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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's RCE submission filed on 04/03/2026 has been entered.
Response to Amendment
The amendment filed 04/03/2026 has been entered. Applicant’s amendments to the claims have overcome each and every objection previously set forth in the Final Office Action mailed 01/16/2026. Claims 1, 3, 5-6, 11-13, and 15 remain pending in the application, with claims 2, 4, 7-10, 14, and 16-20 having been cancelled.
Response to Arguments
Applicant's arguments in the Remarks filed 04/03/2026 have been fully considered but they are not persuasive. Applicant argues on pg. 7-8 that Covington fails to describe the amended portion of claim 1. The examiner respectfully disagrees.
In paragraph 140-141, Covington describes the medical scan similarity analysis function. This algorithm computes a distance between feature vectors of medical scan images and can identify a similar medical scan (the second slice in claim 1) which is the image with the smallest similarity distance. Since a larger distance indicates that vectors are different from one another, the smallest distance indicates the image with the highest similarity.
Paragraph 49 is cited to describe how the system can identify similar scan data. Paragraph 49 lists the medical scan similarity analysis function as a method for retrieving similar scan data (a scan similar to the first slice in claim 1). Paragraph 252, which describes medical scans 3005 and 3006 that are mapped in claim 1, also describes that the medical scan similarity analysis function may be used to retrieve a similar image. In view of the foregoing, Covington is relied on to teach the amended portion of claim 1.
Claim Objections
Claim 1 is objected to because of the following informalities: “image similarity between first slice” should read “image similarity between the first slice”. Appropriate correction is required.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitations are: “processing units”, “receiving unit”, and “medical imaging unit” in claim 13.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Regarding claim 13, the broadest reasonable interpretation for “processing units”
will be defined as the following corresponding structure and equivalents thereof: any
type of computational circuit capable of executing the described method steps, as
described in paragraphs 156-157 in the specification. The broadest reasonable
interpretation for “receiving unit” will be defined as the following corresponding structure
and equivalents thereof: any hardware/software combination that can be configured to
receive one or more medical images captured by a medical imaging unit and/or execute
a program, as described in paragraphs 140-141 in the specification. The broadest
reasonable interpretation for “medical imaging unit” will be defined as the following
corresponding structure and equivalents thereof: any imaging device intended to
capture anatomical objects associated with a patient, as described in paragraph 46 of
the specification.
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.
Claims 1, 5-6, 12-13, and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Alpert et al. (U.S. Patent No. 10,706,575 B2), hereinafter Alpert, in view of Covington et al. (U.S. Patent No. 2022/0037019 A1), hereinafter Covington, in further view of Bak et al. (U.S. Patent No. 2017/0256057 A1), hereinafter Bak.
Regarding claim 1, Alpert teaches a computer-implemented method for automated processing of medical images to output alerts for detected dissimilarities in the medical images (Alpert, abstract and col 3, ln 12-15: “Asymmetry detection compares images of a pair of organs to identify discrepancies between the two images which may constitute a tumor”), the method comprising:
receiving a first medical image of an anatomical object of a patient, the first medical image being acquired at a first instance of time (Alpert, col 5, ln 30: “first image”; images compared are from two instances of time, see col 3, ln 15-17: “Asymmetry detection can be similarly employed in cases where the same body part is imaged at two different times”);
receiving a second medical image of the anatomical object of the patient, the second medical image being acquired at a second instance of time (Alpert, col 5, ln 31: “second image”; see last citation regarding two instances of time);
determining an image similarity between first image data of the first slice and second image data of the second slice (Alpert, cross patch distinctness (CPD) score, which indicates a degree of similarity between images; col 6, ln 50-55: “the CPD score is calculated for each respective pair or set of patches…The CPD calculation accounts for patch distinctness (i.e., saliency) within and between images”; col 6, ln 64-66: “a larger score indicates increasing distinctness of a given patch compared to the other patches of the image”; the compared images may be two-dimensional slices, col 4, ln 18-21: “The images can be two dimensional or three dimensional, or a set of two dimensional images wherein the plurality of images represents a third dimension.”);
determining a dissimilarity between the first slice and the second slice based on the image similarity (Alpert, cross saliency score, col 8, ln 49-50: “the final cross saliency score (CS) is calculated. In various embodiments, the final score uses both CPD and NNE measurements”; saliency indicates degree of difference, col 4, ln 1-5: “The distinctness (i.e., saliency) of a set of pixels within an image is characterized by a degree of difference of the patch under consideration compared to the average patch of the image”), the dissimilarity defining at least one location of dissimilarity between the first slice and the second slice (Alpert, col 6, ln 1-6: “the results can indicate the location of the identified asymmetry or asymmetries within the image”; refer also to the most previous set of citations – the saliency between a set of pixels indicates the degree of dissimilarity at the location where the pixels are located; see examples of locations of patch differences described in col 11, ln 1-30); and
outputting an alert for the dissimilarity as a third medical image, the third medical image being generated based on at least one of the first medical image or the second medical image (Alpert, original image with overlaid cross-saliency scores, col 8, ln 64-67: “The presentation can be in the form of a graph, a table, and/or the original image(s) overlaid with the cross-saliency scores”).
Alpert teaches wherein the compared images may be two-dimensional slices, but fails to explicitly teach: analyzing the first medical image to identify one or more lesions; automatically extracting a first slice of the first medical image based on the one or more lesions identified in the first medical image; extracting a second slice of the second medical image by identifying, from a plurality of slices of the second medical image, the second slice based on a slice similarity between the second slice and the first slice, the second slice having a highest slice similarity with the first slice of each of the plurality of slices of the second medical image, the slice similarity based on a first slice feature vector of the first slice including characteristic features of the first slice and a second slice feature vector of the second slice including second characteristic features of the second slice.
Further, Alpert teaches determining an image similarity between sets of patches (Alpert, col 6, ln 50-51: “the CPD score is calculated for each respective pair or set of patches”), but fails to explicitly teach determining an image similarity by: obtaining a first feature signature from the first medical image based on the first image data of the first slice by defining a plurality of first patches in the first slice and obtaining for each of the plurality of first patches a first feature vector based on image data of a respective first patch, the first feature signature including the plurality of first feature vectors, obtaining a second feature signature from the second medical image based on the second image data of the second slice by defining a plurality of second patches in the second slice and obtaining for each of the plurality of second patches a second feature vector based on image data of a respective second patch, the second feature signature including the plurality of second feature vectors, and calculating a similarity signature based on the first feature signature and the second feature signature, the similarity signature indicating the image similarity between the first slice and the second slice.
Lastly, as demonstrated above, Alpert teaches outputting a third medical image with alerts for dissimilarity between the first slice and second slice, but fails to explicitly teach the third medical image including a visual indication at the at least one location of dissimilarity on the third medical image of the dissimilarity between the first slice and the second slice (emphasis added).
However, Covington teaches a method for comparing two medical images (Covington, para 39), further disclosing: analyzing a first medical image to identify one or more lesions (Covington, para 251: “the lesion is detected in an image slice of the image data 410”; para 250: “the lesion detection function 3020 is performed on image data 410 on medical scan entries 3005 and 3006 to determine an anatomical location of the lesion, to determine a subset of image slices that contains the lesion for each medical scan”); automatically extracting a first slice of the first medical image based on the one or more lesions identified in the first medical image (Covington, para 252: “medical scan entry 3005”; see Figure 12D, medical scan 3005 shows a slice, from a scan from a prior year, containing a lesion; see para 251 where slices containing the lesion are identified); extracting a second slice of the second medical image (Covington, para 252: “medical scan entry 3006”; see Figure 12D; slices are from two different images, para 249: “medical scan entry 3006 can be received as longitudinal data 433 of medical scan entry 3005”) by identifying, from a plurality of slices of the second medical image, the second slice based on a slice similarity between the second slice and the first slice (Covington, identify a similar 2-D image, para 140: “identifying one or more similar medical scans or one or more similar cropped two-dimensional images from a database of medical scans”; scan similarity can be performed on slices, para 37: “automatically determining the image slice that most closely matches the anatomical region corresponding to the currently displayed slice of the current scan”), the second slice having a highest slice similarity with the first slice of each of the plurality of slices of the second medical image (Covington, determine the scan with the smallest distance, para 141: “The medical scan similarity analysis function can include computing a similarity distance such as the Euclidian distance between the feature vectors, and assigning the similarity distance to the corresponding medical scan in the set. Similar medical scans can be identified based on determining one or more medical scans in the set with a smallest computed similarity distance”; the medical scan can be one slice, para 59: “medical scan image data 410 can include one or more image slices”), the slice similarity based on a first slice feature vector of the first slice including characteristic features of the first slice and a second slice feature vector of the second slice including second characteristic features of the second slice (Covington, para 141: “scan similarity algorithm, which can include generating a feature vector for the given medical scan and for medical scans in the set of medical scans, where the feature vector can be generated based on quantitative and/or category based visual features, inferred features, abnormality location and/or characteristics such as the predetermined size and/or volume, patient history and/or risk factor features, or other known or inferred features”). It would have been obvious to a person having ordinary skill in the art, before the effective filing date of the claimed invention, to have combined the method of automatically extracting slices, taught by Covington, with the method of Alpert in order to automatically select relevant images for longitudinal comparison, reducing the burden on the medical professional to select the slices out of a potentially large number of images/slices (Covington, para 46: “The medical scan image analysis system can be used to generate and/or perform computer vision based medical scan image analysis functions utilized by other subsystems of the medical scan processing system as described herein, aiding medical professionals to diagnose patients and/or to generate further data and models to characterize medical scans”; para 36: “the medical scan assisted review system can automatically select a previous scan that compares most favorably to the longitudinal parameters”; see also para 39). Further, Covington teaches wherein the images may subsequently be compared to detect changes, similar to the method taught by Alpert (Covington, para 49: “At least one cross-sectional image can be selected from each medical scan of the subset of medical scans for display on a display device associated with a user of the medical scan comparison system in conjunction with the medical scan”; para 264: “the measurement data can be displayed as state change data of abnormalities detected in longitudinal data as described in conjunction with the of the medical scan assisted review system 102”; see also para 39 and 269).
Additionally, Covington teaches a third medical image including a visual indication at the at least one location of dissimilarity on the third medical image of the dissimilarity between the first slice and the second slice (Covington, overlays an indication at the abnormality located in the image, para 39: “this data can be displayed in one window, for example, where an increase in abnormality size is indicated by overlaying or highlighting an outline of the current abnormality over the corresponding image slice of the previous abnormality, or vice versa”; the data is a comparison between two medical images, para 39: “comparing image data of one or more previous scans and the current scan and/or by comparing abnormality data of the previous scan to abnormality data of the current scan. In some embodiments, such metrics can be calculated by utilizing the medical scan similarity analysis function, for example, where the output of the medical scan similarity analysis function such as the similarity score indicates distance, error, or other measured discrepancy”). It would have been obvious to a person having ordinary skill in the art, before the effective filing date of the claimed invention, to have combined the visual indication at the location of dissimilarity, taught by Covington, with the method of Alpert in order to visually indicate to the user where the dissimilarities are located in the medical image, thus further aiding clinicians during diagnosis, treatment planning, etc. (Covington, para 39: “increase in abnormality size is indicated…for example, indicating if a growth rate is lessening or worsening over time”).
Lastly, Bak teaches a method for determining dissimilarities between two images (Bak, abstract), further disclosing: obtaining a first feature signature from the first image based on the first image data of the first slice by defining a plurality of first patches in the first slice (Bak, para 26: “divides the first image into a first plurality of patches”; step 902 in Fig. 9) and obtaining for each of the plurality of first patches a first feature vector based on image data of a respective first patch (Bak, patch feature vectors of para 27, para 27: “extracts a first plurality of feature vectors from each of the first plurality of patches”; step 903 in Fig. 9), the first feature signature including the plurality of first feature vectors (Bak, plurality of first feature vectors is the first feature signature),
obtaining a second feature signature from the second image based on the second image data of the second slice by defining a plurality of second patches in the second slice (Bak, para 26: “divides…the second image into a second plurality of patches wherein each patch of the second plurality of patches corresponds to one of the first plurality of patches at a same location”; step 902 in Fig. 9) and obtaining for each of the plurality of second patches a second feature vector based on image data of a respective second patch (Bak, patch feature vectors of para 27, para 27: “extracts…a second plurality of feature vectors from each of the second plurality of patches”; step 903 in Fig. 9), the second feature signature including the plurality of second feature vectors (Bak, plurality of second feature vectors is the second feature signature), and
calculating a similarity signature based on the first feature signature and the second feature signature (Bak, dissimilarity measures for patches, para 27: “executable code 140 may learn a dissimilarity function for feature vectors extracted from patches. Executable code 140 may define the dissimilarity measure as…”, see Equation 2 in para 27 where the variables are the feature vectors from the patches), the similarity signature indicating the image similarity between the first slice and the second slice (Bak, dissimilarity measure of para 27 indicates image similarity – if dissimilarity is low, then this indicates more similarity between images; para 18: “image comparison module 147 may determine that image 102 depicts the same object as image 101 if the aggregate image measures for image 101 and image 102 are similar”).
Alpert and Bak each disclose methods for determining dissimilarities between two images based on the similarity between corresponding patches. A person of ordinary skill in the art, before the effective filing date of the claimed invention, would have recognized that the patch level feature vector comparison method of Bak could have been substituted for the asymmetry detection method of Alpert because both utilize quantified values indicating similarity between two patches. Furthermore, a person of ordinary skill in the art would have been able to carry out the substitution.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to substitute the patch level feature vector comparison of Bak for the asymmetry detection method of Alpert according to known methods to yield the predictable result of determining differences between two images based on extracted image features in each patch. A person of ordinary skill in the art would have been able to utilize the dissimilarity measure of Bak, substituted for the CPD score of Alpert, in order to influence the final saliency score of Alpert, which determines dissimilarity between two patches.
Regarding claim 5 (dependent on claim 1), Alpert in view of Covington and Bak teaches wherein the calculating the similarity signature includes, for each first patch of the plurality of first patches, calculating a local similarity based on the first feature vector of a respective first patch and the second feature vector of a corresponding second patch, wherein the local similarity indicates a degree of similarity between the image data of the respective first patch and the image data of the corresponding second patch (Bak, patch dissimilarity measure; see Equation 2 in para 27, para 27: “executable code 140 may learn a dissimilarity function for feature vectors extracted from patches…
p
i
k
and
p
j
k
are the feature vectors extracted from patches at location k in the first image i and the corresponding location k in the second image j”; para 32: “each patch dissimilarity measure being a dissimilarity between corresponding patches of the first plurality of patches and the second plurality of patches”).
Regarding claim 6 (dependent on claim 5), Alpert in view of Covington and Bak teaches wherein the determining the dissimilarity comprises: identifying dissimilar pairs of first image patches and second image patches based on the local similarities (see combination of Alpert in view of Bak in claim 1 and 5 wherein Bak determines local similarities. The dissimilarity measure, taught by Bak, is similar to the CPD score in that it is an indicator of similarity used to identify dissimilar patches. Alpert teaches further wherein if patches are not distinct from each other, the patch is not considered salient, or different - col 6, ln 64-67 to col 7, ln 1-2: “Thus, a larger score indicates increasing distinctness of a given patch compared to the other patches of the image.”).
Regarding claim 12 (dependent on claim 1), Alpert in view of Covington and Bak teaches wherein the determining the image similarity between image data of the first medical image and image data of the second medical image comprises: applying a trained machine learning algorithm on image data of the first medical image and the second medical image, the trained machine learning algorithm is adapted to determine image similarities between medical images (Bak, executable code is trained with training data, para 27: “recognition performance may be a function of available training data, which may limit the number of patch metrics that executable code 140 can learn efficiently”; see combination in claim 1 wherein the images compared are medical images).
Regarding claim 13 (dependent on claim 1), Alpert in view of Covington and Bak teaches a computer-implemented device for automated processing of medical images to output alerts for detected dissimilarities in medical images (Alpert, abstract and col 3, ln 12-15: “Asymmetry detection compares images of a pair of organs to identify discrepancies between the two images which may constitute a tumor”), the computer-implemented device comprising:
one or more processing units (Alpert, col 9, ln 16-21: “one or more processors (CPUs) 305”; Fig. 3);
a receiving unit which is configured to receive one or more medical images (Alpert, col 9, ln 63: “The storage 330 stores one or more images 334”) captured by a medical imaging unit (Alpert, col 4, ln 12-18: “The images can be any type of image including, but not limited to, electron microscopy (EM), x-ray computed tomography (CT), magnetic resonance (MR)…among others”); and
a memory coupled to the one or more processing units (Alpert, col 9, ln 16-21: “memory 325, coupled with CPUs by the interconnect 320”; Fig. 3), the memory comprising a module configured to perform the method of claim 1 (Alpert, col 10, ln 1: “asymmetry detection instructions 328”; see combination with Covington and Bak to teach the method in 1).
Regarding claim 15 (dependent on claim 1), Alpert in view of Covington and Bak teaches a non-transitory computer readable medium storing a computer program (Alpert, col 9, ln 62-63: “The memory 325 stores asymmetry detection instructions 328”; instructions further detailed in col 10, ln 1-14; see also Fig. 3) that, when executed by a system, causes the system to perform the method of claim 1 (Alpert, col 10, ln 3-5: “the asymmetry detection instructions 328 are executed by one or more CPUs 305 to analyze one or more images 334”; see combination with Covington and Bak to teach the method in claim 1).
Claims 3 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Alpert in view of Covington, in further view of Bak and Dong et al. (U.S. Patent No. 2012/0207396 A1), hereinafter Dong.
Regarding claim 3 (dependent on claim 1), Alpert in view of Covington and Bak teaches using a pre-determined threshold to compare image similarity (Alpert, col 7, ln 48-51: “externally salient patches are defined in cases where the difference in variation between the matched patches is above a first threshold”), but the compared similarity is not explicitly the CPD taught by Alpert or the patch dissimilarity measure taught by Bak (the image similarity). However, Dong teaches a method for comparing image patches (Dong, para 31: “image processor 218 may perform a similarity determination procedure to determine whether a patch A (P(A)) 314 is similar to a patch B (P(B)) 318”). Dong teaches wherein the determining the dissimilarity comprises: comparing the image similarity with a pre-determined threshold (Dong, para 33: “candidate patch 318 is determined to be a similar patch with respect to target patch 314 if a similarity distance between the two patches 314 and 318 is less than a selectable similarity threshold value”; determining similar patches also determines the dissimilar patches, which are the patch pairs that are above the threshold and thus not similar).
Alpert in view of Covington and Bak discloses a base method for determining a similarity for each patch pair (similarity signature in claim 1), but does not specify specific methods for comparing these values to a threshold (Bak is relied on to teach the dissimilarity measure in claim 1, but does not disclose a threshold). Dong teaches the known technique of comparing a similarity value to a threshold to define at what point image pairs are considered similar or dissimilar. A person having ordinary skill in the art, before the effective filing date of the claimed invention, could have applied the known technique, as taught by Dong, in the same way to the patches and similarity signature in the method taught by Alpert in view of Covington and Bak and achieved predictable results of clearly defining which patches are dissimilar based on the similarity value (Dong, para 9: “Another critical part of the local image similarity measure is the threshold at which a pixel or an image patch is considered to be similar…If the threshold is too large, the similar measure may include some pixels that are not similar. If it is too small, the similar measure will not find a statistically significant number of similar pixels”). While Dong teaches a local image patch comparison, the method of comparing the similarity of two patches to a threshold could be applied to patches from two different images.
Regarding claim 11 (dependent on claim 1), Alpert in view of Covington and Bak teaches wherein the calculating the similarity signature includes, for each of the plurality of first patches, calculating a similarity value between the first slice and in the second slice (Bak, para 27: “dissimilarity measure”; see Equation 2 in para 27, para 27: “executable code 140 may learn a dissimilarity function for feature vectors extracted from patches…
p
i
k
and
p
j
k
are the feature vectors extracted from patches at location k in the first image i and the corresponding location k in the second image j”; see combination with Covington in claim 1 wherein the two images compared are the first and second slice).
Alpert in view of Covington and Bak teaches using a pre-determined threshold to compare image similarity (Alpert, col 7, ln 48-51: “externally salient patches are defined in cases where the difference in variation between the matched patches is above a first threshold”), but the compared similarity is not explicitly the CPD taught by Alpert or the patch dissimilarity measure taught by Bak; thus failing to explicitly teach the at least one location of dissimilarity is defined based on a comparison of the similarity value with a threshold. However, Dong teaches a method for comparing image patches (Dong, para 31: “image processor 218 may perform a similarity determination procedure to determine whether a patch A (P(A)) 314 is similar to a patch B (P(B)) 318”). Dong teaches the at least one location of dissimilarity is defined based on a comparison of the similarity value with a threshold (Dong, para 33: “candidate patch 318 is determined to be a similar patch with respect to target patch 314 if a similarity distance between the two patches 314 and 318 is less than a selectable similarity threshold value”; determining similar patches also determines the dissimilar patches, which are the patch pairs that are above the threshold and thus not similar).
Alpert in view of Covington and Bak discloses a base method for determining a similarity for each patch pair (similarity signature in claim 1) and using the similarity to determine locations of dissimilarity (Alpert, col 6, ln 1-6: “the results can indicate the location of the identified asymmetry or asymmetries within the image”), but does not specify specific methods for comparing these values to a threshold (Bak is relied on to teach the dissimilarity measure in claim 1, but does not disclose a threshold). Dong teaches the known technique of comparing a similarity value to a threshold to define at what point image pairs are considered similar or dissimilar. A person having ordinary skill in the art, before the effective filing date of the claimed invention, could have applied the known technique, as taught by Dong, in the same way to the patches and similarity signature in the method taught by Alpert in view of Covington and Bak and achieved predictable results of clearly defining which patches are dissimilar based on the similarity value (Dong, para 9: “Another critical part of the local image similarity measure is the threshold at which a pixel or an image patch is considered to be similar…If the threshold is too large, the similar measure may include some pixels that are not similar. If it is too small, the similar measure will not find a statistically significant number of similar pixels”). While Dong teaches a local image patch comparison, the method of comparing the similarity of two patches to a threshold could be applied to patches from two different images.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Chen (CN Patent No. 109271870 A) teaches a method for determining vector similarity of image patches (pg. 10, para 21: “the detection image and the reference image are divided into blocks for feature extraction to obtain multiple local features. Since local features can better highlight the detailed features of pedestrians and fully integrate the advantages of local and global features of the detection image and the reference image, it is beneficial to improve the accuracy of subsequent pedestrian re-identification. Next, the vector similarity between the feature vector of the detection image and the feature vector of each reference image is calculated”).
Barkol et al. (U.S. Patent No. 2011/0216979 A1) teaches a method for determining the similarity between image patches.
PNG
media_image1.png
405
308
media_image1.png
Greyscale
Examples of content-based medical image retrieval using feature similarity measures:
U.S. Patent No. 2019/0307327 A1 (para 239-240)
Mustapha, A., Hussain, A., Samad, S.A. et al. Design and development of a content-based medical image retrieval system for spine vertebrae irregularity. BioMed Eng OnLine 14, 6 (2015). https://doi.org/10.1186/1475-925X-14-6.
PNG
media_image2.png
400
614
media_image2.png
Greyscale
Srivastava, A., Gupta, P., & ParthaSarathi, M. (2016, June). Brain slice representation via feature point maps and retrieval using similarity distance metrics. In 2016 Conference on Advances in Signal Processing (CASP) (pp. 311-314). IEEE.
Glatard, T., Montagnat, J., & Magnin, I. E. (2004, October). Texture based medical image indexing and retrieval: application to cardiac imaging. In Proceedings of the 6th ACM SIGMM international workshop on Multimedia information retrieval (pp. 135-142).
Bergamasco, L. C., & Nunes, F. L. (2015). Three-dimensional Content-Based Cardiac Image Retrieval using global and local descriptors. AMIA ... Annual Symposium proceedings. AMIA Symposium, 2015, 1811–1820.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to EMMA E DRYDEN whose telephone number is (571)272-1179. The examiner can normally be reached M-F 9-5 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, ANDREW BEE can be reached at (571) 270-5183. 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.
/EMMA E DRYDEN/Examiner, Art Unit 2677
/ANDREW W BEE/Supervisory Patent Examiner, Art Unit 2677
Prosecution Insights