DETAILED 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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 02/21/2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
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 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.
Claims 1-5, 8-14 and 16-19 are rejected under 35 U.S.C. 103 as being unpatentable over Schaefferkoetter US PG-Pub(US 20230009528 A1) in view of Whiteley et al. ("FastPET: Near Real-Time Reconstruction of PET
Histo-Image Data Using a Neural Network").
Regarding Claim 1, Schaefferkoetter teaches a computer-implemented method comprising: receiving positron emission tomography (PET) measurement data from an image scanning system(¶[0005] discloses “In some embodiments, a computer-implemented method includes receiving positron emission tomography (PET) measurement data from an image scanning system” ); receiving co-modality measurement data from the image scanning system(¶[0009] discloses “The at least one processor is also configured to receive modality measurement data from the image scanning system.”);
generating a co-modality image based on the co-modality measurement data(¶[0065] discloses “At step 604, an anatomy image is generated based on the anatomy measurement data”, a modality image is generated based on modality/anatomy measurement data.);
applying a trained machine learning process to the PET image and the co- modality image (¶[0064] “Further, and at step 506, a neural network is trained based on the PET images and the corresponding anatomy images. For example, image scanning system 102 may train a neural network with the PET images and MR or CT images. At step 508, the trained neural network is stored in a data repository.”, ¶[0064] discloses the PET image and anatomy/modality images are used to train a neural network)and, based on the application of the trained machine learning process to the PET and the co-modality image, generating registered attenuation map data characterizing a registered attenuation map(¶[0066] “Proceeding to step 606, an initial attenuation map is determined based on the anatomy image. For example, transformation engine 402 of neural network engine 116 may generate an initial attenuation map 403 based on MR measurement data 103 (or CT measurement data 133). Further, and at step 608, a trained neural network is applied to the initial attenuation map and the PET image to generate an enhanced attenuation map. The neural network could have been trained in accordance with method 500, for example. As an example, registration engine 406 may register initial attenuation map 403 to PET image 115, and generate attenuation map 105 based on the registration.”, discloses using the modality image to generate an initial attenuation map and then taking the initial attenuation map with the PET image to generate a registered attenuation map. );
and storing the registered attenuation map data in a data repository (¶[0067] “At step 610, image volume data is generated based on the enhanced attenuation map and the PET image. The image volume data can identify and characterize an image volume (e.g., a 3D image volume). For example, image reconstruction system 104 can generate final image volume 191 based on attenuation maps 105 and corresponding PET image 115. At step 612, the final image volume is stored in a database.”, discloses using the attenuation map to create a final image volume that is stored in a database.).
However, Schaefferkoetter does not explicitly teach generating a histo-image based on the PET measurement data;
Whiteley teaches generating a histo-image based on the PET measurement data(Page 67, FastPET Reconstruction Architecture, Paragraph 1, “Fig. 1 illustrates the FastPET pipeline starting with the PET/CT scanner generating raw data in the form of PET list-mode events and CT-based attenuation maps, followed by conversion of the list-mode data into a histo-image by an MLAP histogrammer and ending with neural network-based reconstruction using the histo-image and the attenuation maps as input..”, discloses a histo-image is generated off PET data.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the claimed invention as taught by Schaefferkoetter with Whiteley in order to generate a histo-image based on the PET measurement data. One skilled in the art would have been motivated to modify Schaefferkoetter in this manner in order show that not only are the reconstructions very fast, but the images are high quality and have lower noise than iterative reconstructions. (Whiteley, Abstract)
Regarding Claim 2, the combination of Schaefferkoetter and Whiteley teach the computer-implemented method of claim 1, where Whiteley further teaches wherein applying the trained machine learning process to the histo-image and the co-modality image comprises inputting the histo-image and the co-modality image to a trained neural network. (Fig. 1. Shows that the histo-image and attenuation map is input into a trained neural network.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the claimed invention as taught by Schaefferkoetter with Whiteley in order to generate a histo-image based on the PET measurement data and inputting the histo-image with the modality image into a CNN. One skilled in the art would have been motivated to modify Schaefferkoetter in this manner in order show that not only are the reconstructions very fast, but the images are high quality and have lower noise than iterative reconstructions. (Whiteley, Abstract)
Regarding Claim 3, the combination of Schaefferkoetter and Whiteley teach the computer-implemented method of claim 2, where Whiteley further teaches further comprising: generating first feature vectors based on the histo-image (Fig. 2(b) shows the histo-image being processed through a first channel to generate a feature vector); generating second feature vectors based on the co-modality image(Fig. 2(b) shows the modality image being processed in the second channel to generate a second feature vector.); and inputting the first feature vectors and the second feature vectors into the trained neural network. (Fig. 2(a) shows the histo-image and modality image being inputted into the CNN to generate a final image volume.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the claimed invention as taught by Schaefferkoetter with Whiteley in order to generate feature vectors and input them into a neural network. One skilled in the art would have been motivated to modify Schaefferkoetter in this manner in order show that not only are the reconstructions very fast, but the images are high quality and have lower noise than iterative reconstructions. (Whiteley, Abstract)
Regarding Claim 4, the combination of Schaefferkoetter and Whiteley teach the computer-implemented method of claim 1, where Schaefferkoetter further teaches further comprising reconstructing a PET image based on the registered attenuation map data and the histo-image. (¶[0033], “The computing device then reconstructs an image volume based on the attenuation map and the reconstructed CT image. The computing device can store the image volume in a data repository.“ discloses reconstructed the PET image with the attenuation map to generate a final image volume.)
Regarding Claim 5, the combination of Schaefferkoetter and Whiteley teach the computer-implemented method of claim 4, where Schaefferkoetter further teaches further comprising providing the PET image for display. (¶[0033], “The computing device can also display the image volume to a physician for evaluation and diagnosis, for example.”, discloses displaying the image volume to a physician)
Regarding Claim 8, the combination of Schaefferkoetter and Whiteley teach the computer-implemented method of claim 1, Schaefferkoetter further teaches wherein the co-modality measurement data is computed tomography (CT) measurement data(¶[0073], the anatomy measurement data is computed tomography (CT) measurement data.), and the co- modality image is a CT image (¶[0063], “ the anatomy imaged can be CT images 137.”)
Regarding Claim 9, the combination of Schaefferkoetter and Whiteley teach the computer-implemented method of claim 1, where Schaefferkoetter further teaches wherein the trained machine learning process is trained on a plurality of histo-images and corresponding co-modality images. ([0023] “In some embodiments, a machine learning model, such as a neural network, can be trained to generate attenuation maps based on modality measurement data (e.g., CT measurement or MR measurement data) and PET measurement data. For example, the machine learning model may be trained based on PET measurement data and corresponding MR measurement data captured from a PET/MR system (e.g., using volunteer subjects or using previously stored imaging data).”, discloses PET and CT images are used to train the machine learning model.)
Regarding Claim 10, the combination of Schaefferkoetter and Whiteley teach the computer-implemented method of claim 1, where Schaefferkoetter further teaches comprising: retrieving machine learning parameters from the data repository, wherein the machine learning parameters characterize the trained machine learning process; and executing the trained machine learning process based on the machine learning parameters. (¶[0051] “computing device 200 receives MR image data 322 and PET image data 324 from image scanning system 102, and aggregates and stores MR image data 322 and PET image data 324 within data repository 320 to generate PET/MR training data 325. Computing device 200 may then obtain PET/MR training data 325, which comprises MR image data 322 and PET image data 324, and provides the PET/MR training data 325 to neural network engine 116 to train the neural network. For example, neural network engine 116 may generate features based on the PET/MR training data 325, and train the neural network based on the generated features.”, ¶[0051] discloses receiving training images from a data store and training the neural network based on features generated from the PET/MR training data. )
Regarding Claim 11, claim 11 is considered a storage medium claim substantially corresponding to claim 1. Please see the discussion of claim 1 above for a discussion of similar limitations. Furthermore,
Schaefferkoetter teaches a non-transitory, computer readable medium storing instructions that(See ¶[0036] for “a non-transitory, computer-readable storage medium”), when executed by at least one processor, cause the at least one processor to perform operations(¶[0036] image reconstruction system 104 can be implemented in software as executable instructions such that, when executed by one or more processors, cause the one or more processors to perform respective functions as described herein. The instructions can be stored in a non-transitory, computer-readable storage medium, for example.)
Regarding claim 12, it is substantially similar to claim 2 respectively, and is rejected in the same manner, the same art, and reasoning applying.
Regarding claim 13, it is substantially similar to claim 3 respectively, and is rejected in the same manner, the same art, and reasoning applying.
Regarding claim 14, it is substantially similar to claim 4 respectively, and is rejected in the same manner, the same art, and reasoning applying.
Regarding Claim 16, claim 16 is considered a system claim substantially corresponding to claim 1. Please see the discussion of claim 1 above for a discussion of similar limitations. Furthermore,
Schaefferkoetter teaches a system(Fig. 1A) comprising: a memory storing instructions; and at least one processor communicatively coupled to the memory and configured to execute the instructions (See ¶[0036], “image reconstruction system 104 can be implemented in software as executable instructions such that, when executed by one or more processors, cause the one or more processors to perform respective functions as described herein. The instructions can be stored in a non-transitory, computer-readable storage medium, for example.”)
Regarding claim 17, it is substantially similar to claim 2 respectively, and is rejected in the same manner, the same art, and reasoning applying.
Regarding claim 18, it is substantially similar to claim 3 respectively, and is rejected in the same manner, the same art, and reasoning applying.
Regarding claim 19, it is substantially similar to claim 4 respectively, and is rejected in the same manner, the same art, and reasoning applying.
Claims 6, 7, 15 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Schaefferkoetter US PG-Pub(US 20230009528 A1) in view of Whiteley et al. ("FastPET: Near Real-Time Reconstruction of PET
Histo-Image Data Using a Neural Network") in view of Piat et al. US PG-Pub(US 20210090212 A1).
Regarding Claim 6, while the combination of Schaefferkoetter and Whiteley teach the computer-implemented method of claim 1, they do not explicitly teach wherein the trained machine learning process generates the registered attenuation map data based on detecting a misalignment between the histo-image and the co-modality image.
Piat teaches wherein the trained machine learning process generates the registered attenuation map data based on detecting a misalignment between the histo-image and the co-modality image. (¶[0052], “The model is defined to output the deformation field, deformed CT or PET data (i.e., spatially transformed for alignment) or other alignment of the CT data with the PET data. In one embodiment, the model is defined as a GAN, so has a generator and discriminator for training”, ¶[0052] discloses determining a deformation field between the CT and PET image to determine any misalignment and registering the images.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the claimed invention as taught by Schaefferkoetter and Whiteley with Piat in order to determine misalignment before registering the images. One skilled in the art would have been motivated to modify Schaefferkoetter and Whiteley in this manner in order to provide a spatial alignment to be used in attenuation correction for PET reconstruction. (Piat, Abstract)
Regarding Claim 7, the combination of Schaefferkoetter, Whiteley and Piat teach the computer-implemented method of claim 6, where Piat further teaches wherein the detected misalignment is between pixel locations of the histo-image and pixel locations the co- modality image. (¶[0053], “The deformation field non-rigidly relates the spatial locations of the CT data to the spatial locations of the PET data. The deformation field may be represented by vectors by location (e.g., pixel or voxel) for the direction and magnitude for change in spatial location of the CT intensity (e.g., density). Other representations may be used, such as diffeomorphic representation provided by a velocity field, v, and a diffeomorphic deformation field, ϕ. The generator may output pointwise velocities v, which are then processed into a diffeomorphic deformation representation. In one embodiment, the generator is defined to regress the deformation field that will be used to warp the CT image, which will then be used to compute the attenuation corrected PET.”, discloses the deformation field is represented by misalignment between pixel locations in the CT and PET images.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the claimed invention as taught by Schaefferkoetter and Whiteley with Piat in order to determine misalignment with pixel location before registering the images. One skilled in the art would have been motivated to modify Schaefferkoetter and Whiteley in this manner in order to provide a spatial alignment to be used in attenuation correction for PET reconstruction. (Piat, Abstract)
Regarding claim 15, it is substantially similar to claim 6 respectively, and is rejected in the same manner, the same art, and reasoning applying.
Regarding claim 20, it is substantially similar to claim 6 respectively, and is rejected in the same manner, the same art, and reasoning applying.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Whiteley et al. US PG-Pub(US 20210104079 A1) teaches acquiring a first PET dataset, back-projection of the first PET dataset to generate a first histo-image In ¶[0014] and ¶[0021]
Xi et al. US PG-Pub(US 20240153166 A1) teaches correction data that includes target PET data having the TOF histo-image format may be determined and used to generate the PET reconstruction image and/or the PET parametric image in ¶[0072]
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HAN D HOANG whose telephone number is (571)272-4344. The examiner can normally be reached Monday-Friday 8-5.
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, JOHN M VILLECCO can be reached at 571-272-7319. 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.
/HAN HOANG/Primary Examiner, Art Unit 2661
Prosecution Insights