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
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, 2, 4-8, 10-11, 13 and 15-18 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Segmentation of Shoulder Muscle MRI Using a New Region and Edge based Deep Auto-Encoder to Khan et al., hereinafter, “Khan”.
Claim 1. Khan teaches A system for segmenting one or more regions of interest (ROI) in medical image data, comprising: [2. The Proposed Semantic Segmentation Framework] The proposed muscle segmentation framework aims to accurately and precisely segment the tear portion from the entire region of the muscle and background region.
a memory configured to store instructions [3.2 Implementation Details] 16 GB RAM
and a first set of a plurality of segmented medical images of a subject at different time points; [3.2 Implementation Details] The dataset contains 15 patients' images, and an augmentation strategy was employed to create more samples. Examiner interprets “to create more samples” to be later than the initial images (samples).
a processor configured to: [3.2 Implementation Details] All experiments were performed on MATLAB R2020b using Dell Core i7
access the memory; [3.2 Implementation Details] All experiments were performed on MATLAB R2020b using Dell Core i7, 16 GB RAM. MATLAB DL toolbox was used for the implementation of segmentation.
fine tune a plurality of trained convolutional neural networks (CNNs) using the first set of the plurality of segmented medical images; [2.2.3 TL-based Fine-Tuned Segmentation Model] VGG16 and VGG19 CNNs were considered to have been already trained on the ImageNet dataset [7], [49]. The ImageNet dataset contains 15 million images…
access a second set of a plurality of medical images of the subject, [4.1 Results] Fig. 5 from (f) to (u) shows the segmented image of the existing CNN models
wherein the second set of the plurality of medical images comprise a plurality of pixels or voxels; Fig. 5 and Fig. 6
segment the second set of the plurality of medical images by inputting the second set of the plurality of medical images into the plurality of finetuned CNNs; Fig. 3, SegNet, U-SegNet, [4.3 Performance comparison of Proposed Architectures] The proposed architecture globally outperforms existing custom, and TL-based fine-tuned the pre-trained semantic segmentation CNNs model.
identify one or more groups of the plurality of pixels or voxels belonging to one or more ROI; Fig. 3, Segmentation Outputs, Tear and Muscle
calculate a plurality of variables from the segmented plurality of medical images; [4.3 Performance comparison of Proposed Architectures], Table 2 IOU% and DS%. dice similarity (DS Score), and Jaccard Coefficient (intersection over union (IOU)) calculated using a plurality of variables
output at least one of segmented ROI or a change in the plurality of variables; Fig. 3, Segmentation Outputs and Fig. 5
and a display configured to display the output. 4.1 Results, The obtained results appear satisfactory and visually distinguishable
Claim 2. Khan teaches wherein each of the plurality of trained CNNs vary in at least one of a network structure, one or more network parameters during training, a training set, or one or more parameters during deployment. [Custom SegNet] The VGG-16/19 encoder have 13/16 Convolutional and 3 fully connected (FC) layers [37]….
Claim 4. Khan teaches wherein the plurality of variables includes at least one of a median, a standard deviation, a label volume variation, a label dice, or a label probability between each of the plurality of fine-tuned CNNs. [4. Result and Discussion], [4.3 Performance comparison of Proposed Architectures], Table 2 IOU% and DS%. dice similarity (DS Score), and Jaccard Coefficient (intersection over union (IOU))
Claim 5. Khan teaches wherein each of the plurality of trained CNNs are trained using a training set of segmented medical images. [2.2.3 TL-based Fine-Tuned Segmentation Model] TL has been utilized to produce a satisfactory performance on a limited amount of medical datasets
Claim 6. Khan teaches wherein the one or more ROI includes one or more muscles. [page 3] we have developed a fully automated muscle segmentation system…The proposed RE-DAE is developed and evaluated on the tear-related shoulder muscle dataset.
Claim 7. Khan teaches wherein the processor is further configured to generate a three-dimensional (3D) model that identifies the one or more groups of the plurality of pixels or voxels belonging to the one or more ROI of the subject. [Abstract] using a 3D MRI shoulder muscle dataset, Fig. 3, Segmentation Outputs, Tear and Muscle (groups)
Claim 8. Khan teaches wherein the first set of the plurality of segmented medical images and the second set of the plurality of medical images include magnetic resonance (MR) images. Fig. 3. Segmentation framework of the muscle MR images using customized CNN models
Claim 10. Reviewed and analyzed in the same way as claim 1. See the above analysis and rationale.
Claim 11. Khan teaches wherein the plurality of CNNs are trained using a training set of a plurality of medical images, [3.1 Dataset] The dataset contains 15 patients' images
and wherein the plurality of CNNS are finetuned [4.3 Performance comparison of Proposed Architectures] …TL-based fine-tuned the pre-trained semantic segmentation CNNs model.
using a set of a plurality of segmented medical images of the subject at different time points. [3.2 Implementation Details] The dataset contains 15 patients' images, and an augmentation strategy was employed to create more samples. Examiner interprets “to create more samples” to be later than the initial images (samples).
Claim 13. Reviewed and analyzed in the same way as claim 2. See the above analysis and rationale.
Claim 15. Reviewed and analyzed in the same way as claim 4. See the above analysis and rationale.
Claim 16. Reviewed and analyzed in the same way as claim 6. See the above analysis and rationale.
Claim 17. Reviewed and analyzed in the same way as claim 7. See the above analysis and rationale.
Claim 18. Reviewed and analyzed in the same way as claim 8. See the above analysis and rationale.
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.
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.
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over by Segmentation of Shoulder Muscle MRI Using a New Region and Edge based Deep Auto-Encoder to Khan et al., hereinafter, “Khan” in view of US 2016/0174902 A1 to Georgescu et al. hereinafter, “Georgescu”.
Claim 3. Khan fails to explicitly teach the trained CNNs use a sliding window approach to segment the second set of the plurality of medical images. Georgescu, is in the field of detecting an object in medical images using neural networks, teaches wherein the trained CNNs use a sliding window approach to segment the second set of the plurality of medical images. [0119] the trained shall neural network can be applied to test all voxels in the 3D medical image in a sliding-window process to generate a number of candidates (e.g., 2000) for the second stage of classification.
Khan is in the field of detecting an object in medical images using neural networks. Thus, before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of Khan with the teachings of Georgescu [0003] for fast and robust anatomical object detection in medical image analysis.
Claim(s) 9 and 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Segmentation of Shoulder Muscle MRI Using a New Region and Edge based Deep Auto-Encoder to Khan et al., hereinafter, “Khan” in view of US 2022/0301224 A1 to Zhang.
Claim 9. Khan fails to explicitly teach training the plurality trained CNNs includes adjusting at least one of a training iteration or a learning rate. Zhang, is in the field of segmenting medical images using deep learning, wherein training the plurality trained CNNs includes adjusting at least one of a training iteration or a learning rate. [0220] if the updated segmentation model is a CNN, the second training module 450 may adjust relevant parameters (e.g., a learning rate, a weight matrix, etc.)
Khan is in the field of segmenting and detecting an object in medical images using neural networks. Thus, before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of Khan with the teachings of Zhang [0003] to provide systems and methods for image segmentation with high accuracy and high speed.
Claim 12. Reviewed and analyzed in the same way as claim 9. See the above analysis and rationale.
Claim(s) 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Segmentation of Shoulder Muscle MRI Using a New Region and Edge based Deep Auto-Encoder to Khan et al., hereinafter, “Khan” in view of US 2022/0301224 A1 to Zhang and in further view of US 2016/0174902 A1 to Georgescu et al. hereinafter, “Georgescu”.
Claim 14. Khan and Zhang fails to explicitly teach the trained CNNs use a sliding window approach to segment the second set of the plurality of medical images. Georgescu, is in the field of detecting an object in medical images using neural networks, teaches claim 14, which has been reviewed and analyzed in the same way as claim 3. See the above analysis and rationale.
Khan is in the field of detecting an object in medical images using neural networks. Thus, before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of Khan with the teachings of Georgescu [0003] for fast and robust anatomical object detection in medical image analysis.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DELOMIA L GILLIARD whose telephone number is (571)272-1681. The examiner can normally be reached 8am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, John Villecco can be reached at (571) 272-7319. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/DELOMIA L GILLIARD/Primary Examiner, Art Unit 2661
Prosecution Insights