Questions about how individual parts of claim 1 might be changed. A question may describe something different from what the claim language recites, or a version of it; no view is offered on which.
1.2Single compression image sequence
What ifWhat if the ultrasound sequence captures one monotonic compression of the target tissue?
Claim language“representing a periodic motion of the target tissue”
A linear ultrasound array records cross-sectional frames while a motorized platen compresses the tissue at constant speed. The analysis uses the frame at first contact as a reference and estimates regional strain at a specified platen displacement.
1.3Independent wall thickness measurements
What ifWhat if independent wall thickness measurements provide regional deformation without following tissue points between frames?
Claim language“tracking each part of the target tissue over time”
At end diastole and end systole, an image segmentation algorithm independently traces the inner and outer ventricular wall boundaries. The system measures thickness in predefined angular sectors in each image and divides the end-systolic minus end-diastolic mean thickness by the end-diastolic mean thickness for each sector.
1.4One tracking score per cycle
What ifWhat if a single reliability value represents tracking quality across the entire cardiac cycle?
Claim language“for each of the regions”
The system takes the median of the normalized correlation peaks from all tissue block matches in the cycle. It compares that pooled value with a cutoff to decide whether to report the cycle's deformation measurements or acquire another cycle.
1.5Continuous weighting of regional strain
What ifWhat if every regional deformation measurement contributes to the overall deformation amount?
Claim language“is not used”
The system maps each reliability value onto a zero-to-one scale and computes a weight of 0.05 plus 0.95 times that value. It sums the weighted regional strain values and divides by the sum of the weights.
1.6Automatic acquisition from another view
What ifWhat if the region flags trigger another acquisition automatically without a user notification?
Claim language“notify a user of the non-target regions”
A probe mount stores two preset imaging angles and switches to the second angle when the analysis flags a region. The system acquires a full cardiac cycle at the second angle and selects the sequence with fewer flagged regions for the overall strain calculation.
Section 2 · machine-generated
Variations
Further arrangements of the same subject matter, described here as of the publication date at the foot of this page.
Other field of use
Ultrasonic strain monitoring of rubber mounts
A contact ultrasonic array acquires cross-sectional images of a rubber isolation mount while a test machine applies cyclic compression. A processor tracks echo patterns in predefined zones and calculates axial strain from the change in distance between tracked points. The processor scores each zone by tracking correlation, excludes zones below a fixed threshold from the area-weighted mean strain, and lists the excluded zone identifiers on the test console.
Component substitution
Phase correlation for regional tracking
A phase-correlation module replaces spatial-domain block matching between successive ultrasound frames. For each tissue window, the module computes the inverse transform of the normalized cross-power spectrum and uses the peak location as the displacement estimate. The processor accumulates displacements over the cycle and calculates regional strain from the change in spacing between tracked points. It compares each region's median peak-to-sidelobe ratio with a preset threshold, omits low-scoring regions from the overall strain, and reports their identifiers.
Parameter or scale variation
High frame rate for small hearts
A high-frequency array records a short-axis section of a small animal heart at 300 frames per second and divides the myocardium into 12 circumferential sectors. The processor tracks tissue windows over three consecutive beats, resamples the resulting strain curves to 50 samples per beat, and averages the curves by sector. It excludes sectors with a median normalized tracking correlation below 0.75, averages the retained sector curves, and lists the excluded sectors beside the overall curve.
Combination with existing systems
Strain processing with electrocardiographic gating
An ultrasound scanner and an electrocardiograph timestamp image frames and electrical samples against a shared clock. The processor segments the image sequence at consecutive R peaks and calculates regional strain relative to the frame nearest the first peak of each cycle. It uses the fraction of points that retain an acceptable tracking match throughout the cycle as the regional reliability score. It averages strain across regions that meet a preset score threshold and sends the excluded region identifiers and cycle timestamp to the monitoring workstation.
Automated or data-driven variant
Trained model for regional tracking reliability
A gradient-boosted decision tree classifier uses regional tracking features from recordings labeled by comparing automated trajectories with manually annotated landmarks. Its inputs include median frame-to-frame correlation, the fraction of points retained through the cycle, and median forward-backward tracking error. At runtime, the processor scores each region, omits strains from regions below a cutoff fixed during validation, and lists those regions in the measurement report.
Automatic repeat capture after weak tracking
A processor connected to a scanner's live image buffer measures tracking reliability and flags sectors whose median frame-to-frame correlation falls below a preset threshold. When the flagged sectors account for more than 25 percent of the reference tissue area, the processor automatically evaluates up to three additional complete cycles from the live stream. It selects the cycle with the greatest retained tissue area and calculates overall strain from the accepted sectors of that cycle. The console reports the selected cycle and its excluded sector identifiers.
Specific version of a part
Hardwired image analysis circuitry
Frame buffers feed fixed block-matching circuits that use parallel absolute-difference accumulators and comparators to estimate tissue displacement. Hardwired arithmetic circuits derive regional strain from displacement gradients, and a video overlay circuit marks regions with poor match scores.
Phased array cardiac acquisition
A phased-array transducer with a 3 MHz center frequency acquires a two-dimensional sector sequence at 60 frames per second. An electrocardiogram channel timestamps successive R waves so the system extracts one cardiac cycle from the buffered frames.
Speckle tracking with block matching
The tracker places 15-by-15-pixel reference blocks along the myocardial wall and locates each block in the next frame by maximizing normalized cross-correlation in a local search window. It fits a quadratic surface around each correlation peak for subpixel displacement estimates and computes regional longitudinal strain from fractional changes in tracked wall length.
Reliability from return tracking error
The system tracks sample points forward through the cardiac cycle and then backward through the same frames. It takes the median return distance within each region and calculates the reliability value as one divided by one plus that median distance expressed in pixels.
Hatching on a segment map
A display controller draws diagonal hatching over flagged segments on a polar map of the ventricular wall. A legend identifies the hatching as marking segments omitted from the overall strain calculation.
Section 3 · quoted from USPTO records
Other work
Passages reproduced word for word from two earlier-published U.S. patent documents, placed beside the language of claim 1. No characterization is offered. Each passage is marked A or B for the document it comes from; ¶ numbers are the paragraph numbers in the USPTO’s published full text of that document.
An ultrasound image acquisition system 802 is coupled to a speckle tracking processor 804.
A · US 2015/0005637 A1 · ¶ 68
1.2wherein the processor is configured to: acquire an ultrasound tomographic image sequence that is formed by transmitting and receiving an ultrasonic wave to and from a target tissue of a subject and that is arranged in a time series representing a periodic motion of the target tissue;
At 608, image frames are acquired, and at 610, specimen displacements are determined using the selected template location.
A · US 2015/0005637 A1 · ¶ 61
In some embodiments, the analyzer 12 may be configured to receive and analyze respective sequences of echocardiographic images (echo cines). Accordingly, block 202 may direct the analyzer processor 100 to receive a sequence of images.
B · US 2019/0125298 A1 · ¶ 55
1.3wherein the processor is configured to: calculate a deformation amount of the target tissue in the periodic motion for each of a plurality of regions of the target tissue defined in advance by executing tracking processing for tracking each part of the target tissue over time in the ultrasound tomographic image sequence;
1.4wherein the processor is configured to: calculate a reliability evaluation value representing reliability of the tracking processing for each of the regions;
The system includes at least one processor configured to, receive signals representing a first at least one echocardiographic image, associate the first at least one echocardiographic image with a first view category of a plurality of predetermined echocardiographic image view categories, determine, based on the first at least one echocardiographic image and the first view category, a first quality assessment value representing a view category specific quality assessment of t
B · US 2019/0125298 A1 · ¶ 4
1.5wherein the processor is configured to: determine regions in which the reliability evaluation value is less than a predetermined evaluation value threshold, as non-target regions in which the deformation amount is not used in a case of calculating an overall deformation amount that is a deformation amount of the target tissue as a whole in the periodic motion, based on the deformation amount for each of the regions; and
1.6wherein the processor is configured to: notify a user of the non-target regions.
In some embodiments, block 208 may direct the analyzer processor 100 to produce signals for causing a representation of the quality assessment value to be transmitted to the display 15 of the user interface system 14 for causing the display to display the quality assessment value in association with the received at least one echocardiographic image.
B · US 2019/0125298 A1 · ¶ 103
An empty cell means only that no passage was reproduced there.
Statements in these documents
Accordingly, improved methods and apparatus for tissue tracking are needed.
A · US 2015/0005637 A1 · ¶ 2
In other alternatives, the first and second images are RF envelope images, and a total tissue displacement is established based on comparisons of image portions of a series of RF envelope images to the template region.
A · US 2015/0005637 A1 · ¶ 3
However, this feedback may not assist echocardiographers in capturing high quality echocardiographic images for use in subsequent quantified clinical measurement of anatomical features.
B · US 2019/0125298 A1 · ¶ 3
Embodiments of this invention relate to echocardiographic image analysis and more particularly to echocardiographic image analysis for image quality assessment.
B · US 2019/0125298 A1 · ¶ 2
Cite aspatent.fyi, US 2026/0354793 A1, claim 1, first published 2026-11-19T04:13:02-05:00, https://patent.fyi/US20260354793/, SHA-256 b124e1863785a1cef0fdf112354c524bf2723b089ccb71cda8117a8b66411b3b