DETAILED ACTION
Claims 6, 7, 9, 10, 14, 15, 17, 19 and 20 have been cancelled.
Claims 21-29 have been added.
Claims 1-5, 8, 11-13, 16, 18 and 21-29 are currently pending.
The previous rejections to claims 1-5 and 8 under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, is withdrawn due to Applicant’s amendment.
Response to Arguments
Applicant's arguments filed 3/5/26 have been fully considered but they are not persuasive.
The Applicant argues on page 9 of the response in essence that: With respect to the § 103 rejections, the Office Action relies on Shen and Pati for additional teachings. However, the Office Action does not rely on Shen or Pati as teaching the above-recited limitations relating to grey level co-occurrence matrix texture data, entropy derived therefrom, connected component analysis based on the entropy data, and determining the tissue resistance index based at least in part on both the number of labeled components and a standard deviation.
Kudavelly discloses detecting a number of organs by analyzing organ boundaries which return stronger echo signals compared to soft tissue. The needle path calculator can select the sequence of densities with the lowest peak density (paragraph 18). Thus, the calculated paths consider the least number of organs (ideally the number being zero) and the lowest peak density (a low standard deviation). Pati discloses the specifics of the limitations directed to relating to grey level co-occurrence matrix texture data, entropy derived therefrom, connected component analysis based on the entropy data.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-4, 11, 12, 18 and 21-29 are rejected under 35 U.S.C. 103 as being unpatentable over Kudavelly et al. US Publication 2014/0350390 (hereafter “Kudavelly”) and Pati et al. US Publication 2022/0164946 (hereafter “Pati”).
Referring to claim 1, Kudavelly discloses a method for determining an optimal needle path comprising:
generating a plurality of candidate needle paths from image data of a patient (paragraph 18, The tissue density analyzer also performs this operation for possible needle paths adjacent to the projected needle path);
extracting a cuboid of image data around each candidate needle path (paragraph 18, Using the coordinate information of the projected path of needle insertion from coordinate generator 42, the tissue density analyzer selects out and analyzes pixels along the projected needle path. Preferably the pixels are a three dimensional set of pixels (voxels) of the 3D Data Set as illustrated in FIG. 2);
calculating a tissue resistance index from each cuboid of image data around each candidate needle path (paragraph 18, When the needle path calculator 54 receives the sequential density estimates for the projected path and several alternative adjacent paths, it can select the one that poses the least hazard and resistance to needle insertion),
wherein calculating the tissue resistance index includes:
determining the tissue resistance index based at least in part on the number of labeled components and the standard deviation (paragraph 18, An organ boundary along the path will also generally return stronger echo signals. If a location comprises only soft tissue, the combined value will be relatively low, indicating less dense substance which should be easily penetrated by a needle. When the needle path calculator 54 receives the sequential density estimates for the projected path and several alternative adjacent paths, it can select the one that poses the least hazard and resistance to needle insertion. For example the needle path calculator can select the sequence of densities with the lowest peak density);
calculating a value for each candidate needle path based on the calculated tissue resistance index (paragraph 22, Another possible implementation is to illustrate the tissue density along an insertion path by a numeric value such as the average or peak or mean value of the sequence of density values); and
selecting the candidate needle path with the lowest value as the optimal needle path (paragraph 18, When the needle path calculator 54 receives the sequential density estimates for the projected path and several alternative adjacent paths, it can select the one that poses the least hazard and resistance to needle insertion).
Kudavelly discloses calculating the tissue resistance index from each cuboid of image data around each candidate needle path, but does not disclose expressly wherein calculating the tissue resistance index includes measuring homogeneity of the cuboid of image data around each candidate needle path to calculate a standard deviation.
Pati discloses wherein measuring the homogeneity of the cuboid of image data around each candidate needle path includes:
generating, for each cuboid, grey level co-occurrence matrix texture for at least one slice image of the cuboid (paragraph 47, In step 54, the image processor makes measurements for entities in each set {E}i to determine attributes of each entity. Texture features include ASM (Active Shape Models) from a Gray-Level Co-occurrence Matrix. Selected features were also applied to an ML model, here a RF (Random Forests) model pretrained to classify tissue parts by tissue type (here epithelium, stroma, necrosis and background tissue) as an additional attribute);
calculating entropy data based on the grey level co-occurrence matrix texture data (paragraph 47, In step 54, the image processor makes measurements for entities in each set {E}i to determine attributes of each entity. Texture features include mean entropy of intensity);
performing a connected component analysis based on the entropy data to determine a number of labeled components (paragraph 47, Selected features were also applied to an ML model, here a RF (Random Forests) model pretrained to classify tissue parts by tissue type (here epithelium, stroma, necrosis and background tissue) as an additional attribute);
measuring homogeneity of each cuboid to calculate a standard deviation (paragraph 47, In step 54, the image processor makes measurements for entities in each set {E}i to determine attributes of each entity. Texture features include standard deviation).
At the time of the effective filing date of the claimed invention, it would have obvious to a person of ordinary skill in the art to measure homogeneity to calculate a standard deviation. The motivation for doing so would have been to use machine learning to better analyze and interpret images of tissue specimens. Therefore, it would have been obvious to combine Pati with Kudavelly to obtain the invention as specified in claim 1.
Referring to claim 2, Kudavelly discloses displaying the candidate needle paths relative to the image data of the patient on a display (paragraph 18, The coordinates of one or more alternative paths which have been identified as more favorable for needle insertion are then coupled to the graphics generator for indication on the displayed image).
Referring to claim 3, Kudavelly discloses displaying the optimal needle path relative to the image data of the patient on a display (paragraph 18, The coordinates of one or more alternative paths which have been identified as more favorable for needle insertion are then coupled to the graphics generator for indication on the displayed image).
Referring to claims 4 and 12, Kudavelly discloses wherein the value is displayed as at least one of a number or color corresponding to the value on a display (paragraph 22, Another possible implementation is to illustrate the tissue density along an insertion path by a numeric value such as the average or peak or mean value of the sequence of density values).
Referring to claim 11, Kudavelly discloses an ablation system comprising:
a computing device including a processor configured to:
extract a cuboid of image data of a patient around each candidate needle path of a plurality of candidate needle paths (paragraph 18, Using the coordinate information of the projected path of needle insertion from coordinate generator 42, the tissue density analyzer selects out and analyzes pixels along the projected needle path. Preferably the pixels are a three dimensional set of pixels (voxels) of the 3D Data Set as illustrated in FIG. 2);
calculate a tissue resistance index from each cuboid of image data around each candidate needle path (paragraph 18, When the needle path calculator 54 receives the sequential density estimates for the projected path and several alternative adjacent paths, it can select the one that poses the least hazard and resistance to needle insertion);
wherein calculating the tissue resistance index includes:
determining the tissue resistance index based at least in part on the number of labeled components and the standard deviation (paragraph 18, An organ boundary along the path will also generally return stronger echo signals. If a location comprises only soft tissue, the combined value will be relatively low, indicating less dense substance which should be easily penetrated by a needle. When the needle path calculator 54 receives the sequential density estimates for the projected path and several alternative adjacent paths, it can select the one that poses the least hazard and resistance to needle insertion. For example the needle path calculator can select the sequence of densities with the lowest peak density);
calculate a value for each candidate needle path based on the calculated tissue resistance index (paragraph 22, Another possible implementation is to illustrate the tissue density along an insertion path by a numeric value such as the average or peak or mean value of the sequence of density values); and
a display operably coupled to the computing device and configured to display each candidate needle path and the calculated value for each candidate needle path relative to image data of the patient (paragraph 18, When the needle path calculator 54 receives the sequential density estimates for the projected path and several alternative adjacent paths, it can select the one that poses the least hazard and resistance to needle insertion).
Kudavelly discloses calculating the tissue resistance index from each cuboid of image data around each candidate needle path, but does not disclose expressly wherein calculating the tissue resistance index includes measuring homogeneity of the cuboid of image data around each candidate needle path to calculate a standard deviation.
Pati discloses wherein measuring the homogeneity of the cuboid of image data around each candidate needle path includes:
generating, for each cuboid, grey level co-occurrence matrix texture for at least one slice image of the cuboid (paragraph 47, In step 54, the image processor makes measurements for entities in each set {E}i to determine attributes of each entity. Texture features include ASM (Active Shape Models) from a Gray-Level Co-occurrence Matrix. Selected features were also applied to an ML model, here a RF (Random Forests) model pretrained to classify tissue parts by tissue type (here epithelium, stroma, necrosis and background tissue) as an additional attribute);
calculating entropy data based on the grey level co-occurrence matrix texture data (paragraph 47, In step 54, the image processor makes measurements for entities in each set {E}i to determine attributes of each entity. Texture features include mean entropy of intensity);
performing a connected component analysis based on the entropy data to determine a number of labeled components (paragraph 47, Selected features were also applied to an ML model, here a RF (Random Forests) model pretrained to classify tissue parts by tissue type (here epithelium, stroma, necrosis and background tissue) as an additional attribute);
measuring homogeneity of each cuboid to calculate a standard deviation (paragraph 47, In step 54, the image processor makes measurements for entities in each set {E}i to determine attributes of each entity. Texture features include standard deviation).
At the time of the effective filing date of the claimed invention, it would have obvious to a person of ordinary skill in the art to measure homogeneity to calculate a standard deviation. The motivation for doing so would have been to use machine learning to better analyze and interpret images of tissue specimens. Therefore, it would have been obvious to combine Pati with Kudavelly to obtain the invention as specified in claim 11.
Referring to claim 18, Kudavelly discloses a non-transitory computer readable storage medium storing instructions, which when executed by a processor, cause the processor to:
extract a cuboid of image data of a patient around a candidate needle path (paragraph 18, Using the coordinate information of the projected path of needle insertion from coordinate generator 42, the tissue density analyzer selects out and analyzes pixels along the projected needle path. Preferably the pixels are a three dimensional set of pixels (voxels) of the 3D Data Set as illustrated in FIG. 2);
calculate a tissue resistance index from the cuboid of image data around the candidate needle path (paragraph 18, When the needle path calculator 54 receives the sequential density estimates for the projected path and several alternative adjacent paths, it can select the one that poses the least hazard and resistance to needle insertion);
wherein calculating the tissue resistance index includes:
determining the tissue resistance index based at least in part on the number of labeled components and the standard deviation (paragraph 18, An organ boundary along the path will also generally return stronger echo signals. If a location comprises only soft tissue, the combined value will be relatively low, indicating less dense substance which should be easily penetrated by a needle. When the needle path calculator 54 receives the sequential density estimates for the projected path and several alternative adjacent paths, it can select the one that poses the least hazard and resistance to needle insertion. For example the needle path calculator can select the sequence of densities with the lowest peak density); and
calculate a value for the candidate needle path based on the calculated tissue resistance index (paragraph 22, Another possible implementation is to illustrate the tissue density along an insertion path by a numeric value such as the average or peak or mean value of the sequence of density values).
Kudavelly discloses calculating the tissue resistance index from each cuboid of image data around each candidate needle path, but does not disclose expressly wherein calculating the tissue resistance index includes measuring homogeneity of the cuboid of image data around each candidate needle path to calculate a standard deviation.
Pati discloses wherein measuring the homogeneity of the cuboid of image data around each candidate needle path includes:
generating, for each cuboid, grey level co-occurrence matrix texture for at least one slice image of the cuboid (paragraph 47, In step 54, the image processor makes measurements for entities in each set {E}i to determine attributes of each entity. Texture features include ASM (Active Shape Models) from a Gray-Level Co-occurrence Matrix. Selected features were also applied to an ML model, here a RF (Random Forests) model pretrained to classify tissue parts by tissue type (here epithelium, stroma, necrosis and background tissue) as an additional attribute);
calculating entropy data based on the grey level co-occurrence matrix texture data (paragraph 47, In step 54, the image processor makes measurements for entities in each set {E}i to determine attributes of each entity. Texture features include mean entropy of intensity);
performing a connected component analysis based on the entropy data to determine a number of labeled components (paragraph 47, Selected features were also applied to an ML model, here a RF (Random Forests) model pretrained to classify tissue parts by tissue type (here epithelium, stroma, necrosis and background tissue) as an additional attribute);
measuring homogeneity of each cuboid to calculate a standard deviation (paragraph 47, In step 54, the image processor makes measurements for entities in each set {E}i to determine attributes of each entity. Texture features include standard deviation).
At the time of the effective filing date of the claimed invention, it would have obvious to a person of ordinary skill in the art to measure homogeneity to calculate a standard deviation. The motivation for doing so would have been to use machine learning to better analyze and interpret images of tissue specimens. Therefore, it would have been obvious to combine Pati with Kudavelly to obtain the invention as specified in claim 18.
Referring to claims 21, 24, and 27, Kudavelly discloses wherein, for each cuboid corresponding to a candidate needle path, data is calculated for the at least one slice image of that cuboid (paragraph 18, Using the coordinate information of the projected path of needle insertion from coordinate generator 42, the tissue density analyzer selects out and analyzes pixels along the projected needle path. Preferably the pixels are a three dimensional set of pixels (voxels) of the 3D Data Set as illustrated in FIG. 2).
Pati discloses wherein the entropy data is calculated for the at least one slice image of that cuboid, and wherein the connected component analysis is performed on the entropy data for the at least one slice image to label regions in the entropy data, and wherein the number of labeled components is a count of the labeled regions produced by the connected component analysis (paragraph 47, In step 54, the image processor makes measurements for entities in each set {E}i to determine attributes of each entity. Texture features include ASM (Active Shape Models) from a Gray-Level Co-occurrence Matrix. Selected features were also applied to an ML model, here a RF (Random Forests) model pretrained to classify tissue parts by tissue type (here epithelium, stroma, necrosis and background tissue) as an additional attribute).
Referring to claim 22, 25, and 28, Kudavelly discloses wherein determining the tissue resistance index comprises determining the number of labeled components and calculating the standard deviation for the cuboid extracted around a candidate needle path, and wherein the tissue resistance index is determined using both the number of labeled components and the standard deviation determined for that cuboid (paragraph 18, An organ boundary along the path will also generally return stronger echo signals. If a location comprises only soft tissue, the combined value will be relatively low, indicating less dense substance which should be easily penetrated by a needle. When the needle path calculator 54 receives the sequential density estimates for the projected path and several alternative adjacent paths, it can select the one that poses the least hazard and resistance to needle insertion. For example the needle path calculator can select the sequence of densities with the lowest peak density).
Pati discloses determining the number of labeled components from the connected component analysis and calculating the standard deviation from the homogeneity measurement for the cuboid extracted (paragraph 47, In step 54, the image processor makes measurements for entities in each set {E}i to determine attributes of each entity. Texture features include ASM (Active Shape Models) from a Gray-Level Co-occurrence Matrix. Selected features were also applied to an ML model, here a RF (Random Forests) model pretrained to classify tissue parts by tissue type (here epithelium, stroma, necrosis and background tissue) as an additional attribute).
Referring to claim 23, 26, and 29, Kudavelly discloses wherein, for each candidate needle path, the tissue resistance index is determined from the cuboid extracted around that candidate needle path, and the value for that candidate needle path is calculated from the tissue resistance index determined from that cuboid (paragraph 22, Another possible implementation is to illustrate the tissue density along an insertion path by a numeric value such as the average or peak or mean value of the sequence of density values), and wherein selecting the candidate needle path with the lowest value comprises comparing the values calculated for the plurality of candidate needle paths (paragraph 18, When the needle path calculator 54 receives the sequential density estimates for the projected path and several alternative adjacent paths, it can select the one that poses the least hazard and resistance to needle insertion).
Claims 5 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Kudavelly et al. US Publication 2014/0350390 and Pati et al. US Publication 2022/0164946 as applied to claims 1 and 11 above, and further in view of Shen et al. US Publication 2023/0225684 (hereafter “Shen et al”).
Referring to claims 5 and 13, Kudavelly discloses calculating the tissue resistance index from each cuboid of image data around each candidate needle path, but does not disclose expressly wherein calculating the tissue resistance index from each cuboid of image data around each candidate needle path.
Shen discloses applying average filters to remove noise from each cuboid of image data around each candidate needle path (paragraph 57, In some embodiments, candidate needle regions may be filtered based on the pixel value in the data since outside the body there may be large difference in pixel value between data points corresponding to the needle (which may be metallic) and other data points corresponding to other components. For example, filtering may comprise comparing the detected pixel values with a threshold pixel value and ignoring any candidate needle regions which do not appear to correspond to the presence of needle structure).
At the time of the effective filing date of the claimed invention, it would have obvious to a person of ordinary skill in the art to remove noise from image data. The motivation for doing so would have been to increase the quality of the image. Therefore, it would have been obvious to combine Shen with Kudavelly to obtain the invention as specified in claims 5 and 13.
Allowable Subject Matter
Claims 8 and 16 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PETER K HUNTSINGER whose telephone number is (571)272-7435. The examiner can normally be reached Monday - Friday 8:30 - 5:00.
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, Benny Q Tieu can be reached at 571-272-7490. 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.
/PETER K HUNTSINGER/Primary Examiner, Art Unit 2682
Prosecution Insights