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) submitted on 08/05/2026 and 02/19/2026 have been considered by the examiner.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION. —The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 16-18 and 20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 16 recites the limitation, “wherein at least one of the matrix W and the vector b is adjustable to enable optimization of at least one image quality metric of the CT image data based on maximizing or minimizing a second objective function.” There is insufficient antecedent basis for this limitation in the claim, and it should likely depend on claim 15 instead of claim 14.
Claim 17 recites the limitation, “wherein the at least one second objective function is at least one of mean-squared error, structural similarity, bias, fidelity of fine details, numerical observer detectability, visual grading score and observer performance.” There is insufficient antecedent basis for this limitation in the claim, and it should likely instead depend on claim 16 instead of claim 14.
Claim 18 recites the limitation, “wherein the matrix W is a diagonal matrix.” There is insufficient antecedent basis for this limitation in the claim, and it should likely depend on claim 15 instead of claim 14.
Claim 20 recites the limitation, “wherein at least one of the matrix W and the vector b of the denoised spectral CT image data a is adjustable by an end user.” There is insufficient antecedent basis for this limitation in the claim, and it should likely depend on claim 15 instead of claim 14.
No prior art rejection is given for these claims, but they would likely be objected once their claim dependency is fixed and they depend on objected to claim 15.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 14, and 19 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Ramani et al. (US Pub. No. 2021/0012463 A1).
Regarding claim 1, Ramani discloses, a method for denoising spectral CT image data, (See Ramani ¶42, “The method 58 further includes performing denoising (e.g., via joint and individual treatment or processing) of the images 64 in the spectral and/or spatial domains utilizing a deep learning-based denoising network”)
the method comprising: determining a denoised linear estimation of spectral CT image data (The denoising framework includes a DL (deep learning) linear transformation step prior to the denoising step. Since this linear transformation is part of the denoising framework, the denoising can be considered to be a linear estimation.
See Ramani ¶39, “The AI based denoising framework may include the following components: (1) one or more optional transformations of the vector of material images (or the material images) into a new set of bases that are more suitable for subsequent DL-based denoising, (2) one or more DL networks for joint denoising of the vector images (or material images), (3) one or more optional transformations to revert to the domain of the original material-vector (or material images), and (4) incorporation of prior knowledge about material images and/or transformations of the material images as part of the denoising process.”
Further see Ramani ¶41, “In certain embodiments, the method 58 also includes performing transformation on the images 60 to generate arbitrary basis images or vector images of the arbitrary basis images 64 (block 66). … Other transforms include conversion to monochromatic images or arbitrary linear combinations of material images based on local statistics, i.e., b.sub.i=Σ.sub.j=1.sup.Lα.sub.ijm.sub.j, with α.sub.ij being the linear transformation coefficient between b.sub.i and m.sub.1, based on CT physics or noise statistics. … At the sophisticated end, the transformation could be a (linear or non-linear) DL network (e.g., deep learning-based transformation network) that, when properly trained, suitably represents the material-images for denoising.”)
by maximizing or minimizing a first objective function, (See Ramani ¶55, “In all the embodiments described above, the DL networks (both in denoisers and in other components such as the first-step transformation and voting scheme) may be jointly trained to minimize a loss function, which typically describes some measure of distance between the noisy input training samples and corresponding noise-free ground-truth.”)
wherein at least one parameter of the denoised linear estimation is determined by at least one machine learning system. (The weights of the DL linear transformation are considered to be the parameters of the machine learning system. Alternatively, the DL of the denoising step itself also uses trained machine learning weights.)
See Ramani ¶55, “In one embodiment, all of the 2D DL denoising networks in the sequential mode are trained at once as a whole. This type of training may be computationally intensive and memory exhaustive. In another embodiment, each 2D denoising block is trained one at a time by freezing the weights of the already trained blocks when training subsequent blocks.”)
Regarding claim 14, Ramani discloses, a CT imaging system comprising: an X-ray source configured to emit X-rays; (See Ramani ¶32, “The CT imaging system 10 includes an X-ray source 12. … As will be appreciated, the X-ray source 12 may also be operated so as to emit X-rays at more than two different energies, though dual-energy embodiments are discussed herein to simplify explanation. Similarly, the X-ray source 12 may emit at polychromatic spectra localized around energy levels (i.e., kVp ranges) other than those listed herein.”)
an X-ray detector configured to generate spectral CT image data; (See Ramani ¶33, “Resulting attenuated X-rays 26 impact a detector array 28 formed by a plurality of detector elements. Each detector element produces an electrical signal that represents the intensity of the X-ray beam incident at the position of the detector element when the beam strikes the detector 28. Electrical signals are acquired and processed to generate one or more scan datasets.”)
and a processor configured to: (See Ramani ¶36, “The DAS 40 may then convert the data to digital signals for subsequent processing by a processor-based system, such as a computer 42.”)
determine a denoised linear estimation of the generated spectral CT image data (The denoising framework includes a DL (deep learning) linear transformation step prior to the denoising step. Since this linear transformation is part of the denoising framework, the denoising can be considered to be a linear estimation.
See Ramani ¶39, “The AI based denoising framework may include the following components: (1) one or more optional transformations of the vector of material images (or the material images) into a new set of bases that are more suitable for subsequent DL-based denoising, (2) one or more DL networks for joint denoising of the vector images (or material images), (3) one or more optional transformations to revert to the domain of the original material-vector (or material images), and (4) incorporation of prior knowledge about material images and/or transformations of the material images as part of the denoising process.”
Further see Ramani ¶41, “In certain embodiments, the method 58 also includes performing transformation on the images 60 to generate arbitrary basis images or vector images of the arbitrary basis images 64 (block 66). … Other transforms include conversion to monochromatic images or arbitrary linear combinations of material images based on local statistics, i.e., b.sub.i=Σ.sub.j=1.sup.Lα.sub.ijm.sub.j, with α.sub.ij being the linear transformation coefficient between b.sub.i and m.sub.1, based on CT physics or noise statistics. … At the sophisticated end, the transformation could be a (linear or non-linear) DL network (e.g., deep learning-based transformation network) that, when properly trained, suitably represents the material-images for denoising.”)
based on maximizing or minimizing a first objective function; (See Ramani ¶55, “In all the embodiments described above, the DL networks (both in denoisers and in other components such as the first-step transformation and voting scheme) may be jointly trained to minimize a loss function, which typically describes some measure of distance between the noisy input training samples and corresponding noise-free ground-truth.”)
wherein the processor is further configured to determine at least one parameter of the linear estimation by at least one machine learning system. (The weights of the DL used for linear transformation are considered to be parameters of a machine learning system. Alternatively, the DL of the denoising step itself uses weights for its trained deep learning neural network.
See Ramani ¶55, “In one embodiment, all of the 2D DL denoising networks in the sequential mode are trained at once as a whole. This type of training may be computationally intensive and memory exhaustive. In another embodiment, each 2D denoising block is trained one at a time by freezing the weights of the already trained blocks when training subsequent blocks.”)
Regarding claim 19, Ramani discloses, the CT imaging system according to claim 14, wherein the spectral CT image data comprises at least one of a set of sinograms (A spectral CT system will inherently acquire sinograms as the scanner rotates around a patient.)
and a set of reconstructed images. (See Ramani ¶40, “The method 58 includes acquiring multi-energy scan datasets and reconstructing material images or obtaining material images (e.g., material decomposition images or basis material images) or vector images of the material images 60 (e.g., such as similar to RGB channels) (block 62).”
Allowable Subject Matter
Claims 2-13 and 15 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.
Regarding claim 2, the method according to claim 1, wherein determining the denoised linear estimation of spectral CT image data comprises: receiving spectral CT image data; processing the spectral CT image data based on the at least one machine learning system such that a matrix W and a vector b is obtained; and forming denoised spectral CT image data a according to the linear estimation as per a= Wx+ b, wherein x is a representation of spectral CT image data comprising at least two spectral components. (The disclosed prior art of record fails to disclose the limitations of this claim.)
Regarding claims 3-13, these claims are objected to since they depend on objected to claim 2.
Regarding claim 15, the CT imaging system according to claim 14, wherein the processor is configured to: process the spectral CT image data based on the at least one machine learning system such that a matrix W and a vector b is obtained; and form denoised spectral CT image data a according to the linear estimation as per a= Wx+ b, wherein x is a representation of spectral CT image data containing at least two spectral components. (The disclosed prior art of record fails to disclose the limitations of this claim.)
Conclusion
Listed below are the prior arts made of record and not relied upon but are considered pertinent to applicant’s disclosure.
Zhou et al. (US Pub. No. 2020/0196973 A1) A deep learning (DL) network reduces artifacts in computed tomography (CT) images based on complementary sparse-view projection data generated from a sparse kilo-voltage peak (kVp)-switching CT scan. The DL network is trained using input images exhibiting artifacts and target images exhibiting little to no artifacts. Another DL network can be trained to perform image-domain material decomposition of the artifact-mitigated images by being trained using target images in which beam hardening is corrected and spatial variations in the X-ray beam are accounted for.
Fu et al (US Pub. No. 2018/0293762 A1) The present approach relates to the use of machine learning and deep learning systems suitable for solving large-scale, space-variant tomographic reconstruction and/or correction problems. In certain embodiments, a tomographic transform of measured data obtained from a tomography scanner is used as an input to a neural network. In accordance with certain aspects of the present approach, the tomographic transform operation(s) is performed separate from or outside the neural network such that the result of the tomographic transform operation is instead provided as an input to the neural network. In addition, in certain embodiments, one or more layers of the neural network may be provided as wavelet filter banks.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DAVID PERLMAN whose telephone number is (571) 270-1417.
The examiner can normally be reached on Monday - Friday; 10:00am -6:30pm.
Examiner interviews are available via telephone 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, Chineyere Wills-Burns can be reached at (571) 272-9752. 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.
/DAVID PERLMAN/Primary Examiner, Art Unit 2673
Prosecution Insights