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 .
Drawings
The drawings submitted on 9/12/2023 are accepted.
Specification
The specification is objected to as failing to provide proper antecedent basis for the claimed subject matter. See 37 CFR 1.75(d)(1) and MPEP § 608.01(o). Correction of the following is required: claim 11 recites “… presenting the attenuation-corrected SPECT imaging data.” The disclosure only mentions at paragraph 0068 (as published) where simulated data may be presented on a display.
Claim Objections
Claims 6 and 17 are objected to because of the following informalities: “… the short-axis SPECT slices is reconstructed” is improper grammar. Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 2-7, 10, 11, 14, 15, 18 and 20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 2, 3, 11, 14, 15 recite the limitation "attenuation-corrected SPECT imaging data." There is insufficient antecedent basis for this limitation in the claim. The Examiner notes that “attenuation-correction (AC) SPECT imaging data” is instantiated in their respective independent claim.
Claim 4 is rejected based on its dependency on claim 3.
Claim 5 recites the limitation "the plurality of NC SPECT training images." There is insufficient antecedent basis for this limitation in the claim.
Claim 6 is rejected based on its dependency on claim 5.
Claims 7 and 18 recite the limitation "the NC SPECT training images." There is insufficient antecedent basis for this limitation in the claim. The Examiner notes that “a plurality of NC SPECT training images” is instantiated in their respective independent claim.
Claims 7 and 18 recite the limitation "the corresponding traditional AC images." There is insufficient antecedent basis for this limitation in the claim.
Claims 7 and 18 recite the limitation "the respective NC SPECT training image." There is insufficient antecedent basis for this limitation in the claim.
Claim 10 recites “… The method of claim 19.” Claim 19 is directed to a system. It is unclear whether claim 10 should be directed at to a method or to a system. For purposes of examination, the Examiner interprets the claim to be directed to the method of claim 1.
The term “presenting” in claim 11 is a relative term which renders the claim indefinite. The term “presenting” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
Claim 20 recites the limitation "the plurality of traditional AC images." There is insufficient antecedent basis for this limitation in the claim. The Examiner notes that “a corresponding plurality of traditional AC SPECT images” is instantiated in claim 13.
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.
Claim(s) 1, 5, 7, 10-13, 16, 18 and 20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Shi et al., (US Pub No. 20220207791 also published as WO 2020214911 on 10/22/2020).
Claim 1: Shi discloses a method [Abstract & Figure 1], comprising:
receiving non-attenuation-corrected (NC) single photon emission computed tomography (SPECT) imaging data, the NC SPECT imaging data including a plurality of image slices [generating an attenuation map from a NAC (non-attenuation corrected) SPECT image dataset (photopeak window or both photopeak combined with scatter windows) through deep learning, estimating attenuated projection data via forward projecting the NAC SPECT image without incorporating the attenuation map, and reconstructing an AC (attenuation corrected) SPECT image from the estimated attenuated projection data using iterative reconstruction with attenuation correction by incorporating the attenuation map generated by deep learning … Both SPECT and attenuation CT images were acquired on a GE NM/CT 850 SPECT/CT scanner … the NAC SPECT image dataset 902 (photopeak window or both photopeak combined with scatter windows) is first used to generate the attenuation map 904 using the deep learning method described above (that is, for example, the well-trained network, p0020, p0061 & p0088-0090]; and
generating simulated attenuation-correction (AC) SPECT imaging data from the NC SPECT imaging data by applying the NC SPECT imaging data to a generator network of a conditional generative adversarial network (cGAN) trained using training data [estimating attenuation coefficients and attenuation maps (ATTMAP) from only single photon emission computed tomography (SPECT) emission data using deep neural networks and performing attenuation correction … attenuation maps produced in accordance with the present invention are then used to correct raw SPECT data or SPECT images reconstructed without attenuation correction to produce highly accurate body images based solely upon SPECT emission data … generator network 10 with a GAN training strategy generates attenuation map images 14 from SPECT emission images … A conditional generative adversarial network (cGAN) framework is employed … two networks were simultaneously trained in the cGAN framework: a discriminator network D (designated as “16” in FIG. 1) that attempts to correctly discriminate between synthetic and real CT-based attenuation maps (that is, ground truth attenuation maps as discussed above), and a generator network G (designated as “10” in FIG. 1) that attempts to produce synthetic attenuation maps that will confuse the discriminator network D, p0035, p0038-0039, p0040, p0046 & p0058-0059], the training data including a plurality of NC SPECT training images and a corresponding plurality of traditional AC SPECT images [Initially, 40 subjects were included in the training set, and 25 subjects were used for evaluation. To evaluate the proposed mean-normalization approach, the cGAN was trained with data pre-processed with mean-normalization, Gaussian-normalization, and maximum-normalization … In each study, the upper left images (200a, 200b) are the primary window and the scatter window SPECT images used as inputs as well as the synthetic attenuation map (ATTMAP) generated by the cGAN model (GAN-PS), p0046, p0058-0059 & p0066].
Claim 5: Shi discloses the method of claim 1, wherein the plurality of NC SPECT training images and the corresponding plurality of traditional AC SPECT images are short-axis SPECT slices [Generative Adversarial Network (GAN) method using both primary and scatter windows data (AC-SPECT w. GAN-PS) and without attenuation correction in both short axis (SA) and vertical long axis (VLA) views … size of the SPECT reconstruction images is 64×64×64, though the attenuation maps typically have a shorter scanning range in the axial direction (25-35 slices) to reduce unnecessary radiation … size of the SPECT reconstruction images is 64×64×64, though the attenuation maps typically have a shorter scanning range in the axial direction (25-35 slices) to reduce unnecessary radiation and as shown in at least Figures 2 & 11, p0023 & p0061].
Claim 7: Shi discloses the method of claim 1, wherein the cGAN is trained by supplying as input to the cGAN, for each of the NC SPECT training images and the corresponding traditional AC images, a region of interest centered on a left ventricle within the respective NC SPECT training image [a training set of 40 human subjects with both cardiac SPECT with .sup.99mTc-tetrofosmin and attenuation CT scans, and a testing set of 8 subjects not involved in the network training were employed using the Generative Adversarial Network (GAN) training strategy … synthetic attenuation maps [i.e., AC images] generated by the generator network 10 were compared with the true attenuation maps by the discriminator network 16 regarding both global Normalized Mean Absolute Error (NMAE=MAE(synthetic)/[max(true)−min(true)]) and localized region of interest (ROI) absolute percentage error (|(roi_mean(synthetic)−roi_mean(true))/roi_mean(true)|) in left ventricle (LV) myocardium (121.8±30.0 cm.sup.3) and LV blood pool (40.7±7.5 cm.sup.3) ROIs. The localized absolute percentage error was also calculated for attenuation corrected SPECT reconstruction images with both true and synthetic attenuation maps, p0074-0083].
Claim 10: Shi discloses the method of claim 19, wherein a cost function of the cGAN includes absolute error between each simulated output and respective ones of the plurality of traditional AC images [synthetic attenuation maps generated by the generator network 10 were compared with the true attenuation maps by the discriminator network 16 regarding both global Normalized Mean Absolute Error (NMAE=MAE(synthetic)/[max(true)−min(true)]) and localized region of interest (ROI) absolute percentage error (|(roi_mean(synthetic)−roi_mean(true))/roi_mean(true)|) in left ventricle (LV) myocardium (121.8±30.0 cm.sup.3) and LV blood pool (40.7±7.5 cm.sup.3) ROIs. The localized absolute percentage error was also calculated for attenuation corrected SPECT reconstruction images with both true and synthetic attenuation maps, p0083].
Claim 11: Shi discloses the method of claim 1, further comprising presenting the attenuation-corrected SPECT imaging data [as shown in Figure 2, p0066].
Claim 12: the product herein has been executed or performed by the system of claim 13 and is therefore likewise rejected.
Claim 13: Shi discloses a system [Abstract & Figure 1], comprising:
one or more data processors; and a non-transitory computer-readable storage medium containing instructions which, when executed on the one or more data processors [e.g., training phase takes about 10 hours on an NVIDIA GTX 1080 Ti GPU, p0056 – the Examiner notes that the aforementioned processor inherently possesses on-board memory for which a program of some type is necessarily required to be executed to perform the disclosed functions], cause the one or more data processors to perform operations including:
receiving non-attenuation-corrected (NC) single photon emission computed tomography (SPECT) imaging data, the NC SPECT imaging data including a plurality of image slices [generating an attenuation map from a NAC (non-attenuation corrected) SPECT image dataset (photopeak window or both photopeak combined with scatter windows) through deep learning, estimating attenuated projection data via forward projecting the NAC SPECT image without incorporating the attenuation map, and reconstructing an AC (attenuation corrected) SPECT image from the estimated attenuated projection data using iterative reconstruction with attenuation correction by incorporating the attenuation map generated by deep learning … Both SPECT and attenuation CT images were acquired on a GE NM/CT 850 SPECT/CT scanner … the NAC SPECT image dataset 902 (photopeak window or both photopeak combined with scatter windows) is first used to generate the attenuation map 904 using the deep learning method described above (that is, for example, the well-trained network, p0020, p0061 & p0088-0090]; and
generating simulated attenuation-correction (AC) SPECT imaging data from the NC SPECT imaging data by applying the NC SPECT imaging data to a generator network of a conditional generative adversarial network (cGAN) trained using training data [estimating attenuation coefficients and attenuation maps (ATTMAP) from only single photon emission computed tomography (SPECT) emission data using deep neural networks and performing attenuation correction … attenuation maps produced in accordance with the present invention are then used to correct raw SPECT data or SPECT images reconstructed without attenuation correction to produce highly accurate body images based solely upon SPECT emission data … generator network 10 with a GAN training strategy generates attenuation map images 14 from SPECT emission images … A conditional generative adversarial network (cGAN) framework is employed … two networks were simultaneously trained in the cGAN framework: a discriminator network D (designated as “16” in FIG. 1) that attempts to correctly discriminate between synthetic and real CT-based attenuation maps (that is, ground truth attenuation maps as discussed above), and a generator network G (designated as “10” in FIG. 1) that attempts to produce synthetic attenuation maps that will confuse the discriminator network D, p0035, p0038-0039, p0040, p0046 & p0058-0059], the training data including a plurality of NC SPECT training images and a corresponding plurality of traditional AC SPECT images [Initially, 40 subjects were included in the training set, and 25 subjects were used for evaluation. To evaluate the proposed mean-normalization approach, the cGAN was trained with data pre-processed with mean-normalization, Gaussian-normalization, and maximum-normalization … In each study, the upper left images (200a, 200b) are the primary window and the scatter window SPECT images used as inputs as well as the synthetic attenuation map (ATTMAP) generated by the cGAN model (GAN-PS), p0046, p0058-0059 & p0066].
Claim 16: the system herein has been executed or performed by the method of claim 5 and is therefore likewise rejected.
Claim 18: the system herein has been executed or performed by the method of claim 7 and is therefore likewise rejected.
Claim 20: the system herein has been executed or performed by the method of claim 10 and is therefore likewise 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.
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) 2-4, 14 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Shi et al., as applied above in view of Mostafapour et al., (Deep learning-guided attenuation correction in the image domain for myocardial perfusion SPECT imaging, 4/2022).
Claim 2: Shi discloses the method of claim 1, wherein the NC SPECT imaging data is associated with a myocardial perfusion imaging (MPI) study [Shi, L., Onofrey, J. A., Liu, H. et al. Deep learning-based attenuation map generation for myocardial perfusion SPECT. Eur J Nucl Med Mol Imaging (2020) … 65 consecutive clinical subjects (including the 40 subjects from the initial evaluation) with both normal and abnormal patients were scanned at Yale New Haven Hospital with .sup.99mTc-tetrofosmin for myocardial perfusion SPECT studies [i.e., NC SPECT image data collected]. One day stress-only low-dose protocol, with the mean administered dose of 15 mCi, was used. The clinical characteristics of the patients enrolled in the study, including gender, age, height, weight and body mass index (BMI), are given in Table 1. Both SPECT and attenuation CT images were acquired on a GE NM/CT 850 SPECT/CT scanner, p0047, p0061 & p0100], the method further comprising generating a coronary artery disease (CAD) evaluation based at least in part on the attenuation-corrected SPECT imaging data.
Shi does not appear to explicitly disclose where the method further comprising generating a coronary artery disease (CAD) evaluation based at least in part on the attenuation-corrected SPECT imaging data.
Mostafapour discloses in a related, well-known study [Abstract] where a coronary artery disease (CAD) evaluation based at least in part on the attenuation-corrected SPECT imaging data [non-invasive examination technique plays a critical role in the evaluation of myocardial ischemia, coronary artery disease, and risk classification … Attenuation correction (AC) in SPECT-MPI improves diagnostic accuracy and normalcy rate, page 435 col. 1 paras. 1 and 4].
It would have been obvious to persons of ordinary skill in the art to have utilized the invention of Shi to provide a coronary artery disease (CAD) evaluation based at least in part on the attenuation-corrected SPECT imaging data as taught by Mostafapour because it provided the patient relevant health information while identifying patients would lead to earlier detection of pathophysiology or cardiac damage before the occurrence of morphological damage in at least the Introduction.
Claim 3: Shi in view of Mostafapour discloses the method of claim 2.
Shi discloses generating attenuation-corrected SPECT imaging data [Evaluations on real human data showed that the present method produces attenuation maps that are consistent with CT-based attenuation maps, and provides accurate attenuation correction for SPECT images. The attenuation maps produced in accordance with the present invention are then used to correct raw SPECT data or SPECT images reconstructed without attenuation correction to produce highly accurate body images based solely upon SPECT emission data, p0038].
Shi does not appear to disclose wherein generating the CAD evaluation includes determining a stress total perfusion deficit value based at least in part on the attenuation-corrected SPECT imaging data.
Mostafapour discloses in a related study [Abstract] wherein generating the CAD evaluation includes determining a stress total perfusion deficit value based at least in part on the attenuation-corrected SPECT imaging data [non-invasive examination technique plays a critical role in the evaluation of myocardial ischemia, coronary artery disease, and risk classification … Attenuation correction (AC) in SPECT-MPI improves diagnostic accuracy and normalcy rate … Clinical assessment was performed through calculating quantitative parameters extracted from Cedars-Sinai Medical Center software, Quantitative Perfusion SPECT (QPS). These quantitative parameters include Defect, Extent, Summed Stress Percent(SS%),Summed Stress Score(SSS),Total Perfusion Deficit (TPD%), Volume, Area, Shape Eccentricity (ECC), and Shape Index (SI), page 435 col. 1 paras. 1 and 4 & page 439 col. 1 para. 2].
It would have been obvious to persons of ordinary skill in the art to have utilized the invention of Shi to support where generating the CAD evaluation includes determining a stress total perfusion deficit value based at least in part on the attenuation-corrected SPECT imaging data as taught by Mostafapour because it provides a metric for the patient and their physician to assess cardiovascular intervention as discussed by Mostafapour in at least para. 1 col. 1 of page 435.
Claim 4: Shi in view Mostafapour discloses the method of claim 3.
Shi does not appear to disclose wherein generating the CAD evaluation includes determining a stress volume value.
Mostafapour discloses determining a stress volume value [Clinical assessment was performed through calculating quantitative parameters extracted from Cedars-Sinai Medical Center software, Quantitative Perfusion SPECT (QPS). These quantitative parameters include Defect, Extent, Summed Stress Percent(SS%),Summed Stress Score(SSS),Total Perfusion Deficit (TPD%), Volume, Area, Shape Eccentricity (ECC), and Shape Index (SI), page 439 col. 1 para. 2].
It would have been obvious to persons of ordinary skill in the art to have utilized the invention of Shi to support determining a stress volume value as taught by Mostafapour because it provides a metric for the patient and their physician to assess cardiovascular intervention as discussed by Mostafapour in at least para. 1 col. 1 of page 435.
Claim 14: the system herein has been executed or performed by the method of claim 2 and is therefore likewise rejected.
Claim 15: the system herein has been executed or performed by the methods of claims 3 and 4 is therefore likewise rejected.
Claim(s) 6 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Shi et al., as applied above.
Claim 6: Shi discloses method of claim 5
Shi does not explicitly disclose wherein each of the short-axis SPECT slices is reconstructed at 4×4×4 mm with a slice thickness of 4 mm.
Shi does however teach wherein each of the short-axis SPECT slices is reconstructed [voxel size of 6.8×6.8×6.8 mm3 … attenuation maps typically have a shorter scanning range in the axial direction (25-35 slices) to reduce unnecessary radiation and as shown in at least Figures 2 & 11, p0023, p0056 & p0061].
Shi does not explicitly disclose wherein each of the short-axis SPECT slices is reconstructed at 4×4×4 mm with a slice thickness of 4 mm.
At the time of the invention before the effective filing date, it would have been an obvious matter of design choice to a person of ordinary skill in the art to have recognized in the invention of Shi utilizing slice dimensions according to a design choice (additionally evidenced by Levy et al., US Patent 8252281) would produce equivalent results because the Applicant has not disclosed that utilizing slices that are reconstructed at 4×4×4 mm with a slice thickness of 4 mm provides a particular advantage or is exclusive in its purpose.
Claim 17: the system herein has been executed or performed by the method of claim 6 and is therefore likewise rejected.
Claim(s) 8, 9 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Shi et al., as applied above in view of Zhao et al., (SCAU-Net: Spatial-Channel Attention U-Net for Gland Segmentation, 2020).
Claim 8: Shi discloses the method of claim 1, wherein the generator network is an Attention UNet 3D model with instance normalization [Network Architectures A modified 3D version of the fully-convolutional U-net architecture is used as the generator network G … Batch normalization (BN) was applied after each convolutional layer and before the ReLU (rectified linear unit). Dropout with a rate of 0.15 was applied to the bottleneck layer of the U-net in the training phase to prevent overfitting, but is removed during testing, p0047-0048].
Although Shi discusses a modified UNet 3D model, Shi does not explicitly disclose an Attention UNet 3D model.
Zhao discloses in a related disclosure from the field of medical imaging [Abstract] utilizing an Attention UNet 3D model [a deep learning image semantic
segmentation network named Spatial-Channel Attention U-Net (SCAU-Net) based on current research status of medical image, Abstract].
It would have been obvious to persons of ordinary skill in the art before the effective filing date of the invention to have applied to the UNet model of Shi the use of an Attention UNet 3D model as disclosed by Zhao because provides to enhance local related features and restrain irrelevant features at the spatial and channel levels as discussed by Zhao throughout the disclosure.
Claim 9: Shi discloses the method of claim 8, wherein the Attention UNet 3D model includes four levels [modified U-net architecture is used as the generator network G in accordance with the disclosed embodiment is four levels deep, which is one level fewer than the original U-net, p0048].
Although Shi discusses a modified UNet 3D model, Shi does not explicitly disclose an Attention UNet 3D model.
Zhao discloses utilizing an Attention UNet 3D model that includes four levels [The entire structure is divided into four parts: encoder, decoder, spatial attention module, channel attention module, Figure 1].
It would have been obvious to persons of ordinary skill in the art before the effective filing date of the invention to have applied to the UNet model of Shi the use of an Attention UNet 3D model as disclosed by Zhao because provides to enhance local related features and restrain irrelevant features at the spatial and channel levels as discussed by Zhao throughout the disclosure.
Claim 19: the system herein has been executed or performed by the method of claim 8 and is therefore likewise rejected.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Sharmila Dorbala, MD, MPH, et al., Single Photon Emission Computed Tomography (SPECT) Myocardial Perfusion Imaging Guidelines: Instrumentation, Acquisition, Processing, and Interpretation, 2018, discusses SPECT imaging guidelines.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BARBARA D REINIER whose telephone number is (571)270-5082. The examiner can normally be reached M-Tu 10am - 6pm.
Examiner interviews are available via telephone 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, Benny Tieu can be reached at 571-272-7490. 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.
/BARBARA D REINIER/Primary Examiner, Art Unit 2682