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 .
Detailed Action
This is a first action on the merits (FAOM) to this instant application in which claims 1-13 are pending. Claims 1, 10 and 11 are independent and claims 2-9 and 12-13 are dependent.
Drawing
The drawings are objected to because Fig. 2 and 4 are understood to be flow charts, each having boxes with only numbers. The boxes should be filled with descriptive language consistent with description provided in the specification so that on may follow the flow chart.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Objection
Claim 11 is objected to because of the following informalities: “The computer-implemented method” on line 1 of the claim (claim 11) should be replaced with - - A computer-implemented method- -.
Appropriate correction is required.
Rejection under 35 USC §102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. §102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
Claim 11 is rejected under 35 U.S.C. 102(a)(1) as being anticipated by Lebel (US-2020/0126190-A1).
Claim No
Claim feature
Prior art
Lebel (US-2020/0126190-A1)
11
The computer-implemented method for denoising an image, the method comprising the steps:
Lebel discloses a computer-implemented method for denoising an image, as claimed, see title, and Figs. 1-6 in Lebel.
providing an image,
providing an image (102)
providing a set of deep learning-based denoising models that are trained using different loss functions, wherein the loss functions differ by their respective weightings of variance and bias, wherein bias is a measure of the denoising model's capability to retain image details, and variance is a measure for the degree of noise reduction achieved by the denoising model,
providing a set of deep learning-based denoising models (110)1 that are trained using different loss functions, wherein the loss functions differ by their respective weightings of variance and bias, wherein bias is a measure of the denoising model's capability to retain image details, and variance is a measure for the degree of noise reduction achieved by the denoising model,
denoising the image using a denoising model which is selected interactively by a user from said set.
In Lebel, denoising the input image 102 by the deep learning models (110) is understood to be interactively selected by an operator.
Claims 1, 5-13 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Guidon (US-2022/0026516-A1).
Claim No
Claim feature
Prior art
Guidon (US-2022/0026516-A1)
1
A method of magnetic resonance (MR) imaging of an object positioned in the examination volume of an MR system,
Guidon discloses a method as claimed.
the method comprising the steps of:
a) subjecting the object to an imaging sequence comprising RF pulses and switched magnetic field gradients, whereby MR signals are generated,
b) acquiring the MR signals,
c) reconstructing a complex-valued MR image from the acquired MR signals,
d) denoising the MR image using a deep learning algorithm that operates on the real and the imaginary parts of the MR image, and
e) computing a magnitude MR image from the denoised complex-valued MR image.
Guidon discloses steps a) and b) as it discloses the imaging method being an MRI imaging method. An MRI imaging method typically includes steps a) and b) for acquiring MR signals and Guidon is understood to meet these steps.
Guidon reconstructs complex image, as stated in step c), from the acquired MR signals as it starts denoising a complex image using a deep learning algorithm.
Guidon meets step d) when it starts with a complex image2 for applying denoising algorithm in order to denoise the complex image.
Guidon meets step e) as it generates a magnitude image from a denoised complex image, see para [0057]3 in Guidon.
5
The method of claim 1, wherein the deep learning algorithm uses a convolutional neural network.
Guidon meets claim 5 as deep learning algorithm in Guidon includes CNN algorithm.
6
The method of claim 5, wherein the convolutional neural network is complex-valued.
Guidon meets claim 6 as CNN denoises complex image.
7
The method of claim 1, wherein the deep learning algorithm uses a set of denoising models that are trained using different loss functions.
Guidon meets claim 7 as denoising different image artifacts may be understood to require the deep learning denoising model to use different loss functions, see para [0069] in Guidon where it discusses use of loss functions.
8
The method of claim 7, wherein the loss functions differ by their respective weightings of variance and bias, wherein bias is a measure of the denoising model's capability to retain image details, and variance is a measure for the degree of noise reduction achieved by the denoising model.
Guidon meets claim 8, as different loss functions will have different weights, variances and capability to retain image details.
9
The method of claim 7, wherein one of the denoising models from said set is selected interactively by a user for denoising the MR image.
Guidon meets claim 9 as the invention in Guidon serves an operator who interactively selects what he/she wants from the system.
10
A computer-implemented method for denoising an image, the method comprising: providing a complex-valued image, denoising the image using a deep learning algorithm that operates on the real and the imaginary parts of the image, and computing a magnitude image from the denoised complex-valued image.
Claim 10 is met by Guidon. Subject matter of claim 10 is like that of claim 1 where claim 1 contains all features of claim 10.
A scope of claim 10 is broader than that of claim 1. See treatment of claim 1 above for claim 10.
11
The computer-implemented method for denoising an image, the method comprising the steps:
Guidon meets preamble of claim 11, as it describes a deep learning based denoising algorithm to be used to denoise an MRI image.
providing an image,
Guidon meets this claim feature as it starts denoising a complex image where the process requires an image that needs to be denoised.
providing a set of deep learning-based denoising models that are trained using different loss functions, wherein the loss functions differ by their respective weightings of variance and bias, wherein bias is a measure of the denoising model's capability to retain image details, and variance is a measure for the degree of noise reduction achieved by the denoising model,
Guidon meets this claim feature as it describes deep learning based denoising algorithm. The deep learning based denoising algorithm in Guidon comprises loss functions, see para [0069] in Guidon.
Loss functions in Guidon can be understood to comprise weighting, variances, and degree of noise reduction as claimed.
denoising the image using a denoising model which is selected interactively by a user from said set.
Guidon meets this claim feature as it can be understood that denoising the image involves an operator who interactively selects a denoising model to reflect intention of the operator.
12
A magnetic resonance (MR) system including at least one main magnet coil for generating a uniform, steady magnetic field (B.sub.0) within an examination volume, a number of gradient coils for generating switched magnetic field gradients in different spatial directions within the examination volume, at least one RF coil for generating RF pulses within the examination volume and/or for receiving MR signals from an object positioned in the examination volume, a control unit for controlling the temporal succession of RF pulses and switched magnetic field gradients, and a reconstruction unit for reconstructing MR images from the received MR signals, wherein the MR system is arranged to perform the method of claim 1.
Guidon meets claim 12 as it discloses a magnetic resonance imaging system which includes all features claimed in claim 12.
13
A computer program comprising instructions stored on a non-transitory computer readable medium which, when the program is executed by a computer, of an MR system, cause the computer to carry out the method of claim 1.
Guidon meets claim 13 as the system Guidon includes a computer which includes non-transitory storage memory which stores an operating software.
Allowable Subject Matter
Claims 2-4 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is an examiner’s statement of reasons for allowance:
As to dependent claim 2, the claim would be allowable if written in independent form because the prior art of the record neither discloses nor suggests the method of claim 1, wherein each of the real and the imaginary part is split into a high-frequency part and a low-frequency part prior to the denoising of the MR image.
Applied reference Guidon discloses using low-pass filter only after denoising but not prior to denoising.
As to dependent claims 3-4, these claims would be allowable if claim 2 is written in independent form.
Any comments considered necessary by applicant must be submitted no later than the payment of the issue fee and, to avoid processing delays, should preferably accompany the issue fee. Such submissions should be clearly labeled “Comments on Statement of Reasons for Allowance.”
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to G.M. HYDER whose telephone number is (571)270-3896. The examiner can normally be reached on M-F 9 AM- 5 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, Stephanie Bloss can be reached on (571) 272-3555. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
G.M. HYDER
Primary Examiner
Art Unit 2852
/G.M. A HYDER/Primary Examiner, Art Unit 2852
1 Examiner comment: The deep learning network 110 in Lebel applies denoising operation on the input image 102 and obtains images (104… 106) with various different artifacts. To obtain artifact images (104…106) having different artifacts, the deep learning denoising uses different loss functions wherein the loss functions can be understood to comprise weighting factors, bias and variance.
2 Examiner Comment: A complex image contains an imaginary part and real part to which the deep learning algorithm in Guidon is applied.
3 [0057] The pristine phase images may be used to improve image quality. For example, denoised complex images may be generated by multiplying the original magnitude images with the pristine phase images. Denoised magnitude images may be generated based on the denoised complex images. The denoised complex images and/or the denoised magnitude images may be input into downstream imaging processing and data processing.
Prosecution Insights