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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 04/11/2026 has been entered.
Response to Arguments
Applicant's arguments filed 04/11/2026 have been fully considered but they are not persuasive.
Regarding Applicant’s arguments regarding Peemen does not teach “without generation of paired noisy and clean sub-images”, the Examiner respectfully disagrees. It is noted that Peemen teaches the pre-trained ANN 114 may be updated to fine tune the ANN 114 to the system specific noise in the training image pairs and no associated clean images will be used in updating the training of the ANN 114 ([0030]). Therefore, reading on the newly amended claim limitation of without paired noisy and clean sub-images.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitations are:
Similarity module, sample pair module, and training module in claims 11-20.
Because these claim limitations are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, they are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof. The corresponding structure are shown in Fig. 1 on the instant application.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claims contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventors, at the time the application was filed, had possession of the claimed invention. Specifically, newly added claim limitation of “without generation of paired noisy and clean sub-images” in claims 1 and 11. It is noted Applicants points to paragraph [0035] of US20230394631 for support. Paragraph [0035] states “Noise2Sim, may then be configured to train a deep network (i.e., deep ANN) without collecting paired noisy or clean target data” and therefore does not provide support for the step of “generation”.
Dependent claims 2-10 and 12-20 depends on rejected claims 1 and 11 and do not mitigate the deficiencies of the parent claims and therefore are also rejected.
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.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Peemen et al. (US 2020/0357097 A1 hereinafter Peemen) in view of Nia et al. (US 2022/0129791 hereinafter Nia) further in view of Image Denoising by Sparse 3-D Transform-Domain Collaborative filtering (IEEE Transactions on image processing, Vol. 16, No. 8, August 2007; Hereinafter Dabov).
As to claim 1 , Peemen teaches a method of training an artificial neural network (ANN) for denoising (method 200 for denoising images retrains or updates an ANN; [0036]), the method comprising: generating, by a similarity module (Pre-trained denoiser; 203 Fig. 2), a respective set of similar sub-images for each noisy input element of a number of noisy input elements included in a single noisy input data set including one or more noisy input images (the training of a pre-trained blind denoiser using only noisy images (training image pairs) that include noise similar to that of sample images needing denoised; [0020]), each noisy input element comprising information (clean image; [0020]) and noise (noisy image; [0020]); generating, by a sample pair module (Acquire training image pairs; 205 Fig. 2), a plurality of training sample pairs (acquiring training image pairs; [0038]), each training sample pair comprising a pair of selected similar elements corresponding to a respective noisy input element (each image in each image pair will have different noise and the number acquired may also be affected by a similarity of image noise used to pre-train the denoiser model; [0038]) without generation of paired noisy and clean sub-images (the pre-trained ANN 114 may be updated to fine tune the ANN 114 to the system specific noise in the training image pairs and no associated clean images will be used in updating the training of the ANN 114; [0030]); and training, by a training module (200 Fig. 2), an ANN (ANN; [0036]) using the plurality of training sample pairs (training image pairs; 205 Fig. 2), each set of similar elements generated prior to training the ANN (The performance of Pre-trained denoiser (203) may be performed in before process blocks 201 and 205; Fig. 2 and [0039]), the plurality of training sample pairs generated during training the ANN (205 occurs during the training process of 200; Fig. 2). However, Peemen does not explicitly teach wherein the training is unsupervised. Nia teaches that a natural way to achieve unsupervised training is with an autoencoder which is a type of ANN ([0155]), it would have been obvious for one ordinary skilled in the art at the time of filing to have used the unsupervised training of ANN with the ANN of Peemen in order to save human labor (Nia [0155]).
Peeman and Nia do not explicitly teach similar sub-images for each noisy input element of a number of noisy input elements included in a single noisy input data set including one or more noisy input images. Dabov teaches an image denoising method (Title) wherein grouping
similar 2-D fragments of the image (pg. 2081, Col.1, paragraph 3, lines 1-5) where each 2D fragments of the image contains noise (Fig. 1), therefore reading on the claimed similar sub-images. It would have been obvious for one ordinary skilled in the art at the time of filing to have combined the denoise training of an ANN process with Dabov’s method in order to reveals even the finest details shared by grouped fragments and at the same time it preserves the essential unique features of each individual fragment (Dabov pg. 2081 Col. 1, paragraph 2, lines 14-16).
As to claim 2 , Peemen, Nia and Dabov teach the method of claim 1, wherein at least some of the noise is independent (the pre-training may be done using any noisy images and do not need to be of the same sample type images; Peemen [0039]).
As to claim 3, Peemen, Nia and Dabov teach the method of claim 1, wherein at least some of the noise is correlated (However, the more similar the training images are to those acquired in process block 205 with respect to noise, the quicker the re-training or updating the denoiser may be; Peemen [0039]).
As to claim 4 , Peemen, Nia and Dabov teach a respective set of similar sub-images for each noisy input element of a number of noisy input elements included in a single noisy input data set (the training of a pre-trained blind denoiser using only noisy images (training image pairs) that include noise similar to that of sample images needing denoised; Peemen [0020]). Dabov however does not explicitly teach the similar elements (training data) comprises a number, k, nearest similar sub-image (Similarity between signal fragments is typically computed as the inverse of some distance measure. Hence, a smaller distance implies higher similarity. Various distance measures can be employed, such as the -norm of the difference between two signal fragments; pg. 2081, Col. 2, paragraph 2, lines 1-5).
As to claim 5 , Peemen, Nia and Dabov teach the method of claim 1, wherein the sub-images are each of a two-dimensional image patch containing a plurality of pixels within a larger image (2-D fragments of the image; Dabov pg. 2081, Col.1, paragraph 3, lines 1-5).
As to claim 6 , Peemen, Nia and Dabov teach the method of claim 1, further comprising randomly and independently selecting, by the sample pair module (Peemen 205 Fig. 2), each similar sub-image (2-D fragments of the image; Dabov pg. 2081, Col.1, paragraph 3, lines 1-5) in each pair (the pre-training may be done using any noisy images and do not need to be of the same sample type images in process block 205 or even have the same type of noise; Peemen [0039]).
As to claim 7 , Peemen, Nia and Dabov teach the method of claim 4, wherein the sub-images are each a three-dimensional image sub-volume containing a plurality of voxels (grouping
similar 2-D fragments of the image into 3-D data arrays; Dabov pg. 2081, paragraph 2, lines 3-4).
As to claim 8 , Peemen, Nia and Dabov teach the method of claim 1, wherein the noisy input data is selected from the group comprising: 2D microscopy images (charged particle microscope; Peemen [0023]), however the combination of Peemen, Nia and Dabov does not explicitly teach the rest of the types of sources for the noisy input data. Peemen teaches the ANN training environment is not limited to microscopy and Nia also alludes to their training data is related to patient medical history, it would have been obvious for one ordinary skilled in the art to gathered the noisy input data from a variety of sources such as those listed in the claim: two-dimensional (2D) natural images, three-dimensional (3D) low-dose (LD) CT (computed tomography) images, photon-counting micro-CT images, and four-dimensional (4D) spectral CT images, seismic data, and k-space data for magnetic resonance imaging (MRI) before the time of filing because both Peemen, Nia and Dabov’s machine learning techniques are within the medical imaging realm and there are limited possible techniques in which to gather images related to medical field.
As to claim 9 , Peemen, Nia and Dabov teach the method of claim 3, wherein each similar sub-image (training image pairs that include noise similar to that of sample images needing denoised; Peemen [0020]).
As to claim 10, Peemen, Nia and Dabov teach a computer readable storage device having stored thereon instructions that when executed by one or more processors result in the following operations comprising: the method according to claim 1 (Peemen Fig. 6 and [0057]).
As to claims 11-19, they differ from claims 1-9 in that they are system. Peemen, Nia and Dabov teach a training system (computer system; Peemen [0055]) for training an artificial neural network (ANN). The rest of the analysis will be the same as those in claims 1-9 above.
As to claim 20, Peemen, Nia and Dabov teach the system according to claim 11, wherein the ANN is a deep ANN (the ANN 114, which may also be referred to as a deep learning system, is a machine-learning computing system; Peemen [0034]).
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CLAIRE X WANG whose telephone number is (571)270-1051. The examiner can normally be reached M-F 9am-5pm.
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, Patricia Mallari can be reached at (571) 272-4729. 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.
CLAIRE X. WANG
Supervisory Patent Examiner
Art Unit 1774
/CLAIRE X WANG/Supervisory Patent Examiner, Art Unit 1774
Prosecution Insights