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 .
Response to Amendment
Applicant’s response to the Non-Final Rejection mailed 9/17/2025 has been received and made of record. Claims 1-7, 9-12, 15-17, 21-22, 26, 68, and 96 remain pending with claims 2-3, 10-12, 15-17 withdrawn from consideration, and claims 8, 13-14, 18-20, 23-25, 27-67, 69-95, and 97-128 are cancelled.
Response to Arguments
Applicant’s remarks have been considered and are persuasive in relation to claim 96, and persuasive for the other claims in relation to the 102 rejection, but not the prior art. Thus, the rejection has been changed to a single reference 103 under Clark to address the issues raised, and is fully disclosed within the rejection below.
Based on these facts, this action is made Non-Final.
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 96 is 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.
Regarding claim 96, the claim discloses “(MECT) image”, but later discloses “the MECT data”, thus is unclear whether the MECT image is meant to being used instead or MECT data, especially when generating a VMI version of the MECT data. For purposes of examination, the examiner will interpret it to mean MECT data.
Appropriate correction is required.
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, 5-6, 9, 68 are rejected under 35 U.S.C. 103 as being unpatentable over D. P. Clark, M. Holbrook, C. T. Badea, "Multi-energy CT decomposition using convolutional neural networks," Proc. SPIE 10573, Medical Imaging 2018: Physics of Medical Imaging, 105731O (9 March 2018), hereinafter referred to as Clark.
Regarding claim 1, Clark teaches a system for transforming a multi-energy computed tomography data, the system comprising: at least one hardware processor (Clark, processor embodied in the system including the “PC workstation” and “Titan X graphics card,” pgs. 2-3) configured to: receive a multi-energy computed tomography (MECT) data of a subject (Clark, Figs. 1, 3, receive MECT data of a subject, pgs. 1-4, 6-8); provide the MECT data to a trained convolutional neural network (CNN) (Clark, Figs. 1, 3, provide MECT data to a “trained” CNN (U-net), pgs. 1-4, 6-8); receive output from the trained CNN indicative of predicted calibrated material mass density for each of a plurality of materials at each pixel location of the MECT data, wherein the plurality of materials represents at least two materials (Clark, Figs. 1, 3, 5, trained CNN outputs calibrated the predicted mass density for the plurality of materials at each pixel location of the MECT data (as depicted in the Material/Decomposition Maps “at each pixel location”), wherein the plurality of materials represent Iodine (I), Barium (Ba), Photoelectric Effect (PE), and Compton Scattering (CS) (“producing I/Ba/PE/CS material maps”), pgs. 1-4, 6-8); and generate a transformed version of the MECT data using the output (Clark, Figs. 1, 3, 5, generate a transformed version of the MECT data, depicting the different material concentrations/densities, using the output densities, pgs. 1-4, 6-8).
Clark does not explicitly disclose that the calibrated material mass density is in physical units, but it would have been obvious to have done so. The reason is the density is disclosed in units of mg/ml as seen and disclosed within Figure 3 and page 4, similar to the density in physical units disclosed in Par. [0129] of the Applicant’s originally filed specification. Thus, it would have been obvious to include mass density in physical units in order to accurately calibrate, test, and predict the data needed to be output and generated.
Regarding claim 5, Clark teaches the system of claim 1, wherein the CNN was trained using MECT data of a phantom comprising a plurality of samples, each of the plurality of samples representing at least one material of the plurality of materials (Clark, Figs. 2, 3, the CNN was trained using “phantom simulations” comprising a plurality of samples representing at least one material (I/Ba/PE/CS), pgs. 3-4), and information indicating a material mass density associated with each of the plurality of samples (Clark, Figs. 2, 3, the information/samples used to train the CNN also included information indicating material mass density (material maps) associated with each of the plurality of samples (I/Ba/PE/CS), pgs. 3-4).
Regarding claim 6, Clark teaches the system of claim 5, wherein the information indicating a material mass density of each of the plurality of samples comprises information indicative of the material mass density of each of the plurality of samples at the position of each pixel of the MECT data (Clark, the information included information indicative of the material mass density of each sample at the position of each pixel of the MECT data (“These CT images were used to train CNNs to generate material maps at each pixel location,” the information being of each pixel location), pgs. 1-4).
Regarding claim 9, Clark teaches the system of claim 5, wherein the plurality of samples includes two samples that represent the same material at two different concentrations (Clark, Figs. 2, 3, plurality of samples includes two samples that represent the same material at two different concentrations (Fig. 3(D)), pgs. 3-4).
Regarding claim 68, the rationale provided in the rejection of claim 1 is incorporated herein. Additionally, the method of claim 68 corresponds to the system of claim 1, and performs the steps disclosed herein.
Claim 96 is rejected under 35 U.S.C. 103 as being unpatentable over D. P. Clark, M. Holbrook, C. T. Badea, "Multi-energy CT decomposition using convolutional neural networks," Proc. SPIE 10573, Medical Imaging 2018: Physics of Medical Imaging, 105731O (9 March 2018), hereinafter referred to as Clark in view of Cong, W., et al., Virtual Monoenergetic CT Imaging via Deep Learning. Elsevier, Vol. 1, Issue 8, 100128, 13 November 2020, hereinafter referred to as Cong.
Regarding claim 96, Clark teaches a method for transforming a multi-energy computed tomography data, the method comprising: receiving a multi-energy computed tomography (MECT) image of a subject (Clark, Figs. 1, 3, receive MECT data of a subject, pgs. 1-4, 6-8); provide the MECT data to a trained convolutional neural network (CNN) (Clark, Figs. 1, 3, provide MECT data to a “trained” CNN (U-net), pgs. 1-4, 6-8); receive output from the trained CNN (Clark, Figs. 1, 3, 5, trained CNN outputs, pgs. 1-4, 6-8).
However, Clark fails to teach where Cong teaches receiving output from the trained CNN indicative of predicted one or more virtual monoenergetic images (VMIs) at one or more X-ray energies (Cong, Figs. 1-3, receive output from the trained CNN indicative of predicted virtual monoenergetic images (VMIs) at one or more X-ray energies (Fig. 1, 80 and 110 keV), pgs. 1-2, 4-7); and generating a VMI version of the MECT data at a particular X-ray energy using the output (Cong, Figs. 1-3, generate a VMI version of the MECT data at a particular X-ray energy using the output for display of multi-material decomposition (Fig. 2), pgs. 1-2, 4-7).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Clark using the teachings of Cong in order to improve image quality of the image at the desired energy level.
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over D. P. Clark, M. Holbrook, C. T. Badea, "Multi-energy CT decomposition using convolutional neural networks," Proc. SPIE 10573, Medical Imaging 2018: Physics of Medical Imaging, 105731O (9 March 2018), hereinafter referred to as Clark as applied to claim 1, and further in view of Cong, W., et al., Virtual Monoenergetic CT Imaging via Deep Learning. Elsevier, Vol. 1, Issue 8, 100128, 13 November 2020, hereinafter referred to as Cong.
Regarding claim 4, Clark teaches the system of claim 1.
However, Clark fails to teach where Cong teaches wherein the transformed data is a virtual monoenergetic image (VMI) (Cong, Figs. 2-3, transformed data is a virtual monoenergetic image (VMI), pgs. 1-2, 5-6).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Clark using the teachings of Cong in order to improve image quality of the image at the desired energy level.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Clark, as applied to claim 1, and further in view of W. Wu, et al., "Image-Domain Material Decomposition for Spectral CT Using a Generalized Dictionary Learning," in IEEE Transactions on Radiation and Plasma Medical Sciences, vol. 5, no. 4, pp. 537-547, July 2021, doi: 10.1109/TRPMS.2020.2997880, (Electronically pub. 26 May 2020)., hereinafter referred to as Wu.
Regarding claim 7, Clark teaches the system of claim 5.
However, Clark fails to teach where Wu teaches wherein the MECT data of the phantom are each a patch of a whole MECT data of the phantom (Wu, MECT data of the phantom are each a patch (ith image patches) of a whole MECT data of the phantom (for the “physical phantom and tissue-synthetic phantom”), pgs. 1, 3-5, 7).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Clark using the teachings of Wu to improve material decomposition by providing patches of MECT data, which would be used to efficiently fine-tune the material mass density predictions.
Claim 21 is rejected under 35 U.S.C. 103 as being unpatentable over Clark, as applied to claim 1, and further in view of Schmidt (DE 102016202604 A1, the attached English language translation is used hereinafter as the Official English language translation of this DE document).
Regarding claim 21, Clark teaches the system of claim 1.
However, Clark fails to teach where Schmidt teaches wherein the plurality of materials comprises at least four of: an iodine contrast-media; calcium; a mixture of blood and iodine; adipose tissue; hydroxyapatite; or blood (Schmidt, plurality of materials for material decomposition “relate to two or more base materials. A base material may for example be a contrast agent, in particular iodine, tissue, in particular soft tissue, blood, water, bone, cartilage, fat and the like. A base material may be for example a combination and / or a mixed form of a plurality of materials,” [emphasis added] thereby comprising an iodine contrast media, blood, mixture of blood and iodine, and adipose tissue (fat), pgs. 32-34/48).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Clark using the teachings of Schmidt to improve material decomposition by providing a plurality of materials that are especially medically pertinent, which would be used to readily visualize these medically pertinent materials.
Claim 22 is rejected under 35 U.S.C. 103 as being unpatentable over Clark, as applied to claim 1, and further in view of Z. Zhang, C. Wu, S. Coleman, D. Kerr, DENSE-INception U-net for medical image segmentation, Computer Methods and Programs in Biomedicine, Volume 192, August 2020, 105395, ISSN 0169-2607, hereinafter referred to as Zhang.
Regarding claim 22, Clark teaches the system of claim 1, wherein the trained CNN comprises: a first convolution layer (Clark, Fig. 1, first arrow, convolution (3x3), pgs. 2-3); a batch normalization layer that receives an output of the convolutional layer (Clark, Fig. 1, first arrow, bnorm (batch normalization) follows convolution and receives its output, pgs. 2-3); a leaky rectified linear unit (Leaky ReLU) that receives an output of the batch normalization layer (Clark, Fig. 1, first arrow, ReLU follows batch normalization and receives its output, pgs. 2-3); and a second convolution layer (Clark. Fig. 1, any of the subsequent orange/brown arrows signifying convolution, pgs. 2-3).
However, Clark fails to teach where Zhang teaches four inception blocks, including a first inception block, a second inception block, a third inception block, and a fourth inception block (Zhang, Fig. 2, four inception blocks, pgs. 3-6, 18/41).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Clark using the teachings of Zhang to improve the convolutional architecture for medical image processing by providing inception blocks, which would be used to increase “the depth and width of network” with a “sparse high performance computing network architecture” (Zhang, pg. 2).
Allowable Subject Matter
Claim 26 is 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.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Vincent Rudolph whose telephone number is (571)272-8243. The examiner can normally be reached M-F 7:30 AM - 3:30 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://www.uspto.gov/interviewpractice.
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.
/VINCENT RUDOLPH/ Supervisory Patent Examiner, Art Unit 2671
Prosecution Insights