# Ejection Fraction Estimation

2 related articles

Subscribe to updates

researchsquare.com Oct 19, 2026
EchoMed Agent needs only 20 labeled cases to estimate ejection fraction, cutting median error to 4.33%
With only 20 locally labeled cases, an agentic framework for echocardiographic video performs left ventricular segmentation and ejection fraction estimation. It chains a low-rank-adapted video segmentation foundation model, a mask-guided long-axis regression module and a natural-language interface; on a 98-case Mayo Clinic cohort it lowers median ejection fraction error from 5.47% to 4.33% and raises the share of cases within ±10 percentage points from 80.6% to 83.3%. On the public EchoNet-Dynamic set, segmentation Dice is 0.934 and median ejection fraction error is 4.24%.
With only 20 locally labeled cases, an agentic framework for echocardiographic video performs left ventricular segmentation and ejection fraction estimation. It chains a low-rank-adapted video segmentation foundation model, a mask-guided long-axis regression module and a natural-language interface; on a 98-case Mayo Clinic cohort it lowers median ejection fraction error from 5.47% to 4.33% and raises the share of cases within ±10 percentage points from 80.6% to 83.3%. On the public EchoNet-Dynamic set, segmentation Dice is 0.934 and median ejection fraction error is 4.24%.
Lehigh University Mayo Clinic
Leshan Sun（First author）
EchoMed Agent Ejection Fraction Estimation AxisHead Low-Rank Adaptation Agentic Workflow
arXiv Sep 25, 2026
A low-rank constraint turns the ultrasound video latent space into a readable cardiac-cycle trajectory, giving ED/ES frames without extra training
The work introduces LRM-Functa, which imposes a low-rank constraint on the time-resolved modulation vectors of VidFuncta (mt = v + Bβϕt), so that the latent space of cardiac ultrasound videos forms periodic spiral trajectories; this allows direct readout of end-diastolic (ED) and end-systolic (ES) frames without additional model training, keeps stable reconstruction and ejection-fraction prediction at the extremely low rank k = 2 on EchoNet-Dynamic, and generalizes to a POCUS cardiac view and to lung-ultrasound B-line classification.
The work introduces LRM-Functa, which imposes a low-rank constraint on the time-resolved modulation vectors of VidFuncta (mt = v + Bβϕt), so that the latent space of cardiac ultrasound videos forms periodic spiral trajectories; this allows direct readout of end-diastolic (ED) and end-systolic (ES) frames without additional model training, keeps stable reconstruction and ejection-fraction prediction at the extremely low rank k = 2 on EchoNet-Dynamic, and generalizes to a POCUS cardiac view and to lung-ultrasound B-line classification.
University of Basel Yale University
Julia Wolleb（First author, Corresponding author）
LRM-Functa Low-Rank Adaptation Implicit Neural Representation Cardiac Phase Detection Ejection Fraction Estimation

You’re all caught up

EchoMed Agent needs only 20 labeled cases to estimate ejection fraction, cutting median error to 4.33%

A low-rank constraint turns the ultrasound video latent space into a readable cardiac-cycle trajectory, giving ED/ES frames without extra training