite subject matter that is ineligible under 35 U.S.C. 101 because they recite abstract ideas.
The USPTO has enumerated groupings of abstract ideas that are firmly rooted in Supreme Court precedent as well as Federal Circuit decisions interpreting that precedent (See MPEP 2106.04(a)). The enumerated groupings of abstract ideas are defined as:
1) Mathematical concepts – mathematical relationships, mathematical formulas or equations, mathematical calculations;
2) Certain methods of organizing human activity – fundamental economic principles or practices (including hedging, insurance, mitigating risk); commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations); managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions); and
3) Mental processes – concepts performed in the human mind (including an observation, evaluation, judgment, opinion).
The operations recited in claims 1 and 12 are mental processes that fall under enumerated grouping 3).
As indicated above in the Response to Arguments section of this Office Action, the limitations enumerated by Applicant above as 1) – 5) are mental processes that can be performed in the mind of a human being. Limitation 6) constitutes insignificant extra-solution activity. Therefore, the recitation of these new limitations in claims 1 and 12 does not result in the claims reciting significantly more than the abstract idea, and therefore the rejections are maintained.
Regarding limitation 1), the BRI for this limitation is that reference data and subject data, such as a reference image and a target image, respectively, are somehow obtained. The BRI is based on para. [0077] of the present disclosure. This step can be performed as a mental process by a person who, for example, looks at a reference image and a subject image that are displayed side by side on a display device.
Regarding limitation 2), the BRI for this limitation is based on the plain meaning of the term “partitioning” because the term is not explicitly defined in the present specification. The plain meaning of the term is dividing or separating something into parts. In the context of the present disclosure, the BRI is that at least a portion of the subject data is divided into multiple sub-regions. This step is also a mental process that can be performed by a person who mentally divides the subject image into parts by focusing on sub-regions of the subject image at different times and considering them individually. Also, mental processes include processes that can be performed by a human being with the aid of a tool, such as pen and paper. MPEP 2106.04(a)(2) citing CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011). Step 2 can also be performed by a human being who uses pen and paper to, for example, subdivide a print out of the subject image into windows.
Regarding limitation 3), a human being can perform the step of mentally calculating respective comparison values between the subject windows and corresponding portions of the reference data by visually comparing the subject and target portions and making a mental note of how similar they are, or by manually labeling the windows of the subject image with numbers based on how similar the portions are. For example, on a scale of 1 to 10, a human being could label windows in the print out with lower or higher numbers in the range based on how dissimilar or similar they are, respectively.
Regarding limitation 4), this step can also be performed by a human being who labels the windows of the subject image print out with the numerical corresponding to the mentally calculated degrees of similarity. The BRI for the term “spatially indexed comparison map”, based on para. [0119] of the present specification, is that is a mapping of the similarity values obtained via the comparison process to the spatial locations of the windowed subregions of the subject image. As indicated above, a person could manually label the windows the printed out subject image based on the determined similarities with the corresponding subregions of the reference image, which would constitute a spatially indexed comparison map.
Applicant argues in part that “[a] human may generally observe that two regions appear different. A human, however, does not mentally partition a dataset into a potentially large number of windows”. Although this may be true in cases where, for example, hundreds or thousands of windowed subregions are compared or in cases where a pixel-by-pixel comparison is performed for images with small pixels and high image resolution. However, the claims are silent as to the number of regions that are compared or as to the granularity of the comparison.
Regarding limitation 5), a human being can use a mental threshold by which that person determines whether a subject image region and a target image region are similar or dissimilar to determine whether or not a region meets criterion for classifying it as a region of interest (ROI).
Regarding limitation 6), transmitting the result of the process performed by the steps of limitations 1) - 5) is insignificant extra-solution activity. Adding insignificant extra-solution activity to the judicial exception does not integrate the abstract idea into a practical application or result in the claim reciting significantly more than the abstract idea. MPEP 2106.05(g).
Once it has been determined that the claim under examination recites an abstract idea, the claim must be further analyzed to determine whether any additional elements in the claim integrate the abstract idea into a practical application (See MPEP 2106.04(d)).
In claim 1, the only additional element other than the abstract idea is the transmitting step. The BRI for this step, based on paras. [0087]-[0088] of the present specification, is that it means that some type of notification is sent, such as a processor that causes a notification to be sent to another device, such as a display device. As indicated above, this step is insignificant extra-solution activity that does not integrate the abstract idea into a practical application. MPEP 2106.05(g). Therefore, the requirements of Prong Two, Step 2A of the Alice/Mayo test are not met.
In addition, simply appending well-understood, routine, conventional activities and/or devices previously known to the industry, specified at a high level of generality, to the judicial exception does not amount to the claim reciting significantly more than the abstract idea. Causing a notification to be displayed on a display device constitutes such an activity and therefore does not integrate the abstract idea into a practical application. Therefore, the recitation of this step in claim 1 does not amount to claim 1 reciting significantly more than the mental process. Therefore, the requirements of Prong Two, step 2B of the Alice/Mayo test also are not met.
The same is true for claim 12, which also recites this step.
Claim 12 also recites additional elements including a computing device, the BRI for which is a processor or similar device (para. [0068] of the present specification), and a nontransitory computer-readable medium, the BRI for which is a storage device or a propagated data signal (paras. [0065]-[0066] of the present specification). These are also well-understood, routine, conventional devices previously known to the industry, specified at a high level of generality, and therefore the recitation of these devices for performing these activities does not amount to claim 12 reciting significantly more than the mental process.
Claims 2-11 and 13-20 do not recite any elements in addition to those discussed above, but merely recite further details about the steps recited in claims 1 and 12. Therefore, these claims do not recite significantly more than the mental process.
For all of these reasons, claims 1-20 are rejected under 35 U.S.C. 101.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-4 and 12-15 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Publ. Appl. No. 2011/0262028 A1 to Lipson et al. (hereinafter referred to as “Lipson”) in view of an article entitled “Part 1. Automated Change Detection and Characterization in Serial MR Studies of Brain-Tumor Patients”, by Patriarche et al., published in September 2007 in Journal of Digital Imaging (hereinafter referred to as “Patriarche”).
Regarding claim 1, Lipson discloses a computer-implemented method of automatically detecting at least one anomaly within a subject dataset, in real-time (Paras. [0065] and [0018], the image processing system shown in Fig. 1 performs a computer-implemented method that processes subject image datasets, referred to in Lipson as the query image, to automatically detect anomalies, such as tumors, circuit board manufacturing defects, etc.), the method comprising the steps of:
receiving, via at least one processor of a computing device, the subject dataset (Fig. 1, para. [0065], the image processing system 14 receives the subject dataset query image 20 via the input system 14. Fig. 2, para. [0067], the image processing system 12 includes at least one processor, image processor 24);
obtaining, via the at least one processor, reference data for comparison with the subject dataset, wherein the reference data comprises reference data received separately from the subject dataset or reference data derived from the subject dataset, or a combination thereof (the BRI for subject dataset, based on para. [0077] of the present disclosure, is that it is data such as a subject image to be compared with a reference image. The BRI for “reference data”, based on para. [0077] of the present disclosure, is that it is reference data such as a reference image to be compared with the subject image. Fig. 3, step 40, para. [0079] and Fig. 2, para. [0065] of Lipson disclose that a target image is obtained by the image processing system 14 by, for example, retrieving the target image from storage device 18 shown in Fig. 2, and is aligned with the subject query image received via the input system 14);
partitioning, via the at least one processor, at least a portion of the subject dataset into a plurality of subject windows (as indicated above in the Response to Arguments section, the BRI for this limitation is dividing or separating the subject dataset into a plurality of subregions. Fig. 3, step 42 of Lipson corresponds to the step of dividing each of the subject query image and the target reference image into a plurality of sub-regions, or windows, para. [0080]: “[e]ither after or before the alignment step, the primary and target images are each divided or segmented into a plurality of sub regions (or more simply regions) or blocks as shown in step 42.”);
calculating, via at least one comparison metric of the at least one processor, respective comparison values between at least some of the plurality of subject windows and reference data selected for comparison with the respective subject windows (Fig. 3, steps 46-50, paras. [0082]-[0086], disclose an iterative process of comparing features of sub-regions of the subject query image, also referred to in Lipson as the primary image, to features of the corresponding sub-regions of the target image. Fig. 3A, step 52, para. [0086] discloses calculating respective comparison values (referred to as “difference scores” in Lipson) for the comparisons indicating the difference, or dissimilarity, between the sub-regions of the subject query image and the corresponding sub-regions of the target image);
generating, via the at least one processor, a spatially indexed comparison map associating the respective comparison values with respective spatial locations of the at least some of the plurality of subject windows (Lipson does not explicitly disclose generating a spatially indexed comparison map);
identifying, via the at least one processor, a region of interest within the subject dataset comprising at least one subject window having a respective comparison value that satisfies a predetermined comparison threshold criterion (As indicated above in this claim rejection, Lipson discloses generating a comparison value referred to in Lipson as a “score” for each respective pair of subject and target sub-regions that are compared. Paras. [0191]-[0192], Fig. 14, disclose that the scores associated with each sub-region window are compared to a predetermined comparison threshold criterion: “[t]he output value (i.e., the score) from the processing of step 346 is compared with a threshold value.”);
based on a determination that the respective comparison value of the at least one subject window satisfies the predetermined comparison threshold criterion, transmitting a notification indicative of the at least one anomaly being present within the subject dataset, the notification comprising a spatial location of the region of interest within the subject dataset (Lipson discloses that based on the comparison of the scores associated with each sub-region window to the predetermined comparison threshold criterion, a determination is made that an anomaly is present, e.g., the solder joint “is classified as a bad connection”, paras. [0092], [0128], [0165], [0169], [0171], [0175] and [0180] disclose outputting the result of the comparison process to a user in various forms, which constitutes transmitting a notification indicative of the at least one anomaly being present within the subject dataset); and
based on a determination that none of the respective comparison values satisfies the predetermined comparison threshold criterion, transmitting a notification indicative of the at least one anomaly not being present within the subject dataset (Lipson discloses that based on the comparison of the scores associated with each sub-region window to the predetermined comparison threshold criterion, a determination is made that an anomaly is not present, e.g., the solder joint is not classified as a bad connection, paras. [0092], [0128], [0165], [0169], [0171], [0175] and [0180] disclose outputting the result of the comparison process to a user in various forms, which constitutes transmitting a notification indicative of the at least one anomaly being present within the subject dataset).
As indicated above, Lipson does not explicitly disclose generating a spatially indexed comparison map associating the respective comparison values with respective spatial locations of the subject sub-region windows. The BRI for the term “spatially indexed comparison map”, based on the description of Figs. 16 and 17 in the present disclosure, is that it means some type of mapping that maps the spatial locations on the subject image to the results of the comparisons.
Patriarche, in the same field of endeavor, discloses a method for determining the presence or absence of brain tumor anomalies in medical images, that compares an MRI baseline reference image with an MRI follow-up subject image to determine whether brain tumor anomalies are present and/or have progressed (Methods section, Image Acquisition and Change Detection section) and generates a color-coded change map superimposed on the patient’s anatomical image (page 210, Fig. 8) for visual inspection (page 210: “[o]nce the algorithm has identified regions it considers to contain real change, it generates … a color-coded change map superimposed on the patient’s anatomical image (for visual inspection). In the color change map, regions which have been identified as changing are colored according to the type of change (Fig. 7). For example, orange corresponds to previously NAWM which has acquired enhancement from one scan to the next in the serial pair, whereas red corresponds to previously NAWM which has acquired NETTA.”).
Since the color-coded change map is superimposed on the anatomical image, it provides a mapping that maps the spatial locations on the subject image to the results of the comparisons, and therefore constitutes a “spatially indexed comparison map” according to the BRI.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the present disclosure, to modify the system and method of Lipson to generate a spatially indexed comparison map associating the respective comparison values with respective spatial locations of the subject sub-region windows of Lipson as taught by Patriarche. One of ordinary skill in the art would have been motivated to make the modification to provide the user with the ability to visually inspect the results and easily see which sub-regions have changed and how they have changed. The modification could have been made by one of ordinary skill in the art before the effective filing date of the present disclosure with a reasonable expectation of success because making the modification merely involves combining prior art elements according to known methods to yield predictable results (modifying software of the image processing system 12 and/or of the output system 16 to generate a color-coded map based on the comparison results as taught by Patriarche).
Regarding claim 2, Lipson discloses that the subject image comprises 1D signals, multidimensional signals, or both (Para. [0056] discloses that the subject image is multidimensional, i.e., 2D).
Regarding claim 3, Lipson discloses that the reference data is obtained separately from the subject dataset and comprises an abnormality reference sub-image or a normal reference sub-image (As indicated above in the rejection of claim 1, the reference target images can be obtained from the storage device 18 whereas the subject query images can be obtained from the input system 14, which means they are obtained separately).
Regarding claim 4, Lipson is silent as to whether the plurality of subject sub-region windows overlap, but they either do overlap or do not overlap, and therefore the alternative language of this claim limitation is taught by Lipson.
Regarding claims 12-15, the rejection of claims 1-4 apply mutatis mutandis to claims 12-15, respectively.
Claims 5 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Lipson in view of Patriarche as applied to claims 1-4 and 12-15 and further in view of an article entitled “Symmetric-Constrained Irregular Structure Inpainting for Brain MRI Registration with Tumor Pathology”, by Liu et al., published May 18, 2021 in Brainlesion (hereinafter referred to as “Liu”).
Regarding claim 5, the BRI for this limitation is that the reference image is synthetically generated, i.e., derived, from at least one of the sub-region windows of the partitioned subject image relying on brain symmetry in the way that the left and right sides of the brain mirror one another. The BRI is based on para. [0099] of the present disclosure, which describes the process of generating the reference image by extracting healthy tissue from a region on one side of the brain and replacing tumorous tissue in the corresponding region on the other side of the brain with the extracted healthy tissue based on the symmetry of the left and right sides of the brain. Lipson does not explicitly disclose this limitation.
Liu, in the same field of endeavor, discloses using this process, which it refers to as inpainting. The method of Liu treats tumors as defective holes in an ideal image and reconstructs the holes with synthetic normal tissue based on the symmetry of the brain. (Abstract, Introduction and section 2.4). Liu discloses that the process facilitates registration and alignment of the subject and reference images, which is otherwise difficult due to the manner in which tumorous regions of the brain lead to asymmetries in the brain that can make registration and alignment difficult.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the present disclosure, to modify the system and method of Lipson as modified by Patriarche further based on the teachings of Liu to generate reference images synthetically using the inpainting method disclosed in Liu. One of ordinary skill in the art would have been motivated to make the modification to improve the accuracy of the registration and alignment of the reference and subject images, which would lead to more accurate anomaly detection. The modification could have been made by one of ordinary skill in the art before the effective filing date of the present disclosure with a reasonable expectation of success because making the modification merely involves combining prior art elements according to known methods to yield predictable results (modifying software executed by the image processing system 12 to generate synthetic reference images based on the subject images and brain symmetry).
Claims 6 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Lipson in view of Patriarche as applied to claims 1-4 and 12-15 and further in view of U.S. Publ. Appl. No. 2026/0074067 A1 to Errico et al. (hereinafter referred to as “Errico”).
Regarding claim 6, neither Lipson nor Patriarche explicitly discloses displaying a bounding box around the anomaly. Errico, in the same field of endeavor, discloses highlighting a region of interest by displaying a bounding box around a region of interest in a medical image (Para. [0041], “[a]dditional graphics displayed on the user interface 132 may include anatomical measurements obtained by the system and/or user, labeled anatomical and/or artificial features visible in the acquired image frames, bounding boxes generated around particular features, etc.”).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the present disclosure, to modify the system andmethod of Lipson as modified by Patriarche further based on the teachings of Errico to cause a bounding box to be displayed around an anomaly on the output display screen 130. One of ordinary skill in the art would have been motivated to make the modification to better emphasize the anomalies to the user and/or to allow the user to observe the anomalies more easily. The modification could have been made by one of ordinary skill in the art before the effective filing date of the present disclosure with a reasonable expectation of success because making the modification merely involves combining prior art elements according to known methods to yield predictable results (modifying the software executed by image processing system 12 of Lipson to cause bounding boxes to be displayed around detected anomalies on the display screen).
Regarding claim 17, the rejection of claim 6 applies mutatis mutandis to claim 17.
Claims 7-10 and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Lipson in view of Patriarche and Errico as applied to claims 6 and 17 and further in view of U.S. Publ. Appl. No. 2022/0189032 A1 to Rao et al. (hereinafter referred to as “Rao”).
Regarding claim 7, the combined teachings of Lipson, Patriarche and Errico do not explicitly disclose performing a segmentation to segment the region of interest within the subject image. Rao, in the same field of endeavor, discloses using a neural network performing a segmentation algorithm that segments ROIs of the subject image dataset (Abstract, Figs. 8 and 9, block 53, Paras. [0073]-[0074]).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the present disclosure, to modify the system and method of Lipson as modified by Patriarche and Errico further based on the teachings of Rao to perform a segmentation algorithm to extract features of the ROIs. One of ordinary skill in the art would have been motivated to make the modification to take advantage of the improvements in image segmentation that are obtained by neural networks that perform segmentation. The modification could have been made by one of ordinary skill in the art before the effective filing date of the present disclosure with a reasonable expectation of success because making the modification merely involves combining prior art elements according to known methods to yield predictable results (modifying the software executed by the system of Lipson to implement neural network segmentation).
Regarding claim 8, Lipson does not explicitly disclose using a deep learning algorithm to perform feature extraction. The neural network 300/autoencoder 400 combination shown in Fig. 5 of Rao uses deep learning to perform feature extraction to extract features from ROIs.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the present disclosure, to modify the system and method of Lipson as modified by Patriarche and Errico further based on the teachings of Rao to use a neural network to perform a deep learning feature extraction to extract features of the ROIs. One of ordinary skill in the art would have been motivated to make the modification to take advantage of the improvements in feature extraction that are obtained by neural networks that perform segmentation. The modification could have been made by one of ordinary skill in the art before the effective filing date of the present disclosure with a reasonable expectation of success because making the modification merely involves combining prior art elements according to known methods to yield predictable results (modifying the software executed by the system of Lipson to implement neural network segmentation and feature extraction).
Regarding claim 9, Lipson does not explicitly disclose classifying via at least one classifier ROIs based on the extracted features. In machine learning algorithms used in image processing applications, image segmentation constitutes classification. Therefore, the neural network 300/autoencoder 400 shown in Fig. 5 of Rao functions as a classifier that classifies features extracted by the neural network 300/autoencoder 400.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the present disclosure, to modify the system and method of Lipson as modified by Patriarche and Errico further based on the teachings of Rao to use a neural network to perform classification of extracted features. One of ordinary skill in the art would have been motivated to make the modification to take advantage of the improvements in segmentation, feature extraction and classification that are obtained by neural networks. The modification could have been made by one of ordinary skill in the art before the effective filing date of the present disclosure with a reasonable expectation of success because making the modification merely involves combining prior art elements according to known methods to yield predictable results (modifying the software executed by the system of Lipson to implement neural network segmentation, feature extraction and classification).
Regarding claim 10, Lipson does not explicitly disclose that a classifier classifies the region of interest as comprising at least one of a tumor, healthy tissue, an aneurysm, a blood clot, gray matter, skull, or brain matter. Rao discloses at least classifying brain matter and skull because the skull stripping module 22a strips the skull from the images, which requires classifying ROIs as either skull or brain matter (Para. [0052], Fig. 4).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the present disclosure, to modify the system and method of Lipson as modified by Patriarche and Errico further based on the teachings of Rao to use a neural network to perform classification of extracted features including classification of brain matter and skull. One of ordinary skill in the art would have been motivated to make the modification to take advantage of the improvements in segmentation, feature extraction and classification that are obtained by neural networks. The modification could have been made by one of ordinary skill in the art before the effective filing date of the present disclosure with a reasonable expectation of success because making the modification merely involves combining prior art elements according to known methods to yield predictable results (modifying the software executed by the system of Lipson to implement neural network segmentation, feature extraction and classification).
Regarding claims 18-20, the rejection of claims 7-9 apply mutatis mutandis to claims 18-20, respectively.
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Lipson and Patriarche as applied to claims 1-4 and 12-15 and further in view of an article entitled “Brain tumor grade classification Using LSTM Neural Networks with Domain Pre-Transforms”, by Fasihi et al., published June 21, 2021 in International Midwest Symposium on Circuits and Systems 1 (2021) 529-532 (hereinafter referred to as “Fasihi”).
Neither Lipson not Patriarche discloses that the processor implements Discrete Cosine Transform, Wavelet domains, or both on at least one of the subject sub-region windows or a corresponding portion of the reference image before calculating the respective comparison values. Fasihi, in the same field of endeavor, discloses a processor implementing Discrete Cosine Transform, Wavelet domains, or both on the ROIs of the subject image (Section III.B. discloses extracting features from ROIs for images that have been processed into the Discrete Cosine Transform (DCT) domain and in the Discrete Wavelet Transform (DWT) domain. Section II. discloses that feature extraction can be improved by using these domains).
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the present disclosure, to modify system and method of Lipson to transform the image data of the subject query image and the reference image into the DCT and/or DWT domains prior to performing the comparisons. One of ordinary skill in the art would have been motivated to make the modification to improve the accuracy of feature extraction by using the DCT and/or DWT domain images in cases in which doing so improves extraction results since Fasihi discloses that doing so can improve feature extraction in certain cases. The modification could have been made by one of ordinary skill in the art before the effective filing date of the present disclosure with a reasonable expectation of success because making the modification merely involves combining prior art elements according to known methods to yield predictable results (modifying the software executed by the image processing system of Lipson to perform DCT and/or DWT transformations on subject and reference images before calculating the comparison values).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DANIEL J SANTOS whose telephone number is (571)272-2867. 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, Matt Bella can be reached at (571)272-7778. 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.
/DANIEL J. SANTOS/Examiner, Art Unit 2667
/MATTHEW C BELLA/Supervisory Patent Examiner, Art Unit 2667
Prosecution Insights