Detailed Action
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . See 35 U.S.C. § 100 (note).
response to amendment
Applicant’s Amendments filed on March 13, 2026 has been entered and made of record.
Currently pending Claim(s)
1–20
Independent Claim(s)
1, 18 and 20
Amended Claim(s)
1, 2, 9, 14 and 18–20
Response to Arguments
This office action is responsive to Applicant’s Arguments/Remarks Made in an Amendment received on March 13, 2026.
In view of amendments filed on March 13, 2026 to the claims, the objection to the claims are withdrawn.
In view of applicant Argument/Remarks filed January March 13, 2026 with respect to claim 18, U.S.C. 112(f) claim interpretation have been carefully considered and the claim interpretation to claim 18 under 35 U.S.C. 112(f) is withdrawn.
In view of applicant Argument/Remarks and amendment filed March 13, 2026 with respect to U.S.C. 101 claim rejection have been carefully considered and the claim rejection is withdrawn.
Applicant’s Reply1 includes substantive amendments to the claims. This Office action has been updated with new grounds of rejection addressing those amendments. Further Applicant’s Arguments/Remarks with respect to independent claims 1 have been considered but are moot because the arguments do not apply to any of the references being used in the current rejection and the arguments are now rejected by newly cited art “Regression forests for efficient anatomy detection and localization in computed tomography scans” (Criminisi at al. hereinafter referred to as “Criminisi”) as explained in the body of rejection below.
Art Rejections
Obviousness 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.
Claim 1, 3–6, 12, 13, 15–18 and 20 are rejected under 35 U.S.C. § 103 as being unpatentable over the combination of US Patent Application Publication 2018/0089530 (published Mar. 29, 2018) (Liu et al. hereinafter referred to as “Liu”) in view of “Regression forests for efficient anatomy detection and localization in computed tomography scans” (Criminisi at al. hereinafter referred to as “Criminisi”).
Claim 7–11 and 14 is rejected under 35 U.S.C. § 103 as being unpatentable over the combination of US Patent Application Publication 2018/0089530 (published Mar. 29, 2018) (Liu et al. hereinafter referred to as “Liu”) in view of Criminisi and further in view of US Patent Application Publication 2020/0327661 (published Oct. 15, 2020) (“Oved”) .
With respect to claim 1, Liu discloses a computer-implemented method for automated processing of volumetric medical images (FIG. 1 ¶ 15 – FIG. 1 illustrates a method for landmark detection in a medical image using a deep neural network … in an advantageous embodiment, the medical image is a 3D medical image, which can also be referred to as a volume …), the method comprising:
a) receiving a volumetric medical image (FIG. 1 – step 201, ¶ 15 – at step 102, a medical image of a patient is received …), wherein the volumetric medical image comprises at least one organ or portion thereof (¶ 20 – the medical image associated with an organ or other anatomical object …); and
b) outputting a normalized location or a relative location referring to a certain reference coordinate system (¶ 20–22 – wherein at step 106, the location of the landmark in the medical image is detected using the trained deep neural network based on the subset of voxels input for each of the plurality of image patches …in particular, the deep neural network can be trained to detect a 2D location (x, y) of the anatomical landmark in a 2D medical image or to detect a 3D location (x, y, z) of the anatomical landmark a 3D medical image … the trained deep neural network can be a deep neural network regressor (regression function) that calculates, for an image patch centered at voxel, a difference vector from that voxel to a predicted location of the target landmark …).
However, Liu fails to explicitly disclose by applying a regression model for estimating anatomical locations to a certain input comprises a sparse sampling descriptor associated with a certain point of interest in the volumetric medical image, wherein the sparse sampling descriptor comprises a vector of intensities of sampled voxels associated with the certain point of interest.
Criminisi, working in the same field of endeavor, recognizes this problem and teaches applying a regression model for estimating anatomical locations (Abstract, p. 1293; Sec. 2, p. 1295 – This paper proposes a new algorithm for the efficient, automatic detection and localization of multiple anatomical structures… This is addressed effectively via tree-based, non-linear regression.” “We tackle this simultaneous feature selection and parameter regression task with a multi-class random regression forest…) to a certain input comprises a sparse sampling descriptor associated with a certain point of interest in the volumetric medical image (Sec. 2.1.1, p. 1295–1296 – Each training voxel is pushed through each of the trees… Our visual features are similar to those in Gall and Lempitsky (2009)… i.e., mean intensities over displaced, asymmetric cuboidal regions of the volume.” Voxels are sampled on a regular grid; each voxel gets a feature vector (descriptor) …), wherein the sparse sampling descriptor comprises a vector of intensities of sampled voxels associated with the certain point of interest (Sec. 2.1.1, p. 1296 – Our visual features are… mean intensities over displaced, asymmetric cuboidal regions of the volume.” The feature vector for each sampled voxel is a vector of mean intensities from several local regions (i.e., a vector of sampled values associated with the point of interest) …).
At the time of the invention, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have included in the invention of Liu applying a regression model for estimating anatomical locations to a certain input comprises a sparse sampling descriptor associated with a certain point of interest in the volumetric medical image, wherein the sparse sampling descriptor comprises a vector of intensities of sampled voxels associated with the certain point of interest as taught by Criminisi since doing so would have predictably and advantageously efficient to compute and capture spatial context, thereby improving both accuracy and computational efficiency. (see at least Criminisi et al. (2013, Sec. 2.1.1, p. 1296)).
Therefore, the claimed subject matter would have been obvious to a person having ordinary skill in the art at the time the invention was made.
With respect to claim 3, which claim 1 is incorporated, Liu discloses receiving a command for determining the certain point of interest (¶ 16, 25 and 27 – Liu describes user interaction for selecting points or regions of interest (e.g., via GUI or annotation tool) …) .
With respect to claim 4, which claim 3 is incorporated, Liu discloses wherein the sparse sampling descriptor is provided in dependence on the command (¶ 17–19 – Liu describes sampling voxels in image patches (grid-based or log-polar) based on user or system input, potentially adapting sampling to user selection …).
With respect to claim 5, which claim 1 is incorporated, Liu discloses providing a sparse sampling model for sparse sampling the volumetric medical image; and sampling voxels from the volumetric medical image using the provided sparse sampling model for obtaining sparse sampling descriptors (¶ 18–20 and 23 – Liu discloses grid-based and log-polar sparse sampling models, and feeding only sampled voxels to the neural network as descriptors …).
With respect to claim 6, which claim 5 is incorporated, Liu discloses wherein the sparse sampling model defines a number N of sampling points distributed in the volumetric medical image and defining locations and distances of the distributed sampling points (¶ 18–20 – Liu describes sampling patterns (grid, log-polar) defining locations and density of sampled voxels …).
With respect to claim 12, which claim 1 is incorporated, Liu discloses wherein the certain reference coordinate system uses at least a certain landmark in the volumetric medical image, wherein outputting the normalized location or the relative location referring to the certain reference coordinate system comprises outputting a relative location referring to the certain landmark (¶ 21 and 24 – Liu describes outputting location relative to detected landmarks …).
With respect to claim 13, which claim 12 is incorporated, Liu discloses wherein, for a certain location, the sparse sampling descriptor associated with the certain location is provided and a displacement from the certain landmark is determined (¶ 21 and 24 – Liu’s regressor outputs displacement vectors from a voxel to the predicted landmark location …).
With respect to claim 15, which claim 1 is incorporated, Liu discloses storing findings in the volumetric medical image using the normalized location or the relative location (¶ 25 and 27 – Liu describes annotating, storing, and displaying landmark findings at detected locations in the image …), and determining, based on the normalized location or the relative location, information associated with the certain point of interest or associated with at least a location nearby the certain point of interest (¶ 25 and 26 – Liu describes probability maps, pose estimation, semantic annotation, and knowledge association based on detected locations …).
With respect to claim 16, which claim 15 is incorporated, Liu discloses executing image registration based on the normalized location or the relative location (¶ 26 and 27 – Liu discusses marginal space search and pose estimation, which could be used in image registration …).
With respect to claim 17, which claim 1 is incorporated, Liu discloses wherein executing the image registration comprises matching the certain point of interest to a location in a further image (¶ 26 and 27 – Liu’s framework supports matching detected landmarks/locations across images …).
With respect to claim 18, Liu discloses a device for automated processing of volumetric medical images (¶ 27 and FIG. 5 – Liu et al. discloses a computer system (502) with processor (504), memory (510, 512), and input/output devices for receiving, storing, and processing volumetric medical images. The system is described as performing automated landmark detection in medical images using deep neural networks (see [0012], [0015], [0027]). Fig. 5 shows the device architecture supporting automated image processing …), comprising:
one or more processing circuits (¶ 27 and FIG. 5 – Processor 504, which controls the overall operation of the computer 502 …); and
a non-transitory memory coupled to the one or more processing circuits, the non-transitory memory comprising a module configured to perform steps including (¶ 15, 27 and FIG. 5 – computer program instructions may be stored in a storage device 512 and loaded into memory 510 …), the method comprising:
a) receiving a volumetric medical image (FIG. 1 – step 201, ¶ 15 – at step 102, a medical image of a patient is received …), wherein the volumetric medical image comprises at least one organ or portion thereof (¶ 20 – the medical image associated with an organ or other anatomical object …); and
b) outputting a normalized location or a relative location referring to a certain reference coordinate system (¶ 20–22 – wherein at step 106, the location of the landmark in the medical image is detected using the trained deep neural network based on the subset of voxels input for each of the plurality of image patches …in particular, the deep neural network can be trained to detect a 2D location (x, y) of the anatomical landmark in a 2D medical image or to detect a 3D location (x, y, z) of the anatomical landmark a 3D medical image … the trained deep neural network can be a deep neural network regressor (regression function) that calculates, for an image patch centered at voxel, a difference vector from that voxel to a predicted location of the target landmark …).
However, Liu fails to explicitly disclose by applying a regression model for estimating anatomical locations to a certain input comprises a sparse sampling descriptor associated with a certain point of interest in the volumetric medical image, wherein the sparse sampling descriptor comprises a vector of intensities of sampled voxels associated with the certain point of interest.
Criminisi, working in the same field of endeavor, recognizes this problem and teaches applying a regression model for estimating anatomical locations (Abstract, p. 1293; Sec. 2, p. 1295 – This paper proposes a new algorithm for the efficient, automatic detection and localization of multiple anatomical structures… This is addressed effectively via tree-based, non-linear regression.” “We tackle this simultaneous feature selection and parameter regression task with a multi-class random regression forest…) to a certain input comprises a sparse sampling descriptor associated with a certain point of interest in the volumetric medical image (Sec. 2.1.1, p. 1295–1296 – Each training voxel is pushed through each of the trees… Our visual features are similar to those in Gall and Lempitsky (2009)… i.e., mean intensities over displaced, asymmetric cuboidal regions of the volume.” Voxels are sampled on a regular grid; each voxel gets a feature vector (descriptor) …), wherein the sparse sampling descriptor comprises a vector of intensities of sampled voxels associated with the certain point of interest (Sec. 2.1.1, p. 1296 – Our visual features are… mean intensities over displaced, asymmetric cuboidal regions of the volume.” The feature vector for each sampled voxel is a vector of mean intensities from several local regions (i.e., a vector of sampled values associated with the point of interest) …).
At the time of the invention, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have included in the invention of Liu applying a regression model for estimating anatomical locations to a certain input comprises a sparse sampling descriptor associated with a certain point of interest in the volumetric medical image, wherein the sparse sampling descriptor comprises a vector of intensities of sampled voxels associated with the certain point of interest as taught by Criminisi since doing so would have predictably and advantageously efficient to compute and capture spatial context, thereby improving both accuracy and computational efficiency. (see at least Criminisi et al. (2013, Sec. 2.1.1, p. 1296)).
Therefore, the claimed subject matter would have been obvious to a person having ordinary skill in the art at the time the invention was made.
With respect to claim 20, (drawn to a computer-readable media (CRM)) the proposed combination of Liu in view of Criminisi, explained in the rejection of method claim 1 renders obvious the steps of the CRM of claim 20, because these steps occur in the operation of the method as discussed above. Thus, the arguments similar to that presented above for claim 1 is equally applicable to claim 20.
Claim 7–11 and 14 is rejected under 35 U.S.C. § 103 as being unpatentable over the combination of US Patent Application Publication 2018/0089530 (published Mar. 29, 2018) (Liu et al. hereinafter referred to as “Liu”) in view of Criminisi and further in view of US Patent Application Publication 2020/0327661 (published Oct. 15, 2020) (“Oved”) .
With respect to claim 7, Liu discloses wherein the certain reference coordinate system comprises Liu references mapping to anatomical objects and pose parameters, which could be interpreted as reference volume …).
However, Liu and Criminisi fails to explicitly disclose an atlas or a single reference volume as atlas.
Oved, working in the same field of endeavor, recognizes this problem and teaches an atlas or a single reference volume as atlas (a reference coordinate system for anatomical localization, mapping anatomical locations to a normalized anatomical scale (see Oved [0008], [0015], [0019], [0026], [0027]). Oved’s normalized anatomical scale is described as a one-dimensional coordinate system of equally spaced positions along an axial dimension of a human body, with mapped anatomical landmarks ([0019], [0015]). This normalized anatomical scale, which assigns unique positions to anatomical landmarks and can represent the anatomy of a single individual or an average, constitutes an atlas as claimed. Atlases are well-known in medical imaging as standardized coordinate systems or templates for anatomical localization …).
At the time of the invention, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have included in the invention of Liu in view of Criminisi to apply an atlas or a single reference volume as atlas as taught by Oved since doing so would have predictably and advantageously allows using a normalized anatomical scale (atlas) for efficient, interoperable, and semantically meaningful anatomical indexing to support multiple applications and facilitate semantic annotation (see at least Oved , ¶ 45).
Therefore, the claimed subject matter would have been obvious to a person having ordinary skill in the art at the time the invention was made.
With respect to claim 8, which claim 7 is incorporated, Liu discloses wherein, Liu discusses annotation and semantic information, which could be considered “injected knowledge” …).
However, Liu and Criminisi fails to explicitly disclose the atlas.
Oved, working in the same field of endeavor, recognizes this problem and teaches the atlas (a reference coordinate system for anatomical localization, mapping anatomical locations to a normalized anatomical scale (see Oved [0008], [0015], [0019], [0026], [0027]). Oved’s normalized anatomical scale is described as a one-dimensional coordinate system of equally spaced positions along an axial dimension of a human body, with mapped anatomical landmarks ([0019], [0015]). This normalized anatomical scale, which assigns unique positions to anatomical landmarks and can represent the anatomy of a single individual or an average, constitutes an atlas as claimed. Atlases are well-known in medical imaging as standardized coordinate systems or templates for anatomical localization …).
At the time of the invention, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have included in the invention of Liu in view of Criminisi to apply the atlas as taught by Oved since doing so would have predictably and advantageously allows using a normalized anatomical scale (atlas) for efficient, interoperable, and semantically meaningful anatomical indexing to support multiple applications and facilitate semantic annotation (see at least Oved , ¶ 45).
Therefore, the claimed subject matter would have been obvious to a person having ordinary skill in the art at the time the invention was made.
With respect to claim 9, which claim 8 is incorporated, Liu discloses wherein the injected knowledge comprises semantic anatomical information (¶ 26 and 27 – Liu supports this via annotation tools and semantic labeling of anatomical landmarks …).
With respect to claim 10, which claim 7 is incorporated, Liu discloses wherein outputting the normalized location or the relative location referring to the certain reference coordinate system Liu’s regressor or classifier outputs landmark positions, which can be mapped to normalized coordinates …).
However, Liu and Criminisi fails to explicitly disclose outputting a normalized location referring to the atlas.
Oved, working in the same field of endeavor, recognizes this problem and teaches outputting a normalized location referring to the atlas (¶ 15, 16, 19 and 26 – Oved teaches outputting normalized locations with respect to the atlas (normalized anatomical scale) …).
At the time of the invention, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have included in the invention of Liu in view of Criminisi to output a normalized location referring to the atlas as taught by Oved since doing so would have predictably and advantageously allows using a normalized anatomical scale (atlas) for efficient, interoperable, and semantically meaningful anatomical indexing to support multiple applications and facilitate semantic annotation (see at least Oved , ¶ 45).
Therefore, the claimed subject matter would have been obvious to a person having ordinary skill in the art at the time the invention was made.
With respect to claim 11, which claim 10 is incorporated, Liu discloses mapping the certain point of interest of the volumetric medical image to a certain normalized location Liu teaches associating semantic annotation, injected knowledge, or clinical information with mapped locations. …).
However, Liu and Criminisi fails to explicitly disclose mapping the certain points in the atlas.
Oved, working in the same field of endeavor, recognizes this problem and teaches mapping the certain points in the atlas (¶ 15, 19, 26 – Oved teaches mapping anatomical landmarks and points of interest to normalized locations in an atlas …).
At the time of the invention, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have included in the invention of Liu in view of Criminisi to map a certain points in the atlas as taught by Oved since doing so would have predictably and advantageously allows using a normalized anatomical scale (atlas) for efficient, interoperable, and semantically meaningful anatomical indexing to support multiple applications and facilitate semantic annotation (see at least Oved , ¶ 45).
Therefore, the claimed subject matter would have been obvious to a person having ordinary skill in the art at the time the invention was made.
With respect to claim 14, which claim 1 is incorporated, Liu discloses wherein outputting the normalized location or the relative location referring to the certain reference coordinate system comprises 24 and 26 – Liu teaches regression outputs that can be mapped to coordinates or displacement vectors …).
However, Liu and Criminisi fails to explicitly disclose outputting a relative displacement vector referring to an atlas.
Oved, working in the same field of endeavor, recognizes this problem and teaches outputting a relative displacement vector referring to an atlas (¶ 19, 21 and 22 – Oved teaches outputting displacement vectors and normalized coordinates with respect to an atlas …).
At the time of the invention, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have included in the invention of Liu in view of Criminisi to output a relative displacement vector referring to an atlas as taught by Oved since doing so would have predictably and advantageously allows using a normalized anatomical scale (atlas) for efficient, interoperable, and semantically meaningful anatomical indexing to support multiple applications and facilitate semantic annotation (see at least Oved , ¶ 45).
Therefore, the claimed subject matter would have been obvious to a person having ordinary skill in the art at the time the invention was made.
Summary
Claims 1, 3–18 and 20 are rejected under at least one of 35 U.S.C. §§ 102 and 103 as being unpatentable over the cited prior art. 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 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.
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 C.F.R. § 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.
LLOWABLE SUBJECT MATTER
Claims 2 and 19 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.
Claim 2 contain subject matter that is not disclosed or made obvious in the cited art.
In regard to claim 2, when considering claim 2 as a whole, prior art of record fails to disclose or render obvious, alone or in combination:
“wherein the regression model comprises a neural network trained to embody a normalized coordinate estimator for point matching between locations in the volumetric medical image and locations in the certain reference coordinate system, wherein the neural network outputs coordinates of the normalized location between 0 and 1.”
In regard to claim 19, when considering claim 2 as a whole, prior art of record fails to disclose or render obvious, alone or in combination:
“wherein the regression model comprises a neural network trained to embody a normalized coordinate estimator for point matching between locations in the volumetric medical image and locations in the certain reference coordinate system, wherein the neural network outputs coordinates of the normalized location between 0 and 1.”
ADDITIONAL CITATIONS
The following table lists several references that are relevant to the subject matter claimed and disclosed in this Application. The references are not relied on by the Examiner, but are provided to assist the Applicant in responding to this Office action.
Citation
Relevance
BRIEF: Binary Robust Independent Elementary Features⋆ (Calonder et al.)
Describes a binary strings as an efficient feature point descriptor, which we call BRIEF. We show that it is highly discriminative even when using relatively few bits and can be computed using simple intensity difference tests. Furthermore, the descriptor similarity can be evaluated using the Hamming distance, which is very efficient to compute, instead of the L2 norm as is usually done. As a result, BRIEF is very fast both to build and to match. We compare it against SURF and U-SURF on standard benchmarks and show that it yields a similar or better recognition performance, while running in a fraction of the time required by either.
Table 1
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 HENOK A SHIFERAW whose telephone number is (571)272-4637. The examiner can normally be reached Monday-Friday, 8:30AM - 5:00PM, (EST).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Henok Shiferaw can be reached at 571-272-4637. 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.
HENOK A. SHIFERAW
Supervisory Patent Examiner
Art Unit 2676
/Henok Shiferaw/Supervisory Patent Examiner, Art Unit 2676
1 Applicant Arguments/Remarks Made in Amendment (3/13/2026)