DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. 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
2. The information disclosure statement (IDS) submitted on 07/24/2024 and 01/06/2026. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 103
3. 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.
4. 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.
5. 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.
6. Claim(s) 1, 10-15 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ghesu et al. (US 2022/0022818 A1) in view of Wang (US 2019/0164291 A1).
7. With reference to claim 1, Ghesu teaches A method, comprising: receiving a binary segmentation mask of an X-ray image, (“The present invention generally relates to methods and systems for the assessment of abnormality patterns associated with COVID-19 (coronavirus disease 2019) from x-ray images.” [0027] “The input medical image may be received directly from an image acquisition device, such as, e.g., a x-ray scanner, as the input medical image is acquired, or can be received by loading a previously acquired input medical image from a storage or memory of a computer system or receiving the input medical image from a remote computer system. At step 204, lungs are segmented from the input medical image using a trained lung segmentation network. The lung segmentation network predicts a probability map representing the segmented lungs. The probability map defines a pixel wise probability that each pixel depicts the lungs. The probability map may be represented as a binary mask by comparing the probability for each pixel to a threshold value (e.g., 0.5).” [0033-0034]) Ghesu also teaches displaying the representation superimposed on the X-ray image on a display device. (“Image 802 is a DRR image, representing a synthesized x-ray image, that is input into lung and abnormality pattern segmentation networks. Image 804 depicts segmentation of abnormality patterns in DRR image 802 (a lesion only DRR) using an intensity mask. Image 806 shows a target lung segmentation mask 814 (shown as outlined regions) and target abnormality pattern segmentation mask 816 (shown as shaded regions) overlaid on DRR image 802. Image 808 shows an output of an assessment of COVID-19 (DRR model output) depicting predicted segmentations for the lungs 818 (shown as outlined regions) and the abnormality patterns 820 (shown as shaded regions) overlaid on DRR image 802, which results in a POa of 43.55%.” [0065] “Input/output devices 1208 may include peripherals, such as a printer, scanner, display screen, etc.” [0107])
PNG
media_image1.png
575
575
media_image1.png
Greyscale
Ghesu does not explicitly teach the binary segmentation mask including a set of positive pixels corresponding to a location of a medical tube in the X-ray image, and a set of negative pixels corresponding to portions of the X-ray image not including the medical tube; iteratively adding points along a trajectory of the positive pixels in the binary segmentation mask to form a polyline, each point forming a node of the polyline; generating a representation of the medical tube based on the polyline; These are what Wang teaches. Wang teaches the binary segmentation mask including a set of positive pixels corresponding to a location of a medical tube in the X-ray image, and a set of negative pixels corresponding to portions of the X-ray image not including the medical tube; (“the data may be image data, image mask data, parameter, or the like, or any combination thereof. In some embodiments, the image data may be initial image data or processed data. Merely by way of example, the processing may be an image segmentation. The image may be a 2D image or a 3D image. The image may be a CT image, an MR image, an Ultrasound image, a PET image, or the like, or any combination thereof. In some embodiments, the image mask may be a binary mask extracted from a specific area of an image. The image mask may be used to supply a screen, extract a region of interest, and/or make a specific image.” [0175] “a number of 2D slices corresponding to a tumor may be acquired, and each 2D slice may indicate a cross section of the tumor. Merely by way of example, a tumor region in which a tumor locate may be recognized by a user in each 2D slice. A line segment of length d.sub.1 on a slice of tumor may be drawn by the user, which may traverse the tumor. In some embodiments, the line segment may be drawn on the slice which has a relatively larger cross-section compared with other slices. A line segment may be a part of a line that is bounded by two distinct end points. A cube of edge length d.sub.2 (d.sub.2=d.sub.1.Math.r, 1<r<2), centered at the midpoint of the line segment may be shaped. The region within the cube may be deemed as the ROI, wherein the tumor locate. Merely by way of example, the region wherein the tumor locate may be completely within the ROI, which determined by the cube.” [0183] “one or more positive seed points may be sampled from the ROI. The positive seed points may be sampled randomly among the voxels in ROI determined in step 1002, wherein the tumor locate. The positive seed points may be taken as sampling seed points of target tumor region. One or more negative seed points may be also sampled from ROI. The negative seed points may be sampled randomly among the voxels in ROI determined in step 1002, wherein the tumor do not locate. … given the straight line d.sub.1 drawn by the user, an internal region centered at the midpoint of the straight line d.sub.1 with a radius of d.sub.3 (d.sub.3=d.sub.1/3) may be created, m positive seed points may be sampled in the internal region. The positive seed points may be part of the tumor. … given the straight line d1 drawn by the user, an external region centered at the midpoint of the straight line d.sub.1 with a radius ranging from d.sub.1.Math.t to d.sub.1.Math.r(1<t<r). n negative seed points may be sampled in the external region. The negative seed points may be part of normal tissues surrounding the tumor. … features of gray-scale histogram of the seed points may be calculated. The gray-scale histogram of an image represents the distribution of the pixels in the image over the gray-level scale.” [0185-0188]) Wang also teaches iteratively adding points along a trajectory of the positive pixels in the binary segmentation mask to form a polyline, each point forming a node of the polyline; generating a representation of the medical tube based on the polyline; (“a region growing may be performed on the seed point iteratively base on the parameters described in step 302. In some embodiments of the present disclosure, the region meet the first threshold may be determined as a bone tissue. … the increment of the pixels may be used to eliminate the influence of adjacent tissues of the bone that is under region growing, and determine the boundary of the bone. … a new region growing may be performed based on the parameters generated in step 304.” [0126-0129] “a number of 2D slices corresponding to a tumor may be acquired, and each 2D slice may indicate a cross section of the tumor. Merely by way of example, a tumor region in which a tumor locate may be recognized by a user in each 2D slice. A line segment of length d.sub.1 on a slice of tumor may be drawn by the user, which may traverse the tumor. In some embodiments, the line segment may be drawn on the slice which has a relatively larger cross-section compared with other slices. A line segment may be a part of a line that is bounded by two distinct end points. A cube of edge length d.sub.2 (d.sub.2=d.sub.1.Math.r, 1<r<2), centered at the midpoint of the line segment may be shaped. The region within the cube may be deemed as the ROI, wherein the tumor locate. Merely by way of example, the region wherein the tumor locate may be completely within the ROI, which determined by the cube.” [0183] “the grayscale of each image corresponded to each seed point may be normalized as a fixed value, denoted by S. Normalized S-dimensional feature of gray-scale histogram in a spherical neighborhood, centered of each seed point with a radius of j, may be calculated. Training and classifying based on S-dimensional feature of gray-scale histogram to acquire parameters of classifier may be performed, acquiring parameters of classifier. … a linear discriminant analysis (LDA) training may be performed to acquire one or more linear or nonlinear classifiers. The LDA training may be based on the gray-scale histograms of the positive seed points and the negative seed points acquired in the step 1004. In step 1006, features of the gray-scale histograms of one or more voxels in the image I may be calculated. In some embodiments, the linear classifier C may be used to traverse every voxel in the image I. In step 1007, the linear classifier C, which is trained in step 1005, may be used to assess each voxel of the image I to determine whether the voxel is part of tumor or not. In step 1008, the result of the coarse segmentation may be acquired.” [0189-0193]) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Wang into Ghesu, in order to improve the accuracy of the segmentation.
8. With reference to claim 10, Ghesu does not explicitly teach calculating a length of a portion of the medical tube by adding lengths of line segments of the polyline between nodes included in the portion. This is what Wang teaches (“a tumor region in which a tumor locate may be recognized by a user in each 2D slice. A line segment of length d.sub.1 on a slice of tumor may be drawn by the user, which may traverse the tumor. In some embodiments, the line segment may be drawn on the slice which has a relatively larger cross-section compared with other slices. A line segment may be a part of a line that is bounded by two distinct end points. A cube of edge length d.sub.2 (d.sub.2=d.sub.1.Math.r, 1<r<2), centered at the midpoint of the line segment may be shaped. The region within the cube may be deemed as the ROI, wherein the tumor locate. Merely by way of example, the region wherein the tumor locate may be completely within the ROI, which determined by the cube.” [0183] “if a mean filtering is performed, a window, calculated based on the mean filtering and the gray-scale histogram, may be proportional to the length of long axis. The filtering may be automatically adjusted in accordance with the different volume of the nodules. … if the first region growing on the filtered image acquired after mean filtering is performed, the operations of the first region growing based on distance function may be performed as following: the points of long axis determined by the user may be taken as seed points, performing region growing with one or more relatively restrictive initial thresholds; a segmentation region grown based on the mean filtered image may cover at least partial of the long axis, the length of the long axis covered by the segmentation region may be assessed based on the initial thresholds; if the assessment fails, the thresholds may be eased and the assessment may continue: if the assessment succeeds, an expansion operation with restricted thresholds may be performed and a dynamic segmentation region may be acquired.” [0211-0212]) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Wang into Ghesu, in order to improve the accuracy of the segmentation.
9. With reference to claim 11, Ghesu does not explicitly teach storing the representation of the medical tube in a memory as a set of coordinate points, each coordinate point corresponding to a node of the polyline. This is what Wang teaches (“The pre-processing step 1402 may include a segmentation, a storage, a processing after segmentation, or the like, or any combination thereof. ... different components may be stored in different storage modules, and then be rendered. The storage module may include a CPU memory, a GPU video memory, a RAM, a ROM, a hardware, a software, a tape, a CD, a DVD, or the like, or any combination thereof.” [0224] “the boundary data may be a mesh grid data corresponding to boundary structures of each tissue within the volume data. The boundary structure may be a two-dimensional boundary line, a three-dimensional boundary surface, etc. The boundary structure of the mesh grid data may include a triangle or quadrate, or an irregular shape, or any combination thereof. The triangle or quadrate may be formed by connecting three or four corresponding volume data. The mesh grid data may include information e.g., a corresponding coordinate of each point therein, a normal vector of a plane where the grid located, a structure information of an adjacent volume data, or the like, or any combination thereof.” [0272]) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Wang into Ghesu, in order to improve the accuracy of the segmentation.
10. With reference to claim 12, Ghesu does not explicitly teach calculating a length of a portion of the medical tube by adding distances calculated between coordinate points included in the portion. This is what Wang teaches (“a tumor region in which a tumor locate may be recognized by a user in each 2D slice. A line segment of length d.sub.1 on a slice of tumor may be drawn by the user, which may traverse the tumor. In some embodiments, the line segment may be drawn on the slice which has a relatively larger cross-section compared with other slices. A line segment may be a part of a line that is bounded by two distinct end points. A cube of edge length d.sub.2 (d.sub.2=d.sub.1.Math.r, 1<r<2), centered at the midpoint of the line segment may be shaped. The region within the cube may be deemed as the ROI, wherein the tumor locate. Merely by way of example, the region wherein the tumor locate may be completely within the ROI, which determined by the cube.” [0183] “if a mean filtering is performed, a window, calculated based on the mean filtering and the gray-scale histogram, may be proportional to the length of long axis. The filtering may be automatically adjusted in accordance with the different volume of the nodules. … if the first region growing on the filtered image acquired after mean filtering is performed, the operations of the first region growing based on distance function may be performed as following: the points of long axis determined by the user may be taken as seed points, performing region growing with one or more relatively restrictive initial thresholds; a segmentation region grown based on the mean filtered image may cover at least partial of the long axis, the length of the long axis covered by the segmentation region may be assessed based on the initial thresholds; if the assessment fails, the thresholds may be eased and the assessment may continue: if the assessment succeeds, an expansion operation with restricted thresholds may be performed and a dynamic segmentation region may be acquired.” [0211-0212] “the boundary data may be a mesh grid data corresponding to boundary structures of each tissue within the volume data. The boundary structure may be a two-dimensional boundary line, a three-dimensional boundary surface, etc. The boundary structure of the mesh grid data may include a triangle or quadrate, or an irregular shape, or any combination thereof. The triangle or quadrate may be formed by connecting three or four corresponding volume data. The mesh grid data may include information e.g., a corresponding coordinate of each point therein, a normal vector of a plane where the grid located, a structure information of an adjacent volume data, or the like, or any combination thereof.” [0272]) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Wang into Ghesu, in order to improve the accuracy of the segmentation.
11. With reference to claim 13, Ghesu does not explicitly teach generating the representation of the medical tube based on the polyline further comprises one of drawing the medical tube centered on the polyline with a fixed thickness, or including a graphical design of the medical tube centered on the polyline. This is what Wang teaches (“a region growing may be performed on the seed point iteratively base on the parameters described in step 302. In some embodiments of the present disclosure, the region meet the first threshold may be determined as a bone tissue. … the increment of the pixels may be used to eliminate the influence of adjacent tissues of the bone that is under region growing, and determine the boundary of the bone. … a new region growing may be performed based on the parameters generated in step 304.” [0126-0129] “a number of 2D slices corresponding to a tumor may be acquired, and each 2D slice may indicate a cross section of the tumor. Merely by way of example, a tumor region in which a tumor locate may be recognized by a user in each 2D slice. A line segment of length d.sub.1 on a slice of tumor may be drawn by the user, which may traverse the tumor. In some embodiments, the line segment may be drawn on the slice which has a relatively larger cross-section compared with other slices. A line segment may be a part of a line that is bounded by two distinct end points. A cube of edge length d.sub.2 (d.sub.2=d.sub.1.Math.r, 1<r<2), centered at the midpoint of the line segment may be shaped. The region within the cube may be deemed as the ROI, wherein the tumor locate. Merely by way of example, the region wherein the tumor locate may be completely within the ROI, which determined by the cube.” [0183] “the grayscale of each image corresponded to each seed point may be normalized as a fixed value, denoted by S. Normalized S-dimensional feature of gray-scale histogram in a spherical neighborhood, centered of each seed point with a radius of j, may be calculated. Training and classifying based on S-dimensional feature of gray-scale histogram to acquire parameters of classifier may be performed, acquiring parameters of classifier. … a linear discriminant analysis (LDA) training may be performed to acquire one or more linear or nonlinear classifiers. The LDA training may be based on the gray-scale histograms of the positive seed points and the negative seed points acquired in the step 1004. In step 1006, features of the gray-scale histograms of one or more voxels in the image I may be calculated. In some embodiments, the linear classifier C may be used to traverse every voxel in the image I. In step 1007, the linear classifier C, which is trained in step 1005, may be used to assess each voxel of the image I to determine whether the voxel is part of tumor or not. In step 1008, the result of the coarse segmentation may be acquired.” [0189-0193]) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Wang into Ghesu, in order to improve the accuracy of the segmentation.
12. With reference to claim 14, Ghesu does not explicitly teach the set of positive pixels indicates a loop in the medical tube, and as a result of performing the method, the representation of the medical tube generated by the polyline precisely aligns the positive pixels. (“a region growing may be performed on the seed point iteratively base on the parameters described in step 302. … the increment of pixels in two adjacent iterations may be assessed based on a threshold.” [0126-0127] “a number of 2D slices corresponding to a tumor may be acquired, and each 2D slice may indicate a cross section of the tumor. Merely by way of example, a tumor region in which a tumor locate may be recognized by a user in each 2D slice. A line segment of length d.sub.1 on a slice of tumor may be drawn by the user, which may traverse the tumor. In some embodiments, the line segment may be drawn on the slice which has a relatively larger cross-section compared with other slices. A line segment may be a part of a line that is bounded by two distinct end points. A cube of edge length d.sub.2 (d.sub.2=d.sub.1.Math.r, 1<r<2), centered at the midpoint of the line segment may be shaped. The region within the cube may be deemed as the ROI, wherein the tumor locate. Merely by way of example, the region wherein the tumor locate may be completely within the ROI, which determined by the cube.” [0183] “one or more positive seed points may be sampled from the ROI. The positive seed points may be sampled randomly among the voxels in ROI determined in step 1002, wherein the tumor locate. The positive seed points may be taken as sampling seed points of target tumor region. One or more negative seed points may be also sampled from ROI. The negative seed points may be sampled randomly among the voxels in ROI determined in step 1002, wherein the tumor do not locate. … given the straight line d.sub.1 drawn by the user, an internal region centered at the midpoint of the straight line d.sub.1 with a radius of d.sub.3 (d.sub.3=d.sub.1/3) may be created, m positive seed points may be sampled in the internal region. The positive seed points may be part of the tumor.” [0185-0186]) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Wang into Ghesu, in order to improve the accuracy of the segmentation.
13. Claim 15 is similar in scope to the combination of claims 1 and 11, and thus is rejected under similar rationale. Ghesu additionally teaches An X-ray imaging system, comprising: a processor, and a memory storing instructions that when executed, cause the processor to (“The present invention generally relates to methods and systems for the assessment of abnormality patterns associated with COVID-19 (coronavirus disease 2019) from x-ray images.” [0027] “Systems, apparatuses, and methods described herein may be implemented using digital circuitry, or using one or more computers using well-known computer processors, memory units, storage devices, computer software, and other components. Typically, a computer includes a processor for executing instructions and one or more memories for storing instructions and data.” [0100])
14. Claim 18 is similar in scope to claim 10 and/or 12, and thus is rejected under similar rationale.
Allowable Subject Matter
15. Claims 19 and 20 are allowed.
Prior art in the record, e.g., existing prior Ghesu et al. (US 2022/0022818 A1) and Wang (US 2019/0164291 A1), alone or combined do not teach the claim features of “the curvature force is based on an angle between a first line segment of the polyline ending at the node and a second line segment beginning at the node, and the elastic force is calculated as a function of a first distance between the node and a previous node of the polyline, and a second distance between the node and a subsequent node of the polyline, and is applied in a direction of either the previous node or the subsequent node.” The examiner has not discovered prior art reference teaching the cited limitations during the application prosecution. Thus, it is believed a unique feature in the invention and is suggested to be allowed with the condition set forth above.
16. Claims 2-9, 16 and 17 are objected to being dependent upon rejected base claims. The claims would be allowable if rewritten in independent form including all the limitations of the base claims and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter:
Regarding claims 2 and 16, the prior arts of record fails to either individually or in combination teach the claimed feature of: “detecting a subset of positive pixels located within the pixel search area; adding a new node to the polyline at a location of a center of mass of the subset of positive pixels; and redefining the trajectory for adding a next node along a line segment formed between the new node and a previous node of the polyline.”
Claims 3-5 are also objected to for depending from claim 2.
Regarding claims 6 and 17, the prior arts of record fails to either individually or in combination teach the claimed feature of: “an elastic force calculated as a function of a distance between the node and neighboring nodes of the polyline, the elastic force having a first component calculated as a function of a first distance between the node and a previous node of the polyline, and a second component calculated as a function of a second distance between the node and a subsequent node of the polyline; and a curvature force calculated as a function of an angle formed between a previous line segment connecting the node to a previous node of the polyline, and a subsequent line segment connecting the node to a subsequent node of the polyline.”
Claims 7-9 are also objected to for depending from claim 6.
Conclusion
17. Any inquiry concerning this communication or earlier communications from the examiner should be directed to Michelle Chin whose telephone number is (571)270-3697. The examiner can normally be reached on Monday-Friday 8:00 AM-4:30 PM.
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:/Awww.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Kent Chang can be reached on (571)272-7667. 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:/Awww.uspto.gov/patents/apply/patent- center for more information about Patent Center and https:/Awww.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.
/MICHELLE CHIN/
Primary Examiner, Art Unit 2614