Detail Office 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 .
Examiner cites particular columns and line numbers in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested that, in preparing responses, the applicant fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner.
Status: Please all the replies and correspondence should be addressed to Examiner’s art unit 2629. Receipt is acknowledged of papers submitted on 06-14-2024 under new application; which have been placed of record in the file. Claims 1-8 and 10-14 are pending. Claims 9 and 15 are cancelled.
Response to Amendment
The preliminary amendments filed on 07-12-2024 does not introduce any new matter into the disclosure. The added material is supported by the original disclosure. Applicant has amended claims 1-4, 6, 8 and 10-13 as well as Cancelled dependent claims 9 and 15. Applicant has amended Claims to remove reference characters, eliminate multiple dependencies, and replace European-style claim phraseology with U.S.-style claim language in order to conform to the current USPTO practices.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged. Applicant has complied with one or more conditions for receiving the benefit of an earlier filing date under 35 U.S.C. . 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c).
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 07-12-2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
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 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.
Claim(s) 1-5, 7-8 and 10-14 is/are rejected under 35 U.S.C. 103 as being unpatentable over BAO Yuan et al. (US-20200380737-A1 IDS) hereinafter referenced as BAO et al. in view of Guo; Hongbin (US-20190350539-A1) hereinafter referenced as Guo.
Regarding Claim 1, BAO et al. discloses A computer-implemented method of processing projection data generated by a computed tomography scanner (Para. 3), the computer-implemented method (para. 3, 12,) comprising: obtaining the projection data generated by the computed tomography scanner (para. 3, disclosing the method for improving the CT image quality may include obtaining single focal spot (SFS) data; paras. 37, 44, fig. 5, disclosing In 510, SFS data may be obtained); processing the projection data using a machine-learning algorithm configured to perform a super-resolution imaging technique on the projection data, to increase the apparent sampling of the projection data in at least one dimension (para. 3, disclosing generating a corresponding optimized image by processing the SFS data based on an image quality optimization model, The image quality optimization model may be a machine learning model, The image quality optimization model may be a machine learning model; paras. 37, 44, disclosing optimize the SFS scan data or image acquired by the CT device in the SFS state to achieve an effect of the FFS image, so as to improve a resolution of the SFS image and reduce artifacts of the SFS image, thereby improving the image quality}; and outputting the processed projection data (para.46, fig. 5, disclosing In 520, a corresponding optimized image may be generated by processing the SFS data based on the image quality optimization Model; wherein: the machine-learning algorithm is trained using a training dataset, the training) dataset comprising: an input training dataset formed of a plurality of input training data entries that each comprise low resolution projection data of an imaged subject (Para.. 50 disclosing the training samples may include the FFS scan data and corresponding SFS scan data; further, para.2 disclosing if the imaging quality of the SFS X-ray tube is improved such that it can match the imaging quality of a flying and an output training dataset formed of a plurality of output training data entries, each output training data entry corresponding to a respective input training data entry (para. 50, fig. 6. Disclosing, In 610, a plurality of FFS images or FFS scan data may be obtained as training samples) and comprising high resolution projection data of the same imaged subject of the respective input training data entry; wherein the high resolution projection data of each output training data entry is generated by a training computed tomography scanner that generates high resolution projection data by: using a dual focal spot acquisition technique to generate the intermediate data, the intermediate data comprising interleaved first sample sets and second sample sets, each sample set obtained using a different focal spot (paras. 2, 38 disclosing flying focal spot (FFS) X-ray tubes. By using the FFS X-ray tube, the amount of data acquired by a CT detector can be improved, and the imaging quality at a focusing region is usually better than the imaging quality at a non-focusing region. Thus, the FFS X-ray tube may improve the imaging quality of a CT image; further, the interleaved sample sets is well-known feature in the context of implementing the FFS in CT); and performing parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data, and wherein the low resolution projection data is generated by discarding the first sample sets or the second sample sets of the intermediate data (please notice the parallel binning is a standard feature and well known feature in implementation of FFS, also at paras. 55-56 discloses low resolution image data from the source domain, X, and high-resolution image data from the target domain, Y, that are not paired, i.e., are not matched (or intermediate data discarded) Further at para. 50 disclosing, the SFS image may be generated by reconstructing projection data obtained by a detector for odd times or even times (interleaving). For a CT device in the multifocal spot state, scan data of one of multiple focal spots may be obtained and reconstructed to generate the SFS image).
However, BAO et al. fails to recite parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data.
However, prior art of Guo discloses parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data (paras. 45-47 discloses two sets of FFS parallel binning on the interleaved data and paras. 5,-6 discloses FFS data do generate the high resolution projection data, para. 12 discloses the reconstruction of FFS data is performed without combining the first dataset and the second dataset into one dataset with a single geometry from which the image reconstruction is performed to achieve high resolution).
BAO et al. teaches The method for improving the CT image quality may include obtaining single focal spot (SFS) data. The SFS data may include single focal spot (SFS) scan data or a single focal spot (SFS)SFS image. The SFS scan data may be acquired by a CT device in a single focal spot (SFS) state. The SFS image may be generated by reconstructing scan data obtained by the CT device via scanning in the SFS state
BAO et al. teaches the image quality optimization model may be generated through sample data training. The sample data may include flying focal spot (FFS) scan data or a flying focal spot (FFS) image. The FFS scan data may be acquired by a CT device in a flying focal spot (FFS) state. The FFS image may be reconstructed based on scan data acquired by the CT device via scanning in the FFS state The image quality optimization model may be a machine learning model. Simulating the SFS image as an FFS image using a deep neural network model..
Guo teaches parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data.
BAO et al. does not teach parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data.
Hence the prior art includes each element claimed, although not necessarily in a single prior art reference, with the only difference between the claimed invention and the prior art being the lack of actual combination of the elements in a single prior art reference.
In combination, BAO et al. performs the same function as it does separately of managing process of generating high resolution image by not to pair the high resolution and low resolution projected data.
Guo performs two sets of FFS data rea parallel binning on the interleaved data and the reconstruction of FFS data is performed without combining the first dataset and the second dataset into one dataset with a single geometry from which the image reconstruction is performed to achieve high resolution
Therefore one of ordinary skill in the art could have combined the elements as claimed by known methods, and that in combination, each element merely performs the same function as it does separately.
The results of the combination would have been predictable and resulted in modifying the invention of BAO et al. to include parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data., as disclosed by Guo thereby reducing artifacts for z-flying focal spot in computed tomography (CT) system as Guo discusses at para. 1.
Therefore, the claimed subject matter would have been obvious to a person having ordinary skill in the art at the time the invention was made.
Regarding Claim 2, BAO et al. discloses the projection data is projection data generated by the computed tomography scanner using a dual focal spot acquisition approach (para. 39 disclosing FFS state may use an FFS X-ray tube to generate beams of a plurality of focal spot).
Regarding Claim 3, BAO et al. discloses the machine-learning algorithm is further trained using a modified training dataset, the modified training data set comprising: a modified input training dataset, in which noise is added to the low resolution projection data of each input training data entry of the training dataset; and the output training dataset of the training dataset (paras. 55-57 disclosing a trained machine learning model. Training samples may be high-frequency image data of a certain count of FFS images and high-frequency image data of SFS images, which noise is added to the low resolution projection data of each input training data entry of the training dataset).
Regarding Claim 4, BAO et al. discloses the machine-learning algorithm is further trained using a second training dataset, the second training dataset comprising: a second input training dataset formed of a plurality of second input training data entries that each comprise low-resolution image data of a scene; and a second output training dataset formed of a plurality of second output training data entries, each second output training data entry corresponding to a respective second input training data entry, and comprising high-resolution image data of the same scene of the respective second input training data entry (para. 38, further Para. 50, discloses regards the technique of super resolution applied to the reconstructed CT images and would be obvious for a skilled person to apply one of the plurality of super-resolution techniques known in the art to CT reconstructed images).
Regarding Claim 5, BAO et al. discloses the values of the low- resolution image data and the high-resolution image data are scaled to correspond to a range of possible values for projection data generated by the computed tomography scanner (paras.55-57 does disclose number of sample in high frequency (high resolution) and low frequency (low resolution)).
Regarding Claim 7, BAO et al. discloses A computer-implemented method of processing projection data generated by a computed tomography scanner (Para. 3), the computer-implemented method (para. 3, 12,) comprising: obtaining the projection data generated by the computed tomography scanner (para. 3, disclosing the method for improving the CT image quality may include obtaining single focal spot (SFS) data; paras. 37, 44, fig. 5, disclosing In 510, SFS data may be obtained); processing the projection data using a machine-learning algorithm configured to perform a super-resolution imaging technique on the projection data, to increase the apparent sampling of the projection data in at least one dimension (para. 3, disclosing generating a corresponding optimized image by processing the SFS data based on an image quality optimization model. The image quality optimization model may be a machine learning model; paras. 37, 44, disclosing optimize the SFS scan data or image acquired by the CT device in the SFS state to achieve an effect of the FFS image, so as to improve a resolution of the SFS image and reduce artifacts of the SFS image, thereby improving the image quality}; and outputting the processed projection data (para.46, fig. 5, disclosing In 520, a corresponding optimized image may be generated by processing the SFS data based on the image quality optimization Model; wherein: the machine-learning algorithm is trained using a training dataset, the training) dataset comprising: an input training dataset formed of a plurality of input training data entries that each comprise low resolution projection data of an imaged subject (Para.. 50 disclosing the training samples may include the FFS scan data and corresponding SFS scan data; further, para.2 disclosing the imaging quality of the SFS X-ray tube is improved such that it can match the imaging quality of a flying focal spot (FFS) image, the quality of a single focal spot (SFS) image may be greatly improved); and an output training dataset formed of a plurality of output training data entries, each output training data entry corresponding to a respective input training data entry (para. 50, fig. 6. Disclosing, In 610, a plurality of FFS images or FFS scan data may be obtained as training samples) and comprising high resolution projection data of the same imaged subject of the respective input training data entry; wherein the high resolution projection data of each output training data entry is generated by a training computed tomography scanner that generates high resolution projection data by: using a dual focal spot acquisition technique to generate the intermediate data, the intermediate data comprising interleaved first sample sets and second sample sets, each sample set obtained using a different focal spot (paras. 2, 38 disclosing flying focal spot (FFS) X-ray tubes. By using the FFS X-ray tube, the amount of data acquired by a CT detector can be improved, and the imaging quality at a focusing region is usually better than the imaging quality at a non-focusing region. Thus, the FFS X-ray tube may improve the imaging quality of a CT image; further, the interleaved sample sets is well-known feature in the context of implementing the FFS in CT); and performing parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data, and wherein the low resolution projection data is generated by discarding the first sample sets or the second sample sets of the intermediate data (please notice the parallel binning is a standard feature and well known feature in implementation of FFS, also at paras. 55-56 discloses low resolution image data from the source domain, X, and high-resolution image data from the target domain, Y, that are not paired, i.e., are not matched (or intermediate data discarded) Further at para. 50 disclosing, the SFS image may be generated by reconstructing projection data obtained by a detector for odd times or even times (interleaving). For a CT device in the multifocal spot state, scan data of one of multiple focal spots may be obtained and reconstructed to generate the SFS image).
However, BAO et al. fails to recite parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data.
However, prior art of Guo discloses parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data (paras. 45-47 discloses two sets of FFS parallel binning on the interleaved data and paras. 5,-6 discloses FFS data do generate the high resolution projection data, para. 12 discloses the reconstruction of FFS data is performed without combining the first dataset and the second dataset into one dataset with a single geometry from which the image reconstruction is performed to achieve high resolution).
BAO et al. teaches The method for improving the CT image quality may include obtaining single focal spot (SFS) data. The SFS data may include single focal spot (SFS) scan data or a single focal spot (SFS)SFS image. The SFS scan data may be acquired by a CT device in a single focal spot (SFS) state. The SFS image may be generated by reconstructing scan data obtained by the CT device via scanning in the SFS state.
BAO et al. teaches the image quality optimization model may be generated through sample data training. The sample data may include flying focal spot (FFS) scan data or a flying focal spot (FFS) image. The FFS scan data may be acquired by a CT device in a flying focal spot (FFS) state. The FFS image may be reconstructed based on scan data acquired by the CT device via scanning in the FFS state The image quality optimization model may be a machine learning model. Simulating the SFS image as an FFS image using a deep neural network model..
Guo teaches parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data.
BAO et al. does not teach parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data.
Hence the prior art includes each element claimed, although not necessarily in a single prior art reference, with the only difference between the claimed invention and the prior art being the lack of actual combination of the elements in a single prior art reference.
In combination, BAO et al. performs the same function as it does separately of managing process of generating high resolution image by not to pair the high resolution and low resolution projected data.
Guo performs two sets of FFS data rea parallel binning on the interleaved data and the reconstruction of FFS data is performed without combining the first dataset and the second dataset into one dataset with a single geometry from which the image reconstruction is performed to achieve high resolution
Therefore one of ordinary skill in the art could have combined the elements as claimed by known methods, and that in combination, each element merely performs the same function as it does separately.
The results of the combination would have been predictable and resulted in modifying the invention of BAO et al. to include parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data., as disclosed by Guo thereby reducing artifacts for z-flying focal spot in computed tomography (CT) system as Guo discusses at para. 1.
Therefore, the claimed subject matter would have been obvious to a person having ordinary skill in the art at the time the invention was made.
Regarding Claim 8, BAO et al. discloses where the step of generating an output training dataset further comprises controlling the training computer tomography using a dual focal spot acquisition technique to generate the intermediate data (para.44, disclosing two focal spots acquisition technique to generate the intermediate data, para. 39 disclosing FFS state may use an FFS X-ray tube to generate beams of a plurality of focal spot).
Regarding Claim 10, BAO et al. discloses A processing system for processing projection data generated by a computed tomography scanner (paras. 3, 25-26, disclosing A processing system for processing projection data generated by a computed tomography scanner) the processing system comprising being configured to: a memory that stores a plurality of instructions; and a processor coupled to the memory and configured to execute the plurality of instructions to carry out a method (paras. 29-32, disclosing the processing system comprising being configured to: a memory that stores a plurality of instructions; and a processor coupled to the memory and configured to execute the plurality of instructions to carry out a method) comprising: obtaining the projection data generated by the computed tomography scanner (para. 3, disclosing the method for improving the CT image quality may include obtaining single focal spot (SFS) data; paras. 37, 44, fig. 5, disclosing In 510, SFS data may be obtained); processing the projection data using a machine-learning algorithm configured to perform a super-resolution imaging technique on the projection data, to increase the apparent sampling of the projection data in at least one dimension (para. 3, disclosing generating a corresponding optimized image by processing the SFS data based on an image quality optimization model. The image quality optimization model may be a machine learning model; paras. 37, 44, disclosing optimize the SFS scan data or image acquired by the CT device in the SFS state to achieve an effect of the FFS image, so as to improve a resolution of the SFS image and reduce artifacts of the SFS image, thereby improving the image quality}; and outputting the processed projection data (para.46, fig. 5, disclosing In 520, a corresponding optimized image may be generated by processing the SFS data based on the image quality optimization Model; wherein: the machine-learning algorithm is trained using a training dataset, the training) dataset comprising: an input training dataset formed of a plurality of input training data entries that each comprise low resolution projection data of an imaged subject (Para.. 50 disclosing the training samples may include the FFS scan data and corresponding SFS scan data; further, para.2 disclosing if the imaging quality of the SFS X-ray tube is improved such that it can match the imaging quality and an output training dataset formed of a plurality of output training data entries, each output training data entry corresponding to a respective input training data entry (para. 50, fig. 6. Disclosing, In 610, a plurality of FFS images or FFS scan data may be obtained as training samples) and comprising high resolution projection data of the same imaged subject of the respective input training data entry; wherein the high resolution projection data of each output training data entry is generated by a training computed tomography scanner that generates high resolution projection data by: using a dual focal spot acquisition technique to generate the intermediate data, the intermediate data comprising interleaved first sample sets and second sample sets, each sample set obtained using a different focal spot (paras. 2, 38 disclosing flying focal spot (FFS) X-ray tubes. By using the FFS X-ray tube, the amount of data acquired by a CT detector can be improved, and the imaging quality at a focusing region is usually better than the imaging quality at a non-focusing region. Thus, the FFS X-ray tube may improve the imaging quality of a CT image; further, the interleaved sample sets is well-known feature in the context of implementing the FFS in CT); and performing parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data, and wherein the low resolution projection data is generated by discarding the first sample sets or the second sample sets of the intermediate data (please notice the parallel binning is a standard feature and well known feature in implementation of FFS, also at paras. 55-56 discloses low resolution image data from the source domain, X, and high-resolution image data from the target domain, Y, that are not paired, i.e., are not matched (or intermediate data discarded) Further at para. 50 disclosing, the SFS image may be generated by reconstructing projection data obtained by a detector for odd times or even times (interleaving). For a CT device in the multifocal spot state, scan data of one of multiple focal spots may be obtained and reconstructed to generate the SFS image).
However, BAO et al. fails to recite parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data.
However, prior art of Guo discloses parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data (paras. 45-47 discloses two sets of FFS parallel binning on the interleaved data and paras. 5,-6 discloses FFS data do generate the high resolution projection data, para. 12 discloses the reconstruction of FFS data is performed without combining the first dataset and the second dataset into one dataset with a single geometry from which the image reconstruction is performed to achieve high resolution).
BAO et al. teaches The method for improving the CT image quality may include obtaining single focal spot (SFS) data. The SFS data may include single focal spot (SFS) scan data or a single focal spot (SFS)SFS image. The SFS scan data may be acquired by a CT device in a single focal spot (SFS) state. The SFS image may be generated by reconstructing scan data obtained by the CT device via scanning in the SFS state
BAO et al. teaches the image quality optimization model may be generated through sample data training. The sample data may include flying focal spot (FFS) scan data or a flying focal spot (FFS) image. The FFS scan data may be acquired by a CT device in a flying focal spot (FFS) state. The FFS image may be reconstructed based on scan data acquired by the CT device via scanning in the FFS state The image quality optimization model may be a machine learning model. Simulating the SFS image as an FFS image using a deep neural network model..
Guo teaches parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data.
BAO et al. does not teach parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data.
Hence the prior art includes each element claimed, although not necessarily in a single prior art reference, with the only difference between the claimed invention and the prior art being the lack of actual combination of the elements in a single prior art reference.
In combination, BAO et al. performs the same function as it does separately of managing process of generating high resolution image by not to pair the high resolution and low resolution projected data.
Guo performs two sets of FFS data rea parallel binning on the interleaved data and the reconstruction of FFS data is performed without combining the first dataset and the second dataset into one dataset with a single geometry from which the image reconstruction is performed to achieve high resolution
Therefore one of ordinary skill in the art could have combined the elements as claimed by known methods, and that in combination, each element merely performs the same function as it does separately.
The results of the combination would have been predictable and resulted in modifying the invention of BAO et al. to include parallel binning on the interleaved first sample sets and second sample sets to generate the high resolution projection data., as disclosed by Guo thereby reducing artifacts for z-flying focal spot in computed tomography (CT) system as Guo discusses at para. 1.
Therefore, the claimed subject matter would have been obvious to a person having ordinary skill in the art at the time the invention was made.
Regarding Claim 11, BAO et al. discloses the projection data is projection data generated by the computed tomography scanner using a dual focal spot acquisition approach (para. 39 disclosing FFS state may use an FFS X-ray tube to generate beams of a plurality of focal spot).
Regarding Claim 12, BAO et al. discloses the machine-learning algorithm is further trained using a modified training dataset, the modified training data set comprising: a modified input training dataset, in which noise is added to the low resolution projection data of each input training data entry of the training dataset; and the output training dataset of the training dataset (paras. 55-57 disclosing a trained machine learning model. Training samples may be high-frequency image data of a certain count of FFS images and high-frequency image data of SFS images, which noise is added to the low resolution projection data of each input training data entry of the training dataset).
Regarding Claim 13, BAO et al. discloses the machine-learning algorithm is further trained using a second training dataset, the second training dataset comprising: a second input training dataset formed of a plurality of second input training data entries that each comprise low-resolution image data of a scene; and a second output training dataset formed of a plurality of second output training data entries, each second output training data entry corresponding to a respective second input training data entry, and comprising high-resolution image data of the same scene of the respective second input training data entry (para. 38, further Para. 50, discloses regards the technique of super resolution applied to the reconstructed CT images and would be obvious for a skilled person to apply one of the plurality of super-resolution techniques known in the art to CT reconstructed images).
Regarding Claim 14, BAO et al. discloses the values of the low- resolution image data and the high-resolution image data are scaled to correspond to a range of possible values for projection data generated by the computed tomography scanner (paras.55-57 does disclose number of sample in high frequency (high resolution) and low frequency (low resolution)).
Allowable Subject Matter
Claim 6 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
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Applicant is requested review cited prior art cited on USPTO 892.
The prior art of Pichumani; Ramani et al. (US 20230127194 A1) disclosure; paras. 37-115, disclosing, metrology applications based on 3D imaging modalities, sample throughput is a critical factor that impacts the cost and viability of a given modality. When performing measurements on structures found in 3D reconstructed tomographic data or with 2D cross sectional images of such data (e.g., X-ray CT data), it is not known a priori the exact number of projection images that need to be acquired for a given sample to achieve a specified level of imaging accuracy. If too few projection images are acquired, the measurements will be inaccurate due to poor signal to noise ratio (SNR) and large imaging artifacts. If too many projections are acquired, then the data acquisition time becomes unacceptable. As identified during the invention as disadvantageous, prior art methods derive the projection count based on worst case accuracy requirements from experimental measurements and theoretical calculations. As was further recognized, these ad hoc and quasi-systematic approaches suffer from the drawback that they can't account for all possible variations of imaging parameters such as beam energy, and sample object attributes such as size, geometry, density, topology, and composition. As a result, the number of acquired images in the prior art is over-specified to meet the worst-case SNR and contrast to noise ratio (CNR) profiles of known sample types and measurement types. This results in longer image acquisition times to guarantee a minimum accuracy level. These disadvantages and drawbacks are avoided by the invention. In particular, no additional margin needs to be built-in to account for unknown variations of these sampling parameters that occur in real world scenarios. For example, it can be exploited that measuring the volume of a large moderately dense object may require an order of magnitude fewer projection images than measuring the critical dimension of a fine wisp-like structure. [0005] In particular, it has been found that in the first acquisition of a raw 2D set a relatively small number of raw sample planes may be used. Such limited number of raw sample planes can be very small, e.g. 2, or can be larger than 2, e.g. 2 to 4, or can be larger than 5, larger than 10, can be in the range between 15 and 20 raw sample planes or can be larger. As a rule, such number of raw sample planes used in acquiring the first raw 2D set is smaller than 100 or smaller than 50. Such limited number of raw sample planes can depend on the complexity of the sample structure to be imaged. As a rule, a lower complex sample structure, e.g. a spherical structure, would require a lower number and more complex structure, e.g. a cube or a copper micropillar interconnect, requires a larger number of raw sample planes. [0006] An example for the measurement parameter which is extracted during the method is the volume of a certain sample structure or of a plurality of selected sample structures or sample areas. As a rule, the height, the width and/or the depth of a sample structure is an example for the measurement parameter to be extracted during the method. Sample structures to be imaged can be a bond line, a pad alignment and/or an extruded solder, in particular of a microbonded semiconductor device. In particular, pad alignment of copper micropillar pads and/or a pad width can be checked with the imaging method. Extracting the measurement parameter can be done in particular by help of a calculation step using a 3D reconstruction algorithm. The iterative repetition of the steps "calculating," "extracting" and "assigning" can be done with a certain number of iteration steps. Such number can be in the range between 2 and 10, in particular in the range between 2 and 8 or in the range between 3 and 5. The number of sample planes can increase between subsequent iteration steps by, e.g., 20% to 200%. A typical sequence of sample plane numbers in a sequence of five iteration steps can be 20, 40, 60, 80 and 100. In the first step of acquiring the raw 2D set, in this example 20 raw sample planes were used and in the subsequent iteration steps 40, 60, 80 and 100 sample planes. The progression of sample plane numbers during the subsequent iteration steps can be arithmetic rather than geometric. An example for the convergence criterion used in the method is a criterion derived from the comparison of a normalized difference of an average measured value of the last N iterations with an average value of the previous N iterations. N can be in the range between 1 and 5 and can be at least 2. For repetitive sample measurements, the algorithm can be accelerated by recording the projection set sizes for a predetermined set of samples and use the median or max as a starting seed value. This seed value could also be used as a fixed set size for all samples if the variation is minimal. A repetition of acquisitions can take place at previously acquired sample planes in order to reduce a noise at a respective sample plane angle by averaging multiple images at this given angle. An acquisition at a specific sample plane can take place with a specific acquisition time. Such acquisition times can differ to reduce noise where appropriate. For instance, shallow near-planar sample planes close to a value of 0 degrees can be acquired with a longer exposure time in order to reduce the noise in the respective images.
The Prior art of Ziabari; Amir et al. (US 20220035961 A1) disclosure; paras. 42-118, disclosing, an artifact reduction artificial intelligence training system for computed tomography (CT) of an object of interest. The system includes a computer-aided design (CAD) model representing the object of interest, stored in memory, an artifact characterization, stored in memory, along with one or more computer subsystems and components executed by the one or more computer subsystems. The components include a CT simulator to generate CT simulated projections based on the CAD model. Some of the CT simulated projections include simulated artifacts based on the artifact characterization and some do not. That is, the same simulation is performed twice: once to produce projections with artifacts and once to produce projections without artifacts. These simulations can be used as pairs of inputs to a deep learning network which attempts to learn the non-linear mapping between the projections with artifacts and the projections without artifacts, thereby learning to reduce such artifacts. A deep learning component can also be included that is configured to train a deep learning artifact reduction model based on the CT simulated projections and generate a set of deep learning artifact reduction model parameters. The trained model can be deployed and applied to real CT scan data to reduce artifacts in CT reconstructed images. CAD models of various geometries are simulated with various defects and various artifacts. The artifacts can be simulated based on calibration or physics-based modeling. For example, beam hardening parameter estimation of materials can be utilized in some embodiments to simulate beam hardening artifacts for training purposes. Simulation of CT utilizing the CAD models and the calibration and/or physics-based artifact models are used to generate synthetic training data sets. The synthetic training sets are used to train a deep learning module. The deep learning-based approach can be modular, meaning it is not limited to the network employed/demonstrated in this disclosure. A model trained on synthetic data can be tested or deployed on real (measured) data sets. Accordingly, high quality CT reconstructions can be provided that leverage CAD models with simulated defects/artifacts and synthetically trained AI. Computed tomography enables non-destructive evaluation including flaw or defect detection and inspection, failure analysis, and assembly analysis in advanced manufacturing, automotive, aerospace, and casting industries, as well as other industries. CT of thick dense parts, such as metal parts, is especially challenging due to the effect called beam-hardening that produces artifacts in the images reconstructed by standard algorithms. Beam hardening complicates the process of detection of defects (e.g., pores, cracks, and inclusions) in CT images; which in turn adversely impacts qualification of manufactured parts. The present disclosure provides a system and method for improving CT resolution by suppressing, reducing, or removing artifacts, such as beam hardening and detector noise artifacts. Embodiments of the system and method can also reduce CT scan time, thus lowering associated labor and costs.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PRABODH M DHARIA whose telephone number is (571)272-7668. The examiner can normally be reached Monday -Friday 9:00 AM to 5:30 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.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Benjamin Lee can be reached on 571-272-2963. 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.
Any response to this action should be mailed to:
Commissioner of Patents and Trademarks
P.O. Box 1450
Alexandria VA 22313-1450
/Prabodh M Dharia/
Primary Examiner
Art Unit 2629
02-17-2026