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 .
Claim Rejections - 35 USC § 102
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.
Claims 1-4, 7-9, 12, 15-17, and 19-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Kustner et al. Fully Automated and Standardized Segmentation of Adipose Tissue Compartments via Deep Learning in 3D Whole-Body MRI of Epidemiologic Cohort Studies (hereinafter “Kustner”, cited in the IDS).
Regarding claim 1, Kustner discloses a system for segmenting adipose tissues in magnetic resonance (MR) images (see page 2 second column, materials and methods, a CNN is proposed for 3D semantic segmentation of whole-body adipose tissue)
PNG
media_image1.png
228
358
media_image1.png
Greyscale
, the system comprising: a multi-channel input for receiving a set of combined multi-contrast MR images of a subject (see the second paragraph of the above cited section, the network is trained and tested on whole-body MRI data from different multicenter epidemiologic patient databases with varying image contrast); an adipose tissue segmentation neural network coupled to the input and configured to generate at least one segmentation map for an adipose tissue (see above cited section first paragraph, a CNN is proposed for 3D semantic segmentation of whole-body adipose tissue which are mapped into SAT, VAT, LT, and background) ; and a display coupled to the adipose tissue segmentation neural network and configured to display the at least one segmentation map for the adipose tissue (see col. 2 page 2 which integrates the model into clinical workflow with automated reporting of adipose tissue head-feet profiles to enable profiling and studying in an epidemiologic setting, see the figures 2-5 that display the segmented tissue outputs).
PNG
media_image2.png
232
344
media_image2.png
Greyscale
Regarding claim 2, Kustner discloses wherein the set of combined multi-contrast MR images includes anatomical, water, and fat images (see paragraph bridging pages 3-4 regarding the architecture where T1 data [anatomical] and Dixon technique data which is fat and water image)
PNG
media_image3.png
269
347
media_image3.png
Greyscale
Regarding claim 3, the anatomical images are Ti-weighted images (see above cited section, T1 weighted).
Regarding claim 4, Kustner discloses the multi-contrast MR images are full field- of-view volumetric MR images (see first cited section above for materials and methods, semantic segmentation of whole-body adipose tissue).
Regarding claim 7, Kustner discloses wherein the adipose tissue segmentation neural network is a 3D convolutional neural network comprising a plurality of densely connected convolutional blocks and a channel and spatial attention mechanism (proposed three-dimensional (3D) densely connected convolutional neural network (DCNet) segmentation network with merge-and-run (MRGE) blocks for multiresolution segmentation, where DCNet has a single- or dual-channel 3D input; Figure 1; FIG. 1 description; page 3, column 2, lines 46-52).
Regarding claim 8, Kustner discloses wherein the 3D convolution neural network further comprises a 3D U-Net convolutional network (robustness and reliability were investigated for all experiments by means of fourfold cross validation of the proposed DCNet and compared against a 3D U-Net segmentation; page 4, column 1, lines 9-17).
Regarding claim 9, Kustner discloses the adipose tissue is one of a visceral adipose tissue and a subcutaneous adipose tissue (Figure 2 depicts adipose tissue (AT) segmented into subcutaneous AT (red) and visceral AT (yellow); Figure 2; Figure 2 description).
Claim 12 is similarly analyzed to claim 1.
Claims 15-17 is similarly analyzed to claim 2-4.
Claims 19-20 are similarly analyzed to claim 7 and 9.
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.
Claims 5-6, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Kustner in view of Moloney et al. US 2021/0201526 (hereinafter “Moloney”).
Regarding claim 5, as discussed above Kustner discloses the limitations of claim 1. Kustner discloses the adipose tissue segmentation neural network (the use of MRI for whole-body assessment of adipose tissue distribution; page 1, column 2, lines 1-14).
Kustner fails to disclose wherein the neural network is a 2.5D convolutional neural network comprises a bi-directional convolutional long-short term memory recurrent network in the through-plane dimension.
Moloney discloses wherein the neural network is a 2.5D convolutional neural network comprises a bi-directional convolutional long-short term memory recurrent network in the through-plane dimension (combining elements from a volumetric representation includes calculating surface areas by counting the number of occupied voxels in a 2.5D manifold, where machine learning approaches may be utilized in computer vision tasks, for instance convolutional neural networks (CNN) employing hardware such as long short-term memory (LSTM) blocks; paragraphs [0064],[0120]).
Kustner and Moloney are analogous art because they are from the same field of endeavor of machine learning with training images.
It would be obvious to one of ordinary skill in the art to take the system as taught by Kustner and add wherein the neural network is a 2.5D convolutional neural network comprises a bi-directional convolutional long-short term memory recurrent network in the through-plane dimension as taught by Moloney to gain the advantage of using less computational power- and memory as compared to a 3D CNN by using a 2.5D CNN and segmenting the images together.
As per claim 6, Kustner in view of Moloney discloses the system according to claim 5. Kustner discloses a 2D U-Net convolutional network (two-dimensional (2D) deep learning networks for abdominal adipose tissue segmentation were proposed, using a CNN-based segmentation architecture derived from the U-Net; page 2, column 1, lines 1-30).
Kustner fails to disclose the 2.5D convolutional neural network. However, Moloney discloses the 2.5D convolutional neural network (combining elements from a volumetric representation includes calculating surface areas by counting the number of occupied voxels in a 2.5D manifold, where machine learning approaches may be utilized in computer vision tasks, for instance convolutional neural networks (CNN); paragraphs [0064],[0120]). It would be obvious to one of ordinary skill in the art to take the system as taught by Kustner and add the 2.5D convolutional neural network as taught by Moloney to gain the advantage of using less computational power and memory as compared to a 3D CNN by using a 2.5D CNN and segmenting the images together.
Claim 18 is similarly analyzed to claim 5.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Kustner in view of Sugino et al. Loss Weightings for Improving Imbalanced Brain Structure Segmentation Using Fully Convolutional Networks (hereinafter “Sugino”, cited in the IDS).
As per claim 10, Kustner discloses the system according to claim 1. Kustner fails to disclose wherein the adipose tissue segmentation neural network is trained using a frequency-balancing boundary-emphasizing Dice Loss (FBDL) function.
Sugino discloses wherein the adipose tissue segmentation neural network is trained using a frequency-balancing boundary-emphasizing Dice Loss (FBDL) function (brain structure segmentation on magnetic resonance images using fully convolutional networks using a Dice loss function and evaluating the effect of median inverse frequency weighting and boundary-based loss functions; abstract, page 3, section 2.3, paragraph 1).
Kustner and Sugino are analogous art because they are from the same field of endeavor of MRI segmentation.
It would be obvious to one of ordinary skill in the art to take the system as taught by Kustner and add wherein the adipose tissue segmentation neural network is trained using a frequency-balancing boundary-emphasizing Dice Loss (FBDL) function as taught by SUGINO to gain the advantage of having the class weights for the neural network include both frequency balancing portions along with boundary conditions to have a well-trained system that is able to differentiate between different tissue types.
Claim 13 is similarly analyzed to claim 10.
Allowable Subject Matter
Claims 11 and 14 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Please see the attached 892 notice of references cited.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOHN B STREGE whose telephone number is (571)272-7457. The examiner can normally be reached M-F 9-5 (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, Chan Park can be reached at (571)272-7409. 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.
/JOHN B STREGE/Primary Examiner, Art Unit 2669
Prosecution Insights