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 statements (IDS) were submitted on 10/16/2024 and 3/5/2026. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Claim Objections
Claims 1, 10, and 15 are objected to because of the following informalities:
Regarding claims 1, 10, and 15, “AI (artificial intelligence)” is objected to for clarity. Examiner suggests amending to “artificial intelligence (AI)” and using just “AI” in the dependent claims.
Regarding claims 1, 10, and 15, Examiner suggests removing “1)” and “2)” to improve clarity.
Appropriate correction is required.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
Regarding claim 10, “means” will be interpreted as a generic processor as described in Fig. 10 and ¶0088-0089.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1, 10, and 15, with claim 1 being exemplary, recite:
“(a) receiving 1) one or more medical images of a patient and 2) a vascular tree template comprising a plurality of points; (b) iteratively adjusting the plurality of points of the vascular tree template based on the one or more medical images using one or more AI (artificial intelligence) agents to generate a patient-specific vascular tree for the patient; and (c) outputting the patient-specific vascular tree” [Emphasis added].
According to the USPTO guidelines, a claim is directed to non-statutory subject matter if:
STEP 1: the claim does not fall within one of the four statutory categories of invention (process, machine, manufacture or composition of matter), or
STEP 2: the claim recites a judicial exception, e.g. an abstract idea, without reciting additional elements that amount to significantly more than the judicial exception, as determined using the following analysis:
STEP 2A (PRONG 1): Does the claim recite an abstract idea, law of nature, or natural phenomenon?
STEP 2A (PRONG 2): Does the claim recite additional elements that integrate the judicial exception into a practical application?
STEP 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
Using the two-step inquiry, it is clear that the independent claims 1, 10, and 15 are directed to an abstract idea as shown below:
STEP 1: Do the claims fall within one of the statutory categories? YES. Independent claims 1, 10, and 15 are directed to method, apparatus, and non-transitory CRM, respectively.
STEP 2A (PRONG 1): Is the claim directed to a law of nature, a natural phenomenon, or an abstract idea? YES. Independent claims 1, 10, and 15 are directed towards a mental process (i.e. an abstract idea).
Regarding claims 1, 10, and 15, limitation (b), in emphasized claims 1, 10, and 15 above, is a mental process. Adjusting the points of a vascular tree template according to a patient’s medical images amounts to determining whether the point, which for example may lie on a blood vessel, should be moved so that the tree template more closely matches the image. The human mind is capable of determining whether the blood vessels in the template tree align with those in an image.
STEP 2A (PRONG 2): Does the claim recite additional elements that integrate the judicial exception into a practical application? No. Independent claims 1, 10, and 15 do not recite additional elements that integrate the judicial exception into a practical application.
Regarding claims 1, 10, and 15, limitations (a) and (c), in emphasized claims 1, 10, and 15 above, are additional elements, receiving and outputting medical images and vessel trees, that fall under insignificant extra-solution activity since it is merely data gathering and data output (see MPEP §2106.05(g)). Limitation (b), recites using one or more AI (artificial intelligence) agents, which amounts to no more than a recitation of the words "apply it" (or an equivalent) or are no more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP §2106.05(f)).
STEP 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception? NO. Independent claims 1, 10, and 15 do not recite additional elements that amount to significantly more than the judicial exception.
Regarding claims 1, 10, and 15, the claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because when considered separately and in combination, the above recited additional elements from claims 1, 10, and 15 do not add significantly more (also known as an “inventive concept”) to the exception. Rather, the additional elements disclosed above perform well-understood, routine, conventional computer functions as recognized by the court decisions listed in MPEP §2106.05(d).
Therefore, independent claims 1, 10, and 15 are directed towards an abstract idea without a practical application or significantly more.
Regarding claims 2, 11, and 16, with claim 2 being exemplary, the additional limitations do not integrate the abstract idea into a practical application or add significantly more to the abstract idea. The limitation: jointly adjusting the plurality of points at each iteration falls under a mental process as it is simply judging whether two blood vessels or two locations along a single blood vessel is aligned with the image, which the human mind would be capable for performing (see MPEP §2106.04(a)(2)(III)).
Regarding claims 3 and 12, with claim 3 being exemplary, the additional limitations do not integrate the abstract idea into a practical application or add significantly more to the abstract idea. The limitation: iteratively adjusting the plurality of points in at least one of a left direction, a right direction, an inferior direction, a superior direction, a posterior direction, or an anterior direction falls under a mental process as the human mind is capable of selecting a direction (see MPEP §2106.04(a)(2)(III)).
Regarding claims 4 and 13, with claim 4 being exemplary, the additional limitations do not integrate the abstract idea into a practical application or add significantly more to the abstract idea. The limitation: wherein the one or more AI agents receives as input at least one of the one or more medical images corresponding to a current position of the one or more AI agents and generates as output a vector corresponding to the adjustments for the plurality of points falls under data input and output (see MPEP §2106.05(g)).
Regarding claims 5 and 15, with claim 5 being exemplary, the additional limitations do not integrate the abstract idea into a practical application or add significantly more to the abstract idea. The limitation: wherein the one or more medical images comprise at least one of one or more bone removed medical images or one or more vessel probability maps falls under selecting a data type (see MPEP §2106.05(g)).
Regarding claims 6 and 17, with claim 6 being exemplary, the additional limitations do not integrate the abstract idea into a practical application or add significantly more to the abstract idea. The limitation: wherein the one or more AI agents are trained using synthesized large vessel occlusion data, the synthesized large vessel occlusion data generated by simulating an occlusion in a particular segment of a vessel tree by: removing the particular segment from the vessel tree; and in response to determining that the particular segment is a sole bloody supply to a downstream segment of the vascular tree, removing the downstream segment from the vascular tree falls under selecting a data type for elements regarding synthetic data (see MPEP §2106.05(g)) and a mental process for elements determining which area of the tree to cut as the human mind could just if a vessel is the sole blood supply by identifying if any other vessels are connected to the downstream branch (see MPEP §2106.04(a)(2)(III)).
Regarding claims 7 and 18, with claim 7 being exemplary, the additional limitations do not integrate the abstract idea into a practical application or add significantly more to the abstract idea. The limitation: generating the vascular tree template by averaging a set of manually identified vascular trees for a patient population falls under a mental process as a human could perform the averaging with aid of pen and paper (see MPEP §2106.04(a)(2)(III)).
Regarding claims 8 and 19, with claim 8 being exemplary, the additional limitations do not integrate the abstract idea into a practical application or add significantly more to the abstract idea. The limitation: selecting a vascular tree from the set of manually identified vascular trees; aligning the remaining vascular trees of the set of manually identified vascular trees to the selected vascular tree; averaging positions of each vascular landmark of the aligned vascular trees; and aligning the set of manually identified vascular trees to the average position of each vascular landmark falls under a mental process as the steps taken could be performed by the human mind. A person could select a tree from a group, determine if different trees are aligned with each other and make appropriate adjustments, and calculate averages with aid of pen and paper (see MPEP §2106.04(a)(2)(III)).
Regarding claims 9 and 20, with claim 9 being exemplary, the additional limitations do not integrate the abstract idea into a practical application or add significantly more to the abstract idea. The limitation: wherein the one or more medical images are computed tomography angiography images of a head and neck of the patient falls under selecting a data type (see MPEP §2106.05(g)).
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.
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.
Claims 1-5, 9-16, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over van de Giessen et al. (Van de Giessen, Martijn, et al. "Probabilistic atlas based labeling of the cerebral vessel tree." Medical Imaging 2015: Image Processing. Vol. 9413. SPIE, 2015) (hereafter, “Giessen”) (IDS) in view of Georgescu et al. (US 2023/0102246) (hereafter, “Georgescu”) (IDS).
Regarding claim 1, Giessen discloses a computer-implemented method comprising: receiving 1) one or more medical images of a patient (Page 2, §2.1 Data, MRA scans) and 2) a vascular tree template comprising a plurality of points (Page 2, §2.1 Data, the skeleton of the vessel tree); iteratively adjusting the plurality of points of the vascular tree template based on the one or more medical images using [one or more AI (artificial intelligence) agents] to generate a patient-specific vascular tree for the patient (Page 4, §2.3 Registration, transforming an example vessel tree and iteratively adapting the transformation parameters such that the likelihood is the highest); and outputting the patient-specific vascular tree (Fig. 1, 2. The figures illustrate the tree for an individual patient).
However, Giessen fails to explicitly disclose one or more AI (artificial intelligence) agents.
Georgescu teaches one or more AI (artificial intelligence) agents (¶0034, An RL (reinforcement learning) agent is trained).
Both Giessen and Georgescu are analogous to the claimed invention because both are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the RL agent of Georgescu into the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to automate detection of occlusions, as suggested by Georgescu at ¶0025, embodiments described herein use such semantic knowledge to automatically detect the presence of large vessel occlusions.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu to obtain the invention as specified in claim 1.
Regarding claim 2, Giessen in view of Georgescu discloses the computer-implemented method of claim 1.
However, Giessen fails to explicitly disclose wherein iteratively adjusting the plurality of points of the vascular tree template based on the one or more medical images using one or more AI (artificial intelligence) agents to generate a patient-specific vascular tree for the patient comprises: jointly adjusting the plurality of points at each iteration.
Georgescu teaches wherein iteratively adjusting the plurality of points of the vascular tree template based on the one or more medical images using one or more AI (artificial intelligence) agents to generate a patient-specific vascular tree for the patient comprises: jointly adjusting the plurality of points at each iteration (¶0034, A respective RL agent is applied for each target vascular path between vascular landmarks to determine the location of that vascular segment. A final tree is constructed by running all RL agents and determining the tree with the most likely probability. Examiner interprets running multiple agents at different segments as “jointly adjusting”).
Both Giessen and Georgescu are analogous to the claimed invention because both are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the RL agent of Georgescu into the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to automate detection of occlusions, as suggested by Georgescu at ¶0025, embodiments described herein use such semantic knowledge to automatically detect the presence of large vessel occlusions.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu to obtain the invention as specified in claim 2.
Regarding claim 3, Giessen in view of Georgescu discloses the computer-implemented method of claim 1.
However, Giessen fails to explicitly disclose wherein iteratively adjusting the plurality of points of the vascular tree template based on the one or more medical images using one or more AI (artificial intelligence) agents to generate a patient-specific vascular tree for the patient comprises: iteratively adjusting the plurality of points in at least one of a left direction, a right direction, an inferior direction, a superior direction, a posterior direction, or an anterior direction.
Georgescu teaches wherein iteratively adjusting the plurality of points of the vascular tree template based on the one or more medical images using one or more AI (artificial intelligence) agents to generate a patient-specific vascular tree for the patient comprises: iteratively adjusting the plurality of points in at least one of a left direction, a right direction, an inferior direction, a superior direction, a posterior direction, or an anterior direction (¶0034, output an action set in three dimensions (e.g., move left, right, up, down, back, forward, etc.)).
Both Giessen and Georgescu are analogous to the claimed invention because both are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the RL agent of Georgescu into the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to automate detection of occlusions, as suggested by Georgescu at ¶0025, embodiments described herein use such semantic knowledge to automatically detect the presence of large vessel occlusions.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu to obtain the invention as specified in claim 3.
Regarding claim 4, Giessen in view of Georgescu discloses the computer-implemented method of claim 1.
However, Giessen fails to explicitly disclose wherein the one or more AI agents receives as input at least one of the one or more medical images corresponding to a current position of the one or more AI agents and generates as output a vector corresponding to the adjustments for the plurality of points.
Georgescu teaches wherein the one or more AI agents receives as input at least one of the one or more medical images corresponding to a current position of the one or more AI agents (¶0034, An RL (reinforcement learning) agent is trained for each respective segment … the input medical image … The RL agents are trained to move along the path from an initial anatomical landmark to a target anatomical landmark by observing as input the centerline probability map. Examiner considers the segment to be correspond to the agent position) and generates as output a vector corresponding to the adjustments for the plurality of points (¶0034, output an action set in three dimensions (e.g., move left, right, up, down, back, forward, etc.). Examiner considers the output to be a vector since it is in 3D).
Both Giessen and Georgescu are analogous to the claimed invention because both are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the RL agent of Georgescu into the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to automate detection of occlusions, as suggested by Georgescu at ¶0025, embodiments described herein use such semantic knowledge to automatically detect the presence of large vessel occlusions.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu to obtain the invention as specified in claim 4.
Regarding claim 5, Giessen in view of Georgescu discloses the computer-implemented method of claim 1.
However, Giessen fails to explicitly disclose wherein the one or more medical images comprise at least one of one or more bone removed medical images or one or more vessel probability maps.
Georgescu teaches wherein the one or more medical images comprise at least one of one or more bone removed medical images (¶0029, bone may also be removed from the input medical image. Since the limitation is recited in the alternative, Examiner considers this citation to fully disclose the limitation) or one or more vessel probability maps.
Both Giessen and Georgescu are analogous to the claimed invention because both are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the RL agent of Georgescu into the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to automate detection of occlusions, as suggested by Georgescu at ¶0025, embodiments described herein use such semantic knowledge to automatically detect the presence of large vessel occlusions.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu to obtain the invention as specified in claim 5.
Regarding claim 9, in which claim 1 is incorporated, Giessen discloses wherein the one or more medical images are computed tomography angiography images (Abstract, computed tomography angiography (CTA)) [of a head and neck of the patient].
However, Giessen fails to explicitly disclose of a head and neck of the patient.
Georgescu teaches of a head and neck of the patient (Fig. 2-4. These figures illustrate medical images of a head and neck).
Both Giessen and Georgescu are analogous to the claimed invention because both are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the RL agent of Georgescu into the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to automate detection of occlusions, as suggested by Georgescu at ¶0025, embodiments described herein use such semantic knowledge to automatically detect the presence of large vessel occlusions.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu to obtain the invention as specified in claim 9.
Regarding claim 10, Giessen discloses an apparatus comprising: [means for] receiving 1) one or more medical images of a patient (Page 2, §2.1 Data, MRA scans) and 2) a vascular tree template comprising a plurality of points (Page 2, §2.1 Data, the skeleton of the vessel tree); [means for] iteratively adjusting the plurality of points of the vascular tree template based on the one or more medical images using [one or more AI (artificial intelligence) agents] to generate a patient-specific vascular tree for the patient (Page 4, §2.3 Registration, transforming an example vessel tree and iteratively adapting the transformation parameters such that the likelihood is the highest); and [means for] outputting the patient-specific vascular tree (Fig. 1, 2. The figures illustrate the tree for an individual patient).
However, Giessen fails to explicitly disclose means for and one or more AI (artificial intelligence) agents.
Georgescu teaches means for (¶0082, computer processors) and one or more AI (artificial intelligence) agents (¶0034, An RL (reinforcement learning) agent is trained).
Both Giessen and Georgescu are analogous to the claimed invention because both are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the RL agent of Georgescu into the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to automate detection of occlusions, as suggested by Georgescu at ¶0025, embodiments described herein use such semantic knowledge to automatically detect the presence of large vessel occlusions.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu to obtain the invention as specified in claim 10.
Regarding claim 11, Giessen in view of Georgescu discloses the apparatus of claim 10.
However, Giessen fails to explicitly disclose wherein the means for iteratively adjusting the plurality of points of the vascular tree template based on the one or more medical images using one or more AI (artificial intelligence) agents to generate a patient-specific vascular tree for the patient comprises: means for jointly adjusting the plurality of points at each iteration.
Georgescu teaches wherein the means for (¶0082, computer processors) iteratively adjusting the plurality of points of the vascular tree template based on the one or more medical images using one or more AI (artificial intelligence) agents to generate a patient-specific vascular tree for the patient comprises: means for jointly adjusting the plurality of points at each iteration (¶0034, A respective RL agent is applied for each target vascular path between vascular landmarks to determine the location of that vascular segment. A final tree is constructed by running all RL agents and determining the tree with the most likely probability. Examiner interprets running multiple agents at different segments as “jointly adjusting”).
Both Giessen and Georgescu are analogous to the claimed invention because both are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the RL agent of Georgescu into the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to automate detection of occlusions, as suggested by Georgescu at ¶0025, embodiments described herein use such semantic knowledge to automatically detect the presence of large vessel occlusions.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu to obtain the invention as specified in claim 11.
Regarding claim 12, Giessen in view of Georgescu discloses the apparatus of claim 10.
However, Giessen fails to explicitly disclose wherein the means (¶0082, computer processors) for iteratively adjusting the plurality of points of the vascular tree template based on the one or more medical images using one or more AI (artificial intelligence) agents to generate a patient-specific vascular tree for the patient comprises: means for iteratively adjusting the plurality of points in at least one of a left direction, a right direction, an inferior direction, a superior direction, a posterior direction, or an anterior direction.
Georgescu teaches wherein the means for iteratively adjusting the plurality of points of the vascular tree template based on the one or more medical images using one or more AI (artificial intelligence) agents to generate a patient-specific vascular tree for the patient comprises: means for iteratively adjusting the plurality of points in at least one of a left direction, a right direction, an inferior direction, a superior direction, a posterior direction, or an anterior direction (¶0034, output an action set in three dimensions (e.g., move left, right, up, down, back, forward, etc.)).
Both Giessen and Georgescu are analogous to the claimed invention because both are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the RL agent of Georgescu into the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to automate detection of occlusions, as suggested by Georgescu at ¶0025, embodiments described herein use such semantic knowledge to automatically detect the presence of large vessel occlusions.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu to obtain the invention as specified in claim 12.
Regarding claim 13, Giessen in view of Georgescu discloses the apparatus of claim 10.
However, Giessen fails to explicitly disclose wherein the one or more AI agents receives as input at least one of the one or more medical images corresponding to a current position of the one or more AI agents and generates as output a vector corresponding to the adjustments for the plurality of points.
Georgescu teaches wherein the one or more AI agents receives as input at least one of the one or more medical images corresponding to a current position of the one or more AI agents (¶0034, An RL (reinforcement learning) agent is trained for each respective segment … the input medical image … The RL agents are trained to move along the path from an initial anatomical landmark to a target anatomical landmark by observing as input the centerline probability map. Examiner considers the segment to be correspond to the agent position) and generates as output a vector corresponding to the adjustments for the plurality of points (¶0034, output an action set in three dimensions (e.g., move left, right, up, down, back, forward, etc.). Examiner considers the output to be a vector since it is in 3D).
Both Giessen and Georgescu are analogous to the claimed invention because both are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the RL agent of Georgescu into the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to automate detection of occlusions, as suggested by Georgescu at ¶0025, embodiments described herein use such semantic knowledge to automatically detect the presence of large vessel occlusions.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu to obtain the invention as specified in claim 13.
Regarding claim 14, Giessen in view of Georgescu discloses the apparatus of claim 10.
However, Giessen fails to explicitly disclose wherein the one or more medical images comprise at least one of one or more bone removed medical images or one or more vessel probability maps.
Georgescu teaches wherein the one or more medical images comprise at least one of one or more bone removed medical images (¶0029, bone may also be removed from the input medical image. Since the limitation is recited in the alternative, Examiner considers this citation to fully disclose the limitation) or one or more vessel probability maps.
Both Giessen and Georgescu are analogous to the claimed invention because both are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the RL agent of Georgescu into the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to automate detection of occlusions, as suggested by Georgescu at ¶0025, embodiments described herein use such semantic knowledge to automatically detect the presence of large vessel occlusions.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu to obtain the invention as specified in claim 14.
Regarding claim 15, Giessen discloses a [non-transitory computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out operations] comprising: receiving 1) one or more medical images of a patient (Page 2, §2.1 Data, MRA scans) and 2) a vascular tree template comprising a plurality of points (Page 2, §2.1 Data, the skeleton of the vessel tree); iteratively adjusting the plurality of points of the vascular tree template based on the one or more medical images using [one or more AI (artificial intelligence) agents] to generate a patient-specific vascular tree for the patient (Page 4, §2.3 Registration, transforming an example vessel tree and iteratively adapting the transformation parameters such that the likelihood is the highest); and outputting the patient-specific vascular tree (Fig. 1, 2. The figures illustrate the tree for an individual patient).
However, Giessen fails to explicitly disclose non-transitory computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out operations and one or more AI (artificial intelligence) agents.
Georgescu teaches non-transitory computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out operations (¶0085, a non-transitory machine-readable storage device, for execution by a programmable processor) and one or more AI (artificial intelligence) agents (¶0034, An RL (reinforcement learning) agent is trained).
Both Giessen and Georgescu are analogous to the claimed invention because both are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the RL agent of Georgescu into the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to automate detection of occlusions, as suggested by Georgescu at ¶0025, embodiments described herein use such semantic knowledge to automatically detect the presence of large vessel occlusions.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu to obtain the invention as specified in claim 15.
Regarding claim 16, Giessen in view of Georgescu discloses the non-transitory computer-readable storage medium of claim 15.
However, Giessen fails to explicitly disclose wherein iteratively adjusting the plurality of points of the vascular tree template based on the one or more medical images using one or more AI (artificial intelligence) agents to generate a patient-specific vascular tree for the patient comprises: jointly adjusting the plurality of points at each iteration.
Georgescu teaches wherein iteratively adjusting the plurality of points of the vascular tree template based on the one or more medical images using one or more AI (artificial intelligence) agents to generate a patient-specific vascular tree for the patient comprises: jointly adjusting the plurality of points at each iteration (¶0034, A respective RL agent is applied for each target vascular path between vascular landmarks to determine the location of that vascular segment. A final tree is constructed by running all RL agents and determining the tree with the most likely probability. Examiner interprets running multiple agents at different segments as “jointly adjusting”).
Both Giessen and Georgescu are analogous to the claimed invention because both are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the RL agent of Georgescu into the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to automate detection of occlusions, as suggested by Georgescu at ¶0025, embodiments described herein use such semantic knowledge to automatically detect the presence of large vessel occlusions.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu to obtain the invention as specified in claim 16.
Regarding claim 20, in which claim 15 is incorporated, Giessen discloses wherein the one or more medical images are computed tomography angiography images (Abstract, computed tomography angiography (CTA)) [of a head and neck of the patient].
However, Giessen fails to explicitly disclose of a head and neck of the patient.
Georgescu teaches of a head and neck of the patient (Fig. 2-4. These figures illustrate medical images of a head and neck).
Both Giessen and Georgescu are analogous to the claimed invention because both are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the RL agent of Georgescu into the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to automate detection of occlusions, as suggested by Georgescu at ¶0025, embodiments described herein use such semantic knowledge to automatically detect the presence of large vessel occlusions.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu to obtain the invention as specified in claim 20.
Claims 7, 8, 18, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over van de Giessen et al. (Van de Giessen, Martijn, et al. "Probabilistic atlas based labeling of the cerebral vessel tree." Medical Imaging 2015: Image Processing. Vol. 9413. SPIE, 2015) (hereafter, “Giessen”) (IDS) in view of Georgescu et al. (US 2023/0102246) (hereafter, “Georgescu”) (IDS) as applied to claims 1 and 15 above, and further in view of Antonsanti et al. (Antonsanti, Pierre-Louis, et al. "Database annotation with few examples: An atlas-based framework using diffeomorphic registration of 3D trees." International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer International Publishing, 2020) (hereafter, Antonsanti).
Regarding claim 7, in which claim 1 is incorporated, Giessen discloses [generating the vascular tree template by averaging a set of] manually identified (Page 2, last paragraph, manually labeled by an expert) [vascular trees for a patient population].
However, neither Giessen nor Georgescu, whether considered individually or in combination, explicitly disclose generating the vascular tree template by averaging a set of vascular trees for a patient population.
Antonsanti teaches generating the vascular tree template by averaging a set of vascular trees for a patient population (Page 4, last paragraph, the atlas converges along the iterations to an average position representative of the set of targets. Examiner considers the atlas as the tree template and the set of targets as trees for a population).
Giessen, Georgescu, and Antonsanti are analogous to the claimed invention because all three are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the tree averaging of Antonsanti into the RL agent of Georgescu and the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to improve performance, as suggested by Antonsanti at Abstract, The proposed method achieves 97.6% labeling precision with only 5 cases for training, while in comparison learning based methods only reach 82.2% on such small training sets.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu and Antonsanti.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu and Antonsanti to obtain the invention as specified in claim 7.
Regarding claim 8, in which claim 7 is incorporated, Giessen discloses [wherein generating the vascular tree template by averaging a set of manually identified vascular trees for a patient population comprises: selecting a vascular tree from the set of manually identified vascular trees; aligning the remaining vascular trees of the set of manually identified vascular trees to the selected vascular tree]; averaging positions of each vascular landmark of the aligned vascular trees (Page 4, §2.2, mean locations of the manually annotated characteristic bifurcation points over all vascular trees. Examiner considers the bifurcation points as vascular landmarks); and aligning the set of manually identified vascular trees to the average position of each vascular landmark (Page 4, §2.2, subsequently registering all trees using an affine transformation. Examiner considers the registration process as “aligning”).
However, neither Giessen nor Georgescu, whether considered individually or in combination, explicitly disclose wherein generating the vascular tree template by averaging a set of manually identified vascular trees for a patient population comprises: selecting a vascular tree from the set of manually identified vascular trees; aligning the remaining vascular trees of the set of manually identified vascular trees to the selected vascular tree.
Antonsanti teaches wherein generating the vascular tree template by averaging a set of manually identified vascular trees for a patient population (Page 4, last paragraph, the atlas converges along the iterations to an average position representative of the set of targets) comprises: selecting a vascular tree from the set of manually identified vascular trees (Page 4, paragraph 3, in order to build the atlas we select one available annotated case); aligning the remaining vascular trees of the set of manually identified vascular trees to the selected vascular tree (Page 4, paragraph 3, compute its deformations onto a set of N targets (the selected case included). These registrations provide a collection of initial momenta {pk i(0) i ,k ∈ [1,...,N]}. Examiner considers the registration as aligning the remaining trees to the selected tree).
Giessen, Georgescu, and Antonsanti are analogous to the claimed invention because all three are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the tree averaging of Antonsanti into the RL agent of Georgescu and the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to improve performance, as suggested by Antonsanti at Abstract, The proposed method achieves 97.6% labeling precision with only 5 cases for training, while in comparison learning based methods only reach 82.2% on such small training sets.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu and Antonsanti.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu and Antonsanti to obtain the invention as specified in claim 8.
Regarding claim 18, in which claim 15 is incorporated, Giessen discloses [generating the vascular tree template by averaging a set of] manually identified (Page 2, last paragraph, manually labeled by an expert) [vascular trees for a patient population].
However, neither Giessen nor Georgescu, whether considered individually or in combination, explicitly disclose generating the vascular tree template by averaging a set of vascular trees for a patient population.
Antonsanti teaches generating the vascular tree template by averaging a set of vascular trees for a patient population (Page 4, last paragraph, the atlas converges along the iterations to an average position representative of the set of targets. Examiner considers the atlas as the tree template and the set of targets as trees for a population).
Giessen, Georgescu, and Antonsanti are analogous to the claimed invention because all three are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the tree averaging of Antonsanti into the RL agent of Georgescu and the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to improve performance, as suggested by Antonsanti at Abstract, The proposed method achieves 97.6% labeling precision with only 5 cases for training, while in comparison learning based methods only reach 82.2% on such small training sets.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu and Antonsanti.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu and Antonsanti to obtain the invention as specified in claim 18.
Regarding claim 19, in which claim 18 is incorporated, Giessen discloses [wherein generating the vascular tree template by averaging a set of manually identified vascular trees for a patient population comprises: selecting a vascular tree from the set of manually identified vascular trees; aligning the remaining vascular trees of the set of manually identified vascular trees to the selected vascular tree]; averaging positions of each vascular landmark of the aligned vascular trees (Page 4, §2.2, mean locations of the manually annotated characteristic bifurcation points over all vascular trees. Examiner considers the bifurcation points as vascular landmarks); and aligning the set of manually identified vascular trees to the average position of each vascular landmark (Page 4, §2.2, subsequently registering all trees using an affine transformation. Examiner considers the registration process as “aligning”).
However, neither Giessen nor Georgescu, whether considered individually or in combination, explicitly disclose wherein generating the vascular tree template by averaging a set of manually identified vascular trees for a patient population comprises: selecting a vascular tree from the set of manually identified vascular trees; aligning the remaining vascular trees of the set of manually identified vascular trees to the selected vascular tree.
Antonsanti teaches wherein generating the vascular tree template by averaging a set of manually identified vascular trees for a patient population (Page 4, last paragraph, the atlas converges along the iterations to an average position representative of the set of targets) comprises: selecting a vascular tree from the set of manually identified vascular trees (Page 4, paragraph 3, in order to build the atlas we select one available annotated case); aligning the remaining vascular trees of the set of manually identified vascular trees to the selected vascular tree (Page 4, paragraph 3, compute its deformations onto a set of N targets (the selected case included). These registrations provide a collection of initial momenta {pk i(0) i ,k ∈ [1,...,N]}. Examiner considers the registration as aligning the remaining trees to the selected tree).
Giessen, Georgescu, and Antonsanti are analogous to the claimed invention because all three are directed towards align vascular trees. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the tree averaging of Antonsanti into the RL agent of Georgescu and the tree aligning method of Giessen. The suggestion/motivation for doing so would have been to improve performance, as suggested by Antonsanti at Abstract, The proposed method achieves 97.6% labeling precision with only 5 cases for training, while in comparison learning based methods only reach 82.2% on such small training sets.
This method of improving Giessen was within the ordinary ability of one of ordinary skill in the art based on the teachings of Georgescu and Antonsanti.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Giessen with the teachings of Georgescu and Antonsanti to obtain the invention as specified in claim 19.
Allowable Subject Matter
Claims 6 and 17 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 as well as amended to overcome the rejection under 35 U.S.C. §101.
The following is a statement of reasons for the indication of allowable subject matter:
Regarding claim 6, Anso (Ansó, Nil Stolt. "Synthetic vascular structure generation for unsupervised pre-training in CTA segmentation tasks." arXiv preprint arXiv:2001.00666 (2020)) discloses synthetic vasculature data (Page 3, §Contributions, we propose a synthetic vessel generation algorithm than can be used to pretrain a CNN model) and pruning segments and their downstream branches (Page 4, right column, paragraph 3, If the existing child happened to be the one pruned and had children of his own, the entire child’s branch is recursively removed). However, none of Anso nor any of the references cited above, whether considered individually or in combination, disclose the removal of downstream segments conditioned on determining a segment to be the sole blood supply.
Regarding claim 17, which is directed towards the non-transitory computer readable medium of 15, the claim otherwise recites the same limitations as claim 6. Therefore, it is indicated as allowable subject matter for the same reasons given above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Liu et al. (US 10,140,733) discloses construction of vascular trees (Col. 4, lines 26-28, Third, a 3-D centerline (vessel tree skeleton) is reconstructed from 2-D points using a bundle adjustment based approach).
Itu et al. (US 2018/0310888) discloses patient specific vascular trees (¶0021, features of a patient-specific vessel tree based on the patient-specific coronary geometry data).
Auvray et al. (US 2024/0404031) discloses removing branches from vascular trees (¶0087, it is possible to remove the branches from an angiogram that were not meant to be analyzed from a certain view).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to XIAOMAO DING whose telephone number is (571)272-7237. The examiner can normally be reached Mon-Fri 9:00-5:00.
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, 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.
/XIAOMAO DING/Examiner, Art Unit 2676
/Henok Shiferaw/Supervisory Patent Examiner, Art Unit 2676
Prosecution Insights