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 statement (IDS) submitted on 09/20/2024 is being considered by the examiner.
Claim Rejections - 35 USC § 102
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 (i.e., changing from AIA to pre-AIA ) 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.
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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-9 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Koehler (US 20210217140 A1).
Regarding claim 1, Koehler discloses (a) accessing medical image data with a computer system ([0020] An object of interest, such as a patient or an organ within a patient, is medically scanned using a CT device 1 to generate CT image data 10.);
(b) applying a noise reduction algorithm to the medical image data using the computer system, generating output as noise-reduced medical image data (abstract: In a method and system for reconstructing computed tomography image data in which CT image data is de-noised.);
(c) generating simulated ensemble data from the medical image data by using the computer system to insert noise to the noise-reduced medical image data (abstract: In a method and system for reconstructing computed tomography image data in which CT image data is de-noised. Then simulated noise is added,);
(d) applying the noise reduction algorithm to the simulated ensemble data using the computer system, generating output as noise-reduced simulated ensemble data (abstract: Then simulated noise is added, followed by another de-noising step to estimate the bias.);
(e) generating an uncertainty measurement map from the noise-reduced medical image data and the noise-reduced simulated ensemble data, the uncertainty measurement map quantifying an uncertainty of noise reduction in the noise-reduced medical image data (abstract: Then, the estimated bias information is used to correct the original de-noised image data to arrive at second pass image data.); and
(f) displaying the noise-reduced medical image data and the uncertainty measurement map to a user ([0027] As such, the second pass image data 15 provides an improved input for image analysis by a physician or further processing steps, for instance to generate a quantitative image.).
Regarding claim 2, Koehler discloses wherein the medical image data comprise computed tomography (CT) image data ([0018] The present invention is illustrated using dual-energy CT image data, but the invention is equally relevant for spectral and other multi-energy CT image data.).
Regarding claim 3, Koehler discloses wherein the CT image data consists of a single CT image ([0020] The object of interest is normally positioned on a support 3, which is translated through the examination area 6 during a scan to obtain slices of CT image data 10 of the object of interest. In multi-energy image data various types of image information may be obtained. For instance, in FIG. 1, for each step two images are shown obtained by dual energy CT image acquisition, one represents the contribution of the photo-electric effect, the other the contribution of Compton-scattering to the total x-ray attenuation.).
Regarding claim 4, Koehler discloses wherein the uncertainty measurement map comprises a bias map ([0016] FIG. 4 shows a bias comparison of the present invention with a state-of-the-art method.).
Regarding claim 5, Koehler discloses wherein the bias map is computed as a difference between the noise-reduced medical image data and an average of the noise-reduced simulated ensemble data ("[0025] The determined bias of the de-noised simulated images itself suffers from noise. In order to reduce this noise, biases may be calculated from an ensemble of simulated noise image data 12, each being processed to generate an ensemble of de-noised simulated image data 104 and a representative value of the bias information of the de-noised simulated image data may be determined, e.g. by taking the mean value or a weighted average of the biases.
[0026] The determined bias information of the de-noised simulated image data is then used as input to estimate 105 bias information 105 of the first pass image data 11. In a good approximation, the bias information 14 of the first pass image data 11 is estimated 106 to be the same as the bias information of the de-noised simulated image data 13. If it is known that areas of the bias information of the de-noised simulated image data 13 are under- or overestimated, this may be taken into account in the estimation 106.").
Regarding claim 6, Koehler discloses wherein the uncertainty measurement map comprises a dispersion map ([0006] The initial noise data preferably includes noise relevant parameters, such as local noise variance estimates, noise power spectrum, correlation coefficient, filters used, slice thickness, or estimates thereof. These parameters are readily available or derived from the image data or scan settings.).
Regarding claim 7, Koehler discloses wherein the dispersion map is computed as a pixel-wise standard deviation amongst the noise-reduced simulated ensemble data ([0023] In the first additional step of the presently claimed reconstruction method artificial noise data is added 103 to the first pass image data 11 to obtain simulated image data 12. Noise characteristics of the artificial noise data are similar to that of the initial noise data, such as similar standard deviation, correlation, spatial variation, or combinations of some or all of these.).
Regarding claim 8, Koehler discloses wherein the uncertainty measurement map comprises both a bias map and a dispersion map ("[0006] The initial noise data preferably includes noise relevant parameters, such as local noise variance estimates, noise power spectrum, correlation coefficient, filters used, slice thickness, or estimates thereof. These parameters are readily available or derived from the image data or scan settings.
[0007] The bias information of the de-noised simulated image data is preferably determined by subtracting the de-noised simulated image data from the first pass image data.").
Regarding claim 9, Koehler discloses generating corrected noise-reduced medical image data with the computer system by correcting the noise-reduced medical image data for the uncertainty of noise reduction in the noise-reduced medical image data using the uncertainty measurement map ([0027] In the final step, the first pass image data 11 is corrected 107 based on the estimated bias information 14 of the first pass image data 11 to generate second pass image data 15. The most straightforward way to achieve this is by subtracting the estimated bias information 14 of the first pass image data 11 from the first pass image data 11.); and
displaying the noise-reduced medical image data and the uncertainty measurement map to the user comprises displaying the corrected noise-reduced medical image data to the user ([0027] As said estimated bias information 14 provides an improved indication of the actual bias, the second pass image data 15 is better de-noised and therefore closer to the ‘true’ situation. As such, the second pass image data 15 provides an improved input for image analysis by a physician or further processing steps, for instance to generate a quantitative image.).
Claim Rejections - 35 USC § 103
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 (i.e., changing from AIA to pre-AIA ) 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.
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.
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(s) 10-17, 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Koehler (US 20210217140 A1) and further in view of Langoju (US 20230029188 A1).
Regarding claims 10 and 19, Koehler does not explicitly disclose but in a similar field of endeavor of noise reduction, Lanoju teaches wherein the noise reduction algorithm is a convolutional neural network-based noise reduction algorithm ([0061] In some embodiments, the noise reduction neural network may include one or more convolutional layers, which in turn comprise one or more convolutional filters (e.g., a convoluted neural network architecture).).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine the known system of noise reduction with uncertainty measurement, as disclosed by Koehler, with the known teaching of machine learning, as taught by Langoju, in order to yield the predictable results of improving image clarity while protecting diagnostic accuracy, as well as tracking and reducing systematic errors so the output images remain clinically reliable.
Claim 11 is rejected as the same way as the discussion for claim 1 above, with the additional limitations (underlined and italicized below) of using machine learning for uncertainty measurement. The additional limitations are taught by Langoju:
(b) accessing a machine learning algorithm with the computer system, wherein the machine learning algorithm has been trained on training data to estimate an uncertainty measurement from a noise-reduced medical image ([0061] In some embodiments, the noise reduction neural network may include one or more convolutional layers, which in turn comprise one or more convolutional filters (e.g., a convoluted neural network architecture).);
(d) generating an uncertainty measurement map using the computer system by applying the noise-reduced medical image data to the machine learning algorithm, generating output as the uncertainty measurement map ([0064] The weights and biases of the noise reduction neural network may be adjusted based on a difference between the output image and the target (e.g., ground truth) image of the relevant image pair. The difference (or loss), as determined by the loss function, may be back-propagated through the neural learning network to update the weights (and biases) of the convolutional layers.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine the known system of noise reduction with uncertainty measurement, as disclosed by Koehler, with the known teaching of machine learning, as taught by Langoju, in order to yield the predictable results of improving image clarity while protecting diagnostic accuracy, as well as tracking and reducing systematic errors so the output images remain clinically reliable.
Claims 12-16 will be rejected the same way as the discussions above for claims 2-4, 6, and 8.
Claim 2 (similar to claim 12), 3 (similar to claim 13), 4 (similar to claim 14), 6 (similar to claim 15), and claim 8 (similar to claim 16).
Regarding claim 17, Koehler does not explicitly disclose but Langoju teaches 17. The method of claim 11, wherein the machine learning algorithm is trained using a probability loss ([0028] In some embodiments, training module 110 includes instructions for implementing one or more gradient descent algorithms, applying one or more loss functions, and/or training routines, for use in adjusting parameters of the one or more neural networks of neural network module 108.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine the known system of noise reduction with uncertainty measurement, as disclosed by Koehler, with the known teaching of machine learning, as taught by Langoju, in order to yield the predictable results of improving image clarity while protecting diagnostic accuracy, as well as tracking and reducing systematic errors so the output images remain clinically reliable.
Regarding claim 20, Koehler discloses (Fig. 4 and [0027] As said estimated bias information 14 provides an improved indication of the actual bias, the second pass image data 15 is better de-noised and therefore closer to the ‘true’ situation. As such, the second pass image data 15 provides an improved input for image analysis by a physician or further processing steps, for instance to generate a quantitative image.).
Koehler does not explicitly disclose but Langoju teaches wherein the machine learning algorithm implements the noise reduction algorithm, such that the output of the machine learning algorithm comprises both the noise-reduced medical image data and the uncertainty measurement map ([0064] The weights and biases of the noise reduction neural network may be adjusted based on a difference between the output image and the target (e.g., ground truth) image of the relevant image pair. The difference (or loss), as determined by the loss function, may be back-propagated through the neural learning network to update the weights (and biases) of the convolutional layers.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine the known system of noise reduction with uncertainty measurement, as disclosed by Koehler, with the known teaching of machine learning, as taught by Langoju, in order to yield the predictable results of improving image clarity while protecting diagnostic accuracy, as well as tracking and reducing systematic errors so the output images remain clinically reliable.
Claim(s) 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Koehler (US 20210217140 A1), in view of Langoju (US 20230029188 A1) and further in view of applicant provided NPL, Wu (Uncertainty Prediction for Deep Learning-based Image Denoising in Low-dose CT Imaging).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine the known system of noise reduction with uncertainty measurement using machine learning, as disclosed by Koehler and Lanoju, with the known teaching of gaussian probability loss, as taught by Wu, in order to yield the predictable results of simplifying optimization by distinguishing between random noise variance and systematic structural bias.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AHMED A NASHER whose telephone number is (571)272-1885. The examiner can normally be reached Mon - Fri 0800 - 1700.
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, Emily Terrell can be reached at (571) 270-3717. 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.
/AHMED A NASHER/ Examiner, Art Unit 2675
/EMILY C TERRELL/Supervisory Patent Examiner, Art Unit 2666
Prosecution Insights