Platform Overview
Features
Cardiac AmyloidosisHeart FailureAortic StenosisPulmonary HypertensionStrain
Operations
Operational ImpactIT & ProcurementReimbursementsCore Lab SolutionsEHR Mining
Clinical Evidence
Our StoryCareersMedia Kit
NewsContact Us Login Book a Demo

Fully Automated Strain Analysis

The only AI-based GLS solution validated in the 2025 Intervendor Comparison Study,3 delivering vendor-agnostic measurements across all major ultrasound platforms with zero human interaction.

The Strain Standardization Challenge

Global longitudinal strain is one of the most powerful parameters in echocardiography, but inter-vendor variability has historically limited its clinical adoption for longitudinal monitoring.

3.7%
max inter-vendor bias (2013)

The first Intervendor Comparison Study in 2013 revealed strain differences of up to 3.7% between vendors, making it unreliable to compare results across ultrasound systems or track patients over time.1

10+
years of standardization effort

The EACVI/ASE Strain Standardization Task Force,2 together with industry partners, has worked for over a decade to set standards and reduce inter-vendor differences in strain measurements.

0.6%
max inter-vendor bias (2025)

The 2025 follow-up study3 confirms that contemporary clinical software now shows a maximum inter-vendor bias of just 0.6% strain units, a landmark improvement validating the standardization effort.

GLS is more sensitive than ejection fraction.

Global longitudinal strain detects subtle myocardial dysfunction before ejection fraction declines, with proven diagnostic and prognostic value across cardiac conditions. But its clinical utility depends on vendor-agnostic, reproducible measurements. That is exactly what fully automated AI analysis now delivers.

Vendor-Agnostic, Fully Automated, Zero Interaction

Us2.ai is the only fully automated AI-based strain analysis solution validated in the 2025 Intervendor Comparison Study,3 operating without any human intervention.

1

Fully Automated GLS

Us2.ai analyzes echocardiographic studies and delivers global longitudinal strain with zero manual interaction. No endocardial border tracing, no region-of-interest adjustment, no user input of any kind. From DICOM to final measurement, fully hands-free.

Zero Interaction
2

Vendor-Agnostic Analysis

Works identically across images from GE, Philips, Canon, Siemens, Fujifilm, and Esaote ultrasound systems. One consistent AI analysis regardless of acquisition platform, eliminating vendor lock-in for strain measurements.

6 Vendors Validated
3

Endocardial & Mid-/Full-Wall

Delivers both endocardial and mid-/full-wall GLS measurements from the three standard apical views (4-chamber, 3-chamber, and 2-chamber), matching the analysis scope of major vendor-specific platforms.

Both Layers
4

Multi-Cycle Averaging

Unlike single-cycle measurements from most vendor-specific platforms, Us2.ai averages GLS across multiple cardiac cycles, reducing beat-to-beat variability for more robust and reproducible clinical results.

Robust Results
Validated in a Landmark Study

The 2025 Intervendor Comparison Study,3 published in European Heart Journal - Cardiovascular Imaging, tested Us2.ai alongside 8 other analysis platforms across 62 subjects and 372 echocardiographic exams from 6 ultrasound manufacturers. It is the largest multi-vendor strain comparison ever conducted.

Validated in the 2025 Intervendor Comparison Study3

Published in the European Heart Journal - Cardiovascular Imaging, this landmark study compared strain measurements across 9 software platforms from 6 ultrasound manufacturers using 372 exams.

Only Fully Automated AI Solution

Us2.ai was the only fully automated, AI-based strain analysis solution tested in the study. All other platforms required semi-automated interaction with manual corrections for tracking quality. Us2.ai required none.

Strong Agreement with Clinical Software

Us2.ai GLS measurements showed strong correlation (r > 0.88) with the mean of all contemporary semi-automated clinical software platforms, confirming agreement with established measurement methods.

Good Test–Retest Reproducibility

In a strictly controlled test–retest scenario with repeated scans, Us2.ai demonstrated reproducibility comparable to ejection fraction measurement (7.4% vs. 6.5% relative mean error), confirming reliable fully automated strain analysis.

Us2.ai Strain: Reproducibility & Agreement

Mid-/Full-Wall ICC Test–retest reliability
0.922
Endocardial ICC Test–retest reliability
0.916
Mid-/Full-Wall Correlation vs. mean clinical SWS
r = 0.88
Endocardial Correlation vs. mean clinical SWS
r = 0.88
Data from Balinisteanu et al., European Heart Journal - Cardiovascular Imaging (2025)

References

  1. Farsalinos KE, Daraban AM, Ünlü S, Thomas JD, Badano LP, Voigt JU. Head-to-Head Comparison of Global Longitudinal Strain Measurements among Nine Different Vendors: The EACVI/ASE Inter-Vendor Comparison Study. J Am Soc Echocardiogr. 2015;28(10):1171–81.e2. doi:10.1016/j.echo.2015.06.011
  2. Thomas JD, Badano LP. EACVI-ASE-industry initiative to standardize deformation imaging: a brief update from the co-chairs. Eur Heart J Cardiovasc Imaging. 2013;14(11):1039–1040. doi:10.1093/ehjci/jet184
  3. Balinisteanu A, Duchenne J, Puvrez A, et al. Vendor differences in 2D-speckle tracking global longitudinal strain: An update on a 10-year standardization effort. Eur Heart J Cardiovasc Imaging. 2025;26(8):1360–1373. doi:10.1093/ehjci/8149265

Peer-reviewed. Vendor-agnostic. Fully automated.

Automated Strain on Every Echo

Us2.ai delivers fully automated, vendor-agnostic GLS measurements with zero human interaction, validated in the largest multi-vendor strain comparison study to date.

Book a Demo