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
Claims 49-50 remain pending in the application in response to the applicant’s amendments to the rejections previously set forth in the Non-Final Office Action mailed 02/26/2026.
Response to Arguments
Applicant’s arguments filed 08/20/2026 with respect to claim(s) 49 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
However, for claim 50, the applicant argues “In the field of machine learning, "training" a model is a pre-operational development phase that occurs before a software platform can be compiled, deployed, or operated.” (see pg. 6, para. 5 to pg. 7, para. 5 of applicant’s remarks), and the examiner disagrees.
In response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., “an "online mode" and an "offline mode" refer to the operational states of the active ultrasound platform itself”) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
The claim only recites the system “having an online mode and an offline mode”. Under reasonable interpretation, an “offline mode” can refer to training a model, and an “online mode” can refer to testing a trained model, as disclosed in Codella below.
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.
Claims 49-50 are rejected under 35 U.S.C. 103 as being unpatentable over Codella et al. (US 20170116728 A1, published April 27, 2017) in view of Abolmaesumi et al. (US 20190125298 A1, published May 2, 2019 with a priority date of April 21, 2016) and Krishnan et al. (US 20050020903 A1, published January 27, 2005), hereinafter referred to as Codella, Abolmaesumi, and Krishnan, respectively.
Regarding claim 49, Codella teaches a cardiac platform (Fig. 49) comprising:
a classifier system receiving imaging information related to a heart of at least one patient and comprising a core classifier and a plurality of downstream classifiers, said core classifier to perform shared feature extraction from said imaging information, wherein each of the plurality of downstream classifiers to receive an output of the shared feature extraction (see para. 0029 Page 4 "The embodiment shown in FIG. 1 comprises: a feature engine 102 [core classifier] that calculates several groups of image features characteristic of texture and content of input images 100 [cardiac CT image as imaging information] and a cognitive engine 116 comprising a plurality of classifiers 118 through 128 [plurality of downstream classifiers], each receiving the output of the feature engine.");
the cardiac ultrasound platform to generate, from an output of at least one of the plurality of downstream classifiers, at least one of the following measurements: the dimensions of the left ventricle in systole and diastole, right ventricular assessment, LA (Left atrium) size, measurement of the aortic valve annulus, the aortic sinuses, the ascending aorta, the pulmonary valve, the mitral valve annulus and the tricuspid valve annulus, RA (Right atrium) size, RV (Right ventricle) size, and to perform at least one of the following functions from at least one of said measurements: LV EF (left ventricle ejection fraction), LV Volume, LV function, RV/LV Ratio (Right ventricle), AO (Aorta), MV (Mitral valve), PV Serial No.: 18/048,873 (Pulmonary valve), TV (Tricuspid valve), Pericardial Effusion, Segmental Abn.(abnormalities), Aortic Measurements, and IVC (Inferior vena cava) size (see para. 0006 "In cardiac imaging, the viewpoint of the image is an essential input for any algorithm designed to measure clinical features of the heart, such as detection of left ventricle, valves, thickness of the pericardium, etc."; see para. 0027 "As such, a viewpoint recognition system for CT imaging should correctly label sagittal, axial and coronal planes. There are also oblique planes that are obtained to assess cardiac chamber morphology, size and function. Short axis view (SHA) through the entire left ventricle is useful in calculation of left ventricle volume and ejection fraction, whereas the function of the left ventricle should be reviewed in long axis views which include the two chamber (2C) and four chamber (4C) views. There are also three chamber and five chamber views that are useful to study the aortic valve and left ventricle outflow.").
Codella teaches a cardiac imaging platform, but does not explicitly teach performing cardiac ultrasound imaging.
Whereas, Abolmaesumi, in an analogous field of endeavor, teaches cardiac ultrasound imaging (Fig. 8; see para. 0079 "Referring to FIG. 8, the neural network 360 includes 5 image quality assessment neural networks, each including the same shared layers 362 but including a different set of view category specific layers 370, 372, 374, 376, and 378…Each of the 5 image quality assessment neural networks takes as an input a sequence of 20 echocardiographic images 380 and outputs a view category specific quality assessment value.").
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified performing cardiac imaging, as disclosed in Codella, by performing cardiac ultrasound imaging, as disclosed in Abolmaesumi. One of ordinary skill in the art would have been motivated to make this modification in order to perform certain quantified clinical measurement of anatomical features and/or to assist in diagnosing a medical condition or a characteristic of the heart, as taught in Abolmaesumi (see para. 0036).
Codella in view of Abolmaesumi teaches classifiers configured to output cardiac parameters, and a neural network is known in the art and is inherently a classifier, but does not explicitly teach where the classifier is a neural network.
Whereas, Krishnan, in an analogous field of endeavor, teaches the classifier is a neural network (Fig. 4 and 6; see para. 0068 – “The model builder (24-2) builds classification models implemented by the classification method (24-1), which are trained (and possibly dynamically optimized) to analyze various extracted features provide diagnostic assistance and assessment on various levels, depending on the implementation. It is to be appreciated that the classification models may be “black boxes” that are unable to explain their prediction to a user (which is the case if classifiers are built using neural networks, example).”; see para. 0081 – “The classification module (44) comprises classification methods (44-1) to analyze the combined extracted parameters using one or more classification models, which are trained/dynamically adapted via model builder (44-2), to provide automatic diagnosis of heart disease and other decision support functions.”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the classifiers, as disclosed in Codella in view of Abolmaesumi, by having the classifier as a neural network, as disclosed in Krishnan. One of ordinary skill in the art would have been motivated to make this modification in order to predict which test will provide an accurate diagnosis based on a feature vector extracted from a patient medical history, as taught in Krishnan (see para. 0086).
Furthermore, regarding claim 50, Codella further teaches having an online mode and an offline mode (see para. 0048 "Training [offline] and testing [online] strategy 130: A leave-one-sample out strategy was used for training and testing.").
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Belohlavek (US 5871019 A, published February 16, 1999) discloses inputting echo tomograms of the heart to a neural network to output LV surface mapping and LV volume calculation.
Singer (US 20150112901 A1, published April 23, 2015) discloses training mode may be configured to train a computer and construct a transformation function to predict an unknown anatomical characteristic and/or an unknown physiological characteristic of a heart Valve, inflow tract and/or outflow tract, using a known anatomical characteristic and/or a known physiological characteristic the heart valve, inflow tract and/or outflow tract.
Simopoulous et al. (US 20080009722 A1, published January 10, 2008) discloses the locations of one or more features of the object are determined by applying a classifier, where a multi-class classifiers include CART, K-nearest neighbors, neural network (e.g., multi-layer perceptron), mixture models, or others.
Rothberg et al. (US 20170360412 A1, published December 21, 2017 with a priority date of June 20, 2016) discloses determine whether the ultrasound image contains the target anatomical view at least in part by providing the ultrasound image as an input to a multi-layer neural network.
Lu et al. (US 20090074280 A1, published March 19, 2009) discloses for learned classifiers, binary or multi-class classifiers may be used, such as Bayesian or neural network classifiers, and the non-sequential processing is provided, such as independent classification for translation, orientation and scale.
Voigt et al. (US 20150366532 A1, published December 24, 2015) discloses the processor applies a probabilistic model to detect valve anatomy.
Mourad et al. (US 20040059220 A1, published March 25, 2004) discloses artificial neural networks may be used to relate one or more variables, such as tissue deformation, displacement, ABP, etc., to desired cardiac tissue properties and cardiac parameters.
Belohlavek et al. (US 20060235319 A1, published October 19, 2006) discloses the use of a trained neural network and diagnostic interpretation unit allows for the evaluation of a full spectrum of functional imaging data, such as cardiac ultrasound images or entire echocardiogram waveforms, to determine indicators of pathologies such as ischemia with a speed and accuracy unattainable by traditional analysis techniques and systems.
Burt (US 9968257 B1, published May 15, 2018) discloses a plurality of separate convolutional neural networks (CNNs) are used to respectively process each of the plurality of two-dimensional images. Each CNN determines a probability map which is then adaptively fused into a single segmented output. A contouring operation is automatically performed to calculate at least one clinical measurement and/or create at least one 3D volume.
Georgescu et al. (US 20160174902 A1, published June 23, 2016) discloses an LV center position is detected in the MR image using a first trained deep neural network regressor; an LV orientation is detected based on the detected LV position using a second trained deep neural network regressor; and locations of the LV apex and mitral valve annulus points are detected based on the detected LV position and orientation using a third trained deep neural network regressor.
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 nonprovisional extension fee (37 CFR 1.17(a)) 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 mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Nyrobi Celestine whose telephone number is 571-272-0129. The examiner can normally be reached on Monday - Thursday, 7:00AM - 5:00PM 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, Pascal Bui-Pho can be reached on 571-272-2714. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/N.C./Examiner, Art Unit 3798
/PASCAL M BUI PHO/Supervisory Patent Examiner, Art Unit 3798
