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 .
Response to Amendment
The rejection under 35 U.S.C. 101 has been withdrawn in light of the amendment to the claims filed on 14 July 2026.
An objection to the specification has been withdrawn in light of the amendment to the claims filed on 14 July 2026.
Priority
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged. Applicant has not complied with one or more conditions for receiving the benefit of an earlier filing date under 35 U.S.C. 119(e) as follows:
The later-filed application must be an application for a patent for an invention which is also disclosed in the prior application (the parent or original nonprovisional application or provisional application). The disclosure of the invention in the parent application and in the later-filed application must be sufficient to comply with the requirements of 35 U.S.C. 112(a) or the first paragraph of pre-AIA 35 U.S.C. 112, except for the best mode requirement. See Transco Products, Inc. v. Performance Contracting, Inc., 38 F.3d 551, 32 USPQ2d 1077 (Fed. Cir. 1994).
The disclosure of the prior-filed application, Application No. 63/290,963 (hereinafter "’963"), fails to provide adequate support or enablement in the manner provided by 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph for one or more claims of this application. In particular, the following claims lack support in the above identified ‘963 provisional application:
Claims 6 & 19: only sparse data sets are disclosed (see ¶ [0128, 0134]), not “without additional clinical datasets and/or biomarkers”;
Claims 8 & 21: only “a measurement threshold may be set to filter (i.e., remove) poor frames” (see ¶ [0119]), the specification fails quantify “poor” to explicit “quality” metric and, thus, fails to disclose a quality threshold;
Claims 9 & 24: the specification fails to disclose or even mention a proximity let alone a proximity score;
Claims 11 & 27: the specification fails to disclose a “cancer score,” “inflammation score,” and “skin and wounds”; and
Claim 22: the specification fails to disclose “retak[ing] all of said ultrasound images,” the specification only discloses “the system returns "Error: Insufficient Amount of Data."” (see ¶ [0069]).
The abovementioned claims and their dependents fail to receive the priority benefit of the earlier filed provisional Application No. 63/290,963 for at least the reasons laid out above.
Specification
The title of the invention is not descriptive. A new title is required that is clearly indicative of the invention to which the claims are directed.
The following title is suggested: ULTRASOUND SYSTEM AND METHOD FOR LIVER STIFFNESS CHARACTERIZATION BASED ON MACHINE LEARNING.
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 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, 3-6, 8-9, 11-12, 14, 16-19, 21, 23-25, & 27 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Brattain et al. (US PGPUB 20210022715; hereinafter "Brattain").
With regards to Claim 1, Brattain discloses a system for characterising tissues (Systems and methods are provided for objective, noninvasive staging of diffuse liver disease, and other diseases, from ultrasound shear wave elastography (“SWE”); see Brattain Abstract; see also ultrasound system 200 of FIG. 2), the system comprising:
a point-of-care ultrasound device for obtaining at least one of ultrasound images and/or raw data of tissues (transducer array 202 for transmitting/receiving echoes and reconstructing said echoes into images; see Brattain ¶ [0035-0036 & 0042] & FIG. 2);
a processor (processing unit 214; see Brattain ¶ [0042] & FIG. 2); and
a memory (processing unit 214 may be implemented via hardware and memory; see Brattain ¶ [0042]) comprising instructions which when executed by the processor configure the processor to:
obtain an ultrasound image of a tissue of interest (receiving acquired ultrasound data at input 102; see Brattain ¶ [0031]);
identify features of interest on the ultrasound image (Act 430 automatically selecting an ROI; see Brattain ¶ [0057] & FIG. 4);
feeding said identified features into a trained machine learning (ML) model (features may be extracted from a rectangular ROI. SWE extracted features, such as stiffness features or data, elastography values, additional statistics histogram, and the like may be evaluated… by a CNN; see Brattain ¶ [0058]); and
identify a tissue pathology based on the identified features fed through the model (Data may then be combined at step 580 for determining the stage of liver fibrosis, which may involve using a classifier as discussed above; see Brattain ¶ [0059-0060]).
Claim 14 recite similar limitations and are rejected under the same rationale as claim 1.
With regards to Claim 31, Brattain discloses wherein the ultrasound device is configured to provide data capture guidance (A confidence metric may be assessed at step 590 where if a sufficient confidence level is not achieved by the results, then the process may be repeated; see Brattain ¶ [0059]).
Claim 16 recite similar limitations and are rejected under the same rationale as claim 3.
With regards to Claim 41, Brattain discloses wherein the features of interest are based on trained features fed into ML system (CNN-based ROI selection; see Brattain TABLE 1).
Claim 17 recite similar limitations and are rejected under the same rationale as claim 4.
With regards to Claim 51, Brattain discloses wherein the processor is configured to:
obtain a plurality of ultrasound images of tissues, each ultrasound image labelled with at least one tissue pathology from a plurality of tissue pathologies (the training data {labelled ultrasound images} comprising shear wave elastography (SWE) data and at least one of clinical data or laboratory data {i.e. labelled tissue pathology} obtained from a plurality of subjects; see Brattain Claim 27); and
train a model based on the labelled ultrasound images (training a machine learning algorithm based on the training data; see Brattain Claim 27).
Claim 18 recite similar limitations and are rejected under the same rationale as claim 5.
With regards to Claim 65, Brattain discloses wherein training said model is based on (claim in the alternative), or wherein training said model is based on the labelled ultrasound images and on additional clinical datasets and/or biomarkers (the training data {labelled ultrasound images} comprising shear wave elastography (SWE) data and at least one of clinical data {i.e. labelled tissue pathology} or laboratory data {i.e. additional clinical datasets and/or biomarkers} obtained from a plurality of subjects; see Brattain Claim 27; see also TABLE 4 for other clinical data examples).
Claim 19 recite similar limitations and are rejected under the same rationale as claim 6.
With regards to Claim 83, Brattain discloses wherein the processor is configured to:
determine a quality of each frame of the plurality of ultrasound images (Automatically assessing image quality may be performed at step 420. Quality criteria or thresholds may be determined by a user based upon the disease being diagnosed. In one non-limiting example, all images with PCFI <70% may be rejected as not meeting the quality criteria; see Brattain ¶ [0057]); and
discard any frame below a quality threshold prior to training the model (Automatically assessing image quality may be performed at step 420. Quality criteria or thresholds may be determined by a user based upon the disease being diagnosed. In one non-limiting example, all images with PCFI <70% may be rejected as not meeting the quality criteria; see Brattain ¶ [0057].
Claim 21 recite similar limitations and are rejected under the same rationale as claim 8.
With regards to Claim 91, Brattain discloses wherein the processor is configured to:
determine a score between the identified features and features in the trained model, wherein the tissue pathology is identified based on the proximity score (During a phased approach of building up the SWE/US multi-image modeling framework, performance metrics may be used, which include AUROC and sensitivity and specificity {i.e. proximity scores} for liver disease, such as hrNASH, as a function of the mean and maximum number of images required per decision; see Brattain ¶ [0062 & 0067]).
Claim 24 recite similar limitations and are rejected under the same rationale as claim 9.
With regards to Claim 111, Brattain discloses wherein physical measures (claimed in the alternative) are presented as one or more of a range of scores, an estimate, and/or a direct measurement (an AUROC of 0.77 for SWE, with sensitivity 91.4% and specificity 52.5% for diagnosis of METAVIR stage ≥F2 fibrosis at a cutoff of 7.29 kPa was shown; see Brattain ¶ [0059 & 0067]), or
wherein the pathology is one of: (F2 fibrosis at a cutoff of 7.29 kPa; see Brattain ¶ [0059 & 0067]), (claimed in the alternative), and the score is a corresponding one of: (an AUROC of 0.77 for SWE, with sensitivity 91.4% and specificity 52.5% for diagnosis of METAVIR stage ≥F2 fibrosis at a cutoff of 7.29 kPa was shown; see Brattain ¶ [0059 & 0067]), (claimed in the alternative), or
wherein the tissue is one of several types found in: a liver (systems and methods are provided for objective, noninvasive staging of diffuse liver disease, and other diseases; see Brattain Abstract), (claimed in the alternative).
Claim 27 recite similar limitations and are rejected under the same rationale as claim 11.
With regards to Claim 1211, Brattain discloses wherein the physical measures include estimates of tissue stiffness in kiloPascals (kPa) (an AUROC of 0.77 for SWE, with sensitivity 91.4% and specificity 52.5% for diagnosis of METAVIR stage ≥F2 fibrosis at a cutoff of 7.29 kPa was shown; see Brattain ¶ [0059 & 0067]).
With regards to Claim 2314, Brattain discloses further comprising directing a user to retake all of said ultrasound images when the system determines that insufficient data was captured (if a single image confidence metric does not meet a predefined confidence level {i.e. insufficient data threshold}, then another US and SWE image pair {i.e. retake all images} may be classified and the classifier outputs combined; see Brattain ¶ [0060]).
With regards to Claim 2514, Brattain discloses comprising:
determining an estimate of one or more of tissue stiffness (claimed in the alternative); and
presenting said tissue stiffness (claimed in the alternative) as one or more of a range of scores, an estimate, and/or a direct measurement (displaying reports indicating liver fibrosis scores {i.e. estimate of stiffness}; see Brattain ¶ [0034]).
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 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.
Claim 22 is rejected under 35 U.S.C. 103 as being unpatentable over Brattain in further view of Gajdos et al. (US PGPUB 20190350564; hereinafter "Gajdos") .
With regards to Claim 2221, while Brattain discloses serially assessing image quality based on a threshold {i.e. when said frame is below the quality threshold} (see Brattain ¶ [0045 & 0047]), it appears that Brattain may be silent to further comprising directing a user to retake one or more ultrasound images
However, Gajdos teaches of a system and method machine learning to tune ultrasound image quality, i.e. assessing image quality and directing a user to retake image if necessary (see Gajdos Abstract & Acts 42-44 as described in ¶ [0072-0073]).
Brattain and Gajdos are both considered to be analogous to the claimed invention because they are in the same field of machine learning in ultrasound imaging. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Brattain to incorporate the above teachings of Gajdos to provide at least directing a user to retake one or more ultrasound images. Doing so would aid in “improv[ing] imaging workflow” (see Gajdos ¶ [0015]).
Response to Arguments
Applicant's arguments with regards to the objection to the specification of 14 July 2026 have been fully considered but they are not persuasive. Applicant argues that “the claims are not limited to liver tissue, nor to specifically measuring liver stiffness.” The Office disagrees. Claim 14 clearly establishes “characterizing liver tissues” and Claims 12 & 25-27 claim estimating stiffness. It should be appreciated that one of ordinary skill in the art would recognize, based on the application as a whole, the suggested title aids in “indexing, classifying, searching, etc.” of the claimed invention, see MPEP § 606.01. Accordingly, Applicant’s argument is not persuasive.
Applicant's arguments with regards to the rejection under 35 U.S.C. 112(a) of 14 July 2026 have been fully considered but they are not persuasive.
Regarding Claims 1 & 14, Applicant argues that “The Applicant submits that a U-net architecture would be well-known to a person skilled in the art and that naming the U-net architecture conveys the structural details of the architecture (e.g., contracting path with convolutional layers and pooling, expanding path with upsampling and skip connections).” The Office disagrees. MPEP § 2161(I) clearly establishes that “It is not enough that one skilled in the art could write a program to achieve the claimed function because the specification must explain how the inventor intends to achieve the claimed function to satisfy the written description requirement.” In other words, Applicant must provide explicit detail how to achieve their specific result. It appears that Applicant is assuming that there is only a single U-net architecture available which will achieve identical results as Applicant. However, according to Siddique et al., there are multiple U-net architecture variants such as Base U-net, 3D U-net, Attention U-net, Inception U-net, Residual U-net, Recurrent U-net, Dense U-net, etc., all which have different architectures and characteristics (see Siddique et al. §II A-J & Table 6 for Ultrasound applications)1. The submits that one of ordinary skill in the art would not be familiar with Applicant’s specific instance of U-net to achieve automatic liver segmentation. For at least this reason, Applicant’s argument is not persuasive.
Applicant also mentions the extracted UTC features of Table 1, without providing any details how said features are extracted or how they are calculated from the maps of UTC features. For at least this reason, Applicant’s argument is not persuasive.
Applicant also argues that “it is not necessary for the specification to disclose every weight, bias, and hyperparameter of the neural network” and that to satisfy the written description requirement “sufficient structure corresponding to claimed features” is to be provided. However, as the Office has argued, Applicant has failed to provide any structures as to how the U-net achieves the claimed function of “identify[ing] features of interest.” For at least this reason, Applicant’s argument is not persuasive.
Applicant also argues that “paragraph [0073] describes using the UTC features (which are enumerated in Table 1) on a frame level using second-order statistics and summarized per patient to produce patient-level features”; however, fails to describe what the “second-order statistics” entrail let alone a single example. For at least this reason, Applicant’s argument is not persuasive.
Applicant goes on to further argue that “noting at paragraph [0073] that the ML model uses 10-fold cross-validation and is trained to classify data points against a library of accrued liver data labeled with stiffness measures in kPa, demographic data, and confirmed diagnoses.” It should be appreciated that cross-validation, even 10-fold cross-validation, merely statistically analyzes the accuracy of the machine learning model, and does not describe how the machine learning model achieves the claimed function. Moreover, cross-validation does not “train” or “classify” data points, rather calculates performance results. For at least this reason, Applicant’s argument is not persuasive.
Accordingly, the instant specification fails to provide any details how the claimed invention achieves “identify[ing] features of interest on the ultrasound image” and “identify[ing] a tissue pathology based on the identified features fed through the model” and, thus, fails to meet the written description requirement.
With regards to Claims 3 & 16, Applicant argues that “The specification states at paragraph [0068] that the system instructs the clinician to capture certain views of the liver (e.g., subcostal or intercostal) while the patient is holding their breath and marks the views as complete once they are acquired (see, e.g., FIG. 7), and that the acquisition guidance advises the user on which categories of views to collect.” However, Applicant failed to provide details as to how the system determines the category to collect or when the acquisition is completed. While FIG. 7 illustrates the system providing the guidance, the instant specification fails to disclose how the system determines which guidance to provide. FIG. 7 and the corresponding description merely describe the result, now how the results is achieved.
With regards to Claims 8, 11-12, 21, 25, & 27 under 35 U.S.C. 112(a), Applicant arguments are persuasive and the corresponding rejection is withdrawn.
With regards to dependent claims, Applicant relies on the virtue of their dependency upon abovementioned independent claims to argue novelty. Accordingly, said argument is not persuasive for at least the same reasons as Claims 1 & 14 as detailed above.
With regards to the rejections under 35 U.S.C. 102(a)(1) & 35 U.S.C. 103, Applicant contends that Brattain alone or in combination fails to disclose the features of Claim 1. In particular, Applicant argues that Brattain does not anticipate “identify features of interest on the ultrasound image" because “Brattain describes a geometric spatial optimization that determines where to measure within a pre-existing stiffness map, and does not "identify features of interest" as recited by claim 1.” The Office disagrees. The ROI is selected from within an SWE image box (see Brattain ¶ [0026]). Regardless if the pixels reflect stiffness values, the data is still computed from ultrasound data and the resultant SWE box is an image, thus, meets the standard for an ultrasound image. For at least this reason, Applicant’s arguments are not persuasive.
Applicant also argues that “Brattain fails to teach or suggest the claimed "identify a tissue pathology based on the identified features fed through the model" because cited Brattain discloses “staging liver fibrosis using a classifier, these nevertheless do not recite identifying a tissue pathology "based on the identified features.” The Office disagrees. Brattain’s step of “determining the stage of liver fibrosis” {i.e. pathology} is performed based on the corresponding ROI and/or extracted SWE features, i.e. features of interest. For at least this reason, Applicant’s arguments are not persuasive.
Applicant also argues that “the system in Brattain takes a pre-computed stiffness
map and calculates statistics, whereas claim 1 recites identifying features from the ultrasound image and using those features as an input to a separately trained ML model for pathology identification.” The Office disagrees. As detailed above, an SWE map is still an image and corresponding stiffness values are determined from raw ultrasound data. One of ordinary skill in the art would recognize that an SWE map or an SWE image box meet the requirements of an ultrasound image. For at least this reason, Applicant’s arguments are not persuasive.
With regards to dependent claims, Applicant relies on the virtue of their dependency upon abovementioned independent claims to argue novelty. Accordingly, said argument is not persuasive for at least the same reasons as Claims 1 & 14 as detailed above.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ASHISH S. JASANI whose telephone number is (571)272-6402. The examiner can normally be reached M-F 8:00 am - 4:00 pm (CST).
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, Keith M. Raymond can be reached on (571) 270-1790. 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.
/ASHISH S. JASANI/Examiner, Art Unit 3798
/KEITH RAYMOND/Supervisory Patent Examiner, Art Unit 3798
1 Siddique et al., “U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications,” 3 June 2021, IEEE Access ( Volume: 9).
Prosecution Insights