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 .
Response to Arguments
Applicant’s arguments, see page 6, filed 1/30/2026 with respect to 35 USC §112 rejection of claims 1-3,10-12 have been fully considered and are persuasive. Applicant has amended claims to remove indefinite claim language. The 35 USC §112 rejection of claims 1-3,10-12 has been withdrawn.
Applicant’s arguments, see page 6-8, filed 1/30/2026 with respect to 35 USC §103 rejection of claims 1-20 have been fully considered but were not persuasive. Applicant argues combination office action does not articulate rationale for combining FastPET and Whitley. Applicant points to paragraph [0020] of instant application specification to disclose methods and systems for generating improved-resolution PET images using data obtained by PET scanners having a poorer response time resolution and paragraph [0028] to disclose to generate higher-resolution histo- images, the Applicant discloses that "the improved-resolution histo-images are generated by a neural network implemented by the processor 60 that is configured to generate a histo-image having a higher effective resolution than the first modality. Applicant argues office action rationale is unrelated to the use of an improved- resolution second histo-image generated from a trained neural network, unrelated to differing resolutions, and unrelated to the subject matter of the claims and the combination lacks a rational underpinning and cannot support a legal conclusion of obviousness. Applicant argues proposed combination is only supported by impermissible hindsight reasoning. Applicant argues the only motivation for the proposed modification in the Office Action is impermissible hindsight based on the knowledge taught in the instant application disclosure.
In response examiner recognizes that references cannot be arbitrarily combined and that there must be some reason why one skilled in the art would be motivated to make the proposed combination of primary and secondary references. However, there is no requirement that a motivation to make the modification be expressly articulated. The test for combining references is what the combination of disclosures taken as a whole would suggest to one of ordinary skill in the art. Rationale for combination does not have to be the same as instant application as references are evaluated by what they suggest to one versed in the art. In response to Applicant's argument that the Examiner's conclusion of obviousness is based upon improper hindsight reasoning, it must be recognized that any judgement on obviousness is in any sense necessarily a reconstruction based upon hindsight reasoning. But so long as it takes into account only knowledge which was within the level of ordinary skill at the time of the invention was made, and does not include knowledge gleaned only from the Applicant's disclosure, such a reconstruction is proper.
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 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.
Claim 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over WILLIAM WHITELEY et al., FastPET: Near Real-Time Reconstruction of PET Histo-Image Data Using a Neural Network, IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES, 5(1): 65-77, 2021. Herein FastPet in view of Whiteley et al (US 20210104079 A1)
Regarding claim 1, FastPET discloses a system, comprising a positron emission tomography (PET) imaging modality configured to execute a first scan to acquire a first PET dataset (Introduction, neural network for direct reconstruction with the development of FastPET); and
a processor (Experiments - Reconstruction Speed , HP Z8G4 computer containing an Intel Xeon Gold 6154 CPU running at 3.0 GHz.) configured to:
back-project the first PET dataset to generate a first histo-image that represents the first PET dataset and having a first resolution (Experiments –Reconstruction Speed, comparison of reconstruction speed between FastPET and Filtered Back-Projection (FBP) and OSEM+PSF both with TOF);
input the first histo-image to a trained neural network (Experiments - Neurology Application Focused Network , Sample images, network inputs and targets from the neurology test set containing each of the tracer types);
input the second histo-image to a reconstruction process configured to generate a reconstructed PET image (Discussion and Challenges , FastPET has been shown capable of true 3D image reconstruction in near real-time)
Whiteley discloses receive a second histo-image from the trained neural network, wherein the second histo-image has a second resolution, wherein the second resolution is higher than the first resolution, and wherein the second histo-image represents higher resolution version of the first PET dataset ([0047] the neural network is trained (e.g., using training system 740) based on differences between the plurality of output image volumes and corresponding ones of the plurality of PET training image volumes)
FastPET and Whiteley are combinable because they are from the same field of invention.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify FastPET algorithm of FastPET to include receive a second histo-image from the trained neural network, wherein the second histo-image has a second resolution, wherein the second resolution is highger than the first resolution, and wherein the second histo-image represents higher resolution version of the first PET dataset as described by Whiteley
The motivation for doing so would have been to histo-image may be generated from TOF sinograms using TOF back-projection, or directly from PET event data by back-projecting each recorded event (Whiteley, [0014]).
Therefore, it would have been obvious to combine FastPET and Whiteley to obtain the invention as specified in claim 1.
Regarding claim 2, FastPET discloses wherein the first resolution is in a range 600 ps and the second resolution is in a range 200 ps (Method - Training and Evaluation Data Sets , Data was acquired on a Siemens Biograph Vision 8 ring PET/CT scanner [41] containing 3.2 mm2 crystals with a TOF resolution of 214 ps. Discussion and Challenges, First is the applicability of this technique to scanners with lower timing resolution in the 400 ps to 700 ps range)
Regarding claim 3, FastPET discloses wherein the first resolution is in a range 200 ps and the second resolution is in a range 10 ps (Method - Training and Evaluation Data Sets , Data was acquired on a Siemens Biograph Vision 8 ring PET/CT scanner [41] containing 3.2 mm2 crystals with a TOF resolution of 214 ps. Discussion and Challenges, First is the applicability of this technique to scanners with lower timing resolution in the 400 ps to 700 ps range)
Regarding claim 4, FastPET discloses wherein the trained neural network is a trained convolutional neural network (Introduction, well suited for convolutional neural networks due to being locally correlated and essentially making reconstruction an image-to-image operation).
Regarding claim 5, FastPET discloses wherein the first PET dataset is selected from the group consisting of: a list-mode dataset, a sinogram dataset, and a histo-image dataset (Method - FastPET Reconstruction Architecture, FastPET pipeline starting with the PET/CT scanner generating raw data in the form of PET list-mode events and CT based attenuation maps).
Regarding claim 6, FastPET discloses wherein the trained neural network is generated by a training dataset comprising a plurality of first histo-images having the first resolution and a plurality of second histo-images having the second resolution, wherein each of the histo-images in the plurality of first histo-images has at least one corresponding histo-image in the second plurality of histo-images, and wherein the second resolution of each histo-image in the second plurality is higher than the first resolution of the corresponding histo-image in the first plurality of histo-images (Method - Neural Network Architecture, The neural network input contains batches of 3D histoimages and matching attenuation maps each with a size of d h w.This creates a 5D input, i.e., b c d h w, to the neural network).
Regarding claim 7, FastPET discloses wherein the first plurality of histo-images correspond to a first set of PET data obtained at a first imaging resolution and the second histo-images correspond to a second set of PET data obtained at a second imaging resolution (Method - Neural Network Architecture, This style of network also contains skip connections where the features extracted in the last layer at each spatial resolution on the contracting side are concatenated to the first layer at the same resolution on the expanding side of the network.).
Regarding claim 8, FastPET discloses wherein the first plurality of histo-images comprise a first
plurality of simulated histo-images generated at a first simulated resolution and the second plurality of histo-images comprises a second plurality of simulated histo-images generated at a second simulated resolution (Method - Neural Network Architecture, The second data set is a simulated low-dose version of the whole-body data set discussed in the previous paragraph. The original data was decimated prior to creating the histo-images by randomly removing counts from the whole-body list-mode f iles with a probability of 0.75).
Regarding claim 9, FastPET discloses wherein the first plurality of simulated histo-images and the second plurality of histo-images are generated by a Monte Carlo based simulation (Discussion and Challenges The solution may be to create computer models, like Monte Carlo simulation, that can generate unlimited data closely following the physics of positron decay and the system matrix of a particular scanner).
Regarding claim 10, FastPET discloses a method of generating reconstructed positron emission tomography (PET) images(Introduction, neural network for direct reconstruction with the development of FastPET), comprising:
executing a first scan to acquire a first PET dataset (Introduction, improved timing resolution of modern PET scanners,);
back-projecting the first PET dataset to generate a first histo-image that represents the first PET data and having a first resolution (Experiments –Reconstruction Speed, comparison of reconstruction speed between FastPET and Filtered Back-Projection (FBP) and OSEM+PSF both with TOF);;
inputting the first histo-image to a trained neural network (Experiments - Neurology Application Focused Network , Sample images, network inputs and targets from the neurology test set containing each of the tracer types);
inputting the second histo-image to a reconstruction process configured to generate a reconstructed PET image (Discussion and Challenges , FastPET has been shown capable of true 3D image reconstruction in near real-time)
Whiteley discloses receiving a second histo-image from the trained neural network, wherein the second histo-image has a second resolution, wherein the second resolution is higher than the first resolution, and wherein the second histo-image represents an higher resolution version of the first PET dataset ([0047] the neural network is trained (e.g., using training system 740) based on differences between the plurality of output image volumes and corresponding ones of the plurality of PET training image volumes)
FastPET and Whiteley are combinable because they are from the same field of invention.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify FastPET algorithm of FastPet to includereceiving a second histo-image from the trained neural network, wherein the second histo-image has a second resolution, wherein the second resolution is higher than the first resolution, and wherein the second histo-image represents an higher resolution version of the first PET dataset as described by Whiteley
The motivation for doing so would have been to histo-image may be generated from TOF sinograms using TOF back-projection, or directly from PET event data by back-projecting each recorded event (Whiteley, [0014]).
Therefore, it would have been obvious to combine FastPET and Whiteley to obtain the invention as specified in claim 10.
Regarding claim 11, FastPET discloses wherein the first resolution is in a range 600 ps and the second resolution is in a range 200 ps (Method - Training and Evaluation Data Sets , Data was acquired on a Siemens Biograph Vision 8 ring PET/CT scanner [41] containing 3.2 mm2 crystals with a TOF resolution of 214 ps. Discussion and Challenges, First is the applicability of this technique to scanners with lower timing resolution in the 400 ps to 700 ps range)
Regarding claim 12, FastPET discloses wherein the first resolution is in a range 200 ps and the second resolution is in a range 10 ps (Method - Training and Evaluation Data Sets , Data was acquired on a Siemens Biograph Vision 8 ring PET/CT scanner [41] containing 3.2 mm2 crystals with a TOF resolution of 214 ps. Discussion and Challenges, First is the applicability of this technique to scanners with lower timing resolution in the 400 ps to 700 ps range)
Regarding claim 13, FastPET discloses wherein the trained neural network is a trained convolutional neural network (Introduction, well suited for convolutional neural networks due to being locally correlated and essentially making reconstruction an image-to-image operation).
Regarding claim 14, FastPET discloses wherein the first PET dataset is a list-mode dataset (Method - FastPET Reconstruction Architecture, FastPET pipeline starting with the PET/CT scanner generating raw data in the form of PET list-mode events and CT based attenuation maps).
Regarding claim 15, FastPET discloses wherein the trained neural network is generated by a training dataset comprising a first plurality of histo-images having the first resolution and a 24second plurality of histo-images having the second resolution, wherein each of the histo- images in the first plurality of histo-images has at least one corresponding histo-image in the second plurality of histo-images, and wherein the second resolution of each histo-image in the second plurality of histo-images is higher than the first resolution of the corresponding histo-image in the first plurality of histo-image (Method - Neural Network Architecture, The neural network input contains batches of 3D histoimages and matching attenuation maps each with a size of d h w.This creates a 5D input, i.e., b c d h w, to the neural network).
Regarding claim 16, FastPET discloses wherein the first plurality of histo-images correspond to a first set of PET data obtained at a first imaging resolution and the second histo-images correspond to a second set of PET data obtained at a second imaging resolution (Method - Neural Network Architecture, This style of network also contains skip connections where the features extracted in the last layer at each spatial resolution on the contracting side are concatenated to the first layer at the same resolution on the expanding side of the network.).
Regarding claim 17, FastPET discloses wherein the first plurality of histo-images comprise a first
plurality of simulated histo-images generated at a first simulated resolution and the second plurality of histo-images comprises a second plurality of simulated histo-images generated at a second simulated resolution (Method - Neural Network Architecture, The second data set is a simulated low-dose version of the whole-body data set discussed in the previous paragraph. The original data was decimated prior to creating the histo-images by randomly removing counts from the whole-body list-mode f iles with a probability of 0.75).
Regarding claim 18, FastPET discloses wherein the first plurality of simulated histo-images and the second plurality of histo-images are generated by a Monte Carlo based simulation (Discussion and Challenges The solution may be to create computer models, like Monte Carlo simulation, that can generate unlimited data closely following the physics of positron decay and the system matrix of a particular scanner).
Regarding claim 19, FastPET discloses A method of training a neural network to generate higher-resolution histo-images (Introduction, neural network for direct reconstruction with the development of FastPET), comprising:
receiving a training dataset comprising a first plurality of histo-images having a first resolution and a second plurality of histo-images having a second resolution (Experiments - Neurology Application Focused Network , Sample images, network inputs and targets from the neurology test set containing each of the tracer types),
inputting each histo-image in the first plurality of histo-images to a neural network configured to generate a corresponding higher-resolution histo-image having an estimated second resolution (Discussion and Challenges , FastPET has been shown capable of true 3D image reconstruction in near real-time);
comparing each of the higher-resolution histo-images to the corresponding histo- image in the second plurality of histo-images to determine any differences between each higher-resolution histo-image and the histo-image in the second plurality of histo-images that correspond to the histo-image in the first plurality of histo-images (Method - Reconstruction Speed, FastPET would complete these reconstructions in respectively 7 seconds and 18 seconds compared to about 8 and 20 minutes for OSEM+PSF. Additionally, the potential for entirely new reconstruction applications are enabled by ultra fast reconstruction such as interventional procedures, improved motion correction with sub-second frames, or a near real-time PET image viewer.); and
modifying the neural network based on the determined differences between each higher-resolution histo-image and a histo-image in the second plurality of histo-images that correspond to the histo-image in the first plurality of histo-images provided to the neural network (Introduction, well suited for convolutional neural networks due to being locally correlated and essentially making reconstruction an image-to-image operation)..
Whiteley discloses wherein each of the histo-images in the first plurality of histo-images has at least one corresponding histo-image in the second plurality of histo-images, and wherein the second resolution of each histo-image in the second plurality of histo-images is higher than the first resolution of the corresponding histo-image in the first plurality of histo-images ([0047] the neural network is trained (e.g., using training system 740) based on differences between the plurality of output image volumes and corresponding ones of the plurality of PET training image volumes)
FastPET and Whiteley are combinable because they are from the same field of invention.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify FastPET algorithm of FastPet to include wherein each of the histo-images in the first plurality of histo-images has at least one corresponding histo-image in the second plurality of histo-images, and wherein the second resolution of each histo-image in the second plurality of histo-images is higher than the first resolution of the corresponding histo-image in the first plurality of histo-images as described by Whiteley
The motivation for doing so would have been to histo-image may be generated from TOF sinograms using TOF back-projection, or directly from PET event data by back-projecting each recorded event (Whiteley, [0014]).
Therefore, it would have been obvious to combine FastPET and Whiteley to obtain the invention as specified in claim 19.
Regarding claim 9, FastPET discloses wherein the first plurality of histo-images and the second plurality of histo-images are simulated histo-images (Discussion and Challenges The solution may be to create computer models, like Monte Carlo simulation, that can generate unlimited data closely following the physics of positron decay and the system matrix of a particular scanner).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHIVANG I PATEL whose telephone number is (571)272-8964. The examiner can normally be reached on M-F 9-5am.
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, Alicia Harrington can be reached on 571-272-2330. 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 https://ppair-my.uspto.gov/pair/PrivatePair. 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.
/SHIVANG I PATEL/Primary Examiner, Art Unit 2615