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”) filed on 01/16/2024 has been reviewed and the listed references have been considered.
Status of Claims
Claims 1-20 are pending.
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they do not include the following reference sign(s) mentioned in the description: paragraph 59 "RF preamplifier 556" . 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. 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.
Specification
The specification is objected to because of the following informalities:
In paragraph 60 "RF transmission coils 560…" should be "RF transmission coils 550…"
According to 37 CFR 1.71, MPEP §§ 608.01, 2161, and 2162, the specification must be in such particularity as to enable any person skilled in the pertinent art or science to make and use the invention without involving extensive experimentation and must clearly convey enough information about the invention to show that applicant invented the subject matter that is claimed. An applicant is ordinarily permitted to use his or her own terminology, as long as it can be understood. Necessary grammatical corrections, are required. Reference characters must be properly applied, no single reference character being used for two different parts or for a given part and a modification of such part. See 37 CFR 1.84(p). Every feature specified in the claims must be illustrated, but there should be no superfluous illustrations.
A substitute specification in proper idiomatic English and in compliance with 37 CFR 1.52(a) and (b) is required. The substitute specification filed must be accompanied by a statement that it contains no new matter.
Claim Rejections - 35 USC § 103
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-2, 6, 9, and 11-12 are rejected under 35 U.S.C. 103 as being unpatentable over Khamene et al. (US 2005/0245810 A1) in view of Lucas et al. ("Multi-contrast high-field quality image synthesis for portable low-field MRI using generative adversarial networks and paired data" - Published 2023).
Regarding claim 1, Khamene teaches “A system (Khamene paragraph [0005] "system and method for registering pre-operative magnetic resonance (MR) image with intra-operative MR image is disclosed"), comprising: a database storing a preoperative high-resolution image of an object of interest (Khamene paragraph [0017] "A patient undergoes a MRI scan prior to an operative procedure via a high field closed MRI system (step 202). The image from the scan is stored for later usage"); and
a control circuit comprising a processor and a memory (Khamene paragraph [0012] "Data is collected for an image of the tissue region or organ and stored for further processing by processor 108"), wherein the memory stores instructions executable by the processor to:
obtain, intraoperatively, a low-field strength magnetic resonance image (MRI) of the object of interest (Khamene paragraph [0024] "series of MR images that have been taken pre-operatively and intra-operatively in accordance with the present invention. An MR image 402 is scanned pre-operatively using a high-resolution closed MRI scanner. A second MR image 404 is scanned intra-operatively using a low-resolution open MRI scanner")” and “transmit, intraoperatively, the distortion-corrected image of the object of interest to a user interface (Khamene paragraph [0016] "A display 106 is included for displaying the images and displaying the registered images")”.
However, Khamene does not teach “input, intraoperatively, the low-field strength MRI of the object of interest into a generator model of a pre-trained generative adversarial network, wherein the generator model is pre-trained with low-field strength MRls and paired high-resolution images to correct image distortions; output, intraoperatively, a distortion-corrected image of the object of interest from the generator model based on the low-field strength MRI”.
Lucas teaches “input, intraoperatively, the low-field strength MRI of the object of interest into a generator model of a pre-trained generative adversarial network, wherein the generator model is pre-trained with low-field strength MRls and paired high-resolution images to correct image distortions (Lucas Figure 1 and page 5 paragraph 2 "The first half of the network (stage 1) contains 3 parallel pix2pix layers20, each trained using individual low-field slices (2- dimensional) from different orthogonal imaging planes (axial, coronal, sagittal) with T1w, T2w, and FLAIR images as input channels, and the corresponding multichannel slice in the high-field volume as targets");
output, intraoperatively, a distortion-corrected image of the object of interest from the generator model based on the low-field strength MRI (Lucas Figure 1 and page 5 paragraph 3"The 3D U-Net was trained with reconstructed outputs from the training set of stage 1")”.
PNG
media_image1.png
451
773
media_image1.png
Greyscale
Lucas Figure 1
It would have been obvious to a person having ordinary skill in the art before
effective filing date of the claimed invention of the instant application to combine a system of MRI imaging as taught by Khamene to use a generative adversarial network to reconstruct a low field image with distortion as taught by Lucas.
The suggestion/motivation for doing so would have been that “Deep learning techniques have been widely investigated for medical image reconstruction, modality transformation, super-resolution and denoising applications. Given the similarity between these prior applications and the signal quality challenges facing low-field MRI, deep learning tools have potential to improve image quality” as noted by the Lucas disclosure on page 3 paragraph 3.
Therefore, it would have been obvious to combine the disclosure of Khamene with the Lucas disclosure to obtain the invention as specified in claim 1 as there is a
reasonable expectation of success and/or because doing so merely combines prior art
elements according to known methods to yield predictable results.
Regarding claim 2, the combination of Khamene and Lucas teaches “The system of Claim 1, wherein the paired high-resolution images are images selected from a group consisting of a high-field strength MRI and a high-resolution computed tomography image (Lucas page 4 paragraph 3"High-field scans consisted of 1 mm isotropic 3D T1w and FLAIR images and 0.5 x 0.5 x 5mm or 0.3 x 0.3 x 3mm T2w images").”
The proposed combination as well as the motivation for combining Khamene and Lucas references presented in the rejection of claim 1, applies to claim 2. Finally the system recited in claim 2 is met by Khamene and Lucas.
Regarding claim 6, the combination of Khamene and Lucas teaches “The system of Claim 1, wherein the low-field strength MRI comprises a distortion of an anatomical structure depicted in the low-field strength MRI (Lucas page 3 paragraph 2 "low-field images are typically of lower quality and resolution compared to those produced by high-field scanners4•5. This limitation may impede adoption and accuracy, particularly for applications demanding higher contrast and spatial resolution, like small lesion detection and volumetrics. For example, portable MRI readily demonstrates white matter (WM) lesions in multiple sclerosis (MS) but tends to miss smaller and more peripheral lesions").”
The proposed combination as well as the motivation for combining Khamene and Lucas references presented in the rejection of claim 1, applies to claim 6. Finally the system recited in claim 6 is met by Khamene and Lucas.
Regarding claim 9, the combination of Khamene and Lucas teaches “The system of Claim 1, wherein the memory stores further instructions executable by the processor to generate, intraoperatively, a low-field strength MRI with a low-field strength magnetic field (Khamene paragraph [0024] "series of MR images that have been taken pre-operatively and intra-operatively in accordance with the present invention. An MR image 402 is scanned pre-operatively using a high-resolution closed MRI scanner. A second MR image 404 is scanned intra-operatively using a low-resolution open MRI scanner").”
Regarding claim 11, the combination of Khamene and Lucas teaches “The system of Claim 1, wherein the memory stores further instructions executable by the processor to transmit, intraoperatively, the distortion-corrected image of the object of interest (Lucas Figure 1 and page 5 paragraph 3"The 3D U-Net was trained with reconstructed outputs from the training set of stage 1") to the user interface (Khamene paragraph [0016] "A display 106 is included for displaying the images and displaying the registered images") in real time (Khamene paragraph [0023] "allows for nearly real time acquisition of update scans during the operative procedure").”
The proposed combination as well as the motivation for combining Khamene and Lucas references presented in the rejection of claim 1, applies to claim 11. Finally the system recited in claim 11 is met by Khamene and Lucas.
Regarding claim 12, the combination of Khamene and Lucas teaches “The system of Claim 1, wherein the object of interest comprises an anatomical structure of a particular patient (Lucas page 3 paragraph 2 "low-field images are typically of lower quality and resolution compared to those produced by high-field scanners4•5. This limitation may impede adoption and accuracy, particularly for applications demanding higher contrast and spatial resolution, like small lesion detection and volumetrics. For example, portable MRI readily demonstrates white matter (WM) lesions in multiple sclerosis (MS) but tends to miss smaller and
more peripheral lesions").”
The proposed combination as well as the motivation for combining Khamene and Lucas references presented in the rejection of claim 1, applies to claim 12. Finally the system recited in claim 12 is met by Khamene and Lucas.
Claims 3, 7-8 are rejected under 35 U.S.C. 103 as being unpatentable over Khamene and Lucas in view of Islam et al. ("Improving portable low-field MRI image quality through image-to-image translation using paired low- and high-field images" - Published 2023).
Regarding claim 3, the combination of Khamene and Lucas teaches “The system of Claim 1, (Lucas page 4 paragraph 4 "To prepare imaging data for model training and testing, we coregistered low-field and high-field scans"), and wherein the system further comprises a training control circuit to:
obtain, preoperatively, a first set of training images, wherein the first set of training images comprises a first low-field strength MRI training image and a first high-resolution training image of a first training object of interest (Lucas page 4 paragraph 3 "All participants received portable 64mT brain MRI scans (Hyperfine SWOOP) on the same day as clinical 3T scans (Siemens) with T1w, T2w, and Fluid-Attenuated Inversion Recovery (FLAIR) sequences at each field strength");
input, preoperatively, the first distortion-corrected training image and the first high- resolution training image into a discriminator model of the generative adversarial network to evaluate the first training image (Lucas Figure 1 and Figure 1 description "Low-field (64mT) scans are used as inputs to the generator and outputs are compared to paired high-field (3T) scans by the discriminator"); and
However, the combination of Khamene and Lucas does not explicitly teach “the generative adversarial network is trained to a desired performance level”, “input, preoperatively, the first low-field strength MRI training image into the generator model of the generative adversarial network to generate a first distortion-corrected training image”, “update, preoperatively, one of the generator model and the discriminator model based on the evaluation of the first distortion-corrected training image by the discriminator model”.
Islam teaches “the generative adversarial network is trained to a desired performance level (Islam page 4 paragraph 2 "the LoHiResGAN network, Eq. (1) represents the LoHiResGAN loss function that the generator, G, aims to minimize against an adversarial discriminator, D, which seeks to maximize it")”,
“input, preoperatively, the first low-field strength MRI training image into the generator model of the generative adversarial network to generate a first distortion-corrected training image (Islam page 2 paragraph 4 "our (LoHiResGAN) image-to-image translation model's effectiveness in generating synthetic 3T MR images from the 64mT images");
“input, preoperatively, the first distortion-corrected training image and the first high- resolution training image into a discriminator model of the generative adversarial network to evaluate the first training image (Islam page 2 paragraph 4 "The brain morphometry was compared between the synthetic 3T images, the paired 3T, and the original 64mT images"); and
update, preoperatively, one of the generator model and the discriminator model based on the evaluation of the first distortion-corrected training image by the discriminator model (Islam page 4 paragraph 2 "the LoHiResGAN network, Eq. (1) represents the LoHiResGAN loss function that the generator, G, aims to minimize against an adversarial discriminator, D, which seeks to maximize it").“
It would have been obvious to a person having ordinary skill in the art before
effective filing date of the claimed invention of the instant application to include an MRI imaging system using a generative adversarial network to reconstruct low field images as taught by Khamene and Lucas to include a generator and a discriminator model that evaluates its performance based on the two models output as taught by Islam because such features is the result of apply a known technique to a known device ready for improvement to yield predictable results. More specifically, a generator model and discriminator model are known features of a generative adversarial network, and applying the generative adversarial network to low field MRI images allows the generation of improved MRI images. Therefore, it would have been recognized that modifying the MRI imaging system to include all the features of a generative adversarial network would have yield predictable results because (i) the level of ordinary skill in the art demonstrated by the references applied shows the ability to incorporate an MRI imaging system and generative adversarial network in the image reconstruction/distortion correction environment and (ii) the benefits of such a combination would have been recognized by those of ordinary skill in the art.
Therefore, it would have been obvious to combine the disclosure of Khamene and Lucas with the Islam disclosure to obtain the invention as specified in claim 3 as there is a reasonable expectation of success and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Regarding claim 7, the combination of Khamene, Lucas and Islam teaches “The system of Claim 1, wherein the paired high-resolution images comprise a first resolution, wherein the low-field strength MRIs comprises a second resolution, wherein the second resolution is less than the first resolution (Lucas page 4 paragraph 3 "High-field scans consisted of 1 mm isotropic 3D T1w and FLAIR images and 0.5 x 0.5 x 5mm or 0.3 x 0.3 x 3mm T2w images. Low-field resolutions were 1.5 x 1.5 x 5mm (T1 w and T2w) or 1.6 x 1.6 x 5mm (FLAIR)"), wherein the memory stores further instructions executable by the processor to adjust the first resolution of the paired high-resolution images based on the second resolution of the low-field strength MRIs prior to training the generative adversarial network (Islam page 3 paragraph 2 "The SynthSeg+ method34 was used to resample the datasets to 1 mm3 isotropic resolution, and FSL-FAST was used for bias field correction without referencing an external atlas for spatial information 16").”
The proposed combination as well as the motivation for combining Khamene, Lucas and Islam references presented in the rejection of claim 3, applies to claim 7. Finally the system recited in claim 7 is met by Khamene, Lucas and Islam.
Regarding claim 8, the combination of Khamene, Lucas and Islam teaches “The system of Claim 1, wherein adjusting the first resolution based on the second resolution comprises smoothing each paired high-resolution image (Islam page 5 paragraph 5 "SynthSR improves the visual appearance, there is significant smoothing").”
The proposed combination as well as the motivation for combining Khamene, Lucas and Islam references presented in the rejection of claim 3, applies to claim 8. Finally the system recited in claim 8 is met by Khamene, Lucas and Islam.
Claims 4-5, 13-18 are rejected under 35 U.S.C. 103 as being unpatentable over Khamene, Lucas, and Islam, in view of Sloan et al. (US 10,346,974 B2).
Regarding claim 13, the combination of Khamene, Lucas, and Islam teaches “A training system Khamene paragraph [0005] "system and method for registering pre-operative magnetic resonance (MR) image with intra-operative MR image is disclosed") for a generative adversarial network, the training system comprising: a training processor; and
a training memory (Khamene paragraph [0015] "Processor 108 includes a database 110 that stores the images") storing a plurality of sets of training images, wherein each set of training images comprises a high-resolution training image of a training object of interest and a paired low-field strength MRI training image of the training object of interest (Lucas page 4 paragraph 4 "To prepare imaging data for model training and testing, we coregistered low-field and high-field scans"), and wherein the memory stores instructions executable by the processor to:
obtain a first set of training images, wherein the first set of training images comprises a first low-field strength MRI training image and a first high-resolution training image of a first training object of interest (Lucas Figure 1 and page 5 paragraph 2 "The first half of the network (stage 1) contains 3 parallel pix2pix layers20, each trained using individual low-field slices (2-dimensional) from different orthogonal imaging planes (axial, coronal, sagittal) with T1w, T2w, and FLAIR images as input channels, and the corresponding multichannel slice in the high-field volume as targets");
input the first low-field strength MRI training image into a generator model of a generative adversarial network to generate a first distortion-corrected training image (Islam page 2 paragraph 4 "our (LoHiResGAN) image-to-image translation model's effectiveness in generating synthetic 3T MR images from the 64mT images");
input the first distortion-corrected training image and the first high-resolution training image into a discriminator model of the generative adversarial network (Lucas Figure 1 and Figure 1 description "Low-field (64mT) scans are used as inputs to the generator and outputs are compared to paired high-field (3T) scans by the discriminator")”.
However, the combination of Khamene, Lucas, and Islam does not explicitly teach ““evaluate, by the discriminator model, the first distortion-corrected training image to identify the first distortion-corrected training image as one of "real" or "fake" and update, preoperatively, the generative adversarial network based on the evaluation of the first distortion-corrected training image by the discriminator model, wherein updating the generative adversarial network comprises: if the discriminator model classified the first distortion-corrected training image from the generator model as "real", updating the discriminator model; and if the discriminator model classified the first distortion-corrected training image from the generator model as "fake", updating the generator model.”
Sloan teaches “evaluate, by the discriminator model, the first distortion-corrected training image to identify the first distortion-corrected training image as one of "real" or "fake" (Sloan column 5 lines 61-66 and column 6 line 1 "The discriminator 46 is configured to receive a simulated image 44 from the image synthesizer 42 and a real image 45. This discriminator 46 is configured to produce a determination 48 of which of the images 44, 45 it judges to be real, and which of the images 44, 45 it judges to be fake (simulated). The discriminator will always classify one of the images 44, 45 as real and the other of the images 44, 45 as fake"); and
update, preoperatively, the generative adversarial network based on the evaluation of the first distortion-corrected training image by the discriminator model, wherein updating the generative adversarial network comprises: if the discriminator model classified the first distortion-corrected training image from the generator model as "real", updating the discriminator model (Sloan column 7 lines 24-26 "The discriminator training process comprises determining a set of weights for the deep learning network of the discriminator" and lines 36-41 "For each of the training data sets, the discriminator receives the real T2-weighted image for that training data set and a simulated T2-weighted image that has been simulated from the Tl-weighted image for that training data set. The discriminator attempts to determine which of the images is real and which is simulated"); and
if the discriminator model classified the first distortion-corrected training image from the generator model as "fake", updating the generator model (Sloan column 7 lines 58- 64 "The discriminator 46 is used in the training of the image synthesizer 42. While training the image synthesizer 42, the weights of the discriminator 48 are frozen so that only the weights of the image synthesizer 42 are updated. The output of the image synthesizer 42 is directly linked as input to the discriminator 48 to allow backpropagation of an error signal of the discriminator 46" and column 8 lines 25-33 "the discriminator 46 which detects which of the given images is real and fake. Since the image synthesizer 42 is actively being trained to trick the discriminator 46 into believing the generated image is genuine, weights within the image synthesizer 42 are adjusted whilst training to maximize the error signal of the discriminator. In other embodiments, any appropriate process may be used to maximize or increase an error signal of the discriminator 48).”
It would have been obvious to a person having ordinary skill in the art before
effective filing date of the claimed invention of the instant application to combine a system of distortion correction of a MRI image as taught by Khamene, Lucas, and Islam to include training and improvement to the generator and discriminator models as taught by Sloan.
The suggestion/motivation for doing so would have been “By training the image synthesizer 42 and discriminator 46 together in an adversarial function, better simulated images may be produced than if the image synthesizer 42 were to be trained alone" as noted by the Sloan disclosure in column 7, lines 9-12.
Therefore, it would have been obvious to combine the disclosure of Khamene, Lucas, and Islam with the Sloan disclosure to obtain the invention as specified in claim 13 as there is a reasonable expectation of success and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Regarding claim 4, the combination of Khamene, Lucas, Islam, and Sloan teaches “The system of Claim 3, wherein the discriminator model comprises a discriminator neural network and the generator model comprises a generator neural network, and wherein the training control circuit is further to adjust at least one weight of at least one layer of the discriminator neural network based on the discriminator model classifying the first distortion- corrected training image from the generator model as "real" (Sloan column 7 lines 24-26 "The discriminator training process comprises determining a set of weights for the deep learning network of the discriminator" and lines 36-41 "For each of the training data sets, the discriminator receives the real T2-weighted image for that training data set and a simulated T2-weighted image that has been simulated from the Tl-weighted image for that training data set. The discriminator attempts to determine which of the images is real and which is simulated").”
The proposed combination as well as the motivation for combining Khamene, Lucas, Islam, and Sloan references presented in the rejection of claim 13, applies to claim 4. Finally the system recited in claim 4 is met by Khamene, Lucas, Islam, and Sloan.
Regarding claim 5, the combination of Khamene, Lucas, Islam, and Sloan teaches “The system of Claim 3, wherein the discriminator model comprises a discriminator neural network and the generator model comprises a generator neural network, and wherein the training control circuit is further to adjust at least one weight of at least one layer of the generator neural network of the generator model (Sloan column 7 lines 54-56 "The image synthesizer training process comprises determining a set of weights for the deep learning network of the image synthesizer 42") based on the discriminator model classifying the first distortion-corrected training image as "fake" (Sloan column 7 lines 58- 64 "The discriminator 46 is used in the training of the image synthesizer 42. While training the image synthesizer 42, the weights of the discriminator 48 are frozen so that only the weights of the image synthesizer 42 are updated. The output of the image synthesizer 42 is directly linked as input to the discriminator 48 to allow backpropagation of an error signal of the discriminator 46").”
The proposed combination as well as the motivation for combining Khamene, Lucas, Islam, and Sloan references presented in the rejection of claim 13, applies to claim 5. Finally the system recited in claim 5 is met by Khamene, Lucas, Islam, and Sloan.
Regarding claim 14, the combination of Khamene, Lucas, Islam, and Sloan teaches “The training system of Claim 13, wherein the discriminator model comprises a discriminator neural network and the generator model comprises a generator neural network, and wherein the training memory stores instructions executable by the training processor to: adjust at least one weight of at least one layer of the discriminator neural network of the discriminator model classified the first distortion-corrected training image from the generator model as "real" (Sloan column 7 lines 24-26 "The discriminator training process comprises determining a set of weights for the deep learning network of the discriminator" and lines 36-41 "For each of the training data sets, the discriminator receives the real T2-weighted image for that training data set and a simulated T2-weighted image that has been simulated from the Tl-weighted image for that training data set. The discriminator attempts to determine which of the images is real and which is simulated"); and
adjust at least one weight of at least one layer of the generator neural network of the generator model (Sloan column 7 lines 54-56 "
The image synthesizer training process comprises determining a set of weights for the deep learning network of the image synthesizer 42")
based on the discriminator model classifying the first distortion-corrected training image as "fake" (Sloan column 7 lines 58- 64 "The discriminator 46 is used in the training of the image synthesizer 42. While training the image synthesizer 42, the weights of the discriminator 48 are frozen so that only the weights of the image synthesizer 42 are updated. The output of the image synthesizer 42 is directly linked as input to the discriminator 48 to allow backpropagation of an error signal of the discriminator 46" and column 8 lines 25-33 "the discriminator 46 which detects which of the given images is real and fake. Since the image synthesizer 42 is actively being trained to trick the discriminator 46 into believing the generated image is genuine, weights within the image synthesizer 42 are adjusted whilst training to maximize the error signal of the discriminator. In other embodiments, any appropriate process may be used to maximize or increase an error signal of the discriminator 48).”
The proposed combination as well as the motivation for combining Khamene, Lucas, Islam, and Sloan references presented in the rejection of claim 13, applies to claim 14. Finally the method recited in claim 14 is met by Khamene, Lucas, Islam, and Sloan.
Regarding claim 15, the combination of Khamene, Lucas, Islam, and Sloan teaches “The training system of Claim 13, further comprising training the generator model to a desired performance level by: obtaining at least one other set of training images of a different subject (Lucas page 4 paragraph 3 "All participants received portable 64mT brain MRI scans (Hyperfine SWOOP) on the same day as clinical 3T scans (Siemens) with T1w, T2w, and Fluid-Attenuated Inversion Recovery (FLAIR)
sequences at each field strength"); and
further training the generative adversarial network with the at least one other set of training images (Lucas page 4 paragraph 4 "To prepare imaging data for model training and testing, we coregistered low-field and high-field scans").
Claim 16 recites a method with steps corresponding to the device elements
recited in claim 13. Therefore, the recited steps of this claim are mapped to the
proposed combination in the same manner as the corresponding elements of device
claim 13. Additionally, the rationale and motivation to combine the Khamene, Lucas, Islam, and Sloan references, presented in rejection of claim 13 apply to this claim. The combination of Khamene, Lucas, Islam, and Sloan also teaches “transmitting a notification to a user interface (Khamene paragraph [0016] "A display 106 is included for displaying the images and displaying the registered images") based on the generative adversarial network reaching the desired performance level (Islam page 4 paragraph 2 "the LoHiResGAN network, Eq. (1) represents the LoHiResGAN loss function that the generator, G, aims to minimize against an adversarial discriminator, D, which seeks to maximize it").”
Regarding claim 17, the combination of Khamene, Lucas, Islam, and Sloan teaches “The method of Claim 16, further comprising obtaining, preoperatively, a high-field strength MRI of the first training object of interest (Lucas page 4 paragraph 3 "All participants received portable 64mT brain MRI scans (Hyperfine SWOOP) on the same day as clinical 3T scans (Siemens) with T1w, T2w, and Fluid-Attenuated Inversion Recovery (FLAIR) sequences at each field strength").”
Regarding claim 18, the combination of Khamene, Lucas, Islam, and Sloan teaches “The method of Claim 16, further comprising obtaining, preoperatively, a high-resolution computed tomography image of the first training object of interest (Lucas page 4 paragraph 3 "High-field scans consisted of 1 mm isotropic 3D T1w and FLAIR images and 0.5 x 0.5 x 5mm or 0.3 x 0.3 x 3mm T2w images. Low-field resolutions were 1.5 x 1.5 x 5mm (T1 w and T2w) or 1.6 x 1.6 x 5mm (FLAIR)").”
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Khamene, and Lucas, in view of Leussler (US 2010/0109667 A1).
Claim 10, the combination of Khamene, and Lucas teaches the system of claim 9 and “the low-field strength magnetic field comprises a magnetic field strength less than or equal to 1 T (Lucas page 3 paragraph 2 "low-field strength MRI scanners operating at 64mT")”.
However, the combination of Khamene, and Lucas does not teach “dome-shaped housing that is configured to house an array of magnets , wherein the array of magnets are arranged to generate the low-field strength magnetic field toward the object of interest within a field of view” and “a radio frequency coil assembly configured to selectively excite magnetization in the object of interest in the field of view”.
Leussler teaches “dome-shaped housing that is configured to house an array of magnets , wherein the array of magnets are arranged to generate the low-field strength magnetic field toward the object of interest within a field of view (Leussler figure 1 and "the TEM RF coil, wherein a TEM RF coil 100 is formed from multiple loop elements such as 101a and 102a. Each loop element 101a, 102a provides the current-forward path, while the current return path is provided by a corresponding return electrical line 101b and 102b, respectively. The resonance frequency of the TEM RF coil is determined by the values of capacitors 104, 105, 106 and 107")” and “a radio frequency coil assembly configured to selectively excite magnetization in the object of interest in the field of view (Leussler paragraph [0026] "In FIG. 4a, the individual microstrip lengths forming the loop elements 401 provide the forward current path. Each loop element 401 has an associated local shield 405 that, in addition to shielding the associated loop element 401 from stray RF fields, also provides the return current path. In FIG. 4b, in addition to the local shield 405, an additional shield 407 is provided for enhanced shielding from stray RF fields. In this embodiment also, the local shield 405 provides the return current path for the loop elements 401. The subject under examination is shown by the innermost circle 403").”
PNG
media_image2.png
669
682
media_image2.png
Greyscale
Leussler Figure 1
It would have been obvious to a person having ordinary skill in the art before
effective filing date of the claimed invention of the instant application to include an MRI imaging system using a generative adversarial network to reconstruct low field images as taught by Khamene and Lucas to include a domed shaped housing including radio frequency coils as taught by Leussler because such features is the result of apply a known technique to a known device ready for improvement to yield predictable results. More specifically, an MRI imaging system using a generative adversarial network with a dome-shaped housing and radio frequency coil assembly is further improving the MRI systems imaging capabilities. Therefore, it would have been recognized that modifying the MRI imaging system to include a dome-shape housing and radio frequency coil assembly would have yield predictable results because (i) the level of ordinary skill in the art demonstrated by the references applied shows the ability to incorporate an MRI imaging system and any MRI imaging system capable of producing low-field images and (ii) the benefits of such a combination would have been recognized by those of ordinary skill in the art.
Therefore, it would have been obvious to combine the disclosure of Khamene, Lucas, and Islam with the Leussler disclosure to obtain the invention as specified in claim 10 as there is a reasonable expectation of success and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Claims 19 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Khamene, Lucas, Islam, and Sloan, in view of Leussler.
Regarding claim 19, the combination of Khamene, Lucas, Islam, and Sloan teaches “The method of Claim 16, further comprising, after training the generative adversarial network to the desired performance level (Islam page 4 paragraph 2 "the LoHiResGAN network, Eq. (1) represents the LoHiResGAN loss function that the generator, G, aims to minimize against an adversarial discriminator, D, which seeks to maximize it"), generating a distortion-corrected image with minimized distortions, wherein generating the distortion-corrected image comprises:
obtaining, intraoperatively, a low-field strength MRI of an object of interest with a low- field strength magnetic resonance imaging system (Khamene paragraph [0024] "series of MR images that have been taken pre-operatively and intra-operatively in accordance with the present invention. An MR image 402 is scanned pre-operatively using a high-resolution closed MRI scanner. A second MR image 404 is scanned intra-operatively using a low-resolution open MRI scanner"), wherein
inputting, intraoperatively, the low-field strength MRI of the object of interest into the generator model, wherein the generator model is to generate the distortion-corrected image (Lucas Figure 1 and page 5 paragraph 2 "The first half of the network (stage 1) contains 3 parallel pix2pix layers20, each trained using individual low-field slices (2-dimensional) from different orthogonal imaging planes (axial, coronal, sagittal) with T1w, T2w, and FLAIR images as input channels, and the corresponding multichannel slice in the high-field volume as targets");and
transmitting, intraoperatively, the distortion-corrected image to a user interface, wherein generation and transmission of the distortion-corrected image occurs in real-time (Khamene paragraph [0016] "A display 106 is included for displaying the images and displaying the registered images").”
However, the combination of Khamene, Lucas, Islam, and Sloan does not teach “the low-field strength MRI comprises a dome-shaped housing and an array of magnets arranged about the dome-shaped housing”.
Leussler teaches “the low-field strength MRI comprises a dome-shaped housing and an array of magnets arranged about the dome-shaped housing (Leussler figure 1 and "the TEM RF coil, wherein a TEM RF coil 100 is formed from multiple loop
elements such as 101a and 102a. Each loop element 101a, 102a provides the current-forward path, while the current return path is provided by a corresponding return electrical line 101b and 102b, respectively. The resonance frequency of the TEM RF coil is determined by the values of capacitors 104, 105, 106 and 107")“.
It would have been obvious to a person having ordinary skill in the art before
effective filing date of the claimed invention of the instant application to include an MRI imaging system using a generative adversarial network to reconstruct low field images as taught by Khamene, Lucas, Islam, and Sloan to include a domed shaped housing including radio frequency coils as taught by Leussler because such features is the result of apply a known technique to a known device ready for improvement to yield predictable results. More specifically, an MRI imaging system using a generative adversarial network with a dome-shaped housing and radio frequency coil assembly is further improving the MRI systems imaging capabilities. Therefore, it would have been recognized that modifying the MRI imaging system to include a dome-shape housing and radio frequency coil assembly would have yield predictable results because (i) the level of ordinary skill in the art demonstrated by the references applied shows the ability to incorporate an MRI imaging system and any MRI imaging system capable of producing low-field images and (ii) the benefits of such a combination would have been recognized by those of ordinary skill in the art.
Therefore, it would have been obvious to combine the disclosure Khamene, Lucas, Islam, and Sloan with the Leussler disclosure to obtain the invention as specified in claim 19 as there is a reasonable expectation of success and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Regarding claim 20, the combination of Khamene, Lucas, Islam, Sloan, and Leussler teaches “The method of Claim 19, further comprising: projecting a low-field strength magnetic field from the array of magnets toward the object of interest located within a field of view, wherein the low-field strength magnetic field comprises a magnetic field strength less than or equal to 1 T (Lucas page 3 paragraph 2 "low-field strength MRI scanners operating at 64mT");
transmitting a radio frequency pulse sequence to a radio frequency coil assembly configured to selectively excite magnetization in the object of interest within the field of view (Leussler paragraph [0026] "In FIG. 4a, the individual microstrip lengths forming the loop elements 401 provide the forward current path. Each loop element 401 has an associated local shield 405 that, in addition to shielding the associated loop element 401 from stray RF fields, also provides the return current path. In FIG. 4b, in addition to the local shield 405, an additional shield 407 is provided for enhanced shielding from stray RF fields. In this embodiment also, the local shield 405 provides the return current path for the loop elements 401. The subject under examination is shown by the innermost circle 403");
and receiving and recording an output signal from the radio frequency coil assembly (Leussler paragraph [0044] "The MR signal received with the RF coils 1103 contains the actual information concerning the local spin densities in a region of interest of the subject 1105 being imaged. The received signals are reconstructed by the reconstruction unit 1109, and displayed on the display unit 1110 as an MR image or an MR spectrum. It is alternatively possible to store the signal from the reconstruction unit 1109 in a storage unit 1115").”
The proposed combination as well as the motivation for combining Khamene, Lucas, Islam, Sloan, and Leussler references presented in the rejection of claim 19, applies to claim 20. Finally the method recited in claim 20 is met by Khamene, Lucas, Islam, Sloan, and Leussler.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JASPREET KAUR whose telephone number is (571)272-5534. The examiner can normally be reached Monday - Friday 7:30 am - 4:00 PST.
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, Amandeep Saini can be reached at (571)272-3382. 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.
/JASPREET KAUR/Examiner, Art Unit 2662
/Siamak Harandi/Primary Examiner, Art Unit 2662