CTNF 18/715,998 CTNF 84736 DETAILED ACTION 1 . Claims 1,3-6, 9,14, 16, 22, 28, 32, 34-36, 39, 44-45, 51, 57 and 60 are pending in the application. Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia 2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Claim Rejections - 35 USC § 102 07-06 AIA 15-10-15 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 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. 07-07-aia AIA 07-07 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 - 07-08-aia AIA (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. 07-15 AIA 3. Claim s 1,3-6, 9,14, 22, 28, 32, 34-36, 39, 44, 51, 57 and 60 rejected under 35 U.S.C. 102( a)(1 ) as being anticipated by Alves; James (hereafter Alves ), US 20170195605 A1, pub., 07/06/2017 As to claim 1, HEIN teaches a method of reconstructing a computed tomography (CT) image ([0001],[0032], 'This disclosure relates to using deep learning (DL) networks to improve the image quality of reconstructed medical images, and, more particularly, to using DL networks to reduce noise and artifacts in reconstructed computed tomography (CT) '), the method comprising: receiving acquired CT projection data of an object (Fig. 1, 6 & 7; [0039], 'In step 102 of method 100, an imaging scan is initialized. The imaging scan can be, e.g., an X-ray computed tomography (CT) scan'); substantially removing at least one unmodeled bias (Fig. 3 shows examples of unmodeled biases) from the acquired CT projection data using at least one trained artificial neural network (ANN) and at least one loss function that incorporates intermediate CT reconstruction information to produce corrected CT projection data (Fig. 2 & 4, [012] [0031], [0060],; [0072], [0034], ' the decision of which artifact corrections to apply, if an artifact is detected which can be corrected, than an applicable artifact correction method is selected (e.g., a DL network that has been trained to correct that particular type of artifact) and is applied to correct the correctable artifact (see [0034]) .; 'Each of the DL networks is trained by applying pieces of the input data (e.g., a sinogram or reconstructed image, depending on which domain, i.e., image or sinogram, the DL network is used in) to the respective DL network to generate an output, and then using a loss function to compare the output from the DL network to the corresponding target data (see [0072]) .); and, generating a reconstructed CT image from the corrected CT projection data, thereby reconstructing the CT image ([0032], [0097], 'The methods described herein integrate artifact-detection CNNs into the CT scanner and image reconstruction workflow, and the integrated artifact-detection CNNs are used to decide workflow operations (see [0032]). . Reconstruction algorithm to use when reconstructing the CT image. Consider that, iterative reconstruction using a total-variation minimization (TV) regularize can reduce streak artifacts( see [0032] ). 'For an artifact-correction CNN in the image domain, the input data is reconstructed images that exhibit the particular artifact, and the target data is corresponding reconstructed images in which the artifact is reduced or absent . (see. [0097] ). As to claim 3, HEIN teaches a source of the unmodeled bias is unknown or substantially indeterminable ( Fig. 3, [0026], [0096], [0097], 'As can be seen from the above discussion, various types of artifacts can be addressed/corrected through changing the scan protocol, and other types of artifacts can be addressed/corrected through algorithms to post-processing the sinogram and/or images. Additionally, some types of artifacts can be partially addressed/corrected through changing the scan protocol, and then further corrected through post-processing. For some types of artifacts (e.g., beam hardening), post-processing to correct the artifacts is more effective in the sinogram domain, and, for other types of artifacts (e.g., metal artifacts), post-processing to correct the artifacts is more effective in the image domain ). As to claim 4, HEIN teaches . the corrected CT projection data is improved in a projection domain, an image domain, or both a projection domain and an image domain relative to the acquired CT projection data ([0052] FIG. 2 shows a non-limiting example of a method 200 for performing artifact detection and correction in both sinogram and image domains. Process 210 shows the steps for performing artifact detection and correction in the sinogram domain, and process 250 shows the steps for performing artifact detection and correction in the image domain.). As to claim 5 HEIN teaches using at least one physical model of a CT data collection process to identify the unmodeled bias from the acquired CT projection data ([0026], e.g., magnetic resonance imaging and computed tomography (CT). CT datasets, in particular, are susceptible to artifacts that can be broadly categorized according to the suspected cause of the artifact, including (1) physics-based artifacts, (2) patient-based artifacts, (3) scanner-based artifacts. Scanner-based artifacts, including ring artifacts, can be due to detector element malfunction or calibration deficiencies..). As to claim 6, HEIN teaches using at least one physical model of a CT data collection process to identify the unmodeled bias from the acquired CT projection data( Abstract [0026]. Scanner-based artifacts, including ring artifacts, can be due to detector element malfunction or calibration deficiencies. determine whether the detected artifact can be corrected through a changed scan protocol or image-processing techniques, and (iii) determine whether the detected artifacts are fatal, in which case the scan is stopped short of completion. When the artifacts can be corrected, corrective measures are taken through a changed scan protocol or through image processing to reduce the artifacts (e.g., convolutional neural network can be trained to perform the image processing ). ) As to claim 9, HEIN teaches the unmodeled bias comprises a potential to propagate through a reconstruction process to create one or more artifacts ([0027] While some artifacts, such as ring and beam hardening artifacts and artifacts from metal implants, can be appreciated and corrected for at various stages of image acquisition and processing). As to claim 14, HEIN teaches the unmodeled bias is selected from the group consisting of: a drift in x-ray energy source( [0092], Beam hardening artifacts can result in a cupped appearance when grayscale is visualized as height. It occurs because conventional sources, like X-ray tubes emit a polychromatic spectrum. Photons of higher photon energy levels are typically attenuated less ), a drift in an x-ray energy detector ([0095] Cone beam effect artifacts result from the geometry of the X-ray beam at multichannel detectors ), an incomplete scatter rejection, an inexact scatter correction, an inexact x-ray energy source calibration, a filtration of x-rays from an x-ray energy source, a physical effect induced by the object, a reconstruction algorithm effect, a beam hardening effect, a scattering effect, and a detector effect (Abstract, [0026], In each domain, a detection network is used to (i) determine if particular types of artifacts are exhibited (e.g., beam-hardening artifact, ring, motion, metal, photon-starvation, windmill, zebra, partial-volume, cupping, truncation, streak artifact, and/or shadowing artifacts), (ii) determine whether the detected artifact can be corrected through a changed scan protocol or image-processing techniques). As to claim 22 HEIN teaches the unmodeled bias comprises at least one residual bias( Claim 16, wherein the processing circuitry is further configured to acquire another neural network, apply the CT image to the another neural network to generate an output indicating whether a residual artifact is exhibited by the CT image, and signal to a user of the apparatus that the residual artifact is exhibited by the CT image, when the output from the another neural network indicates that the residual artifact is exhibited by the CT image.) As to claim 28, HEIN teaches the unmodeled bias is substantially specific to an anatomy of the object ([0026], Patient-based artifacts can be generated by motion, metal implants, truncation (e.g., patient anatomy outside of scanner field of view), and other patient-related factors). As to claim 32, HEIN teaches A computed tomography (CT) system, comprising: at least one x-ray energy source; at least one x-ray detector configured and positioned to detect x-ray energy transmitted through an object from the x-ray energy source (Fig.6 [0117]) ; `at least one trained artificial neural network (ANN) and at least one loss function that incorporates intermediate CT reconstruction information that are configured to remove unmodeled bias from acquired CT projection data ([0072]).); [0110] -[0111] FIG. 5 shows an example of the inter-connections between layers in an artificial neural network (ANN), which can also be referred to as a DL network, and a CNN is a particular type of ANN that includes convolutional layers With regard to the CNN architecture, generally, convolutional layers are placed close to the input layer, whereas fully connected layers, which perform the high-level reasoning, are placed further down the architecture towards the loss function . ) ; and, at least one controller that is operably connected, or connectable, at least to the x-ray detector and to the trained ANN, wherein the controller comprises, or is capable of accessing, computer readable media comprising non-transitory computer executable instructions which, when executed by at least one electronic processor, perform at least (Claim 20, A non-transitory computer-readable storage medium including executable instructions, which when executed by circuitry, cause the circuitry to perform ): receiving acquired CT projection data of an object substantially removing at least one unmodeled bias from the acquired CT projection data using the trained ANN and the loss function to produce corrected CT projection data; and, generating a reconstructed CT image from the corrected CT projection data (all these limitation discussed in claim 1 above). Claim 34 is rejected the same as claim 3 except claim 34 is directed to system claim. All the limitations of claim 34 are addressed in claim 3. Thus, argument analogous to that presented above for claim 3 is applicable to claim 34. Claim 35 is rejected the same as claim 4 except claim 35 is directed to system claim. All the limitations of claim 35 are addressed in claim 4. Thus, argument analogous to that presented above for claim 4 is applicable to claim 35. Claim 36 is rejected the same as claim 5 except claim 36 is directed to system claim. All the limitations of claim 36 are addressed in claim 5. Thus, argument analogous to that presented above for claim 5 is applicable to claim 36. Claim 39 is rejected the same as claim 9 except claim 39 is directed to system claim. All the limitations of claim 39 are addressed in claim 9. Thus, argument analogous to that presented above for claim 9 is applicable to claim 39. Claim 44 is rejected the same as claim 14 except claim 44 is directed to system claim. All the limitations of claim 44 are addressed in claim 14. Thus, argument analogous to that presented above for claim 14 is applicable to claim 44. Claim 51 is rejected the same as claim 22 except claim 51 is directed to system claim. All the limitations of claim 51 are addressed in claim 22. Thus, argument analogous to that presented above for claim 22 is applicable to claim 51. Claim 57 is rejected the same as claim 28 except claim 57 is directed to system claim. All the limitations of claim 57 are addressed in claim 28. Thus, argument analogous to that presented above for claim 28 is applicable to claim 57. As to claim 60, HEIN teaches A computer readable media comprising non-transitory computer executable instruction which, when executed by at least electronic processor (Claim 20, A non-transitory computer-readable storage medium including executable instructions, which when executed by circuitry, cause the circuitry to perform), regarding the remaining limitation, all the remaining limitation are similar to the limitations of claim 1, thus the rejection applied to claim 1 is also applied to the remaining limitations . Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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 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. 07-20-aia AIA 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 of this title, 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. 07-21 AIA 4. Claim s 16 and 45 are rejected under 35 U.S.C. 103(a) as being unpatentable over HEIN, US20210012543, pub. 01/14/2021, in view of Patrick J et al. ( hereafter Patrick), “Penalized-Likelihood Sinogram Restoration for Computed Tomography” IEEE TRANSACTIONS ONMEDICALIMAGING,VOL.25,NO.8,AUGUST2006 . As to claim 16, HEIN teaches, the ANN is trained to estimate sinogram ([0031], Accordingly, the methods described herein use DL networks (e.g., CNNs) to identify potential artifacts in X-ray CT data and images. In certain implementations, the inputs to the CNNs are image data and sinograms , and the output from the CNN is a list indicating which artifacts are present and in which part of the sinogram /image the artifact is present ). however it is noted that HEIN does not specifically teach “estimate unbiased projections from a plurality of biased and/or unbiased sinogram pairs.” On the other hand Patrick teaches estimate unbiased projections from a plurality of biased and/or unbiased sinogram pairs ( Abstract, page 1028 left col., 2nd par., page 1031 left col section C, Penalized-Likelihood Sinogram Restoration, where a resolution-variance curves obtained for the three sinogram restoration strategies which are shown in Fig. 6. A weights equal to the unbiased estimate of the variances are applied ) It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate a method of sinogram restoration based on weights equal to the unbiased estimate of the variances taught by Patrick into HEIN . The suggestion/motivation for doing so would have been allows user of HELN to estimate the true, noise-free sinogram from noisy, logged, or unlogged detector measurements Claim 45 is rejected the same as claim 16 except claim 45 is directed to system claim. All the limitations of claim 45 are addressed in claim 16. Thus, argument analogous to that presented above for claim 16 is applicable to claim 45. Contact Information Any inquiry concerning this communication or earlier communication from the examiner should be directed to Mekonen Bekele whose telephone number is (469) 295-9077.The examiner can normally be reached on Monday-Friday from 9:00AM to 6:50 PM Eastern Time. If attempt to reach the examiner by telephone are unsuccessful, the examiner’s supervisor Eng, George can be reached on (571) 272-7495.The fax phone number for the organization where the application or proceeding is assigned is 571-237-8300. Information regarding the status of an application may be obtained from the patent Application Information Retrieval (PAIR) system. Status information for published application may be obtained from either Private PAIR or Public PAIR. Status information for unpublished application is available through Privet PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have question on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866. /MEKONEN T BEKELE/Primary Examiner, Art Unit 2699 Application/Control Number: 18/715,998 Page 2 Art Unit: 2699 Application/Control Number: 18/715,998 Page 3 Art Unit: 2699 Application/Control Number: 18/715,998 Page 4 Art Unit: 2699 Application/Control Number: 18/715,998 Page 5 Art Unit: 2699 Application/Control Number: 18/715,998 Page 6 Art Unit: 2699 Application/Control Number: 18/715,998 Page 7 Art Unit: 2699 Application/Control Number: 18/715,998 Page 8 Art Unit: 2699 Application/Control Number: 18/715,998 Page 9 Art Unit: 2699 Application/Control Number: 18/715,998 Page 10 Art Unit: 2699
Prosecution Insights