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 .
Priority
Receipt is acknowledged of papers submitted under 35 U.S.C. 119(a)-(d), which papers have been placed of record in the file.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 07/03/2026 is in compliance with the provisions on 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Request for Continued Examination and Claim Amendments
Acknowledgement of receiving amendments to the claims filed in the Request for Continued Examination (RCE), which were received by the office on 07/15/2026.
Response to Arguments Applicant's arguments filed 07/15/2026 have been fully considered and are persuasive.
In the remarks, regarding the Rejections under 35 U.S.C. 101, given the amendments to the claims and the applicant’s detailed explanation, the Rejections under 35 U.S.C. 101 have been reconsidered and are withdrawn.
The remarks concerning the cited art rejections have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Sato (JP 2006-167287 A), Nakada et al. (JP 2016-087139 A) Siemionow et al. (US 2026/0154819 A1) and Shim (US 2021/0219828 A1).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 2 6-13 and 116-18 are rejected under 35 U.S.C. 103 as being unpatentable over Sato (JP 2006167287 A) in view of Nakada et al.
(JP 2016087139 A) (hereinafter known as Nakada) and further in view of Siemionow et al. (US 2026/0154819 A1) (hereinafter known as Siemionow).
Regarding Claim 1, Sato teaches an image processing apparatus (Sato, FIG. 1, vascular stenosis rate analysis system 1) comprising at least one processor (Sato, FIG 1, control unit 12 and image processing unit 13 and paragraph [0018]), and the at least one processor is configured to:
extract a target organ from a medical image to generate a target image (Sato, Fig 2, step S2, paragraphs [0027]: Sato teaches extracting a blood vessel shape from three-dimensional image data obtained by an X-ray CT apparatus, a magnetic resonance imaging apparatus, or an ultrasonic diagnostic apparatus); set a reference axis passing through the target organ (Sato, see Claim 1 and paragraph [0012] and FIG 3, showing the core line through the vessel: Sato teaches generating a blood vessel core line as a reference axis through the extracted vessel (“blood vessel information generating means for generating blood vessel information including a blood vessel core line and a plurality of blood vessel contour points on the blood vessel orthogonal cross section orthogonal to the blood vessel core line”); set a plurality of small regions in the target organ along the reference axis (Sato, paragraphs [0029-0030]; FIG 3 and FIG 2, step S6: Sato teaches processing a plurality of blood vessel orthogonal cross-section positions distributed along the core line. Sato further teaches setting an analysis target range along the axis. See paragraph [0060]); derive a first evaluation value representing a physical quantity related to a size of each of the plurality of small regions based on pixel data in at least one cross section orthogonal to the reference axis and corresponding to each of the plurality of small regions (Sato, FIG 9, P2, paragraphs [0036- 0063]:Sato teaches calculating blood vessel diameter and cross-sectional area at each orthogonal cross section along the core line as size-based physical quantities derived from pixel/contour point data: {Diameter, Cross-sectional area, Derived from orthogonal cross sections, Stenosis rate per position});
derive at least one second evaluation value representing a relationship between the first evaluation values in the plurality of small regions (Sato, FIGs 10, step S7, FIG 11A, step S11, paragraphs [0003-0005], [0051-0054]: Sato teaches deriving relationship values between size measurements at different positions along the axis: Regression line comparison and Stenosis rate as relationship});
derive a third evaluation value indicating presence or absence of an abnormality in the entire target organ based on the at least one second evaluation value; and display the target image and the evaluation result on a display (Sato, FIG 10, step S76a, FIG 15, P4, paragraphs [0051], [0070-0072]: Sato teaches determining stenosis presence/absence (abnormality) based on the computed stenosis rates and regression analysis.).
While Sato uses regression analysis and direct mathematical computation, Sato does not explicitly teach that the second evaluation value is derived by sequentially inputting, in an order along the reference axis, the first evaluation values corresponding to the plurality of small regions into a trained machine learning model.
In reference Nakada, Nakada teaches a blood vessel analysis system comprising a blood vessel state determination unit (103) that explicitly processes cross-sectional area values sequentially along the vessel axis to determine abnormality type ((Nakada, paragraphs [0074-0077], [0102 – 0109]).
Nakada teaches that ordered per-position cross-sectional size values along the vessel axis are sequentially processed to derive an evaluation of the vessel state (branching/stenosis/aneurysm/normal) based on spatial patterns in those ordered values. However, Nakada performs this sequential analysis using rule-based threshold logic, not a trained machine learning model.
In reference Siemionow, Siemionow teaches a computer-implemented system for automated vessel analysis comprising a pre-trained reasoning module implemented as a convolutional neural network (Siemionow, paragraphs [0012], [0017], [0031]; “The reasoning module may be a convolutional neural network”).
Siemionow teaches that a trained neural network can receive vessel dimensional parameters derived from 3D segmented vessel analysis and output a stenosis significance assessment, explicitly replacing traditional clinical evaluation with ML-based inference from dimensional data.
These arts are analogous since they are all related to imaging systems and methods performing medical imaging. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to modify the blood vessel stenosis analysis system of Sato, which generates per-position size measurements (diameter, cross-sectional area) from cross sections orthogonal to a vessel core line and derives relationship values through regression analysis, with the sequential ordered processing of Nakada, which explicitly processes cross-sectional area values in order along the vessel axis to determine abnormality type from spatial patterns and to further replace the rule-based determination method with a trained neural network as taught by Siemionow, which demonstrates that a pre-trained CNN reasoning module can receive vessel dimensional parameters and output a stenosis significance classification, because:
(1) All three references operate in the same technical field of vessel morphometric analysis from medical imaging data, and a person of ordinary skill would naturally look to advances in the same field for improvements. See KSR Int’l Co. v. Teleflex Inc., 550 U.S. 398, 417 (2007); MPEP § 2141.01(a).
(2) Sato already generates an ordered sequence of per-position size measurements along the vessel axis in the form of the minimum diameter curve, which is a plot of diameter values in order along the blood vessel core line. This ordered sequence constitutes the natural input data structure for sequential analysis.
(3) Nakada demonstrates that sequential processing of ordered cross-sectional size values along the vessel axis is an effective analytical framework for determining abnormality type (branching, stenosis, aneurysm) from spatial patterns in the ordered values. Combining Nakada’s explicit sequential processing with Sato’s per-position measurement framework provides a more comprehensive analytical approach. See KSR, 550 U.S. at 417 (combining known elements to yield predictable results).
(4) Siemionow explicitly teaches that a trained neural network can receive vessel dimensional parameters and output a stenosis significance classification, demonstrating that ML-based inference is a viable and effective replacement for traditional assessment methods in vessel analysis. A person of ordinary skill would have been motivated to apply Siemionow’s ML-based approach to the sequential vessel size data generated by Sato and processed by Nakada, because a trained ML model can learn more complex, non-linear spatial patterns from the ordered size data than hand-crafted threshold rules (Nakada) or linear regression (Sato), potentially improving diagnostic accuracy. See KSR, 550 U.S. at 417 (use of known technique to improve similar devices in the same way); MPEP § 2143(I)©.
(5) The combination yields predictable results: the trained ML model receives the same type of data (vessel size measurements derived from orthogonal cross sections) that Sato generates and Nakada processes and produces the same type of output (abnormality assessment) that all three references produce through their respective methods. The substitution of the analysis method (from rule-based to ML-based) does not change the underlying data structure or the analytical objective. See KSR, 550 U.S. at 416 (combination of familiar elements according to known methods to yield predictable results).
Regarding Claim 2, the combination of Sato, Nakada and Siemionow teaches the image processing apparatus according to claim 1 and wherein the at least one second evaluation value is an evaluation value related to a difference in sizes between small regions (Sato teaches that the first evaluation value is a size-based physical quantity (diameter and cross-sectional area, as discussed above for Claim 1) and derives relationships between per-position size values including ratios (stenosis rate = ratio of actual to normal diameter per Equation (1): “Stenosis rate = (blood vessel diameter of normal part − blood vessel diameter of stenosis part) / blood vessel diameter of normal part”) and differences (distance between corresponding contour points per Equation (4): “Stenosis = 100 × Si / Sr”).)
Regarding Claim 6, the combination of Sato, Nakada and Siemionow teaches the image processing apparatus according to claim 1 and wherein the evaluation result based on the third evaluation is an occurrence probability of a finding representing a feature of a shape of the target organ (Siemionow, Siemionow, paragraph 0126]: Siemionow teaches that the reasoning module outputs a reliability parameter in addition to the significance classification. The reliability parameter is a measure of confidence (probability) in the abnormality finding.).
Regarding Claim 7, the combination of Sato, Nakada and Siemionow teaches the image processing apparatus according to claim 6 and wherein the finding includes at least one of atrophy, swelling, stenosis, or dilation that occurs in the target organ (Sato, see claim 1: Sato teaches detection of stenosis (“calculating a local stenosis rate in the stenosis range using the temporary normal blood vessel and the blood vessel shape”). Nakada, FIG 9B and FIG 9C: Nakada teaches detection of both stenosis (area decrease ≥50%) and aneurysm/dilation (area increase ≥20% then return to baseline) from sequential cross-sectional analysis (“the vascular state determination unit 103 can determine that the vascular region area in the vascular structure cross-sectional view is reduced to a predetermined ratio or more (for example, 50% or more)”; FIG. 9B; “the area of the blood vessel region R932… is once increased”; FIG. 9C).)
Regarding Claim 8, the combination of Sato, Nakada and Siemionow teaches the image processing apparatus according to claim 1 and wherein the processor is configured to display a position of a small region having a relatively high contribution to evaluation result in the target organ on the display as distinguished from a position of the small region having a relatively low contribution (Sato teaches three-dimensional color display of local stenosis rates, where color at each position along the vessel is determined by the degree of stenosis. Regions with high stenosis (high contribution to abnormality finding) are displayed in a different color (red) than regions with low stenosis (low contribution), which are displayed in a different color (blue). This constitutes displaying positions with high contribution distinguishably from positions with low contribution.).
Claim 9 is rejected for the same reasons as Claims 6 and 8 combined.
Claim 10 is rejected for the same reasons as Claims 7 and 8 combined.
Regarding Claim 11, the combination of Sato, Nakada and Siemionow teaches the image processing apparatus according to claim 8 and wherein the processor is configured to display at least one of a first evaluation value or at least one second evaluation value of the small region having the relatively high contribution to the evaluation result in the target organ on the display (Sato teaches displaying per-position measurement values at positions of interest: “a number indicating the intercostal distance calculated in the intercostal space” is displayed at each position (by analogy from Sato’s display teachings).
Claims 12 and 13 are rejected for the same reasons as Claims 9–11 and 10–11 combined, respectively.
Claim 16 is rejected for the same reasons as Claim 1.
Claim 17 is rejected for the same reasons as Claim 1.
Claim 18 is rejected for the same reasons as claims 1 and 2.
Claims 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Sato (JP 2006-167287 A) in view of Nakada et al. (JP 2016-087139 A)
(hereinafter known as Nakada) and Siemionow et al. (US 2026/0154819 A1) (hereinafter known as Siemionow) and further in view of Shim
(US 2021/0219828 A1).
Regarding Claim 14, the combination of Sato, Nakada and Siemionow teaches the image processing apparatus according to claim 1 but does not explicitly teach wherein the medical image is a tomographic image of an abdomen, and the target organ is a pancreas.
In reference Shim, Shim teaches medical imaging of the pancreas, including dividing the pancreas into head, body, and tail portions for differentiated analysis (Shim, paragraph [0094]: “The medical images include images of the pancreas… the pancreas is divided into a head portion, a body portion, and a tail portion”).
These arts are analogous since they are all related to imaging systems and methods performing medical imaging. Therefore, it would have been obvious to a one of ordinary skill in the art to apply the axis-based, cross-sectional, ML-driven morphometric analysis framework of Sato, Nakada, and Siemionow to the pancreas as taught by Shim, because (1) the pancreas is an elongated organ amenable to axis-based cross-sectional analysis; (2) Shim demonstrates that per-region analysis of the pancreas (head/body/tail) is a known approach for pancreatic imaging; and (3) applying established morphometric analysis techniques to a different target organ is a predictable application of known methods.
Regarding Claim 15, the combination of Sato, Nakada, Siemionow and Shim teaches the image processing apparatus according to claim 14 and wherein the processor is configured to set the small region by dividing the pancreas into a head portion, a body portion, and a caudal portion (Shim, paragraph [0094]: Shim teaches dividing the pancreas into head, body, and tail (caudal) portions (“the pancreas is divided into a head portion, a body portion, and a tail portion”).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SUPERVISORY PATENT EXAMINER TWYLER HASKINS whose telephone number is (571)272-7406. The SUPERVISORY PATENT EXAMINER TWYLER HASKINS can normally be reached Mon- Thursday: 7:30 am-4:30 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http:/Awwww.uspto.gov/interviewpractice.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https:/Awww.uspto.gov/patents/apply/patent-center for more information about Patent Center and https:/Awww.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/TWYLER L HASKINS/ Supervisory Patent Examiner, Art Unit 2639
Prosecution Insights