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 .
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d) or (f) based on applications (Application No. CN202411476529.0 and CN202510564095.8) filed in China on 22 Oct 2024 and 30 Apr 2025, respectively.
Information Disclosure Statement
No information disclosure statement (IDS) has been filed in the instant case. Applicant is reminded of the requirements of 37 CFR 1.56. If applicant is aware of any materially relevant prior art, it should be submitted in an IDS for consideration. See MPEP 609 and 37 CFR 1.97 for further information.
Specification
The disclosure is objected to because of the following informalities:
“In this embodiment, A breast” should read “In this embodiment, a breast” ([0057]);
“. when extracting” should read “. When extracting” ([0064]).
Appropriate correction is required.
Claim Objections
Claims 2-3 and 5 are objected to because of the following informalities:
“wherein the processing an ultrasound RF signal of a breast tumor to obtain a lesion location RF signal” should read “wherein the processing the ultrasound RF signal of the breast tumor to obtain the lesion location RF signal” (claim 2);
“wherein the preprocessing the ultrasound RF signal to obtain an ultrasound image comprises” should read “wherein the preprocessing the ultrasound RF signal to obtain the ultrasound image comprises” (claim 3);
“wherein the processing the lesion location RF signal based on a feature extraction model to obtain a feature pixel matrix comprises” should read “wherein the processing the lesion location RF signal based on the feature extraction model to obtain the feature pixel matrix comprises” (claim 5).
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.
Claim 3 is 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.
Claim 3 recites “the ultrasound RF signal” throughout the claim. The antecedent basis for each of “the ultrasound RF signal” recited in claim 3 is unclear. In particular, claim 1, to which claim 3 depends, recites “an ultrasound radio frequency (RF) signal of a breast tumor” and claim 3 also recites “an ultrasound RF signal based on a byte offset of the header file”. For purposes of the examination, the limitation “correspondingly acquiring an ultrasound RF signal based on a byte offset of the header file” in the claim is being given a broadest reasonable interpretation as “acquiring a corresponding ultrasound RF signal based on a byte offset of the header file”.
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 1-2, 4-6, 10-11, 13-15, and 17-19 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Byra et al. (Byra et al. Joint segmentation and classification of breast masses based on ultrasound radio-frequency data and convolutional neural networks. Ultrasonics. (2022). 121:106682. doi: 10.1016/j.ultras.2021.106682. A copy attached to this Office action.) – hereinafter referred to as Byra.
Regarding claim 1, Byra discloses a method of breast tumor classification based on ultrasound (at least Fig. 3) comprising:
processing an ultrasound radio frequency (RF) signal of a breast tumor to obtain a lesion location RF signal (Fig. 3: Architecture of the Y-Net convolutional neural network including input of radio-frequency (RF) data; pg. 3: 3.2. Deep learning methods: 2048 x 256 RF data matrices processed through STEM layer for Y-Net contraction path);
processing the lesion location RF signal based on a feature extraction model to obtain a feature pixel matrix (Fig. 3; pg. 2: 3.2. Deep learning methods: feature maps from the contraction and expansion blocks to extract features for classification; pg. 3: 3.2. Deep learning methods: 2048 x 256 RF data matrices were input into the Y-Net convolutional neural network for output of at least 256 x 256); and
identifying and classifying the feature pixel matrix based on a preset strategy to obtain a class of the breast tumor (Fig. 3: "Segmentation" and "Malignant/benign" classification; Fig. 5: Segmentation results from RF data; Fig. 9: Class activation maps for malignant (red color) and benign (blue color) masses; pg. 3: 3.4. Interpretability: feature maps extracted from each block of the Y-Net were weighted using classification layer weights to yield activation maps).
It is noted that “breast imaging reporting and data system (BI-RADS)” recited in the preamble is being given a limited patentable weight as an intended use. Additionally, Byra also suggests its method being used with BI-RADS lexicon (see pg. 8 of Byra: 5. Discussion).
Regarding claim 2, Byra discloses all limitations of claim 1, as discussed above, and Byra further discloses:
preprocessing the ultrasound RF signal to obtain an ultrasound image (pg. 2: 3.1. Ultrasound data: breast mass B-mode US images were reconstructed based on RF data); and
processing the ultrasound image to obtain the lesion location RF signal (Fig. 3: Architecture of the Y-Net convolutional neural network including input of ultrasound images; pg. 2: 3.2. Deep learning methods: Y-Nets were developed for input of RF data and US images based on RF data for Y-Net contraction path).
Regarding claim 4, Byra discloses all limitations of claim 2, as discussed above, and Byra further discloses:
acquiring annotation information of the ultrasound image (pg. 3: 3.2. Deep learning methods: first Y-net trained using US images, manual segmentations and malignant/benign labels; 3.1. Ultrasound data: manual segmentation of region of interest (ROIs) presenting breast masses outlined by radiologist using the US images),
wherein the annotation information is provided to distinguish between a lesion and a background region in the ultrasound image (Fig. 5-6: Manual ROI includes lesion in white and background in black);
binarizing the ultrasound image based on the annotation information to obtain a mask image that is binarized (Fig. 5-6: Manual ROI binarized between white (lesion) and black (background));
determining a lesion area in the ultrasound image based on the mask image (Fig. 5-6: Manual ROI including lesion area in white);
determining a lesion boundary in the ultrasound image based on the lesion area (Fig. 5-6: Manual ROI including lesion area and boundary in white);
expanding the lesion area in the ultrasound image based on the lesion boundary (Fig. 5-6: CNN, RF data including lesion area greater than that in Manual ROI; pg. 3: 3.3. Training and evaluation: Detected breast mass was evaluated by determining whether the centroid of automatic ROI of CNN, RF data was within the manual ROI),
wherein a location of the expanded lesion area in the ultrasound image is a target location (Fig. 5-6: CNN, RF data including lesion area in white greater than that in Manual ROI); and
selecting an ultrasound RF signal corresponding to the target location as the lesion location RF signal (pg. 3: 3.3. Training and evaluation: Detected breast mass was considered correctly detected if the centroid of automatic ROI of CNN, RF data was within the manual ROI).
Regarding claim 5, Byra discloses all limitations of claim 1, as discussed above, and Byra further discloses:
performing, by the feature extraction model, feature extraction based on the lesion location RF signal to obtain a feature map (pg. 3: 3.4. Interpretability: feature maps extracted from each block of the Y-Net); and
performing fusion and stitching on the feature map to obtain the feature pixel matrix (pg. 3: 3.4. Interpretability: feature maps were resized and weighted using classification layer weights to yield activation maps; Fig. 9: CAM, RF data).
Regarding claim 6, Byra discloses all limitations of claim 1, as discussed above, and Byra further discloses:
performing stepwise classification on the feature pixel matrix by stepwise identification (Fig. 3: Architecture of the Y-Net convolutional neural network including global average pooling (GAP) at specific convolutional blocks (CB) on the input of RF data matrices; pg. 3: 3.2. Deep learning methods: 2048 x 256 RF data matrices input into Y-Net contraction path; pg. 2: 3.2. Deep learning methods: global average pooling (GAP) applied to extract features for classification);
clustering classification results of the stepwise classification (Fig. 3: Architecture of the Y-Net convolutional neural network including concatenation of 3 GAP's input into a fully connected layer (FC)); and
processing the clustered classification results based on a benign class and a malignant class to obtain a final class (Fig. 3: Architecture of the Y-Net convolutional neural network including classification of malignant vs. benign following the FC).
Regarding claim 10, Byra discloses all limitations of claim 1, as discussed above, and Byra further discloses:
a computer device, comprising a memory, a processor, and a computer program stored on the memory and runnable on the processor, wherein the processor is configured to execute the computer program to implement steps of the method of claim 1 (pg. 3: 3.3. Training and evaluation: networks were trained on a computer equipped with a GeForce RTX 2080 Ti graphics card).
Regarding claims 11 and 15, Byra discloses all limitations of claims 6 and 10, respectively, as discussed above, and Byra further discloses:
preprocessing the ultrasound RF signal to obtain an ultrasound image (pg. 2: 3.1. Ultrasound data: breast mass B-mode US images were reconstructed based on RF data); and
processing the ultrasound image to obtain the lesion location RF signal (Fig. 3: Architecture of the Y-Net convolutional neural network including input of ultrasound images; pg. 2: 3.2. Deep learning methods: Y-Nets were developed for input of RF data and US images based on RF data for Y-Net contraction path).
Regarding claims 13 and 17, Byra discloses all limitations of claims 11 and 15, respectively, as discussed above, and Byra further discloses:
acquiring annotation information of the ultrasound image (pg. 3: 3.2. Deep learning methods: first Y-net trained using US images, manual segmentations and malignant/benign labels; 3.1. Ultrasound data: manual segmentation of region of interest (ROIs) presenting breast masses outlined by radiologist using the US images),
wherein the annotation information is provided to distinguish between a lesion and a background region in the ultrasound image (Fig. 5-6: Manual ROI includes lesion in white and background in black);
binarizing the ultrasound image based on the annotation information to obtain a mask image that is binarized (Fig. 5-6: Manual ROI binarized between white (lesion) and black (background));
determining a lesion area in the ultrasound image based on the mask image (Fig. 5-6: Manual ROI including lesion area in white);
determining a lesion boundary in the ultrasound image based on the lesion area (Fig. 5-6: Manual ROI including lesion area and boundary in white);
expanding the lesion area in the ultrasound image based on the lesion boundary (Fig. 5-6: CNN, RF data including lesion area greater than that in Manual ROI; pg. 3: 3.3. Training and evaluation: Detected breast mass was evaluated by determining whether the centroid of automatic ROI of CNN, RF data was within the manual ROI),
wherein a location of the expanded lesion area in the ultrasound image is a target location (Fig. 5-6: CNN, RF data including lesion area in white greater than that in Manual ROI); and
selecting an ultrasound RF signal corresponding to the target location as the lesion location RF signal (pg. 3: 3.3. Training and evaluation: Detected breast mass was considered correctly detected if the centroid of automatic ROI of CNN, RF data was within the manual ROI).
Regarding claims 14 and 18, Byra discloses all limitations of claims 6 and 10, respectively, as discussed above, and Byra further discloses:
performing, by the feature extraction model, feature extraction based on the lesion location RF signal to obtain a feature map (pg. 3: 3.4. Interpretability: feature maps extracted from each block of the Y-Net); and
performing fusion and stitching on the feature map to obtain the feature pixel matrix (pg. 3: 3.4. Interpretability: feature maps were resized and weighted using classification layer weights to yield activation maps; Fig. 9: CAM, RF data).
Regarding claim 19, Byra discloses all limitations of claim 10, as discussed above, and Byra further discloses:
performing stepwise classification on the feature pixel matrix by stepwise identification (Fig. 3: Architecture of the Y-Net convolutional neural network including global average pooling (GAP) at specific convolutional blocks (CB) on the input of RF data matrices; pg. 3: 3.2. Deep learning methods: 2048 x 256 RF data matrices input into Y-Net contraction path; pg. 2: 3.2. Deep learning methods: global average pooling (GAP) applied to extract features for classification);
clustering classification results of the stepwise classification (Fig. 3: Architecture of the Y-Net convolutional neural network including concatenation of 3 GAP's input into a fully connected layer (FC)); and
processing the clustered classification results based on a benign class and a malignant class to obtain a final class (Fig. 3: Architecture of the Y-Net convolutional neural network including classification of malignant vs. benign following the FC).
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 3, 12, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Byra, as applied to claims 2, 11, and 15 respectively above, and further in view of McCormick (McCormick. “A File Reader for the VisualSonics Vevo770 Digital RF Data”. The MIDAS Journal – Medical Imaging and Computing. 2011. doi: 10.54294/v88ozn. A copy attached to this Office action).
Regarding claims 3, 12, and 16, Byra discloses all limitations of claims 2, 11, and 15, respectively, as discussed above, and Byra discloses (see claims 2, 11, and 15 respectively above):
processing the ultrasound image to obtain the lesion location RF signal (Fig. 3: Architecture of the Y-Net convolutional neural network including input of ultrasound images; pg. 2: 3.2. Deep learning methods: Y-Nets were developed for input of RF data and US images based on RF data for Y-Net contraction path).
Byra does not disclose:
acquiring information of a header file of the ultrasound RF signal; and
correspondingly acquiring an ultrasound RF signal based on a byte offset of the header file.
McCormick, however, in the same field of processing RF signal to obtain an ultrasound image teaches:
acquiring information of a header file of the ultrasound RF signal (pg. 4: 2 File Storage and Metadata Extraction: each .rdb binary file has .rdi metadata header file); and
correspondingly acquiring an ultrasound RF signal based on a byte offset of the header file (pg. 4: 2 File Storage and Metadata Extraction: Information on acquired signal that are required to read, analyze, and scan convert the binary data must be extracted from the metadata header file, and Image Data section of metadata header file contains information on byte offsets for the RF data).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Byra’s method to include McCormick’s method of acquiring ultrasound RF signal based on byte offset of a header file. One of ordinary skill in the art would have combined the elements as claimed by known methods (i.e., acquiring ultrasound RF signal based on a byte offset of a header file, as disclosed by McCormick), and the combination would have yielded a reasonable expectation of success since both Byra and McCormick are directed to processing ultrasound RF signal. The motivation for the combination would have been “to read, analyze, and scan convert the binary data (of raw RF data)”, as taught by McCormick (pg. 4: 2 File Storage and Metadata Extraction), to process RF data in obtaining an ultrasound image.
Allowable Subject Matter
Claims 7-9 and 20 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.
The following is a statement of reasons for the indication of allowable subject matter:
When claims 7-9 and 20 are considered as a whole, prior arts do not disclose, neither individually nor in combination, at least processing ultrasound RF signal of a breast tumor to obtain a feature pixel matrix, and classifying the feature pixel matrix into benign and malignant classes in a stepwise classification by performing different levels of identification on a classification result of the feature pixel matrix, wherein the different levels of identification comprises different sets and sub-sets of BI-RADS classes. In particular, Byra, a prior art made of record above, discloses at least processing ultrasound RF signal of a breast tumor to classify between benign and malignant classes (see at least Fig. 3, 5-6, and 9; 3.2. Deep learning methods and 4. Results). Additionally, Jarosik et al. (Jarosik et al. Breast lesion classification based on ultrasonic radio-frequency signals using convolutional neural networks. Biocybernetics and Biomedical Engineering. (2020). 40(3):977-986. doi: 10.1016/j.bbe.2020.04.002. A copy attached to this Office action), a prior art being made of record herein, also discloses at least processing ultrasound RF signal of a breast tumor to classify between benign and malignant classes (see at least Fig. 3-4 and 3.2. Classification performance). Furthermore, Xie et al. (Xie et al. Spectral analysis enhanced net (SAE-Net) to classify breast lesions with BI-RADS category 4 or higher. Ultrasonics. (2024). 143: 107406. doi: 10.1016/j.ultras.2024.107406. A copy attached to this Office action), another prior art being made of record herein, discloses at least processing ultrasound RF signal of known BI-RADS 4+ classes to classify between benign and malignant classes (see at least Fig. 1 and 3.3. Prediction results distribution). But none of Byra, Jarosik et al, nor Xie et al. discloses at least performing different levels of identification on a classification result of a feature pixel matrix, wherein the different levels of identification comprises different sets and sub-sets of BI-RADS classes.
The technical advantage of the claimed invention is “to facilitate effective identification and classification in a screening and identification task for breast tumor tissue and improve the accuracy of identification and classification, effective feature extraction may be performed in advance on the lesion location RF signal in the ultrasound RF signal of the breast tumor” ([0057] of the specification of the instant application).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Younhee Choi whose telephone number is (571)272-7013. The examiner can normally be reached M-F 9AM-5PM EST.
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, Anhtuan Nguyen can be reached at 571-272-4963. 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.
/Y.C./Examiner, Art Unit 3797
/ANHTUAN T NGUYEN/Supervisory Patent Examiner, Art Unit 3795
07/01/26
Prosecution Insights