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 .
Claims 1-10 are pending in the application.
Claim Objections
Claim 5 recites two “decoder”. For the purpose of prior art rejection, Examiner considers the first decoder an “encoder”. Claim 10 has similar issue.
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) 1-10 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Chen et al. (Chen YT, Yang EH, Chang WL, Lin J, Cheng HC, Huang CR. Mask focal modulation network for gastric intestinal metaplasia segmentation. In 2024 International Joint Conference on Neural Networks (IJCNN) 2024 Jun 30 (pp. 1-8). IEEE. Hereafter Chen).
As per claim 1, Chen teaches an analyzing method for gastric endoscopic image utilizing image segmentation technology (Abstract), the analyzing method adapted to a computer system (page 5 right column 4th line “a GTX 3080 GPU”) and comprising:
obtaining a gastric endoscopic image and cutting the gastric endoscopic image into a plurality of patches (Fig. 1 “Image” with dimension HXWX3 being input image; Abstract “gastric IM segmentation from endoscopic images”; Fig. 1 “patch partition”);
inputting one of the patches into an encoder to obtain an encoded feature map (Fig. 1 “Encoder”; page 3 right col. B. Encoder Module “The encoder has four stages. The width and height of the feature maps are divided by 2 and the number of channels is doubled in each stage as shown in Fig. 1”);
inputting the encoded feature map into a decoder to obtain a decoded feature map (Fig. 1 “Pixel Decoder”; page 3 right col. C. Pixel Decoder Module “The output f4 of the pixel decoder is the feature embedding of size 1/4 of the original resolution”);
inputting the decoded feature map into a mask focal modulation decoder, wherein the mask focal modulation decoder comprises a plurality of mask focal modulation stages (Fig. 1 showing 3 mask focal modulation stages; See below attached para. from page 3 right col. section D), and wherein one of the mask focal modulation stages is utilized to receive the decoded feature map and a first prototype feature (Fig. 1 the first stage receiving the decoded feature map and a first prototype feature “Prototypes NXC”);
PNG
media_image1.png
295
687
media_image1.png
Greyscale
inputting the first prototype feature into a focal modulation function to obtain a focal modulation feature (Fig. 2; page 4 eqn. (2)
PNG
media_image2.png
57
73
media_image2.png
Greyscale
is a focal modulation function applied to the first prototype feature);
inputting the decoded feature map into a scaling function then into a projection function to obtain a scaled feature (See below attached eqn. (2) and description from page 4 left col.;
PNG
media_image3.png
56
108
media_image3.png
Greyscale
representing applying a scaling function R(.) to decoded feature map fs, then applying projection function F(.));
PNG
media_image4.png
218
705
media_image4.png
Greyscale
;
generating a second prototype feature based on a mask, the scaled feature, and the focal modulation feature (See above attached para. from page 4 left col., in which MFM(pb,fs,mb) representing a second prototype feature, mb a binary mask,
PNG
media_image3.png
56
108
media_image3.png
Greyscale
the scaled function and
PNG
media_image2.png
57
73
media_image2.png
Greyscale
the focal modulation feature. See description in page 4 left col.); and
generating a prediction mask based on the second prototype feature, wherein the prediction mask comprises a plurality of pixels for segmenting a gastric intestinal metaplasia area (Fig. 1 “Predict Mask” with dimension HXWXK; Abstract “Gastric intestinal metaplasia (IM)”).
As per claim 2, dependent upon claim 1, Chen teaches wherein generating the prediction mask based on the second prototype feature comprises:
inputting the second prototype feature corresponding to a last stage among the mask focal modulation stages into a plurality of neural networks to obtain a mask feature and a category feature (See below Chen partial Fig. 1 (annotation added), in which second prototype feature from last stage with dimension NXC is input to neural networks MLP, generating a mask feature (“Mask Embeddings”) and a category feature (“Class Embeddings”));
performing element-wise multiplication on the mask feature and the decoded feature map to obtain a binarization mask (See below partial Fig. 1 first multiplication representing element-wise multiplication on the mask feature and the decoded feature map to obtain a binarization mask (“Binary Masks”)); and
performing element-wise multiplication on the binarization mask and the category feature to obtain the prediction mask (See below partial Fig. 1 second multiplication representing element-wise multiplication on the binarization mask and the category feature to obtain the prediction mask).
PNG
media_image5.png
312
785
media_image5.png
Greyscale
As per claim 3, dependent upon claim 1, Chen teaches wherein generating the second prototype feature based on the mask, the scaled feature, and the focal modulation feature comprises:
performing element-wise multiplication on the mask, the scaled feature, and the focal modulation feature to obtain the second prototype feature (page 4 eqn. (2), see below attached para.).
PNG
media_image6.png
221
689
media_image6.png
Greyscale
As per claim 4, dependent upon claim 1, Chen teaches wherein the mask comprises a plurality of values, and the analyzing method further comprises: determining whether each of the values of the mask is less than a threshold to generate a next stage mask (See below attached para. from page 4 left col.).
PNG
media_image7.png
347
680
media_image7.png
Greyscale
.
As per claim 5, dependent upon claim 1, Chen teaches wherein the
Claim 6, an independent system claim, recites steps corresponding to method claim 1. Therefore the recited steps of 6 are mapped to Chen in the same manner as corresponding steps in claim 1. Chen additionally teaches system elements, such as a memory and a processor (page 5 right column 4th line “a GTX 3080 GPU”).
Claim 7, dependent upon claim 6, recites similar steps corresponding to method claim 2. Therefore the recited steps of 7 are mapped to Chen in the same manner as corresponding steps in claim 2.
Claim 8, dependent upon claim 6, recites similar step corresponding to method claim 3. Therefore the recited step of 8 is mapped to Chen in the same manner as corresponding step in claim 3.
Claim 9, dependent upon claim 6, recites similar step corresponding to method claim 4. Therefore the recited step of 9 is mapped to Chen in the same manner as corresponding step in claim 4.
Claim 10, dependent upon claim 6, recites similar elements corresponding to method claim 5. Therefore the recited elements of 10 are mapped to Chen in the same manner as corresponding elements in claim 5.
Conclusion
Additional prior art Öztürk et al. (Öztürk Ş, Cukur T. Focal modulation network for lung segmentation in chest X-ray images. Turkish Journal of Electrical Engineering and Computer Sciences. 2023;31(6):1006-20) discloses a method for segmentation of lung regions using a focal modulation UNet model (FMN-UNet). The method includes receiving a high-resolution CXR image, projecting the input through a convolutional encoder stage to extract a relatively compact latent representation, processing encoded feature maps at the lowest and highest resolutions to capture both global and local contextual relationships between image features, and projecting feature maps through a convolutional decoder stage to produce segmentation masks. See Fig. 1, page 1008 2nd para., page 1009-1011 section 2.2. FMN-UNet.
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to XUEMEI G CHEN whose telephone number is (571)270-3480. The examiner can normally be reached Monday-Friday 9am-6pm.
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 M 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.
/XUEMEI G CHEN/Primary Examiner, Art Unit 2661
Prosecution Insights