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 .
Information Disclosure Statement
The Information Disclosure Statement filed 03/04/2025 has been considered by examiner.
Response to Amendment
Applicant has amended claims 3-5, 7, 10-12, 16-18, and 23. Applicant has cancelled claims 6, 20, and 22. Claims 1-5, 7-21 and 23 are pending.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-4, 16-19, 21, and 23 are rejected under 35 U.S.C. 103 as being unpatentable over Qin (US 10964072 B2), in view of Hsieh (US 20140056497 A1).
With respect to claim 1, Qin teaches a method for correcting a metal artifact (“Implementations of the disclosure provide for methods, systems, and media for image reconstruction using metal artifacts reductions techniques.” Col 1 lines 46-48), comprising: obtaining a first image acquired by a first imaging device and a second image acquired by a second imaging device, the second imaging device including a computed tomography (CT) device (“In some embodiments, a method for image reconstruction is provided, the method may include: receiving a first computed tomography (CT) image and a second CT image” col 1 line 48-51 and “In some embodiments, the first CT image and the second CT image may be generated by different imaging devices (e.g., different CT scanning systems).” Col 10 lines 10-13);
registering the first image and the second image (“In some embodiments, images (e.g., CT images) may be registered to generate prior images and/or to implement other functions in accordance with the present disclosure.” Col 10 lines 4-6);
determining a template image based on the registered first image and second image (see figure 6 element 603, prior image), generating a metal artifact image (see figure 6 element 606), and generating a corrected image by correcting, based on the metal artifact image (see figure 7), however Qin does not teach determining a metal artifact image based on the template image; and generating a corrected image by correcting, based on the metal artifact image, the second image.
Hsieh teaches determining template images based on the registered first image and second image (see figure 2 element 78); determining a metal artifact image based on the template images (see figure 2 element 74); and generating a corrected image by correcting, based on the metal artifact image, the second image (see figure 2 element 86).
Hsieh is analogous art in the same field of endeavor as the claimed invention. Hsieh is directed towards metal artifact correction (“FIG. 2 is a process flow diagram of an embodiment of a method for performing metal artifact correction on images” paragraph 0009). A person of ordinary skill would have found it obvious to combine the teachings of Qin and Hsieh by utilizing Qin’s dual image method of template generation as input into the correction image generation process of Hsieh, with the expectation that doing so would result in improved artifact reduction aiding in artifact correction of images (“…improve artifact reduction and to improve the shape of the metal after correction.” Paragraph 0028).
With respect to claim 2, Qin and Hsieh teach the method of claim 1, Qin further teaches wherein the first imaging device includes a CT device having a first energy level, the second imaging device includes a CT device having a second energy level, and the first energy level is greater than the second energy level (“In some embodiments, the first CT image is a kilovoltage computed tomography (KVCT) image. The second CT image is a megavoltage computed tomography (MVCT) image.” Col 1 lines 57-60 First image treated as second image and vice versa, and “Aspects of the present disclosure address the above deficiencies by providing mechanisms (e.g., systems, methods, machine-readable media, etc.) for image reconstruction and MAR. The mechanisms can reconstruct CT images, such as kilovoltage computed tomography (KVCT) images, megavoltage computed tomography (MVCT) images, megavoltage cone beam computed tomography (MVCBCT) images, etc. For example, the mechanisms can reconstruct a KVCT image based on a prior image generated based on a MVCT image (e.g., a MVCBCT image). More particularly, for example, the mechanisms can register the KVCT image and the MVCT image to generate the prior image.” Col 3 lines 35-46).
With respect to claim 3, Qin and Hsieh teach the method of claim 1, Qin further teaches wherein the first imaging device includes a megavoltage CT device and the second imaging device includes a kilovoltage CT device (“In some embodiments, the first CT image is a kilovoltage computed tomography (KVCT) image. The second CT image is a megavoltage computed tomography (MVCT) image.” Col 1 lines 57-60 First image treated as second image and vice versa, and “Aspects of the present disclosure address the above deficiencies by providing mechanisms (e.g., systems, methods, machine-readable media, etc.) for image reconstruction and MAR. The mechanisms can reconstruct CT images, such as kilovoltage computed tomography (KVCT) images, megavoltage computed tomography (MVCT) images, megavoltage cone beam computed tomography (MVCBCT) images, etc. For example, the mechanisms can reconstruct a KVCT image based on a prior image generated based on a MVCT image (e.g., a MVCBCT image). More particularly, for example, the mechanisms can register the KVCT image and the MVCT image to generate the prior image.” Col 3 lines 35-46).
With respect to claim 4, Qin and Hsieh teach the method of claim 1. Qin further teaches wherein the first image includes a cone- beam CT image, and the second image includes a diagnostic CT image (“Aspects of the present disclosure address the above deficiencies by providing mechanisms (e.g., systems, methods, machine-readable media, etc.) for image reconstruction and MAR. The mechanisms can reconstruct CT images, such as kilovoltage computed tomography (KVCT) images, megavoltage computed tomography (MVCT) images, megavoltage cone beam computed tomography (MVCBCT) images, etc. For example, the mechanisms can reconstruct a KVCT image based on a prior image generated based on a MVCT image (e.g., a MVCBCT image). More particularly, for example, the mechanisms can register the KVCT image and the MVCT image to generate the prior image.” Col 3 lines 35-46).
With respect to claim 16, Qin and Hsieh teach the method of claim 1. Qin further teaches wherein the generating a corrected image by correcting, based on the metal artifact image, the second image includes: obtaining a processed metal artifact image by filtering the metal artifact image (see figure 7); and obtaining the corrected image by correcting, based on the processed metal artifact image, an image (see figure 7), and Hsieh teaches correcting the second image (see figure 2 element 86).
With respect to claim 17, Qin and Hsieh teach the method of claim 1. Hsieh further teaches wherein the generating a corrected image by correcting, based on the metal artifact image, the second image includes: obtaining the corrected image by subtracting the metal artifact image from the second image (“The metal artifact signal 72, .delta.(x, y, z), may be generated by subtraction of the two first-pass reconstructed images 70, f(x, y, z) and g(x, y, z) or the two scans (e.g., images 66), where f represents an image obtained at a first energy spectrum and g represents an image obtained at a second energy spectrum.” Paragraph 0027).
With respect to claim 18, Qin and Hsieh teach the method of claim 1. Qin further teaches it comprising: updating, based on the corrected image, the second image for one or more iterations (see figure 7, prior image).
With respect to claim 19, Qin and Hsieh teach the method of claim 18, wherein the updating, based on the metal artifact image, the second image for one or more iterations includes: updating the template image based on an updated second image (see figure 7, prior image); updating the metal artifact image based on an updated template image (see figure 7, prior image); obtaining an updated corrected image by correcting, based on the updated metal artifact image, the updated second image (see figure 7, prior image).
With respect to claim 21, Qin and Hsieh teach all limitations in consideration of claim 1 due to the substantial similarity between claims 1 and 21 with claim 21 being directed towards a system enabled to do the processes of claim 1. Qin further teaches A system for correcting a metal artifact, comprising: at least one storage device configured to store computer instructions (“The data storage 104 may be configured or used to store information. The information may include programs, software, algorithms, data, text, number, images, voice, or the like, or any combination thereof. The data storage 104 may receive the information from image processing device 101, a CT scanning device 103, and/or other modules or units that may generate information.” Col 6 lines 31-37); and at least one processor configured to be in communication with the at least one storage device (“The data storage 104 may be configured or used to store information. The information may include programs, software, algorithms, data, text, number, images, voice, or the like, or any combination thereof. The data storage 104 may receive the information from image processing device 101, a CT scanning device 103, and/or other modules or units that may generate information.” Col 6 lines 31-37).
With respect to claim 23, Qin and Hsieh teach all claim limitations in consideration of claim 1, due to the substantial similarities between claim 1 and claim 23, with claim 23 being directed towards a storage medium which enables a computer to perform the functions of claim 1. Qin further teaches a non-transitory computer-readable storage medium storing computer instructions, wherein when a computer reads the computer instructions in the storage medium, the computer performs a method for correcting a metal artifact (“The data storage 104 may be configured or used to store information. The information may include programs, software, algorithms, data, text, number, images, voice, or the like, or any combination thereof. The data storage 104 may receive the information from image processing device 101, a CT scanning device 103, and/or other modules or units that may generate information.” Col 6 lines 31-37)
Claims 5, 7-9 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Qin and Hiseh as applied to claim 1 above, and further in view of Bzdusek (US 9600856 B2).
With respect to claim 5, Qin and Hiseh teach the method of claim 1, but do not teach the rest of the limitations. Bzdusek teaches wherein the determining a template image based on the registered first image and second image includes: determining regions with different densities based on the first image (“Corresponding structures in the first image and the second image are manually and/or automatically identified 56 using the image segmentation routine 36. A structure includes, for example, an organ, a tumor, or other regions. Suitably, the structures are identified in at least one of regions of the images where the density or distribution of identified interest points is below a threshold, typically representative of a low density or distribution of identified points (e.g., because there are limited interest points, points with significant matching error, or other reasons), and regions of the images that have boundary contrast exceeding a threshold, typically representative of a good boundary contrast (implying a reliable segmentation accuracy)” col 5 lines 35-47), wherein the regions with different densities include a high-density region (“Suitably, the structures are identified in at least one of regions of the images where the density or distribution of identified interest points is below a threshold, typically representative of a low density or distribution of identified points (e.g., because there are limited interest points, points with significant matching error, or other reasons), and regions of the images that have boundary contrast exceeding a threshold, typically representative of a good boundary contrast (implying a reliable segmentation accuracy)” exceed threshold, col 5 line 38-47), a medium-density region (“Suitably, the structures are identified in at least one of regions of the images where the density or distribution of identified interest points is below a threshold, typically representative of a low density or distribution of identified points (e.g., because there are limited interest points, points with significant matching error, or other reasons), and regions of the images that have boundary contrast exceeding a threshold, typically representative of a good boundary contrast (implying a reliable segmentation accuracy)” in between thresholds, col 5 line 38-47), and a low-density region (“Suitably, the structures are identified in at least one of regions of the images where the density or distribution of identified interest points is below a threshold, typically representative of a low density or distribution of identified points (e.g., because there are limited interest points, points with significant matching error, or other reasons), and regions of the images that have boundary contrast exceeding a threshold, typically representative of a good boundary contrast (implying a reliable segmentation accuracy)” below threshold, col 5 line 38-47); and obtaining the template image by filling the regions with different densities based on CT values of regions in the second image corresponding to the regions with different densities (“Once the registration map is generated, the registration map can be applied 66 to the first image to register the first image to the second image. That is to say, the first image can be mapped to the coordinate frame of the second image to yield a registered image. The registration map can also be applied to propagate any object of interest (OOI) from the first to the second image.” Col 6 lines 50-56 , first image as second image and vice versa).
Bzdusek is analogous art in the same field of endeavor as the clamed invention. Bzdusek is directed towards CT image processing (See figures 1 and 2 and “The imaging modalities 12 suitably include one or more of a computed tomography (CT) scanner” col 2 (last line)-col 3 lines 1-2). A person of ordinary skill before the effective filing date of the claimed invention, would have found it obvious to combine Qin and Hsieh with Bzdusek, by utilizing Buzdusek’s registration based techniques, with the expectation that doing so would lead to more accurate (“One challenge, however, is that when performing point-based registration there can be surface or other areas with no or a dearth of identifiable points, which can lead to a lack of accuracy in the area of sparse point density. Therefore, an image segmentation routine 36 is employed.” Col 4 lines 12-17) and efficient computations across different densities (“Once the image-based registration of the pair of images is complete, corresponding pairs of boundary points from the corresponding structures are selected 60 as additional interest points, preferably intelligently to reduce computation time” col 6 lines 6-10).
With respect to claim 7, Qin, Hsieh, and Bzdusek teach the method of claim 5. Bzdusek further teaches wherein the determining regions with different densities based on the first image includes:determining the high-density region, the medium-density region, and the low- density region by processing the first image using local threshold segmentation (“Corresponding structures in the first image and the second image are manually and/or automatically identified 56 using the image segmentation routine 36. A structure includes, for example, an organ, a tumor, or other regions. Suitably, the structures are identified in at least one of regions of the images where the density or distribution of identified interest points is below a threshold, typically representative of a low density or distribution of identified points (e.g., because there are limited interest points, points with significant matching error, or other reasons), and regions of the images that have boundary contrast exceeding a threshold, typically representative of a good boundary contrast (implying a reliable segmentation accuracy)” col 5 lines 35-47).
With respect to claim 8, Qin, Hsieh, and Bzdusek teach the method of claim 7. Bzdusek teaches wherein the determining the high-density region, the medium-density region, and the low-density region by processing the first image using local threshold segmentation includes: dividing the first image into a plurality of sub-regions (“Corresponding structures in the first image and the second image are manually and/or automatically identified 56 using the image segmentation routine 36. A structure includes, for example, an organ, a tumor, or other regions. Suitably, the structures are identified in at least one of regions of the images where the density or distribution of identified interest points is below a threshold, typically representative of a low density or distribution of identified points (e.g., because there are limited interest points, points with significant matching error, or other reasons), and regions of the images that have boundary contrast exceeding a threshold, typically representative of a good boundary contrast (implying a reliable segmentation accuracy)” col 5 lines 35-47); determining, based on at least two local thresholds, a high-density sub-region, a medium-density sub-region, and alow-density sub-region of each sub-region among the plurality of sub-regions (“Corresponding structures in the first image and the second image are manually and/or automatically identified 56 using the image segmentation routine 36. A structure includes, for example, an organ, a tumor, or other regions. Suitably, the structures are identified in at least one of regions of the images where the density or distribution of identified interest points is below a threshold, typically representative of a low density or distribution of identified points (e.g., because there are limited interest points, points with significant matching error, or other reasons), and regions of the images that have boundary contrast exceeding a threshold, typically representative of a good boundary contrast (implying a reliable segmentation accuracy)” col 5 lines 35-47), and generating the high-density region, the medium-density region, and the low-density region by combining the high-density sub-regions, the medium-density sub-regions, and the low-density sub-regions of the plurality of sub-regions (“Once the image-based registration of the pair of images is complete, corresponding pairs of boundary points from the corresponding structures are selected 60 as additional interest points, preferably intelligently to reduce computation time. For example, the corresponding pairs of boundary points are limited to vertice pairs representing the extent of the structures in regions sparsely populated by interest points from the point based registration routine 32.” Col 6 lines 6-13 And “The selected boundary points (interest points) are combined 62 with the identified interest points from the point based registration routine 32.” Col 6 limes 23-25).
With respect to claim 9, Qin, Hsieh, and Bzdusek teach the method of claim 8. Bzdusek further teaches wherein the dividing the first image into a plurality of sub- regions includes: dividing the first image into the plurality of sub-regions based on contouring information (“Corresponding structures in the first image and the second image are manually and/or automatically identified 56 using the image segmentation routine 36. A structure includes, for example, an organ, a tumor, or other regions. Suitably, the structures are identified in at least one of regions of the images where the density or distribution of identified interest points is below a threshold, typically representative of a low density or distribution of identified points (e.g., because there are limited interest points, points with significant matching error, or other reasons), and regions of the images that have boundary contrast exceeding a threshold, typically representative of a good boundary contrast (implying a reliable segmentation accuracy)” col 5 lines 35-47).
With respect to claim 11, Qin, Hsieh, and Bzdusek teach the method of claim 5, Bzdusek further teaches wherein the obtaining the template image by filling the regions with different densities based on CT values of regions in the second image corresponding to the regions with different densities includes: filling the high-density region based on CT values of pixels of a first region in the second image, the first region being a region in the second image corresponding to the high-density region (“Suitably, the structures are identified in at least one of regions of the images where the density or distribution of identified interest points is below a threshold, typically representative of a low density or distribution of identified points (e.g., because there are limited interest points, points with significant matching error, or other reasons), and regions of the images that have boundary contrast exceeding a threshold, typically representative of a good boundary contrast (implying a reliable segmentation accuracy)” below threshold, col 5 line 38-47);
filling the medium-density region based on an average of CT values of pixels of a second region in the second image, the second region being a region in the second image corresponding to the medium-density region (“Suitably, the structures are identified in at least one of regions of the images where the density or distribution of identified interest points is below a threshold, typically representative of a low density or distribution of identified points (e.g., because there are limited interest points, points with significant matching error, or other reasons), and regions of the images that have boundary contrast exceeding a threshold, typically representative of a good boundary contrast (implying a reliable segmentation accuracy)” below threshold, col 5 line 38-47);
filling the low-density region based on an average of CT values of pixels of a third region in the second image, the third region being a region in the second image corresponding to the low-density region (“Suitably, the structures are identified in at least one of regions of the images where the density or distribution of identified interest points is below a threshold, typically representative of a low density or distribution of identified points (e.g., because there are limited interest points, points with significant matching error, or other reasons), and regions of the images that have boundary contrast exceeding a threshold, typically representative of a good boundary contrast (implying a reliable segmentation accuracy)” below threshold, col 5 line 38-47);
and generating the template image based on the filled high-density region, the filled medium-density region, and the filled low-density region (“Once the registration map is generated, the registration map can be applied 66 to the first image to register the first image to the second image. That is to say, the first image can be mapped to the coordinate frame of the second image to yield a registered image. The registration map can also be applied to propagate any object of interest (OOI) from the first to the second image.” Col 6 lines 50-56 , first image as second image and vice versa).
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Qin, Hsieh, and Bzdusek as applied to claim 5 above, and further in view of Timmer (US 7340027 B2).
With respect to claim 10, Qin, Hsieh, and Bzdusek teach the method of claim 5. Bzdusek further teaches wherein the determining regions with different densities based on the first image includes determining the high-density region and the medium-density region by processing the first image using local threshold segmentation (“Corresponding structures in the first image and the second image are manually and/or automatically identified 56 using the image segmentation routine 36. A structure includes, for example, an organ, a tumor, or other regions. Suitably, the structures are identified in at least one of regions of the images where the density or distribution of identified interest points is below a threshold, typically representative of a low density or distribution of identified points (e.g., because there are limited interest points, points with significant matching error, or other reasons), and regions of the images that have boundary contrast exceeding a threshold, typically representative of a good boundary contrast (implying a reliable segmentation accuracy)” col 5 lines 35-47); and generating a composite image by fusing the second image and the first image (“That is to say, the first image can be mapped to the coordinate frame of the second image to yield a registered image.” Col 6 lines 52-54), but does not teach determining the low-density region by processing the composite image using local threshold segmentation.
Timmer teaches determining the low-density region by processing the composite image using local threshold segmentation (“For such composite imaging subjects, metal artifacts are reduced but remain very visible in the corrected reconstructed image, especially between high density and medium density regions. In medical imaging applications, medium density regions typically correspond to bone while high density regions typically correspond to metal implants, dental fillings, operation clips (used in certain interventional computed tomography applications), prosthesis devices, and the like. Hence, in medical computed tomography imaging, the region of interest commonly contains medium density regions.” Col 1 lines 44-54 and “According to one aspect, a method is provided for producing a corrected reconstructed image from acquired tomographic projection data. Acquired projection data corresponding to a region are reconstructed into an uncorrected reconstructed image. Pixels of the uncorrected reconstructed image are classified at least into high density, medium density, and low density pixel classes. Pixels of the uncorrected reconstructed image that are of the high density and low density classes are replaced with pixel values of the low density pixel class to generate a synthetic image.” Col 1 lines 58-67).
Timmer is analogous art in the same field of endeavor as the claimed invention. Timmer is directed towards metal artifact correction in CT images (“The following relates to the diagnostic imaging arts. It finds particular application in computed tomography imaging of a subject that includes high density regions such as metal implants, dental fillings, and the like, and will be described with particular reference thereto. However, it also finds application in other types of tomographic imaging such as single photon emission computed tomography (SPECT), positron emission tomography (PET), three-dimensional x-ray imaging, and the like.” Col 1 lines 10-18). A person of ordinary skill in the art before the effective filing date of the claimed invention would have found it obvious to combine the teachings of Qin, Hsieh, and Bzdusek, with Timmer by utilizing Timmer’s density determination strategy inside the combined systems artifact removal scheme, with the expectation that doing so would lead to the increasing the combined system’s ability to determine density regions across varying density regions (“This known method works well for certain imaging applications in which there is a single, well-defined high density region surrounded by much lower density tissue. It does not work well, however, with a plurality of high density regions, or where there are medium density regions in addition to the high density region. For such composite imaging subjects, metal artifacts are reduced but remain very visible in the corrected reconstructed image, especially between high density and medium density regions. In medical imaging applications, medium density regions typically correspond to bone while high density regions typically correspond to metal implants, dental fillings, operation clips (used in certain interventional computed tomography applications), prosthesis devices, and the like. Hence, in medical computed tomography imaging, the region of interest commonly contains medium density regions.” Col 1 lines 39-54).
Claims 12-14 are rejected under 35 U.S.C. 103 as being unpatentable over Qin and Hsieh as applied to claim 1 above, and further in view of Benson (US8503750B2).
With respect to claim 12, Qin and Hsieh teach the method of claim 1. Benson further teaches wherein the determining a metal artifact image based on the template image includes: determining a metal region based on the second image (
PNG
media_image1.png
67
305
media_image1.png
Greyscale
col 5 lines 38-42); generating a metal projection map by performing forward projection on the metal region, a non-zero region in the metal projection map being a metal projection region (
PNG
media_image1.png
67
305
media_image1.png
Greyscale
col 5 lines 38-42); generating a second image projection map by performing forward projection on the second image (
PNG
media_image2.png
75
312
media_image2.png
Greyscale
col 5 lines 42-27); generating a template image projection map by performing forward projection on the template image (
PNG
media_image2.png
75
312
media_image2.png
Greyscale
col 5 lines 42-27); determining a projection map difference between the second image projection map and the template image projection map in the metal projection region(
PNG
media_image2.png
75
312
media_image2.png
Greyscale
col 5 lines 42-27); and determining the metal artifact image based on the projection map difference (
PNG
media_image2.png
75
312
media_image2.png
Greyscale
col 5 lines 42-27).
Benson is analogous art in the same field of endeavor as the claimed invention. Benson is directed towards metal artifact removal in CT images (
PNG
media_image3.png
31
323
media_image3.png
Greyscale
col 2 lines 59-60). A person of ordinary skill in the art, before the effective filing date of the claimed invention, would have found it obvious to combine the teachings of Qin and Hsieh with Benson by utilizing Benson’s interpolation based processes and metal artifact identification as a part of the combined system’s metal artifact image generation, with the expectation that doing so would support artifact removal over images of varying energies (
PNG
media_image4.png
42
304
media_image4.png
Greyscale
col 2 lines 53-55).
With respect to claim 13, Qin, Hsieh, and Benson teach the method of claim 12. Benson further teaches wherein the determining the metal artifact image based on the projection map difference includes: obtaining a processed projection map difference by smoothing a boundary region in the projection map difference (see figure 5 element 70); and obtaining the metal artifact image by performing a back projection reconstruction based on the processed projection map difference (
PNG
media_image5.png
93
309
media_image5.png
Greyscale
col 7 lines 51-57).
With respect to claim 14, Qin and Hsieh teach the method of claim 13. Benson further teaches wherein the smoothing a boundary region in the projection map difference includes: determining an extended distance between an upper boundary and a lower boundary of the boundary region (
PNG
media_image6.png
424
313
media_image6.png
Greyscale
Col 10 lines 35-67); and obtaining the processed projection map difference by performing a linear interpolation based on the extended distance between the upper boundary and the lower boundary (col 11 lines 6-53, convolution).
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Qin, Hsieh, and Benson as applied to claim 14 above, and further in view of Borsch (CN-111656399-A).
With respect to claim 15, Qin, Hsieh and Benson teach the method of claim 14. Benson further teaches wherein the determining an extended distance between an upper boundary and a lower boundary of the boundary region includes: determining the extended distance between the upper boundary and the lower boundary using a machine learning model (col 10 line 67-col 11 line 1, different definitions).
Benson does not explicitly teach utilizing a machine learning model however Brosch teaches using a machine learning model to determine distances involving boundaries (“Although the two-step method can generate good dividing result, but has been found, if the searching step and classifying step are integrated together, and using the learning method (specifically, end to end machine learning method). directly estimating the distance of the expected boundary of the object in the image according to the image value (especially grey value) around the grid triangle, then improving the reliability and accuracy of the boundary detection. The improved reliability and accuracy of boundary detection are directly converted into model adaptation and thus improved reliability and accuracy of segmentation of objects in the image.” Page 16 (last paragraph) -17 (first paragraph)).
Brosch is analogous art reasonably pertinent to the problem of image segmentation being faced by the inventor. Borsch is directed towards image segmentation (“The invention relates to a segmentation system for segmenting an object in an image, a method and a computer program. The invention also relates to a training system for training a neural network, a method and a computer program.”). A person of ordinary skill in the art, before the effective filing date of the claimed invention, would have found it obvious to combine Qin, Hsieh, and Benson noting that Benson mentions the use of different definitions and that incorporating machine learning into that process would lead to improved boundary detection (“The improved reliability and accuracy of boundary detection are directly converted into model adaptation and thus improved reliability and accuracy of segmentation of objects in the image.” Page 17 lines 2-4).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to REBECCA C WILLIAMS whose telephone number is (571)272-7074. The examiner can normally be reached M-F 7:30am - 4:00pm.
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 W 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.
/REBECCA COLETTE WILLIAMS/Examiner, Art Unit 2677
/ANDREW W BEE/Supervisory Patent Examiner, Art Unit 2677
Prosecution Insights