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 .
Specification
The disclosure is objected to because of the following informalities:
SBRT, DIR, NSCLC, GTV, and OAR should be defined before abbreviation.
In paragraph [0021] line 2, “In some aspects, the techniques described herein relate to a method, further including determining a dose distribution for one or more of a plurality of phases includes” is incomplete and grammatically incorrect.
In paragraph [0117] line 4, “In addition, Fig. 11 demonstrates the algorithm's was sensitivity to variations in k, underscoring the robustness and adaptability of the method for diverse clinical scenarios” appears as if it should recite “In addition, Fig. 11 demonstrates the algorithm's sensitivity to variations in k, underscoring the robustness and adaptability of the method for diverse clinical scenarios.”
Appropriate correction is required.
Claim Objections
Claims 1, 2, 5, 11, 12, 13, 15, 16, and 17 are objected to because of the following informalities:
Claim 10 appears as if it should depend on claim 9 instead of claim 1.
In Claim 11 line 2, there should be an “or” before optical imaging.
In Claim 12 line 1, “deformation” should be “deformed.”
In Claim 13 line 7, there is an extra space between “wherein” and “at.”
In Claim 15 line 4, “Initializing” should be lowercase.
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. In particular, see Claim 13 which recites “a user device comprising a means for input and output.” 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.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
The following is a quotation of pre-AIA 35 U.S.C. 112, fourth paragraph:
Subject to the following paragraph [i.e., the fifth paragraph of pre-AIA 35 U.S.C. 112], a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claim 10 is rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends. Claim 10 depends from claim 9. Claim 9 recites determining a dose distribution for one or more phases and applying dose parameters to a deformed distribution. Claim 10 then recites the limitation of “determining a dose distribution for one or more of a plurality of phases comprises.” However, claim 10 does not further narrow the subject matter of claim 9 and instead merely repeats the subject matter already recited in claim 9. Applicant may cancel the claim, amend the claim to place the claim in proper dependent form, rewrite the claim in independent form, or present a sufficient showing that the dependent claim complies with the statutory requirements.
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. Claim 1 recites steps that constitute mental processes, i.e., acts that can performed in the human mind or using pen and paper. The claim recites receiving medical images, delineating or classifying regions of interest, determining how contours shift across phases, and outputting the updated contours. These steps describe analyzing and interpreting image information, identifying features, determining positional changes, and reporting the results, all of which are abstract mental processes. This judicial exception is not integrated into a practical application because the only additional elements are limiting the data to medical images, describing tumors/ROIs/physiological phases, receiving and outputting the data, and reciting generic processors, memory, and storage. These elements do not meaningfully limit the abstract idea because field of use (medical imaging) is insufficient, receiving and outputting information are insignificant extra-solution activities, and generic computer implementation is conventional and does not provide a technological improvement. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the specification describes the computing environment as generic and conventional, performing ordinary data-processing functions. Additionally, the combination of steps, which includes receiving images, analyzing them mentally (albeit via computer), and outputting contours, is a routine sequence of data-processing actions that does not add an inventive concept. Accordingly, claim 13 is rejected for containing identical subject matter to Claim 1. Furthermore, claims 2-12 and 14-20 depend from claims 1 and 13, respectively, and are rejected for the same reasons set forth for claims 1 and 13.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-3, 5-15, and 17-20 are rejected under 35 U.S.C. 103 as being unpatentable over Qin et. al (“The evaluation of a hybrid biomechanical deformable registration method on a multistage physical phantom with reproducible deformation”) in view of Hébert et. al (U.S. 20,220,398,717).
Regarding Claim 1, Qin teaches a method for deformable image registration (Fig. 1 (shown below)), the method comprising:
PNG
media_image1.png
856
1297
media_image1.png
Greyscale
receiving at least one set of medical images for a patient, wherein at least one medical image comprises pre-drawn contours (Qin: Methods and Materials);
Multi-modality tissue-equivalent phantom: “The contours of the prostate phantom and urethra structure were delineated on MR phase 0.”
Explanation: Qin teaches receiving medical images (MR), each with manually drawn contours that generates the volume mesh.
determining deformed contours for the one or more regions of interest (e.g., tumor) in the at least one set of medical images using a finite element analysis algorithm over one or more of a plurality of phases of a physiological cycle (e.g., phases of breath cycle) (Qin: Abstract and Methods and Materials);
Methods: “The BM-DIR method was quantitatively evaluated on a novel phantom capable of ten reproducible gradually-increasing deformation stages using the urethra tube as a surrogate.”
Mesh Generation: “A multi-organ tetrahedral mesh is generated using TetGen.”
Boundary Conditions: “Based on that assumption, the surface node displacement is linearly interpolated from IM-DIR DVF and utilized as the boundary condition for the FEM deformation.”
BM-DIR refinement: “A finite element solver package (ABAQUS, v6.14, Pawtucket, RI) was used to calculate the displacement of internal nodes.”
Quantitative evaluation of BM-DIR on the multistage phantom: “The IM-DIR and BM-DIR were performed between Phase 0 as reference and Phase i (i = 1 to 10) for CT, MR and masked MR with prostate contour as constrain, generating six types of DVFs for each phase.”
Quantitative evaluation of BM-DIR on the multistage phantom: “The urethra tube was deformed from phase i to phase 0 via different DVFs.”
Explanation: Qin teaches FEM mesh creation, FEM solver execution, applying boundary conditions, and producing deformed contours using a deformable vector field (DVF). Qin uses a 10-phase physiologic deformation phantom, where he teaches a plurality (10) of physiologic deformation states, each with its own medical image and each requiring FEM computation.
and outputting the deformed contours relative to the one or more regions of interest (Qin: Methods and Materials and Figure 3 (shown below));
Quantitative evaluation of BM-DIR on the multistage phantom: “The DSC, Hausdorff and mean surface distance as defined in [44] were calculated between the propagated and human-delineated urethra tube to evaluate the accuracy of internal DVF.”
PNG
media_image2.png
1015
1185
media_image2.png
Greyscale
Qin fails to teach the limitation of “delineating (e.g., clustering) one or more regions of interest in the at least one set of medical images using a trained clustering machine learning algorithm.”
However, Hébert teaches a “deep learning model (or a machine learning model), such as a deep convolutional neural network (DCNN), autoencoder neural network, or variational autoencoder neural network,” that “can be trained and used to generate, from one or more training data (e.g., medical images), a plurality of feature vectors that include the low-dimensional feature space representation. The plurality of feature vectors is then split or clustered into different groups each corresponding to a different motion phase of periodic (physiological) motion of a target region in a patient” (paragraph [0092]). Hébert explains that conventional image registration “is a very time-consuming operation that consumes a great amount of resources” and that these “typical approaches are limited in their applications and do not allow for performing a fast image classification, such as in real time during a radiotherapy treatment fraction” (paragraph [0036]). It further states that “the disclosed embodiments address these challenges providing an image classification technique that replaces the current classification algorithm with a clustering approach in a lower-dimensional (low-dimensional) feature space, such as k-means clustering,” and emphasizes that this approach “provides results faster which increases the overall applicability and use of the disclosed image classification techniques” (paragraph [0037]).
Thus, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to combine Hébert’s ML-based clustering delineation with Qin’s FEM-based contour deformation method because both references address the same underlying task of obtaining anatomical structure contours for deformation and registration. Qin relies on manually drawn contours, which introduce labor, variability, and delay, whereas Hébert teaches an automatic, reproducible, clustering-based delineation techniques that reduces time and computational burden while producing comparable anatomical classification results. Substituting automated ML delineation for manual segmentation constitutes a predictable improvement because better and more efficient contour delineation directly improves downstream FEM accuracy, reduces operator dependence, and is explicitly taught as a superior alternative to registration-based delineation.
Regarding Claim 2, Qin in view of Hébert teaches the method of claim 1, and Hébert further teaches that delineating (e.g. clustering) one or more regions of interest in the at least one set of medical images using a trained clustering machine learning algorithm comprises:
initializing cluster parameters (Hébert: Fig. 7);
PNG
media_image3.png
452
553
media_image3.png
Greyscale
training a cluster machine learning algorithm using the at least one medical image comprising pre-drawn contours (Hébert: Detailed Description);
Paragraph [0092]: “FIG. 7 illustrates an example flow diagram for deep learning, where a deep learning model (or a machine learning model), such as a deep convolutional neural network (DCNN), autoencoder neural network, or variational autoencoder neural network, can be trained and used to generate, from one or more training data (e.g., medical images), a plurality of feature vectors that include the low-dimensional feature space representation.
Paragraph [0047]: “Further, the medical images 146 may also include medical image data, for instance, training images, ground truth images, contoured images, and dose images.”
delineating a plurality of contours of the one or more regions of interest (e.g., clustering) (Hébert: Detailed Description);
Paragraph [0092]: “The plurality of feature vectors is then split or clustered into different groups each corresponding to a different motion phase of periodic (physiological) motion of a target region in a patient.”
and clustering voxels of a medical scan image of the second set within the one or more regions of interest (Hébert: Detailed Description);
Paragraph [0037]: “The disclosed embodiments address these challenges providing an image classification technique that replaces the current classification algorithm with a clustering approach in a lower-dimensional (low-dimensional) feature space, such as k-means clustering.”
Explanation: Clustering feature vectors generated from localized voxel neighborhoods constitutes clustering the underlying voxels, because the feature vectors represent the voxel intensities and spatial characteristics of the medical image. K-means clustering is a well-known voxel-clustering technique in medical imaging segmentation.
Thus, it would have been obvious to one of ordinary skill in the art, prior to filing, to combine Hébert’s ML-based clustering delineation with Qin’s FEM-based contour deformation method because automatic ML-based ROI delineation is a known substitute for manual contouring and improves reproducibility and speed (see paragraph [0036] above). Qin explicitly depends on accurate organ contours to construct FEM meshes. Thus, using ML-generated contours provides more consistent FEM initialization. Additionally, both references address identifying anatomical structures for downstream deformation analysis, yielding predictable improvements in processing speed, automation, and clustering accuracy.
Regarding Claim 3, Qin in view of Hébert teaches the method of claim 1, and Hébert further teaches that the trained clustering machine learning algorithm comprises an unsupervised or supervised machine learning algorithm (see paragraph [0037] and [0092] above).
Thus, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to incorporate Hébert’s teaching of supervised or unsupervised training into Qin’s FEM-based contour deformation method because selecting a supervised or unsupervised learning method is a routine design choice in machine learning, and each method yields predictable benefits. Unsupervised clustering (such as k-means) is conventionally used when ground truth labels are unavailable, while supervised models are used when labeled training data improve segmentation accuracy. A person of ordinary skill in the art would have recognized that either method could be predictably substituted to improve or automate contour delineation in Qin’s deformable registration pipeline.
Regarding Claim 5, Qin in view of Hébert teaches the method of claim 1, and Qin further teaches that determining deformed contours for the at least one set of medical images comprises:
deriving a deformation field using the finite element analysis algorithm, wherein the deformation field is dependent on an adjustable parameter (i.e., k) (Qin: Methods and Materials);
Boundary conditions: “Surface node displacement is linearly interpolated from IM-DIR DVF and utilized as the boundary condition for the FEM deformation.”
BM-DIR refinement: “A finite element solver package (ABAQUS, v6.14, Pawtucket, RI) was used to calculate the displacement of internal nodes.”
BM-DIR refinement: “For simplicity, uniform physical properties of Poisson ratio and Young’s moduli were assigned for the prostate phantom in this study.”
BM-DIR refinement: “The refined DVF is generated by interpolating the displacements on internal nodes to the image grid by scattered linear interpolation.”
Explanation: The FEM deformation field necessarily depends on adjustable parameters including Young’s modulus, Poisson’s ratio, deformation-specific boundary conditions, and phase-specific deformable vector field (DVF) inputs.
and applying the deformation field over the delineated one or more regions of interest over one or more of a plurality of phases of the physiological cycle, thereby forming deformed contours (Qin: Abstract (shown above), Methods and Materials (shown above), and Fig. 3 (shown above));
Regarding Claim 6, Qin in view of Hébert teaches the method of claim 1, and Qin further teaches that the method further comprises receiving an adjusted value of the adjustable parameter from a user (Qin: Methods and Materials);
Mesh generation: “To ensure the generation of high-quality mesh, we fine-tuned the parameters of TetGen based on nine tetrahedron quality measures for the typical critical organs in radiotherapy treatment.”
BM-DIR refinement: “A finite element solver package (ABAQUS, v6.14, Pawtucket, RI) was used to calculate the displacement of internal nodes.”
BM-DIR refinement: “Solid soft-tissue organs physical deformation was described using a linear elastic model with the default setting of Poisson ratio 0.40 and Young’s moduli 0.27 MPa.”
Explanation: Qin states that the material parameters (Young’s modulus, Poisson ration) were assigned, requiring user input. Additionally, TetGen mesh generation requires user-chosen parameters such as element size, mesh density, and smoothing levels. Lastly, ABAQUS requires user adjustment of step size, solver type, convergence tolerance, and boundary condition weighting. Therefore, Qin requires user input to set and adjust FEM parameters including material properties, meshing parameters, and solver settings.
Regarding Claim 7, Qin in view of Hébert teaches the method of claim 1, and Qin further teaches that in response to the user adjusting the adjustable parameter, the deformed contours are re-evaluated with the adjusted parameter (e.g. k') and the re-evaluated deformed contours are output. Qin explicitly discloses that the FEM must be re-solved whenever model parameters change, including boundary conditions derived from the IM-DIR field (which differ across the 10 phases), material parameters such as Young’s Modulus and Poisson’s ratio assigned to each organ, and solver/mesh parameters chosen in ABAQUS and TetGen (see Qin: Boundary conditions and BM-DIR refinement (shown above)). Because the DVF depends directly on these user-assigned parameters, Qin necessarily recomputes the DVF whenever an adjustable parameter changes. Then, Qin propagates contours using an updated DVF that is different for each phase, producing new deformed contours for all 10 phases (see Qin: Quantitative evaluation of BM-DIR on the multistage phantom (shown above)).
Regarding Claim 8, Qin in view of Hébert teaches the method of claim 1, and Qin further teaches that the finite element analysis algorithm comprises a modified Poisson's equation, a modified Navier-Stokes equation, a modified Lagrangian mechanics-based algorithm, or an elastodynamic equation (Qin: Methods and Materials)
BM-DIR refinement: “A finite element solver package (ABAQUS, v6.14, Pawtucket, RI) was used to calculate the displacement of internal nodes.”
BM-DIR refinement: “Solid soft-tissue organs physical deformation was described using a linear elastic model with the default setting of Poisson ratio 0.40 and Young’s moduli 0.27 MPa.”
Explanation: Linear elasticity FEM is a Lagrangian solid-mechanics formulation, because the displacement field is computed with respect to the material configuration of the organ. The standard governing PDE used in linear elasticity FEM is the Navier-Cauchy equation, which is a classical form of a Lagrangian mechanics equation and an elastodynamic equation when time terms are included.
Regarding Claim 9, Qin in view of Hébert teaches the method of claim 1, and Hébert further teaches determining a dose distribution for one or more of the plurality of phases (Hébert: Fig. 1 (shown below)), wherein determining the dose distribution comprises:
PNG
media_image4.png
301
618
media_image4.png
Greyscale
determining a dose distribution for fewer than the plurality of phases (Hébert: Detailed Description);
Paragraph [0059]: “The radiation therapy treatment plans 142 may provide information about a particular radiation dose to be applied to each patient.”
Paragraph [0063]: “After the target tumor and the OAR(s) have been located and delineated, a dosimetrist, physician, or healthcare worker may determine a dose of radiation to be applied to the target tumor, as well as any maximum amounts of dose that may be received by the OAR proximate to the tumor (e.g., left and right parotid, optic nerves, eyes, lens, inner ears, spinal cord, brain stem, and the like).”
deriving dose parameters from the fewer than the plurality of phases dose distribution (Hébert: Detailed Description);
Paragraph [0063]: “After the radiation dose is determined for each anatomical structure (e.g., target tumor, OAR), a process known as inverse planning may be performed to determine one or more treatment plan parameters that would achieve the desired radiation dose distribution. Examples of treatment plan parameters include volume delineation parameters (e.g., which define target volumes, contour sensitive structures, etc.), margins around the target tumor and OARs, beam angle selection, collimator settings, and beam-on times.”
Paragraph [0063]: “During the inverse-planning process, the physician may define dose constraint parameters that set bounds on how much radiation an OAR may receive (e.g., defining full dose to the tumor target and zero dose to any OAR; defining 95% of dose to the target tumor, defining that the spinal cord, brain stem, and optic structures receive ≤45 Gy, ≤55 Gy and <54 Gy, respectively).”
and applying the dose parameters to deformed distribution for the plurality of phases (Hébert: Detailed Description);
Paragraph [0060]: “In addition, if the target tumor is close to the OAR (e.g., prostate in near proximity to the bladder and rectum), then by segmenting the OAR from the tumor, the radiotherapy system 100 may study the dose distribution not only in the target but also in the OAR.”
Paragraph [0063]: “Thus, the image processing device 112 can generate a tailored radiation therapy treatment plan 142 having these parameters in order for the radiation therapy device 130 to provide radiotherapy treatment to the patient.”
Thus, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to incorporate Hébert’s phase-dependent dose evaluation into Qin’s deformable image registration workflow because Qin already focuses on accurately modeling organ deformation across multiple phases of a physiological cycle (e.g., ten phantom phases). Qin teaches that the purpose of deformable image registration is to “enable adaptive radiation therapy (ART), not only for the purposes of contour propagation, but also for dose warping [1,2,3,4,5], treatment response evaluation [6, 7] and 4D-inverse plan adaptation” (Qin: Introduction). Using those deformations to compute dose accumulation is a well-known objective in radiotherapy planning, as evaluating dose over physiological phases improves treatment accuracy, accounts for anatomic motion, and reduces unintended dose to organs-at-risk (see Hébert: paragraphs [0060] and [0063] (shown above)).
Regarding Claim 10, Qin in view of Hébert teaches the method of claim 1, and additional limitations are met as in the consideration of Claim 9 above.
Regarding Claim 11, Qin in view of Hébert teaches the method of claim 1, and Qin further teaches that the medical images comprise 4D CT, 4D PET CT, MRI, ultrasound, radionuclide imaging, or optical imaging (see Qin: Quantitative evaluation of BM-DIR on the multistage phantom (shown above)).
Regarding Claim 12, Qin in view of Hébert teaches the method of claim 1, and Qin further teaches that
the deformation contours are subsequently used for diagnostic and/or treatment planning (see Qin: Introduction (shown above)).
Regarding Claim 13, Qin in view of Hébert teaches the same limitations as discussed with respect to claim 1 above. The only additional feature in claim 13 is the recitation of a “a user device comprising a means for input and output” and “one or more computing systems comprising one or more processors and one or more storage devices, wherein the one or more storage devices have instructions stored thereon, that when executed by the one or more processors, causes the one or more processors to perform a method.” Qin’s system necessarily includes these components. Qin explicitly performs all computations using ABAQUS, IM-DIR, and TetGen executed on a workstation-based computing platform, which inherently comprises processors (for running ABAQUS and IM-DIR), memory and storage (for storing CT/MRI images, meshes, displacement fields, and FEM parameters), input/output means (for importing images, exporting deformation fields, and displaying registration results), and computer executable instructions stored on a non-transitory medium (ABAQUS and TetGen are software packages executed by the workstation).
Regarding Claim 15, Qin in view of Hébert teaches the system of claim 13, and additional limitations are met as in the consideration of Claim 2 above.
Regarding Claim 17, Qin in view of Hébert teaches the system of claim 13, and additional limitations are met as in the consideration of Claim 5 above.
Regarding Claim 18, Qin in view of Hébert teaches the system of claim 13, and additional limitations are met as in the consideration of Claim 6 above.
Regarding Claim 19, Qin in view of Hébert teaches the system of claim 13, and additional limitations are met as in the consideration of Claim 7 above.
Regarding Claim 20, Qin in view of Hébert teaches the system of claim 13, and additional limitations are met as in the consideration of Claim 8 above.
Claims 4 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Qin et. al in view of Hébert et. al, further in view of Layer et. al (“PET image segmentation using a Gaussian mixture model and Markov random fields”). Layer teaches the use a Gaussian Mixture Model (GMM) for image segmentation and clustering of image intensities into anatomical classes.
It would have been obvious to one of ordinary skill in the art, prior to filing, to incorporate the GMM-based clustering approach of Layer into the trained clustering algorithm of Hébert. Hébert teaches that image delineation is performed using a clustering machine learning algorithm in a low-dimensional feature space such as k-means clustering (see paragraph [0037] above), and emphasizes that clustering algorithms may be substituted to improve segmentation speed and accuracy. Layer discloses that “an improved statistical approach using a Gaussian mixture model (GMM) is proposed to obtain initial estimates of a target volume” (Layer: Abstract). Layer further explains that the GMM approach provides “stable results,” “improvements for small volumes,” and more accurate volume estimates compared to threshold-based or hard-clustering methods (Layer: Abstract). Because both references address automatic segmentation of medical images for radiotherapy workflows, and because GMM is a well-known probabilistic clustering machine learning model that provides predictable improvements over k-means (e.g., soft labeling, better modeling of tissue heterogeneity), a person of ordinary skill in the art, before the effective filing date of the claimed invention, would have been motivated to substitute the k-means example in Hébert with the GMM of Layer to obtain better performance, robustness, and swiftness (Layer: Abstract), yielding improved clustering performance.
Regarding Claim 16, Qin in view of Hébert teaches the system of claim 13, and additional limitations are met as in the consideration of Claim 4 above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Khan (U.S Patent No. 9,919,163) teaches determining a dose distribution for one or more target regions across multiple phases, applying a deformation parameter to a dose distribution for a subset of phases, determining dose parameters based on dose distribution changes across phases, and identifying an optimal treatment phase based on motion or dose characteristics.
Novosad (U.S Patent No. 20,220,180,523) teaches systems using trained neural networks to perform radiotherapy image segmentation.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WILLIAM ADU-JAMFI whose telephone number is (571)272-9298. The examiner can normally be reached M-T 8:00-6:00.
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, Andrew Bee can be reached at (571) 270-5183. 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.
/WILLIAM ADU-JAMFI/Examiner, Art Unit 2677
/ATIBA O FITZPATRICK/Primary Examiner, Art Unit 2677