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) submitted on 08/05/2025 and 04/26/2025 are being considered by the examiner.
Claim Objections
Claim 21 is objected to because of the following informalities: claim 21 claims “the system of claim 11”, however the claim 11 is a method claim. Perhaps, claim 21 should read as: “the system of claim 13”. Appropriate correction or explanation is required and respectfully requested.
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.
Claims 1-3, 8-14 and 19-24 are rejected under 35 U.S.C. 103 as being unpatentable over Sieniek (US PAP 2020/0225811 A1) in view of Li et al. (“High-speed intra-operative assessment of breast tumor margins by multimodal ultrasound and photoacoustic tomography”). The prior art is provided by the applicant.
With respect to claims 1, 13 and 24, Sieniek teaches a method, a system and a non-transitory computer readable medium (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11):
PNG
media_image1.png
196
402
media_image1.png
Greyscale
receiving, a mammogram of a resected breast tissue specimen; providing the mammogram as input to a tumor margin classifier comprising a trained machine learning model (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11); producing, based on the input, and using the trained machine learning model, a prediction of whether the specimen has a positive tumor margin status or a negative tumor margin status; and outputting the prediction (see claims 1-11) but fails to explicitly mention that producing and outputting are provided intra-operatively, in real time while using the trained machine learning model.
Li et al. discloses a system/method for providing the mammogram as input to a tumor margin classifier comprising a trained machine learning model (see text pages 1-11) which explicitly teaches producing, based on the input, intra-operatively, in real time, and using the trained machine learning model, a prediction of whether the specimen has a positive tumor margin status or a negative tumor margin status; and outputting the prediction intra-operatively (see text page 8). Li et al. teaches that the ideal CNN-based classification algorithm will require little pre-processing and provide general margin assessment or all tumor types in real time. The CNN-based classification algorithm reported here was able to distinguish between positive and negative margin status of 2 mm margin area for in situ tumor at a speed of 0.7 s/frame in order to provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation (see abstract; pages 1-11).
Sieniek and Li et al. disclose the similar methods/apparatuses/non-transitory computer readable medium for providing the mammogram as input to tumor margin classifier comprising trained machine learning model.
It 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 to provide teachings of producing and outputting that are provided intra-operatively, in real time while using the trained machine learning model as suggested by Li et al. in the method, the apparatus and a non-transitory computer readable medium of Sieniek et al., since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
It would have been obvious to treat Sieniek and Li et al. as related art whereby an improvement on one of the systems/methods would readily be apparent as an improvement on either of the systems.
The Examiner’s conclusion that claims 1, 13 and 24 would have been obvious is based on the fact that all the claimed elements were known in the prior art, that one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and that the combination teaches nothing more than predictable results to one of ordinary skill in the art. KSR, 550 U.S. 398, 82 USPQ2d at 1385 (2007); Sakraida v. AG Pro, Inc., 425 U.S. 273, 282, 189 USPQ 449, 453 (1976); Anderson ’s-Black Rock, Inc. v. Pavement Salvage Co., 396 U.S. 57, 62-63, 163 USPQ 673, 675 (1969); Great Atlantic & P. Tea Co. v. Supermarket Equipment Corp., 340 U.S. 147, 152, 87 USPQ 303, 306 (1950).
With respect to claim 2, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) teaches the method of claim 1, comprising using the prediction to determine whether to resect additional breast tissue, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
With respect to claim 3, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) teaches the method of claim 1, wherein the trained machine learning model comprises an image classifier model pre-trained based on non- mammography images, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
With respect to claim 8, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) teaches the method of claim 1 wherein the prediction of whether the specimen has a positive tumor margin status or a negative tumor margin status comprises a probability that the specimen has a positive tumor margin status, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
With respect to claim 9, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) teaches the method of claim 1 wherein the prediction of whether the specimen has a positive tumor margin status or a negative tumor margin status comprises a probability that the specimen has a negative tumor margin status, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
With respect to claim 10, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) teaches the method of claim 1 wherein the trained machine learning model is configured to generate the prediction of whether the specimen has a positive tumor margin status or a negative tumor margin status based on at least one input in addition to the mammogram, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
With respect to claim 11, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) teaches the method of claim 1 wherein the mammogram comprises a two-dimensional image of the resected breast tissue, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
With respect to claim 12, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) teaches the method of claim 1 wherein the mammogram comprises a three-dimensional image of the resected breast tissue, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
With respect to claim 14, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) teaches the system of claim 13, wherein the trained machine learning model comprises an image classifier model pre-trained based on non- mammography images, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
With respect to claim 19, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) teaches the system of claim 13 wherein the prediction of whether the specimen has a positive tumor margin status or a negative tumor margin status comprises a probability that the specimen has a positive tumor margin status, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
With respect to claim 20, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) teaches the system of claim 13 wherein the prediction of whether the specimen has a positive tumor margin status or a negative tumor margin status comprises a probability that the specimen has a negative tumor margin status, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
With respect to claim 21 (as the best understood by examiner), Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) teaches the system of claim 13 wherein the trained machine learning model is configured to generate the prediction of whether the specimen has a positive tumor margin status or a negative tumor margin status based on at least one input in addition to the mammogram, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
With respect to claim 22, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) teaches the system of claim 13 wherein the mammogram comprises a two-dimensional image of the resected breast tissue since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
With respect to claim 23, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) teaches the system of claim 13 wherein the mammogram comprises a three-dimensional image of the resected breast tissue, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
Claims 4-7 and 15-18 are rejected under 35 U.S.C. 103 as being unpatentable over Sieniek (US PAP 2020/0225811 A1) in view of Li et al. (“High-speed intra-operative assessment of breast tumor margins by multimodal ultrasound and photoacoustic tomography”) as applied to claims 3 and 14 above, and further in view of Justaniah et al. (“Claisifying Breast Density from Mammogram with Pretrained CHHs and Weighted Average Ensembles”; text pages 1-23). The prior art is provided by the applicant.
With respect to claims 4 and 15, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) teaches the method of claim 3 and the system of claim 14 but fail to explicitly mention that the trained machine learning model comprises at least one dense layer connected to the image classifier model.
Justaniah et al. discloses a system/method for providing the mammogram as input to tumor margin and breast density classifier comprising trained machine learning model (see text pages 1-23) which explicitly teaches that the trained machine learning model comprises at least one dense layer connected to the image classifier model (see text page 11) since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
Sieniek, Li et al. and Justaniah et al. disclose the similar methods/apparatuses for providing the mammogram as input to tumor margin classifier comprising trained machine learning model.
It 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 to provide teachings that the trained machine learning model comprises at least one dense layer connected to the image classifier model as suggested by Justaniah et al. in the method and the apparatus of Sieniek et al. as modified Li et al., since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
It would have been obvious to treat Sieniek, Li et al. and Justaniah et al. as related art whereby an improvement on one of the systems/methods would readily be apparent as an improvement on either of the systems.
The Examiner’s conclusion that claims 4 and 15 would have been obvious is based on the fact that all the claimed elements were known in the prior art, that one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and that the combination teaches nothing more than predictable results to one of ordinary skill in the art. KSR, 550 U.S. 398, 82 USPQ2d at 1385 (2007); Sakraida v. AG Pro, Inc., 425 U.S. 273, 282, 189 USPQ 449, 453 (1976); Anderson ’s-Black Rock, Inc. v. Pavement Salvage Co., 396 U.S. 57, 62-63, 163 USPQ 673, 675 (1969); Great Atlantic & P. Tea Co. v. Supermarket Equipment Corp., 340 U.S. 147, 152, 87 USPQ 303, 306 (1950).
With respect to claims 5 and 16, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) and Justaniah et al. (see pages 1-23) teaches the method of claim 4 and the system of claim 15; wherein weights assigned to neurons in the at least one dense layer result from training of the at least one dense layer using mammograms and expert margin status classifications as inputs with the image classifier model frozen, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
With respect to claims 6 and 17, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) and Justaniah et al. (see pages 1-23) teaches the method of claim 5 and the system of claim 16; wherein the weights assigned to neurons in the at least one dense layer additionally result from training of the at least one dense layer in combination with the image classifier model and with the image classifier model unfrozen, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
With respect to claims 7 and 18, Sieniek (see abstract; Figs. 1A-7; paragraphs 0020-0043; claims 1-11) as modified by Li et al. (see text pages 1-11) and Justaniah et al. (see pages 1-23) teaches the method of claim 4 and the system of claim 15; wherein the trained machine learning model comprises at least one dropout layer following the at least one dense layer, since such a modification would provide user with the capabilities to enhance, intra-operatively, in real time, speed and accuracy for breast tumor margin evaluation.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Barnard et al. (US PAP 2023/0248323 A1; see abstract; Figs. 1-9; paragraphs 0006, 0010-0015, 0029-0031, 0034 and 0037; claims 1 and 14-21) and Ben-Ari (US Patent 10,037,601 B1; see abstract; Figs. 1-8; Column 12, line 3 – column 15, line 60; claims 1, 11 and 14) teaches pre-trained deep learning-based X-ray mammography images and systems.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to IRAKLI KIKNADZE whose telephone number is (571)272-6494. The examiner can normally be reached 9:00 AM - 6:00 PM.
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, David J. Makiya can be reached at 571-272-2273. 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.
Irakli Kiknadze
/IRAKLI KIKNADZE/
Primary Examiner, Art Unit 2884
/I.K./ September 1, 2026
