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 that application claims priority to foreign application with application number EP 22305928.8 dated 06/27/2022.
Copies of certified papers required by 37 CFR 1.55 have been received. Priority is acknowledged under 35 USC 119(e) and 37 CFR 1.78.
Information Disclosure Statement
The IDS(s) dated 12/24/2024 has/have been considered and placed in the application file.
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.
The USPTO recognizes that applicants may have claims directed to computer readable media that cover signals per se, which the USPTO must reject under 35 U.S.C. § 101 as covering both non-statutory subject matter and statutory subject matter. In an effort to assist the patent community in overcoming a rejection or potential rejection under 35 U.S.C. § 101 in this situation, the USPTO suggests the following approach.
A claim drawn to such a computer readable medium that covers both transitory and non-transitory embodiments may be amended to narrow the claim to cover only statutory embodiments to avoid a rejection under 35 U.S.C. § 101 by adding the limitation "non-transitory" to the claim. Cf. Animals - Patentability, 1077 Off. Gaz. Pat. Office 24 (April 21, 1987) (suggesting that applicants add the limitation "non-human" to a claim covering a multi-cellular organism to avoid a rejection under 35 U.S.C. § 101). Such an amendment would typically not raise the issue of new matter, even when the specification is silent because the broadest reasonable interpretation relies on the ordinary and customary meaning that includes signals per se. The limited situations in which such an amendment could raise issues of new matter occur, for example, when the specification does not support a non-transitory embodiment because a signal per se is the only viable embodiment such that the amended claim is impermissibly broadened beyond the supporting disclosure. See, e.g., Gentry Gallery, Inc. v. Berkline Corp., 134 F.3d 1473(Fed. Cir. 1998).
Claim(s) 14-15 is rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter as follows:
Claim(s) 14-15 define a “computer program product” embodying functional descriptive material. However, the claim does not define a non-transitory computer-readable medium or memory and is thus non-statutory for that reason (i.e., “examination the pending claims must be interpreted as broadly as their terms reasonably allow). The broadest reasonable interpretation of a claim drawn to a computer readable medium (also called machine readable medium and other such variations) typically covers forms of non-transitory tangible media and transitory propagating signals per se in view of the ordinary and customary meaning of computer readable media, particularly when the specification is silent. See MPEP 2111.01.
Any amendment to the claim should be commensurate with its corresponding disclosure.
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.
Claim(s) 1, 4, and 9-15 is/are rejected under 35 U.S.C. 103 as obvious over Pack et al (US 20200160509 A1, hereafter referred to as Pack) and Autrusseau et al (US 2022067928 A1, hereafter referred to as Autrusseau), further in view of Tetteh et al (Tetteh, G., Efremov, V., Forkert, N. D., Schneider, M., Kirschke, J., Weber, B., ... & Menze, B. H. (2020). Deepvesselnet: Vessel segmentation, centerline prediction, and bifurcation detection in 3-d angiographic volumes. Frontiers in Neuroscience, 14, 592352, hereafter referred to as Tetteh).
Claim 1
Regarding Claim 1, Pack teaches “A method for recognizing at least one bifurcation of a vascular tree in a real image of a vascular tree of a subject, notably a cerebral one, the method being computer-implemented, the method comprising:
a phase of generating synthetic images of at least one bifurcation of a vascular tree (Pack in ¶¶63-65, Fig. 5 discloses generating each synthetic volume from a source image derived geometric model with specified simulation parameters), the phase of generating comprising, for each synthetic image, the steps of:
receiving a real image comprising at least one bifurcation of a vascular tree (Pack in ¶64, Fig. 5 discloses receiving CTA volumes whose lumen geometry is segmented),
modeling the real image by an imaging model with a specific set of values for a set of parameters (Pack in ¶¶61, 63-65 discloses modeling observed vessel geometry with specified geometry, material, contrast, noise and scan parameters), the imaging model comprising at least a geometrical model of the bifurcation (Pack in ¶64 discloses a segmented 3D geometric representation of the imaged lumen),
the geometrical model being a tridimensional model of the bifurcation (Pack in ¶64 discloses a segmented 3D geometric representation of the imaged lumen) (Pack in ¶64, Fig. 5 discloses segmenting clinical CTA images to obtain the lumen geometry),
generating the image corresponding to the imaging model with a modified set of values, the generated image being the synthetic image (Pack in ¶¶64-65 discloses rendering synthetic images from the source derived geometry and modifying model parameters by scaling, rotation, warping, contrast variation or noise variation),
a phase of training a recognition predictor adapted to obtain bifurcation recognition data in an input image, to obtain a trained recognition predictor (Pack in ¶¶63-66 discloses synthetic image training datasets and neural network training), the phase of training comprising the steps of:
forming a training dataset based on the synthetic images (Pack in ¶¶63-66 discloses synthetic image training datasets and neural network training), and
training the recognition predictor by using the training dataset (Pack in ¶¶63-66 discloses synthetic image training datasets and neural network training), and a phase of inferring (Pack in ¶¶48-53 discloses using trained vascular image analysis on received patient data), the phase of inferring comprising the steps of:
receiving a real image to be analyzed, the real image to be analyzed being an image of the vascular tree of the subject (Pack in ¶¶48-53 discloses using trained vascular image analysis on received patient data).”
Pack does not explicitly teach all of “receiving a real image comprising at least one bifurcation of a vascular tree … the geometrical model being a tridimensional model of the bifurcation and including a graph of the vascular tree, the graph being a set of nodes linked by branches with a weight … a phase of training a recognition predictor adapted to obtain bifurcation recognition data in an input image, to obtain a trained recognition predictor … applying the trained recognition predictor on the image to be analyzed to obtain bifurcation recognition data.”
However, Autrusseau teaches “receiving a real image comprising at least one bifurcation of a vascular tree (Autrusseau in ¶160 discloses processing acquired 3D cerebral vascular images containing bifurcations), …
the geometrical model being a tridimensional model of the bifurcation and including a graph of the vascular tree (Autrusseau in ¶12 discloses representing the imaged bifurcation by a skeleton derived vascular graph with 3D node coordinates), the graph being a set of nodes linked by branches with a weight (Autrusseau in ¶¶ 232-235 discloses assigning numerical weights to edges connecting vascular graph nodes)”.
Autrusseau is analogous art because Autrusseau, like Pack, is in the field of computer vascular image analysis and is reasonably pertinent to the problem of accurately locating vascular bifurcations.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the segmented geometrical model of Pack with the weighted vascular graph of Autrusseau because Autrusseau teaches that weighted edge filtering provides improved bifurcation detection by removing small weight edges associated with artifacts or vessels without bifurcations (¶¶232-235), and one of ordinary skill would have recognized that incorporating this feature into the method of Pack would identify bifurcation locations within the source derived model, with a reasonable expectation of success because Autrusseau’s skeletonization operates on segmented vascular volumes while Pack’s lumen geometry remains available.
Pack and Autrusseau do not explicitly teach all of “a phase of training a recognition predictor adapted to obtain bifurcation recognition data in an input image, to obtain a trained recognition predictor … applying the trained recognition predictor on the image to be analyzed to obtain bifurcation recognition data.”
However, Tetteh teaches “a phase of training a recognition predictor adapted to obtain bifurcation recognition data in an input image, to obtain a trained recognition predictor (Tetteh in §§3.1.1, 3.2.3 discloses training a bifurcation detection network using synthetic volumes with corresponding bifurcation labels), …
applying the trained recognition predictor on the image to be analyzed to obtain bifurcation recognition data (Tetteh in §§3.2, 3.4.3, Fig. 10 discloses a bifurcation detection stage that consumes segmentation and centerline channels produced from the image).”
Tetteh is analogous art because Tetteh, like Pack and Autrusseau, is in the field of computerized vascular image analysis and is reasonably pertinent to the problem of training bifurcation recognition with limited annotated real images.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the training and inference processing of Pack and Autrusseau with the bifurcation labeled training and detection processing of Tetteh because Tetteh teaches that synthetic bifurcation labeled data provides training examples without extensive manual annotation (§3.1.1), and one of ordinary skill would have recognized that incorporating this feature into the method of Pack and Autrusseau would train and apply a predictor to locate bifurcations in received images, with a reasonable expectation of success because the retained geometry and graph provides corresponding training targets, and Tetteh supplies the segmentation and centerline channels required for bifurcation detection.
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Claim 4
Regarding Claim 4, Pack and Autrusseau, further in view of Tetteh teaches The method for recognizing according to claim 1, wherein, during the step of generating, a geometrical distortion is applied to the geometrical model (Pack in ¶65 discloses warping source derived geometric models before synthetic image generation to enrich the training dataset).
Claim 9
Regarding Claim 9, Pack and Autrusseau, further in view of Tetteh teaches The method for recognizing according to claim 1,wherein each image is taken by a MRA-TOF technique (Tetteh in §§3.1.2, 3.4.3 discloses clinical TOF MRA brain volumes and bifurcation recognition in those volumes).
Claim 10
Regarding Claim 10, Pack and Autrusseau, further in view of Tetteh teaches The method for recognizing according to claim 1, wherein the bifurcation recognition data are chosen among the following elements: the class or the type of bifurcation, the presence of the bifurcation, the location of the bifurcation, the bifurcation angle of the bifurcation, the geodesic distance between two bifurcations, the cross-section area of the detected bifurcation, and the tortuosity parameter of the bifurcation (Tetteh in §3.4.3, Fig. 10 discloses bifurcation presence and location).
Claim 11
Regarding Claim 11, Pack and Autrusseau, further in view of Tetteh teaches The method for recognizing according to claim 1, wherein the recognition predictor is a neural network (Tetteh in §§3.2.1-3.2.3 discloses neural network stages for vessel segmentation, centerline prediction, and bifurcation detection).
Claim 12
Regarding Claim 12, Pack and Autrusseau, further in view of Tetteh teaches The method for recognizing according to claim 11, wherein the neural network is a convolutional neural network (Tetteh in §§3.2.1-3.2.3 discloses convolutional implementations of the stages connected).
Claim 13
Regarding Claim 13, Pack and Autrusseau, further in view of Tetteh teaches A method comprising carrying out the steps of a method for recognizing at least one bifurcation of a vascular tree in a real image of a vascular tree of a subject, the method being according to claim 1, the method being chosen in the list consisting of
a method for predicting that a subject is at risk of developing an aneurysm, the method for predicting at least comprising the step of: (Autrusseau in ¶21 discloses predicting whether a subject is at risk of developing an aneurysm from determined bifurcation parameters)
carrying out the steps of the method for recognizing, to obtain bifurcation recognition data (Tetteh in §1.1.3 discloses obtaining bifurcation detections from the subject’s vascular image),
predicting that the subject is at risk of developing the aneurysm based on the obtained bifurcation recognition data (Autrusseau in ¶21 discloses predicting aneurysm risk from the subject’s determined bifurcation geometry),
a method for diagnosing an aneurysm, the method for diagnosing at least comprising the step of:
carrying out the steps of the method for recognizing, to obtain bifurcation recognition data, and diagnosing the aneurysm based on the obtained bifurcation recognition data (Autrusseau in ¶21 discloses diagnosis based on determined bifurcation parameters),
a method for identifying a therapeutic target for preventing and/or treating an aneurysm, the method comprising at least the step of:
carrying out the steps of the method for recognizing to a first subject, to obtain first obtained bifurcation recognition data, the first subject being a subject suffering from the aneurysm, carrying out the steps of the method for recognizing to a second subject, to obtain obtained bifurcation recognition data, the second subject being a subject not suffering from the aneurysm, and selecting a therapeutic target based on the comparison of the first and second obtained bifurcation recognition data (Autrusseau in ¶¶21-24 discloses comparing diseased and nondiseased subjects bifurcation parameters to select a therapeutic target),
a method for identifying a biomarker, the biomarker being a diagnostic biomarker of an aneurysm, a susceptibility biomarker of an aneurysm, a prognostic biomarker of an aneurysm or a predictive biomarker in response to the treatment of an aneurysm, the method comprising at least the step of:
carrying out the steps of the method for recognizing to a first subject, to obtain first obtained bifurcation recognition data, the first subject being a subject suffering from the aneurysm, carrying out the steps of the method for recognizing to a second subject, to obtain second obtained bifurcation recognition data, the second subject being a subject not suffering from the aneurysm, and selecting a biomarker based on the comparison of the first and second determined parameters (Autrusseau in ¶¶21-24 discloses the listed biomarker categories and comparison of diseased and nondiseased subjects parameters), and
a method for screening a compound useful as a probiotic, a prebiotic or a medicine, the compound having an effect on a known therapeutical target, for preventing and/or treating an aneurysm, the method comprising at least the step of:
carrying out the steps of the method for recognizing to a first subject, to obtain first obtained bifurcation recognition data, the first subject being a subject suffering from the aneurysm and having received the compound, carrying out the steps of the method for recognizing to a second subject, to obtain second obtained bifurcation recognition data, the second subject being a subject suffering from the aneurysm and not having received the compound, and selecting a compound based on the comparison of the first and second determined parameters (Autrusseau in ¶25 discloses comparing treated and untreated subjects parameters to screen a compound, including a medicine).
Claim 14
Regarding Claim 14, Pack and Autrusseau, further in view of Tetteh teaches A computer program product comprising instructions for carrying out the steps of a method according to claim 1 when said computer program product is executed on a suitable computer device (Autrusseau in ¶27 discloses computer readable storage medium containing executable program instructions).
Claim 15
Regarding Claim 15, Pack and Autrusseau, further in view of Tetteh teaches A computer readable medium having encoded thereon a computer program according to claim 14 (Autrusseau in ¶27 discloses computer readable storage medium containing executable program instructions).
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as obvious over Pack et al (US 20200160509 A1, hereafter referred to as Pack), Autrusseau et al (US 2022067928 A1, hereafter referred to as Autrusseau), and Tetteh et al (Tetteh, G., Efremov, V., Forkert, N. D., Schneider, M., Kirschke, J., Weber, B., ... & Menze, B. H. (2020). Deepvesselnet: Vessel segmentation, centerline prediction, and bifurcation detection in 3-d angiographic volumes. Frontiers in Neuroscience, 14, 592352, hereafter referred to as Tetteh), and Ge et al (CN111967393B, hereafter referred to as Ge), further in view of Autrusseau et al (Autrusseau, F., Nader, R., Nouri, A., L’Allinec, V., & Bourcier, R. (2022, August). Toward a 3d arterial tree bifurcation model for intra-cranial aneurysm detection and segmentation. In 2022 26th International Conference on Pattern Recognition (ICPR) (pp. 4500-4506). IEEE, hereafter referred to as Nader).
Claim 2
Regarding Claim 2, Pack and Autrusseau, further in view of Tetteh teaches The method for recognizing according to claim 1, wherein:
the imaging model comprises a noise model, the noise model modelling the noise of the image by a Gaussian noise with a standard deviation, the standard deviation of the Gaussian noise being one of the parameters of the model, the standard deviation being equal to a first value (Tetteh in §3.1.1 discloses a synthetic vascular image noise model with Gaussian noise and selectable mean and standard deviation),
Pack and Autrusseau, further in view of Tetteh does not explicitly teach all of during the step of generating, a Gaussian filter with a standard deviation is applied on the real image to obtain an image with a Gaussian noise with a standard deviation having a second value, the second value being different from the first value, the standard deviation of the Gaussian filter depending from the first value and the second value.
However, Ge teaches during the step of generating, a Gaussian filter with a standard deviation is applied on the real image to obtain an image with a Gaussian noise with a standard deviation having a second value (Ge in ¶¶n0050-0051, n0063 discloses extracting and annotating captured video images, applying Gaussian filter denoising to original images to form new training images, and including the new images in the training set).
Ge is analogous art because Ge, like Pack and Autrusseau, further in view of Tetteh, is in the field of computerized image analysis and object localization and is reasonably pertinent to the problem of generating labeled training variants from acquired images with differing noise conditions.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the source image training variant generation of Pack and Autrusseau, further in view of Tetteh with the Gaussian filter augmentation of captured originals of Ge because Ge teaches that this augmentation provides additional training images and improved image quality for detection (¶¶n0050-0051, n0063), and one of ordinary skill would have recognized that incorporating this feature into the method of Pack and Autrusseau, further in view of Tetteh would generate filtered real source variants while retaining the segmented anatomical model, with a reasonable expectation of success because the operation uses the existing sampled source image array without a coordinate warp and changes image appearance rather than the underlying labeled anatomy.
Pack and Autrusseau, and Tetteh, further in view of Ge does not explicitly teach all of the second value being different from the first value, the standard deviation of the Gaussian filter depending from the first value and the second value.
However, Nader teaches the second value being different from the first value (Nader in §II.B, Eqs. (2)-(8) discloses the input/output noise variance relationship under Gaussian filtering), the standard deviation of the Gaussian filter depending from the first value and the second value (Nader in §II.B, Eqs. (2)-(8) discloses selecting Gaussian filter width from initial and desired output noise deviations).
Nader is analogous art because Nader, like Pack and Autrusseau, and Tetteh, further in view of Ge, is in the field of computational image modeling for recognition and is reasonably pertinent to the problem of controlling the noise statistics of generated vascular training images.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the Gaussian filter training variant generation of Pack and Autrusseau, and Tetteh, further in view of Ge with the input/target noise calibration of Nader because Nader teaches that this calibration provides filtered images selected target noise statistics (§II.B, Eqs. (2)-(8)), and one of ordinary skill would have recognized that incorporating this feature into the method of Pack and Autrusseau, and Tetteh, further in view of Ge would select the real image filter width from its modeled initial noise deviation and a different, lower target deviation, with a reasonable expectation of success because the disclosed weighted variance relation applies to the additive independent Gaussian noise component under the same linear convolution, while the source derived anatomy and graph supply the retained labels.
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as obvious over Pack et al (US 20200160509 A1, hereafter referred to as Pack), Autrusseau et al (US 2022067928 A1, hereafter referred to as Autrusseau), and Tetteh et al (Tetteh, G., Efremov, V., Forkert, N. D., Schneider, M., Kirschke, J., Weber, B., ... & Menze, B. H. (2020). Deepvesselnet: Vessel segmentation, centerline prediction, and bifurcation detection in 3-d angiographic volumes. Frontiers in Neuroscience, 14, 592352, hereafter referred to as Tetteh), further in view of Li et al (Li, X., & Wee, W. G. (2014). Retinal Vessel Detection and Measurement for Computer-aided Medical Diagnosis: Retinal Vessel Detection and Measurement. Journal of digital imaging, 27(1), 120-132, hereafter referred to as Li).
Claim 3
Regarding Claim 3, Pack and Autrusseau, further in view of Tetteh teaches “The method for recognizing according to claim 1”.
Pack and Autrusseau, further in view of Tetteh does not explicitly teach all of “wherein the parameters of geometrical model further include the diameters of the bifurcation, the values of the diameters being obtained by applying a convolution kernel on the real image.”
However, Li teaches “wherein the parameters of geometrical model further include the diameters of the bifurcation, the values of the diameters being obtained by applying a convolution kernel on the real image (Li in “LoG and Canny Filters”, “Vessel Diameter Measurement”, Eqs. (1)-(4) discloses convolution based edge detection on real grayscale vessel images and measuring diameter between the resulting vessel boundaries).”
Li is analogous art because Li, like Pack, Autrusseau, and Tetteh, is in the field of computerized vascular image analysis and is reasonably pertinent to the problem of obtaining vessel diameters from noisy image boundaries.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the source image contour and diameter extraction of Pack, Autrusseau, and Tetteh with the convolution based vessel edge detection of Li because Li teaches that convolution based vessel edge detection provides filtered boundaries usable for diameter measurement (“LoG and Canny Filters”, “Vessel Diameter Measurement”, “D-S-based Fusion for Edge Detection”), and one of ordinary skill would have recognized that incorporating this feature into the method of Pack, Autrusseau, and Tetteh would populate the source model with diameters measured from convolution derived contours, with a reasonable expectation of success because Autrusseau already extracts aligned 2D slices of the actual vascular volume for contour/width analysis, so the detector supplies that existing interface without importing Li’s retinal photometric refinement.
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Claim(s) 5-6 is/are rejected under 35 U.S.C. 103 as obvious over Pack et al (US 20200160509 A1, hereafter referred to as Pack), Autrusseau et al (US 2022067928 A1, hereafter referred to as Autrusseau), and Tetteh et al (Tetteh, G., Efremov, V., Forkert, N. D., Schneider, M., Kirschke, J., Weber, B., ... & Menze, B. H. (2020). Deepvesselnet: Vessel segmentation, centerline prediction, and bifurcation detection in 3-d angiographic volumes. Frontiers in Neuroscience, 14, 592352, hereafter referred to as Tetteh), further in view of Goel et al (US 20190279367 A1, hereafter referred to as Goel).
Claim 5
Regarding Claim 5, Pack and Autrusseau, further in view of Tetteh teaches “The method for recognizing according to claim 1, … the coefficients being parameters of the set of parameters (Pack in ¶¶64-65 discloses parameterized geometric representations, including splines), the coefficients being modified during the step of generating (Pack in ¶65 discloses scaling source derived geometry during generation).”.
Pack and Autrusseau, further in view of Tetteh does not explicitly teach all of “wherein the geometrical model defines reference points for the bifurcation, the geometrical model comprising interpolating functions linking the reference points, each interpolating function being a function defined by coefficients”.
However, Goel teaches “wherein the geometrical model defines reference points for the bifurcation (Goel in ¶61 discloses image derived centerline samples and periodically recorded centers of mass for each vascular branch), the geometrical model comprising interpolating functions linking the reference points (Goel in ¶¶62-63 discloses fitting the samples branch points with uniform cubic B-splines and stitching child and parent centerlines into a continuous structure), each interpolating function being a function defined by coefficients (Goel in ¶62 discloses B-spline centerline representation”.
Goel is analogous art because Goel, like Pack, Autrusseau, and Tetteh, is in the field of computerized vascular image modeling and is reasonably pertinent to the problem of retaining continuous, analytically defined branching geometry from image derived samples.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the source derived geometrical representation of Pack, Autrusseau, and Tetteh with the fitted branch aware B-spline centerline model of Goel because Goel teaches that the fitted branch aware B-spline centerline model provides a continuous centerline supporting a lumen surface convertible into image data (¶¶62-63), and one of ordinary skill would have recognized that incorporating this feature into the method of Pack, Autrusseau, and Tetteh would implement Pack’s training data scaling by modifying the same curves control coordinate coefficients before rendering, with a reasonable expectation of success because the fixed B-spline basis is linear in those coefficients and coordinated scaling preserves branch joins and image/label correspondence.
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Claim 6
Regarding Claim 6, Pack, Autrusseau, and Tetteh, further in view of Goel teaches The method for recognizing according to claim 5, wherein each interpolating function is a B-spline function defined by B-spline's coefficients and the coefficients are the B-spline's coefficients (Goel in ¶62 discloses uniform B-spline centerline functions).
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as obvious over Pack et al (US 20200160509 A1, hereafter referred to as Pack), Autrusseau et al (US 2022067928 A1, hereafter referred to as Autrusseau), Tetteh et al (Tetteh, G., Efremov, V., Forkert, N. D., Schneider, M., Kirschke, J., Weber, B., ... & Menze, B. H. (2020). Deepvesselnet: Vessel segmentation, centerline prediction, and bifurcation detection in 3-d angiographic volumes. Frontiers in Neuroscience, 14, 592352, hereafter referred to as Tetteh), and Goel et al (US 20190279367 A1, hereafter referred to as Goel), further in view of Tremblay et al (US 20190251397 A1, hereafter referred to as Tremblay).
Claim 7
Regarding Claim 7, Pack, Autrusseau, and Tetteh, further in view of Goel teaches The method for recognizing according to claim 5.
Pack, Autrusseau, and Tetteh, further in view of Goel does not explicitly teach all of wherein the values of the coefficients are modified by adding a random value multiplied by a weight to the specific value.
However, Tremblay teaches wherein the values of the coefficients are modified by adding a random value multiplied by a weight to the specific value (Tremblay in ¶¶32, 50, 53-54 discloses random object scale selection and synthetic training variation).
Tremblay is analogous art because Tremblay, like Pack, Autrusseau, and Tetteh, further in view of Goel, is in the field of synthetic image generation for neural-network recognition and is reasonably pertinent to the problem of diversifying training examples while retaining relevant object structure.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the coefficient level model scaling of Pack, Autrusseau, and Tetteh, further in view of Goel with randomized object scale selection of Tremblay because Tremblay teaches that randomized object scale selection provides training variation that directs recognition toward relevant structure rather than incidental image details (¶¶32, 50. 53-54), and one of ordinary skill would have recognized that incorporating this feature into the method of Pack, Autrusseau, and Tetteh, further in view of Goel would produce randomized model scales by adding a weighted random value to each branch curve coefficient before rendering, with a reasonable expectation of success because Pack already scaled geometry and the fixed spline representation allows a common positive random scale while preserving branch joins and registered labels.
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as obvious over Pack et al (US 20200160509 A1, hereafter referred to as Pack), Autrusseau et al (US 2022067928 A1, hereafter referred to as Autrusseau), and Tetteh et al (Tetteh, G., Efremov, V., Forkert, N. D., Schneider, M., Kirschke, J., Weber, B., ... & Menze, B. H. (2020). Deepvesselnet: Vessel segmentation, centerline prediction, and bifurcation detection in 3-d angiographic volumes. Frontiers in Neuroscience, 14, 592352, hereafter referred to as Tetteh), further in view of Autrusseau et al (Autrusseau, F., Nader, R., Nouri, A., L’Allinec, V., & Bourcier, R. (2022, August). Toward a 3d arterial tree bifurcation model for intra-cranial aneurysm detection and segmentation. In 2022 26th International Conference on Pattern Recognition (ICPR) (pp. 4500-4506). IEEE, hereafter referred to as Nader).
Claim 8
Regarding Claim 8, Pack and Autrusseau, further in view of Tetteh teaches The method for recognizing according to claim 1, wherein the imaging model includes a background model (Pack in ¶63 discloses including surrounding structures and variable background material in the synthetic image model),
Pack and Autrusseau, further in view of Tetteh does not explicitly teach all of the background model comprising a shape with two distinct values.
However, Nader teaches the background model comprising a shape with two distinct values (Nader in p. 4, §II.A.3 discloses an artery derived mask arranging dark fluid surrounding regions separately from brighter brain material).
Nader is analogous art because Nader, like Pack and Autrusseau, further in view of Tetteh, is in the field of synthetic vascular image modeling and is reasonably pertinent to the problem of representing the different materials surrounding cerebral bifurcations.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the background component of Pack and Autrusseau, further in view of Tetteh with the mask based representation of dark and bright background regions of Nader because Nader teaches that the masked based representation of dark and bright background regions provides a model of the differing appearances surrounding cerebral arteries (p. 4, §§II.A.3, III.A-B), and one of ordinary skill would have recognized that incorporating this feature into the method of Pack and Autrusseau, further in view of Tetteh would assign the corresponding background characteristics using a two valued region shape before rendering, with a reasonable expectation of success because Pack already models background material and the segmented cerebral artery supplies the mask geometry without changing the graph or recognition label interfaces.
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JUSTIN P CASCAIS whose telephone number is (703) 756-5576. The examiner can normally be reached Monday-Friday 8:00-4:00.
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, Mr. O'Neal Mistry can be reached on (313) 446-4912. 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.
/J.P.C./Examiner, Art Unit 2674
/ONEAL R MISTRY/Supervisory Patent Examiner, Art Unit 2674
Date: 9/24/2026
