DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
Please provide certified copies of the foreign priority documents to the office.
Information Disclosure Statement
The information disclosure statement (“IDS”) filed on 07/01/2024 has been reviewed and the listed references have been considered.
Drawings
The 4-page drawings have been considered and placed on record in the file.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 15 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. Specifically, Claim 15 recites “the at least one implant”. There is insufficient antecedent basis for “at least one implant” in the claim.
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, 2, 8 and 9 are rejected under 35 U.S.C. 103 as being unpatentable over Wright (US 2021/0327065 A1) in view of Liu et al. (Automatic lung segmentation in chest X ray images using improved U Net).
Regarding claim 1, Wright teaches, A processor implemented method, comprising: collecting, via one or more hardware processors, an X-ray image (Wright, ¶0021: “a method for using a computer system”; and ¶0022: “radiographic imagery means, processing means, and display means to take x-ray images”) of a subject as input; (Wright, ¶0042: “x-ray taken from the front to back of a patient resulting in a radiograph”) extracting, using a (Wright, ¶0024: “confidently classify implants using plain radiographs, automated image processing using artificial intelligence (AI), machine learning (ML), deep learning and regression analysis for implant identification”) a plurality of features of at least one implant in the X-ray image, (Wright, ¶0036: “obtaining an initial conventional x-ray radiograph, or other suitable imaging of the affected area, and especially procuring the profile of an implanted prosthesis”) (Wright, ¶0084: “a match has been calculated employing image pixel processing comparisons”) the extracted plurality of features with a set of manufacturer specifications; (Wright, ¶0084: “determine an implant database match and to generate a report on the identified implant including information on the manufacturer of the identified implant”) and identifying, via the one or more hardware processors, type (Wright, ¶0018: “Implant identification information designating a type of the medical implant”) and manufacturer of the at least one implant, (Wright, ¶0030: “obtain the identified prosthesis manufacturer company information”) based on a match found for the extracted plurality of features (Wright, ¶0084: “a matching program 80 configured to perform matching operations using a matching algorithm based on implant profile”) with the manufacturer specifications. (Wright, ¶0079: “The models are listed by manufacturer model numbers found within the prosthesis profile matching database”. However, Wright does not explicitly teach, wherein the 3-block classifier extracts the plurality of features using a) an encoder-decoder block, b) a convolution dense block, and c) a classification block.
In an analogous field of endeavor, Liu teaches, wherein the 3-block classifier extracts the plurality of features using a) an encoder-decoder block, (Liu, page 2, ¶02: “The encoder is Efficientnet-b4”; and Liu, page 2, ¶03: “The decoder consists of five blocks”) b) a convolution dense block, (Liu, page 2, ¶03: “two-dimensional convolution layer continues to extract image information”) and c) a classification block. (Liu, page 7, ¶02: “segmentation can be regarded as pixel-level classification”).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Wright using the teachings of Liu to introduce a 3-block classifier. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of automatically classifying an implant detected in an x-ray image. Therefore, it would have been obvious to combine the analogous arts Wright and Liu to obtain the invention in claim 1.
Regarding claim 2, Wright in view of Liu teaches, The processor implemented method of claim 1, wherein an encoder section of the encoder-decoder block comprises a plurality of convolution blocks arranged in a sequence, (Liu, Fig. 3: the blocks are arranged in a sequence) and wherein a first convolution block in the plurality of convolution blocks comprises of a 2D convolution layer, a leakyRelu layer, and a Dropout layer, (Liu, Fig. 3: Please refer to the first block in the image below) and each subsequent convolution block among the plurality of convolution blocks comprises the 2D convolution layer, the leakyRelu layer, the Dropout layer, and a batch normalization layer. (Liu, Fig. 3: Please refer to the subsequent blocks of the image below).
PNG
media_image1.png
429
764
media_image1.png
Greyscale
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Wright in view of Liu using the additional teachings of Liu to introduce a batch normalization layer. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of stabilizing and accelerating the training of the classifier. Therefore, it would have been obvious to combine the analogous arts Wright and Liu to obtain the invention in claim 2.
Regarding claim 8, it recites a system with elements corresponding to the steps of the method recited in claim 1. Therefore, the recited elements of system claim 8 are mapped to the proposed combination in the same manner as the corresponding steps in method claim 1. Additionally, the rationale and motivation to combine Wright and Liu presented in rejection of claim 1, apply to this claim. Additionally, Wright teaches, A system, comprising: one or more hardware processors; (Wright, ¶0022: “The system can be used together with radiographic imagery means, processing means”) a communication interface; (Wright, ¶0107: “the information transfer may be implemented by a global computer network”) and a memory storing a plurality of instructions, (Wright, ¶0108: “instructions on a computer-readable medium such as random access memory”) wherein the plurality of instructions cause the one or more hardware processors to: (Wright, ¶0107: “hardware, software or firmware applications may be implemented”).
Regarding claim 9, it recites a system with elements corresponding to the steps of the method recited in claim 2. Therefore, the recited elements of system claim 9 are mapped to the proposed combination in the same manner as the corresponding steps in method claim 2. Additionally, the rationale and motivation to combine Wright and Liu presented in rejection of claim 2, apply to this claim.
Claims 3 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Wright (US 2021/0327065 A1) in view of Liu et al. (Automatic lung segmentation in chest X ray images using improved U Net) and in further view of Ansari et al. (US 2021/0304855 A1).
Regarding claim 3, Wright in view of Liu teaches, The processor implemented method of claim 1. However, the combination of Wright and Liu does not explicitly teach, wherein a decoder section of the encoder-decoder block comprises a plurality of 2D transposed convolution up-sampling blocks arranged in a sequence, and wherein each of the plurality of 2D transposed convolution up-sampling blocks comprises of a convolutional 2D transpose layer, a batch normalization layer, a leakyRelu layer, and a Dropout layer.
In an analogous field of endeavor, Ansari teaches, wherein a decoder section of the encoder-decoder block comprises a plurality of 2D transposed convolution up-sampling blocks arranged in a sequence, and wherein each of the plurality of 2D transposed convolution up-sampling blocks comprises of a convolutional 2D transpose layer, a batch normalization layer, a leakyRelu layer, and a Dropout layer. (Ansari, ¶0051: “the decoding layers 108 may include one or more constituent processing layers/filters, such as a transposed convolution layer, a batch normalization layer, an ReLU layer, a dropout layer/filter, upsampling layer, etc”).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Wright in view of Liu using the teachings of Ansari to introduce up sampling through a transposed convolution. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of increasing the resolution of the input. Therefore, it would have been obvious to combine the analogous arts Wright, Liu and Ansari to obtain the invention in claim 3.
Regarding claim 10, it recites a system with elements corresponding to the steps of the method recited in claim 3. Therefore, the recited elements of system claim 10 are mapped to the proposed combination in the same manner as the corresponding steps in method claim 3. Additionally, the rationale and motivation to combine Wright, Liu and Ansari presented in rejection of claim 3, apply to this claim.
Claims 4 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Wright (US 2021/0327065 A1) in view of Liu et al. (Automatic lung segmentation in chest X ray images using improved U Net) and in further view of Schnieder et al. (US 2023/0206942 A1).
Regarding claim 4, Wright in view of Liu teaches, The processor implemented method of claim 1, wherein the convolution dense block comprises a convolution block and a plurality of dense blocks, wherein the convolution block comprises 256 filters, (Liu, page 5, ¶01: “To use Efficientnet-b4, the images were downsized to 256 × 256 pixels as a pre-processing step”) (Liu, page 2, ¶02: “Upsampling also makes the information, such as the restored edge of the segmented image, finer”) using the 256 filters and one or more feature maps, and features of each of the plurality of dense blocks is combined with data (Liu, page 2, ¶02: “finally recovered feature map integrates more low-level features and enables the fusion of elements of different scales”) from an activation layer (Liu, page 2, ¶05: “LeakyReLU29 was used as the activation function”) using a concatenation block. (Liu, page 2, ¶02: “concatenate three residual blocks in each decoding block”).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Wright in view of Liu using the additional teachings of Liu to introduce feature maps. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of combining features of different levels for feature identification. Therefore, it would have been obvious to combine the analogous arts Wright and Liu to obtain the above-described limitations in claim 4. However, the combination of Wright and Liu does not explicitly teach, a leakyRelu layer, and a batch normalization layer, and each of the plurality of dense blocks comprises a dense layer, the leakyRelu layer, and the batch normalization layer.
In an analogous field of endeavor, Schneider teaches, a leakyRelu layer, and a batch normalization layer, and each of the plurality of dense blocks comprises a dense layer, the leakyRelu layer, and the batch normalization layer (Schneider, ¶0514: “The classification dense network may include two linear blocks, each of which includes linear layers, LeakyReLU activation layers, batch normalization layers, and dropout layers followed by a final linear layer that outputs class wise logits”).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Wright in view of Liu using the teachings of Schneider to introduce a dense network. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of automatic image classification using a dense network. Therefore, it would have been obvious to combine the analogous arts Wright, Liu and Schneider to obtain the invention in claim 4.
Regarding claim 11, it recites a system with elements corresponding to the steps of the method recited in claim 4. Therefore, the recited elements of system claim 11 are mapped to the proposed combination in the same manner as the corresponding steps in method claim 4. Additionally, the rationale and motivation to combine Wright, Liu and Schneider presented in rejection of claim 4, apply to this claim.
Claims 5 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Wright (US 2021/0327065 A1) in view of Liu et al. (Automatic lung segmentation in chest X ray images using improved U Net), in further view of Ansari et al. (US 2021/0304855 A1) and still in further view of Grover et al. (US 2019/0053790 A1).
Regarding claim 5, Wright in view of Liu and in further view of Ansari teaches, The processor implemented method of claim 4. However, the combination of Wright, Liu and Schneider does not explicitly teach, wherein a sobel filter is used for capturing a plurality of edge-based features of the at least one implant, wherein the plurality of edge-based features comprises one or more of edges of the at least one implant, one or more screws present in the at least one implant, one or more domes of the at least one implant, and pointed bottom shape of implant.
In an analogous field of endeavor, Grover teaches, wherein a sobel filter is used (Grover, ¶0102: “the Sobel edge detection method was used to find the location parameters of each gel”) for capturing a plurality of edge-based features of the at least one implant, (Grover, ¶0011: “one or more implant features including: echogenicity, length/width of the implant, the location of the implant, the homogeneity or heterogeneity of the implant”) wherein the plurality of edge-based features comprises one or more of edges of the at least one implant, (Grover, ¶0037: “the edge information is extracted, numerous morphological techniques may be applied to the image(s). These include, but are not limited to erosion, dilation, and filling techniques, which formulate and extract ROIs”) one or more screws present in the at least one implant, one or more domes of the at least one implant, and pointed bottom shape of implant. (Grover, ¶0047: “The ROI can also be extracted by having the program search for a specific shape, or near specific shape, that the implant will adopt in situ. Examples of such shapes refer to both 2D and 3D aspects, including but not limited to circles, squares, rectangles, triangles, spheres, cubes, cylinders, or pyramids, or even irregular shapes”).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Wright in view of Liu and in further view of Schneider using the teachings of Grover to introduce detection of edge-based features. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of automatically identifying the features of a medical implant. Therefore, it would have been obvious to combine the analogous arts Wright, Liu, Schneider and Grover to obtain the invention in claim 5.
Regarding claim 12, it recites a system with elements corresponding to the steps of the method recited in claim 5. Therefore, the recited elements of system claim 12 are mapped to the proposed combination in the same manner as the corresponding steps in method claim 5. Additionally, the rationale and motivation to combine Wright, Liu, Ansari and Grover presented in rejection of claim 5, apply to this claim.
Claims 6, 7, 14 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Wright (US 2021/0327065 A1) in view of Liu et al. (Automatic lung segmentation in chest X ray images using improved U Net) and in further view of Pham et al. (US 2022/0383037 A1).
Regarding claim 6, Wright in view of Liu teaches, The processor implemented method of claim 1. However, the combination of Wright and Liu does not explicitly teach, wherein the classification block classifies the extracted plurality of features to a set of pre-defined feature classes.
In an analogous field of endeavor, Pham teaches, wherein the classification block classifies the extracted plurality of features to a set of pre-defined feature classes. (Pham, ¶0143: “determining a set of attributes for an object portrayed within a digital image from a combination of a high-level attribute feature map and a low-level attribute feature map utilizing a classifier neural network”)
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Wright in view of Liu using the teachings of Pham to introduce identifying a set of features. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of automatic classification of features based on the detected attributes. Therefore, it would have been obvious to combine the analogous arts Wright, Liu and Pham to obtain the invention in claim 6.
Regarding claim 7, Wright in view of Liu teaches, The processor implemented method of claim 1, wherein the 3-block classifier uses. However, the combination of Wright and Liu does not explicitly teach, a supervised contrastive loss function to eliminate a class imbalance problem while identifying the type and manufacturer of the at least one implant, and wherein while calculating loss of one class type the supervised contrastive loss function considers embeddings of one or more other classes.
In an analogous field of endeavor, Pham teaches, a supervised contrastive loss function to eliminate a class imbalance problem (Pham, ¶0095: “the multi-attribute extraction system 106 utilizes a multi-attribute, supervised contrastive loss from a multi-label setting that avoids strong label biases due to data imbalances in labeled classes”) while identifying the type and manufacturer of the at least one implant, and wherein while calculating loss of one class type the supervised contrastive loss function considers embeddings of one or more other classes. (Pham, ¶0098: “the multi-attribute extraction system 106 decreases the distances between attribute-aware embeddings of samples (e.g., pulls together) that have a shared attribute”).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Wright in view of Liu using the teachings of Pham to introduce a loss function. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of automatically balancing classifications of the feature classes based on the determined loss. Therefore, it would have been obvious to combine the analogous arts Wright, Liu and Pham to obtain the invention in claim 7.
Regarding claim 13, it recites a system with elements corresponding to the steps of the method recited in claim 6. Therefore, the recited elements of system claim 13 are mapped to the proposed combination in the same manner as the corresponding steps in method claim 6. Additionally, the rationale and motivation to combine Wright, Liu and Pham presented in rejection of claim 6, apply to this claim.
Regarding claim 14, it recites a system with elements corresponding to the steps of the method recited in claim 7. Therefore, the recited elements of system claim 14 are mapped to the proposed combination in the same manner as the corresponding steps in method claim 7. Additionally, the rationale and motivation to combine Wright, Liu and Pham presented in rejection of claim 7, apply to this claim.
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Liu et al. (Automatic lung segmentation in chest X ray images using improved U Net), in view of Ansari et al. (US 2021/0304855 A1), in further view of Schnieder et al. (US 2023/0206942 A1), still in further view of Grover et al. (US 2019/0053790 A1), yet in further view of Pham et al. (US 2022/0383037 A1) and even in further view of Wright (US 2021/0327065 A1).
Regarding claim 15, Liu teaches, A 3-block classifier, (Liu, Fig. 3: a 3 block classifier) comprising: an encoder-decoder block; (Liu, page 2, ¶02: “The encoder is Efficientnet-b4”; and Liu, page 2, ¶03: “The decoder consists of five blocks”) a convolution dense block; (Liu, page 2, ¶03: “two-dimensional convolution layer continues to extract image information”) and a classification block, (Liu, page 7, ¶02: “segmentation can be regarded as pixel-level classification”) wherein an encoder section of the encoder-decoder block comprises a plurality of convolution blocks arranged in a sequence, (Liu, Fig. 3: the blocks are arranged in a sequence) wherein a first convolution block in the plurality of convolution blocks comprises of a 2D convolution layer, a leakyRelu layer, and a Dropout layer, (Liu, Fig. 3: Please refer to the first block in the image below) and each subsequent convolution block among the plurality of convolution blocks comprises the 2D convolution layer, the leakyRelu layer, the Dropout layer, and a batch normalization layer, (Liu, Fig. 3: Please refer to the subsequent blocks of the image below”) (Liu, page 5, ¶01: “To use Efficientnet-b4, the images were downsized to 256 × 256 pixels as a pre-processing step”) (Liu, page 2, ¶02: “Upsampling also makes the information, such as the restored edge of the segmented image, finer”) using the 256 filters and one or more feature maps, and features of each of the plurality of dense blocks is combined with data (Liu, page 2, ¶02: “finally recovered feature map integrates more low-level features and enables the fusion of elements of different scales”) from an activation layer (Liu, page 2, ¶05: “LeakyReLU29 was used as the activation function”) using a concatenation block (Liu, page 2, ¶02: “concatenate three residual blocks in each decoding block”). However, Liu does not explicitly teach, a decoder section of the encoder-decoder block comprises a plurality of 2D transposed convolution up-sampling blocks arranged in a sequence, wherein each of the plurality of 2D transposed convolution up-sampling blocks comprises of a convolutional 2D transpose layer, a batch normalization layer, a leakyRelu layer, and a Dropout layer, a leakyRelu layer, and a batch normalization layer, and each of the plurality of dense blocks comprises a dense layer, the leakyRelu layer, and the batch normalization layer and a sobel filter is used for capturing a plurality of edge-based features of the at least one implant, wherein the plurality of edge-based features comprises one or more of edges of the at least one implant, one or more screws present in the at least one implant, one or more domes of the at least one implant, and pointed bottom shape of implant, the classification block classifies the extracted plurality of features to a set of pre-defined feature classes, and a supervised contrastive loss function is used to eliminate a class imbalance problem while identifying the type and manufacturer of the at least one implant, wherein while calculating loss of one class type the supervised contrastive loss function considers embeddings of one or more other classes.
In an analogous filed of endeavor, Ansari teaches, a decoder section of the encoder-decoder block comprises a plurality of 2D transposed convolution up-sampling blocks arranged in a sequence, wherein each of the plurality of 2D transposed convolution up-sampling blocks comprises of a convolutional 2D transpose layer, a batch normalization layer, a leakyRelu layer, and a Dropout layer, (Ansari, ¶0051: “the decoding layers 108 may include one or more constituent processing layers/filters, such as a transposed convolution layer, a batch normalization layer, an ReLU layer, a dropout layer/filter, upsampling layer, etc”).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu using the teachings of Ansari to introduce up sampling through a transposed convolution. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of increasing the resolution of the input. Therefore, it would have been obvious to combine the analogous arts Liu and Ansari to obtain the above-described limitations in claim 15. However, the combination of Liu and Ansari does not explicitly teach, a leakyRelu layer, and a batch normalization layer, and each of the plurality of dense blocks comprises a dense layer, the leakyRelu layer, and the batch normalization layer and a sobel filter is used for capturing a plurality of edge-based features of the at least one implant, wherein the plurality of edge-based features comprises one or more of edges of the at least one implant, one or more screws present in the at least one implant, one or more domes of the at least one implant, and pointed bottom shape of implant, the classification block classifies the extracted plurality of features to a set of pre-defined feature classes, and a supervised contrastive loss function is used to eliminate a class imbalance problem while identifying the type and manufacturer of the at least one implant, wherein while calculating loss of one class type the supervised contrastive loss function considers embeddings of one or more other classes.
In another analogous field of endeavor, Schneider teaches, a leakyRelu layer, and a batch normalization layer, and each of the plurality of dense blocks comprises a dense layer, the leakyRelu layer, and the batch normalization layer (Schneider, ¶0514: “The classification dense network may include two linear blocks, each of which includes linear layers, LeakyReLU activation layers, batch normalization layers, and dropout layers followed by a final linear layer that outputs class wise logits”).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu in view of Ansari using the teachings of Schneider to introduce a dense network. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of automatic image classification using a dense network. Therefore, it would have been obvious to combine the analogous arts Liu, Ansari and Schneider to obtain the above-described limitations in claim 15. However, the combination of Liu, Ansari and Schneider does not explicitly teach, a sobel filter is used for capturing a plurality of edge-based features of the at least one implant, wherein the plurality of edge-based features comprises one or more of edges of the at least one implant, one or more screws present in the at least one implant, one or more domes of the at least one implant, and pointed bottom shape of implant, the classification block classifies the extracted plurality of features to a set of pre-defined feature classes, and a supervised contrastive loss function is used to eliminate a class imbalance problem while identifying the type and manufacturer of the at least one implant, wherein while calculating loss of one class type the supervised contrastive loss function considers embeddings of one or more other classes.
In still another analogous field of endeavor, Grover teaches, a sobel filter is used (Grover, ¶0102: “the Sobel edge detection method was used to find the location parameters of each gel”) for capturing a plurality of edge-based features of the at least one implant, (Grover, ¶0011: “one or more implant features including: echogenicity, length/width of the implant, the location of the implant, the homogeneity or heterogeneity of the implant”) wherein the plurality of edge-based features comprises one or more of edges of the at least one implant, (Grover, ¶0037: “the edge information is extracted, numerous morphological techniques may be applied to the image(s). These include, but are not limited to erosion, dilation, and filling techniques, which formulate and extract ROIs”) one or more screws present in the at least one implant, one or more domes of the at least one implant, and pointed bottom shape of implant, (Grover, ¶0047: “The ROI can also be extracted by having the program search for a specific shape, or near specific shape, that the implant will adopt in situ. Examples of such shapes refer to both 2D and 3D aspects, including but not limited to circles, squares, rectangles, triangles, spheres, cubes, cylinders, or pyramids, or even irregular shapes”).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu in view of Ansari and in further view of Schneider using the teachings of Grover to introduce detection of edge-based features. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of automatically identifying the features of a medical implant. Therefore, it would have been obvious to combine the analogous arts Liu, Ansari, Schneider and Grover to obtain the above-described limitations in claim 15. However, the combination of Liu, Ansari, Schneider and Grover does not explicitly teach, the classification block classifies the extracted plurality of features to a set of pre-defined feature classes, and a supervised contrastive loss function is used to eliminate a class imbalance problem while identifying the type and manufacturer of the at least one implant, wherein while calculating loss of one class type the supervised contrastive loss function considers embeddings of one or more other classes.
In yet another analogous field of endeavor, Pham teaches, the classification block classifies the extracted plurality of features to a set of pre-defined feature classes, (Pham, ¶0143: “determining a set of attributes for an object portrayed within a digital image from a combination of a high-level attribute feature map and a low-level attribute feature map utilizing a classifier neural network”) and a supervised contrastive loss function is used to eliminate a class imbalance problem (Pham, ¶0095: “the multi-attribute extraction system 106 utilizes a multi-attribute, supervised contrastive loss from a multi-label setting that avoids strong label biases due to data imbalances in labeled classes”) classes. (Pham, ¶0098: “the multi-attribute extraction system 106 decreases the distances between attribute-aware embeddings of samples (e.g., pulls together) that have a shared attribute”).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu in view of Ansari, in further view of Schneider and still in further view of Grover using the teachings of Pham to introduce a loss function. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of automatically balancing classifications of the feature classes based on the determined loss. Therefore, it would have been obvious to combine the analogous arts Liu, Ansari, Schneider, Grover and Pham to obtain the above-described limitations in claim 15. However, the combination of Liu, Ansari, Schneider, Grover and Pham does not explicitly teach, while identifying the type and manufacturer of the at least one implant.
In still another analogous field of endeavor, Wright teaches, while identifying the type (Wright, ¶0018: “Implant identification information designating a type of the medical implant”) and manufacturer of the at least one implant. (Wright, ¶0084: “determine an implant database match and to generate a report on the identified implant including information on the manufacturer of the identified implant”).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu in view of Ansari, in further view of Schneider, still in further view of Grover and yet in further view of Pham using the teachings of Wright to introduce implant feature matching. A person skilled in the art would be motivated to combine the known elements as described above and achieve the predictable result of automatically identifying the type and manufacturer information using the detected features of the implant. Therefore, it would have been obvious to combine the analogous arts Liu, Ansari, Schneider, Grover, Pham and Wright to obtain the invention in claim 15.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MEHRAZUL ISLAM whose telephone number is (571)270-0489. The examiner can normally be reached Monday-Friday: 8am-5pm.
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, Saini Amandeep can be reached on (571) 272-3382. 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.
/MEHRAZUL ISLAM/Examiner, Art Unit 2662
/AMANDEEP SAINI/Supervisory Patent Examiner, Art Unit 2662
Prosecution Insights